diff --git a/README.md b/README.md
index 08371015f02382e6fcba318f4aaea54ae52cd3c4..5f4f5625039e17bc7326cc10fbbc7896bb06453b 100644
--- a/README.md
+++ b/README.md
@@ -4,18 +4,6 @@ library_name: peft
## Training procedure
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
@@ -29,6 +17,5 @@ The following `bitsandbytes` quantization config was used during training:
- bnb_4bit_compute_dtype: float32
### Framework versions
-- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
diff --git a/adapter_model.bin b/adapter_model.bin
index e9b913951f0eafb85b209a393e5f742ac4bf6408..56402b256e1d53f7ec8d1862916f2f4f8c38d7e9 100644
--- a/adapter_model.bin
+++ b/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:ed6e90196f5a274b5d5ff0f18e648b6396fc99189dc82111fcfd2e83656a72f7
+oid sha256:cd9c3d8987621f868abe4c7d938c69dc21744df4cfc4475a0b74a7024edbc457
size 39409357
diff --git a/checkpoint-1000/adapter_model.bin b/checkpoint-1000/adapter_model.bin
index 34fbbd2c7ce064739b832ea4f04685aa6d41faa0..787af5d85433e12ed384f46355f1f145e3bacdb7 100644
--- a/checkpoint-1000/adapter_model.bin
+++ b/checkpoint-1000/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:f453889b7b5f1f21797413708a1c82782ca563c8173a223b50fb5e004837c160
+oid sha256:14cc62274569aa6e55637b983042d5dd9e0c0998e567c185e59fc1a7793b8762
size 39409357
diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt
index efd8cd5608cddb3c4edda6e0d5da2052af77a93d..9327c9466f4af4e3b4008f0022cd8f47e7ba2259 100644
--- a/checkpoint-1000/optimizer.pt
+++ b/checkpoint-1000/optimizer.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:980ce4082f86e8643d829ecc076ea00335d9e2d80d18c421ae802d241b9e3197
+oid sha256:906c3906783a3003c8ab79253037e8ca3d96e109bb687416c0d13ac8d187d364
size 78844421
diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth
index faca5241da3506eadd57588fb689a90f390f5558..c4f6e431605a7da3e2efbdf0dc1fae0f500de983 100644
--- a/checkpoint-1000/rng_state.pth
+++ b/checkpoint-1000/rng_state.pth
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:a5432f961e7c82cbe7b6ec30d027cf3db4d17372f65774be8cf037a208cbc1ac
+oid sha256:370c3a07f37a8aae6ea141b54ca992b21699546baf7407eb587b6056f787333b
size 14575
diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt
index df7757b8324bccfaf0b6d6a0d952f9ebd94027b5..156adb97a2dcba9f834d2be826c444ceb19ad242 100644
--- a/checkpoint-1000/scheduler.pt
+++ b/checkpoint-1000/scheduler.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:203097d159784262bd5c95fedbda5673a26bd26ba8483bc4d9972c3ce0a53781
+oid sha256:bf42ce3ee82b0e0801aee2cff99b338860ec65fe61d91dcf5be231df5b9fa888
size 627
diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json
index e75c2b4bd63a8b9fb8aec5addf777c7352df2c99..d47d4341a5255e60a8632070e4f982fb0d9f49d9 100644
--- a/checkpoint-1000/trainer_state.json
+++ b/checkpoint-1000/trainer_state.json
@@ -1,7 +1,7 @@
{
"best_metric": null,
"best_model_checkpoint": null,
- "epoch": 20.23395510591211,
+ "epoch": 11.297440423654017,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
@@ -9,6011 +9,6011 @@
"is_world_process_zero": true,
"log_history": [
{
- "epoch": 0.02,
- "learning_rate": 0.00019987244897959184,
- "loss": 3.2215,
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
"step": 1
},
{
- "epoch": 0.04,
- "learning_rate": 0.00019974489795918367,
- "loss": 2.8365,
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
"step": 2
},
{
- "epoch": 0.06,
- "learning_rate": 0.00019961734693877553,
- "loss": 2.602,
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
"step": 3
},
{
- "epoch": 0.08,
- "learning_rate": 0.00019948979591836736,
- "loss": 2.4196,
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
"step": 4
},
{
- "epoch": 0.1,
- "learning_rate": 0.0001993622448979592,
- "loss": 2.2574,
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
"step": 5
},
{
- "epoch": 0.12,
- "learning_rate": 0.00019923469387755102,
- "loss": 2.2239,
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
"step": 6
},
{
- "epoch": 0.14,
- "learning_rate": 0.00019910714285714288,
- "loss": 2.1661,
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
"step": 7
},
{
- "epoch": 0.16,
- "learning_rate": 0.0001989795918367347,
- "loss": 2.0987,
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
"step": 8
},
{
- "epoch": 0.18,
- "learning_rate": 0.00019885204081632654,
- "loss": 2.015,
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
"step": 9
},
{
- "epoch": 0.2,
- "learning_rate": 0.00019872448979591837,
- "loss": 1.9771,
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
"step": 10
},
{
- "epoch": 0.22,
- "learning_rate": 0.00019859693877551023,
- "loss": 2.0271,
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
"step": 11
},
{
- "epoch": 0.24,
- "learning_rate": 0.00019846938775510203,
- "loss": 1.9812,
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
"step": 12
},
{
- "epoch": 0.26,
- "learning_rate": 0.0001983418367346939,
- "loss": 2.0834,
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
"step": 13
},
{
- "epoch": 0.28,
- "learning_rate": 0.00019821428571428572,
- "loss": 1.9174,
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
"step": 14
},
{
- "epoch": 0.3,
- "learning_rate": 0.00019808673469387755,
- "loss": 1.8409,
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
"step": 15
},
{
- "epoch": 0.32,
- "learning_rate": 0.00019795918367346938,
- "loss": 1.929,
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
"step": 16
},
{
- "epoch": 0.34,
- "learning_rate": 0.00019783163265306124,
- "loss": 2.0041,
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
"step": 17
},
{
- "epoch": 0.36,
- "learning_rate": 0.00019770408163265305,
- "loss": 1.9385,
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
"step": 18
},
{
- "epoch": 0.38,
- "learning_rate": 0.0001975765306122449,
- "loss": 1.9592,
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
"step": 19
},
{
- "epoch": 0.4,
- "learning_rate": 0.00019744897959183674,
- "loss": 1.9701,
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
"step": 20
},
{
- "epoch": 0.42,
- "learning_rate": 0.0001973214285714286,
- "loss": 1.9277,
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
"step": 21
},
{
- "epoch": 0.45,
- "learning_rate": 0.00019719387755102042,
- "loss": 1.8394,
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
"step": 22
},
{
- "epoch": 0.47,
- "learning_rate": 0.00019706632653061226,
- "loss": 1.8666,
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
"step": 23
},
{
- "epoch": 0.49,
- "learning_rate": 0.00019693877551020409,
- "loss": 1.8997,
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
"step": 24
},
{
- "epoch": 0.51,
- "learning_rate": 0.00019681122448979592,
- "loss": 1.9432,
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
"step": 25
},
{
- "epoch": 0.53,
- "learning_rate": 0.00019668367346938777,
- "loss": 1.9137,
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
"step": 26
},
{
- "epoch": 0.55,
- "learning_rate": 0.0001965561224489796,
- "loss": 1.905,
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
"step": 27
},
{
- "epoch": 0.57,
- "learning_rate": 0.00019642857142857144,
- "loss": 1.8708,
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
"step": 28
},
{
- "epoch": 0.59,
- "learning_rate": 0.00019630102040816327,
- "loss": 1.9097,
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
"step": 29
},
{
- "epoch": 0.61,
- "learning_rate": 0.00019617346938775513,
- "loss": 1.896,
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
"step": 30
},
{
- "epoch": 0.63,
- "learning_rate": 0.00019604591836734696,
- "loss": 1.8834,
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
"step": 31
},
{
- "epoch": 0.65,
- "learning_rate": 0.0001959183673469388,
- "loss": 1.8323,
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
"step": 32
},
{
- "epoch": 0.67,
- "learning_rate": 0.00019579081632653062,
- "loss": 1.804,
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
"step": 33
},
{
- "epoch": 0.69,
- "learning_rate": 0.00019566326530612248,
- "loss": 1.8906,
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
"step": 34
},
{
- "epoch": 0.71,
- "learning_rate": 0.00019553571428571428,
- "loss": 1.8693,
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
"step": 35
},
{
- "epoch": 0.73,
- "learning_rate": 0.00019540816326530614,
- "loss": 1.9308,
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
"step": 36
},
{
- "epoch": 0.75,
- "learning_rate": 0.00019528061224489797,
- "loss": 1.8082,
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
"step": 37
},
{
- "epoch": 0.77,
- "learning_rate": 0.0001951530612244898,
- "loss": 1.848,
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
"step": 38
},
{
- "epoch": 0.79,
- "learning_rate": 0.00019502551020408163,
- "loss": 1.8866,
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
"step": 39
},
{
- "epoch": 0.81,
- "learning_rate": 0.0001948979591836735,
- "loss": 1.7844,
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
"step": 40
},
{
- "epoch": 0.83,
- "learning_rate": 0.0001947704081632653,
- "loss": 1.8485,
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
"step": 41
},
{
- "epoch": 0.85,
- "learning_rate": 0.00019464285714285715,
- "loss": 1.7917,
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
"step": 42
},
{
- "epoch": 0.87,
- "learning_rate": 0.00019451530612244898,
- "loss": 1.7342,
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
"step": 43
},
{
- "epoch": 0.89,
- "learning_rate": 0.00019438775510204084,
- "loss": 1.8479,
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
"step": 44
},
{
- "epoch": 0.91,
- "learning_rate": 0.00019426020408163267,
- "loss": 1.8639,
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
"step": 45
},
{
- "epoch": 0.93,
- "learning_rate": 0.0001941326530612245,
- "loss": 1.8166,
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
"step": 46
},
{
- "epoch": 0.95,
- "learning_rate": 0.00019400510204081633,
- "loss": 1.7566,
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
"step": 47
},
{
- "epoch": 0.97,
- "learning_rate": 0.00019387755102040816,
- "loss": 1.8071,
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
"step": 48
},
{
- "epoch": 0.99,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.8612,
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
"step": 49
},
{
- "epoch": 1.01,
- "learning_rate": 0.00019362244897959185,
- "loss": 1.7819,
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
"step": 50
},
{
- "epoch": 1.03,
- "learning_rate": 0.00019349489795918368,
- "loss": 1.8647,
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
"step": 51
},
{
- "epoch": 1.05,
- "learning_rate": 0.0001933673469387755,
- "loss": 1.8196,
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
"step": 52
},
{
- "epoch": 1.07,
- "learning_rate": 0.00019323979591836737,
- "loss": 1.8027,
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
"step": 53
},
{
- "epoch": 1.09,
- "learning_rate": 0.00019311224489795917,
- "loss": 1.8927,
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
"step": 54
},
{
- "epoch": 1.11,
- "learning_rate": 0.00019298469387755103,
- "loss": 1.8481,
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
"step": 55
},
{
- "epoch": 1.13,
- "learning_rate": 0.00019285714285714286,
- "loss": 1.7781,
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
"step": 56
},
{
- "epoch": 1.15,
- "learning_rate": 0.00019272959183673472,
- "loss": 1.8101,
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
"step": 57
},
{
- "epoch": 1.17,
- "learning_rate": 0.00019260204081632653,
- "loss": 1.7257,
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
"step": 58
},
{
- "epoch": 1.19,
- "learning_rate": 0.00019247448979591838,
- "loss": 1.8185,
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
"step": 59
},
{
- "epoch": 1.21,
- "learning_rate": 0.00019234693877551021,
- "loss": 1.8557,
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
"step": 60
},
{
- "epoch": 1.23,
- "learning_rate": 0.00019221938775510204,
- "loss": 1.7418,
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
"step": 61
},
{
- "epoch": 1.25,
- "learning_rate": 0.00019209183673469388,
- "loss": 1.6879,
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
"step": 62
},
{
- "epoch": 1.27,
- "learning_rate": 0.00019196428571428573,
- "loss": 1.7651,
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
"step": 63
},
{
- "epoch": 1.29,
- "learning_rate": 0.00019183673469387756,
- "loss": 1.7759,
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
"step": 64
},
{
- "epoch": 1.32,
- "learning_rate": 0.0001917091836734694,
- "loss": 1.7691,
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
"step": 65
},
{
- "epoch": 1.34,
- "learning_rate": 0.00019158163265306123,
- "loss": 1.7794,
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
"step": 66
},
{
- "epoch": 1.36,
- "learning_rate": 0.00019145408163265306,
- "loss": 1.8152,
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
"step": 67
},
{
- "epoch": 1.38,
- "learning_rate": 0.00019132653061224492,
- "loss": 1.8052,
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
"step": 68
},
{
- "epoch": 1.4,
- "learning_rate": 0.00019119897959183675,
- "loss": 1.8054,
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
"step": 69
},
{
- "epoch": 1.42,
- "learning_rate": 0.00019107142857142858,
- "loss": 1.8114,
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
"step": 70
},
{
- "epoch": 1.44,
- "learning_rate": 0.0001909438775510204,
- "loss": 1.7749,
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
"step": 71
},
{
- "epoch": 1.46,
- "learning_rate": 0.00019081632653061227,
- "loss": 1.777,
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
"step": 72
},
{
- "epoch": 1.48,
- "learning_rate": 0.0001906887755102041,
- "loss": 1.7896,
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
"step": 73
},
{
- "epoch": 1.5,
- "learning_rate": 0.00019056122448979593,
- "loss": 1.8335,
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
"step": 74
},
{
- "epoch": 1.52,
- "learning_rate": 0.00019043367346938776,
- "loss": 1.8155,
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
"step": 75
},
{
- "epoch": 1.54,
- "learning_rate": 0.00019030612244897962,
- "loss": 1.8224,
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
"step": 76
},
{
- "epoch": 1.56,
- "learning_rate": 0.00019017857142857142,
- "loss": 1.7889,
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
"step": 77
},
{
- "epoch": 1.58,
- "learning_rate": 0.00019005102040816328,
- "loss": 1.8866,
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
"step": 78
},
{
- "epoch": 1.6,
- "learning_rate": 0.0001899234693877551,
- "loss": 1.8439,
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
"step": 79
},
{
- "epoch": 1.62,
- "learning_rate": 0.00018979591836734697,
- "loss": 1.7906,
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
"step": 80
},
{
- "epoch": 1.64,
- "learning_rate": 0.00018966836734693877,
- "loss": 1.8627,
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
"step": 81
},
{
- "epoch": 1.66,
- "learning_rate": 0.00018954081632653063,
- "loss": 1.7497,
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
"step": 82
},
{
- "epoch": 1.68,
- "learning_rate": 0.00018941326530612246,
- "loss": 1.7936,
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
"step": 83
},
{
- "epoch": 1.7,
- "learning_rate": 0.0001892857142857143,
- "loss": 1.8341,
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
"step": 84
},
{
- "epoch": 1.72,
- "learning_rate": 0.00018915816326530612,
- "loss": 1.7868,
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
"step": 85
},
{
- "epoch": 1.74,
- "learning_rate": 0.00018903061224489798,
- "loss": 1.7493,
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
"step": 86
},
{
- "epoch": 1.76,
- "learning_rate": 0.0001889030612244898,
- "loss": 1.7926,
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
"step": 87
},
{
- "epoch": 1.78,
- "learning_rate": 0.00018877551020408164,
- "loss": 1.8278,
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
"step": 88
},
{
- "epoch": 1.8,
- "learning_rate": 0.00018864795918367347,
- "loss": 1.7387,
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
"step": 89
},
{
- "epoch": 1.82,
- "learning_rate": 0.0001885204081632653,
- "loss": 1.7669,
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
"step": 90
},
{
- "epoch": 1.84,
- "learning_rate": 0.00018839285714285716,
- "loss": 1.7686,
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
"step": 91
},
{
- "epoch": 1.86,
- "learning_rate": 0.000188265306122449,
- "loss": 1.7759,
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
"step": 92
},
{
- "epoch": 1.88,
- "learning_rate": 0.00018813775510204082,
- "loss": 1.7016,
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
"step": 93
},
{
- "epoch": 1.9,
- "learning_rate": 0.00018801020408163265,
- "loss": 1.8123,
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
"step": 94
},
{
- "epoch": 1.92,
- "learning_rate": 0.0001878826530612245,
- "loss": 1.8315,
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
"step": 95
},
{
- "epoch": 1.94,
- "learning_rate": 0.00018775510204081634,
- "loss": 1.7679,
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
"step": 96
},
{
- "epoch": 1.96,
- "learning_rate": 0.00018762755102040817,
- "loss": 1.7874,
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
"step": 97
},
{
- "epoch": 1.98,
- "learning_rate": 0.0001875,
- "loss": 1.8008,
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
"step": 98
},
{
- "epoch": 2.0,
- "learning_rate": 0.00018737244897959186,
- "loss": 1.7177,
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
"step": 99
},
{
- "epoch": 2.02,
- "learning_rate": 0.00018724489795918367,
- "loss": 1.7272,
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
"step": 100
},
{
- "epoch": 2.04,
- "learning_rate": 0.00018711734693877552,
- "loss": 1.7848,
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
"step": 101
},
{
- "epoch": 2.06,
- "learning_rate": 0.00018698979591836735,
- "loss": 1.744,
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
"step": 102
},
{
- "epoch": 2.08,
- "learning_rate": 0.00018686224489795919,
- "loss": 1.7005,
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
"step": 103
},
{
- "epoch": 2.1,
- "learning_rate": 0.00018673469387755102,
- "loss": 1.8247,
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
"step": 104
},
{
- "epoch": 2.12,
- "learning_rate": 0.00018660714285714287,
- "loss": 1.6855,
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
"step": 105
},
{
- "epoch": 2.14,
- "learning_rate": 0.0001864795918367347,
- "loss": 1.7627,
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
"step": 106
},
{
- "epoch": 2.17,
- "learning_rate": 0.00018635204081632654,
- "loss": 1.7564,
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
"step": 107
},
{
- "epoch": 2.19,
- "learning_rate": 0.00018622448979591837,
- "loss": 1.8237,
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
"step": 108
},
{
- "epoch": 2.21,
- "learning_rate": 0.00018609693877551022,
- "loss": 1.7421,
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
"step": 109
},
{
- "epoch": 2.23,
- "learning_rate": 0.00018596938775510206,
- "loss": 1.7517,
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
"step": 110
},
{
- "epoch": 2.25,
- "learning_rate": 0.0001858418367346939,
- "loss": 1.7515,
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
"step": 111
},
{
- "epoch": 2.27,
- "learning_rate": 0.00018571428571428572,
- "loss": 1.7842,
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
"step": 112
},
{
- "epoch": 2.29,
- "learning_rate": 0.00018558673469387755,
- "loss": 1.8001,
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
"step": 113
},
{
- "epoch": 2.31,
- "learning_rate": 0.0001854591836734694,
- "loss": 1.7653,
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
"step": 114
},
{
- "epoch": 2.33,
- "learning_rate": 0.00018533163265306124,
- "loss": 1.694,
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
"step": 115
},
{
- "epoch": 2.35,
- "learning_rate": 0.00018520408163265307,
- "loss": 1.7457,
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
"step": 116
},
{
- "epoch": 2.37,
- "learning_rate": 0.0001850765306122449,
- "loss": 1.7899,
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
"step": 117
},
{
- "epoch": 2.39,
- "learning_rate": 0.00018494897959183676,
- "loss": 1.7473,
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
"step": 118
},
{
- "epoch": 2.41,
- "learning_rate": 0.0001848214285714286,
- "loss": 1.6639,
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
"step": 119
},
{
- "epoch": 2.43,
- "learning_rate": 0.00018469387755102042,
- "loss": 1.762,
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
"step": 120
},
{
- "epoch": 2.45,
- "learning_rate": 0.00018456632653061225,
- "loss": 1.7378,
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
"step": 121
},
{
- "epoch": 2.47,
- "learning_rate": 0.0001844387755102041,
- "loss": 1.672,
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
"step": 122
},
{
- "epoch": 2.49,
- "learning_rate": 0.0001843112244897959,
- "loss": 1.7267,
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
"step": 123
},
{
- "epoch": 2.51,
- "learning_rate": 0.00018418367346938777,
- "loss": 1.7825,
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
"step": 124
},
{
- "epoch": 2.53,
- "learning_rate": 0.0001840561224489796,
- "loss": 1.7566,
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
"step": 125
},
{
- "epoch": 2.55,
- "learning_rate": 0.00018392857142857143,
- "loss": 1.8169,
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
"step": 126
},
{
- "epoch": 2.57,
- "learning_rate": 0.00018380102040816326,
- "loss": 1.6801,
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
"step": 127
},
{
- "epoch": 2.59,
- "learning_rate": 0.00018367346938775512,
- "loss": 1.7292,
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
"step": 128
},
{
- "epoch": 2.61,
- "learning_rate": 0.00018354591836734695,
- "loss": 1.737,
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
"step": 129
},
{
- "epoch": 2.63,
- "learning_rate": 0.00018341836734693878,
- "loss": 1.7696,
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
"step": 130
},
{
- "epoch": 2.65,
- "learning_rate": 0.0001832908163265306,
- "loss": 1.7239,
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
"step": 131
},
{
- "epoch": 2.67,
- "learning_rate": 0.00018316326530612247,
- "loss": 1.7441,
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
"step": 132
},
{
- "epoch": 2.69,
- "learning_rate": 0.0001830357142857143,
- "loss": 1.7825,
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
"step": 133
},
{
- "epoch": 2.71,
- "learning_rate": 0.00018290816326530613,
- "loss": 1.7411,
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
"step": 134
},
{
- "epoch": 2.73,
- "learning_rate": 0.00018278061224489796,
- "loss": 1.7119,
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
"step": 135
},
{
- "epoch": 2.75,
- "learning_rate": 0.0001826530612244898,
- "loss": 1.7443,
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
"step": 136
},
{
- "epoch": 2.77,
- "learning_rate": 0.00018252551020408165,
- "loss": 1.7197,
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
"step": 137
},
{
- "epoch": 2.79,
- "learning_rate": 0.00018239795918367348,
- "loss": 1.7273,
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
"step": 138
},
{
- "epoch": 2.81,
- "learning_rate": 0.0001822704081632653,
- "loss": 1.7681,
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
"step": 139
},
{
- "epoch": 2.83,
- "learning_rate": 0.00018214285714285714,
- "loss": 1.8088,
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
"step": 140
},
{
- "epoch": 2.85,
- "learning_rate": 0.000182015306122449,
- "loss": 1.7301,
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
"step": 141
},
{
- "epoch": 2.87,
- "learning_rate": 0.00018188775510204083,
- "loss": 1.6853,
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
"step": 142
},
{
- "epoch": 2.89,
- "learning_rate": 0.00018176020408163266,
- "loss": 1.6966,
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
"step": 143
},
{
- "epoch": 2.91,
- "learning_rate": 0.0001816326530612245,
- "loss": 1.7938,
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
"step": 144
},
{
- "epoch": 2.93,
- "learning_rate": 0.00018150510204081635,
- "loss": 1.7639,
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
"step": 145
},
{
- "epoch": 2.95,
- "learning_rate": 0.00018137755102040816,
- "loss": 1.7527,
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
"step": 146
},
{
- "epoch": 2.97,
- "learning_rate": 0.00018125000000000001,
- "loss": 1.7386,
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
"step": 147
},
{
- "epoch": 2.99,
- "learning_rate": 0.00018112244897959185,
- "loss": 1.7223,
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
"step": 148
},
{
- "epoch": 3.01,
- "learning_rate": 0.00018099489795918368,
- "loss": 1.7571,
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
"step": 149
},
{
- "epoch": 3.04,
- "learning_rate": 0.0001808673469387755,
- "loss": 1.7054,
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
"step": 150
},
{
- "epoch": 3.06,
- "learning_rate": 0.00018073979591836737,
- "loss": 1.6581,
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
"step": 151
},
{
- "epoch": 3.08,
- "learning_rate": 0.00018061224489795917,
- "loss": 1.681,
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
"step": 152
},
{
- "epoch": 3.1,
- "learning_rate": 0.00018048469387755103,
- "loss": 1.7425,
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
"step": 153
},
{
- "epoch": 3.12,
- "learning_rate": 0.00018035714285714286,
- "loss": 1.7108,
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
"step": 154
},
{
- "epoch": 3.14,
- "learning_rate": 0.00018022959183673472,
- "loss": 1.7194,
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
"step": 155
},
{
- "epoch": 3.16,
- "learning_rate": 0.00018010204081632655,
- "loss": 1.6953,
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
"step": 156
},
{
- "epoch": 3.18,
- "learning_rate": 0.00017997448979591838,
- "loss": 1.669,
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
"step": 157
},
{
- "epoch": 3.2,
- "learning_rate": 0.0001798469387755102,
- "loss": 1.744,
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
"step": 158
},
{
- "epoch": 3.22,
- "learning_rate": 0.00017971938775510204,
- "loss": 1.6467,
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
"step": 159
},
{
- "epoch": 3.24,
- "learning_rate": 0.0001795918367346939,
- "loss": 1.7103,
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
"step": 160
},
{
- "epoch": 3.26,
- "learning_rate": 0.00017946428571428573,
- "loss": 1.6662,
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
"step": 161
},
{
- "epoch": 3.28,
- "learning_rate": 0.00017933673469387756,
- "loss": 1.6657,
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
"step": 162
},
{
- "epoch": 3.3,
- "learning_rate": 0.0001792091836734694,
- "loss": 1.791,
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
"step": 163
},
{
- "epoch": 3.32,
- "learning_rate": 0.00017908163265306125,
- "loss": 1.7704,
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
"step": 164
},
{
- "epoch": 3.34,
- "learning_rate": 0.00017895408163265305,
- "loss": 1.7229,
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
"step": 165
},
{
- "epoch": 3.36,
- "learning_rate": 0.0001788265306122449,
- "loss": 1.76,
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
"step": 166
},
{
- "epoch": 3.38,
- "learning_rate": 0.00017869897959183674,
- "loss": 1.6482,
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
"step": 167
},
{
- "epoch": 3.4,
- "learning_rate": 0.0001785714285714286,
- "loss": 1.8076,
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
"step": 168
},
{
- "epoch": 3.42,
- "learning_rate": 0.0001784438775510204,
- "loss": 1.7368,
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
"step": 169
},
{
- "epoch": 3.44,
- "learning_rate": 0.00017831632653061226,
- "loss": 1.6264,
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
"step": 170
},
{
- "epoch": 3.46,
- "learning_rate": 0.0001781887755102041,
- "loss": 1.6289,
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
"step": 171
},
{
- "epoch": 3.48,
- "learning_rate": 0.00017806122448979592,
- "loss": 1.7913,
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
"step": 172
},
{
- "epoch": 3.5,
- "learning_rate": 0.00017793367346938775,
- "loss": 1.6985,
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
"step": 173
},
{
- "epoch": 3.52,
- "learning_rate": 0.0001778061224489796,
- "loss": 1.6936,
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
"step": 174
},
{
- "epoch": 3.54,
- "learning_rate": 0.00017767857142857141,
- "loss": 1.8068,
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
"step": 175
},
{
- "epoch": 3.56,
- "learning_rate": 0.00017755102040816327,
- "loss": 1.7243,
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
"step": 176
},
{
- "epoch": 3.58,
- "learning_rate": 0.0001774234693877551,
- "loss": 1.6893,
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
"step": 177
},
{
- "epoch": 3.6,
- "learning_rate": 0.00017729591836734696,
- "loss": 1.8122,
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
"step": 178
},
{
- "epoch": 3.62,
- "learning_rate": 0.0001771683673469388,
- "loss": 1.6562,
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
"step": 179
},
{
- "epoch": 3.64,
- "learning_rate": 0.00017704081632653062,
- "loss": 1.6999,
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
"step": 180
},
{
- "epoch": 3.66,
- "learning_rate": 0.00017691326530612245,
- "loss": 1.7229,
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
"step": 181
},
{
- "epoch": 3.68,
- "learning_rate": 0.00017678571428571428,
- "loss": 1.6764,
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
"step": 182
},
{
- "epoch": 3.7,
- "learning_rate": 0.00017665816326530614,
- "loss": 1.6982,
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
"step": 183
},
{
- "epoch": 3.72,
- "learning_rate": 0.00017653061224489797,
- "loss": 1.696,
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
"step": 184
},
{
- "epoch": 3.74,
- "learning_rate": 0.0001764030612244898,
- "loss": 1.6797,
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
"step": 185
},
{
- "epoch": 3.76,
- "learning_rate": 0.00017627551020408164,
- "loss": 1.637,
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
"step": 186
},
{
- "epoch": 3.78,
- "learning_rate": 0.0001761479591836735,
- "loss": 1.7074,
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
"step": 187
},
{
- "epoch": 3.8,
- "learning_rate": 0.0001760204081632653,
- "loss": 1.705,
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
"step": 188
},
{
- "epoch": 3.82,
- "learning_rate": 0.00017589285714285716,
- "loss": 1.6153,
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
"step": 189
},
{
- "epoch": 3.84,
- "learning_rate": 0.00017576530612244899,
- "loss": 1.7354,
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
"step": 190
},
{
- "epoch": 3.86,
- "learning_rate": 0.00017563775510204084,
- "loss": 1.6941,
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
"step": 191
},
{
- "epoch": 3.88,
- "learning_rate": 0.00017551020408163265,
- "loss": 1.7231,
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
"step": 192
},
{
- "epoch": 3.91,
- "learning_rate": 0.0001753826530612245,
- "loss": 1.7663,
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
"step": 193
},
{
- "epoch": 3.93,
- "learning_rate": 0.00017525510204081634,
- "loss": 1.6532,
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
"step": 194
},
{
- "epoch": 3.95,
- "learning_rate": 0.00017512755102040817,
- "loss": 1.7115,
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
"step": 195
},
{
- "epoch": 3.97,
- "learning_rate": 0.000175,
- "loss": 1.6955,
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
"step": 196
},
{
- "epoch": 3.99,
- "learning_rate": 0.00017487244897959186,
- "loss": 1.6863,
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
"step": 197
},
{
- "epoch": 4.01,
- "learning_rate": 0.00017474489795918366,
- "loss": 1.7012,
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
"step": 198
},
{
- "epoch": 4.03,
- "learning_rate": 0.00017461734693877552,
- "loss": 1.5927,
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
"step": 199
},
{
- "epoch": 4.05,
- "learning_rate": 0.00017448979591836735,
- "loss": 1.6272,
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
"step": 200
},
{
- "epoch": 4.07,
- "learning_rate": 0.00017436224489795918,
- "loss": 1.5994,
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
"step": 201
},
{
- "epoch": 4.09,
- "learning_rate": 0.00017423469387755104,
- "loss": 1.7141,
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
"step": 202
},
{
- "epoch": 4.11,
- "learning_rate": 0.00017410714285714287,
- "loss": 1.7547,
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
"step": 203
},
{
- "epoch": 4.13,
- "learning_rate": 0.0001739795918367347,
- "loss": 1.6254,
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
"step": 204
},
{
- "epoch": 4.15,
- "learning_rate": 0.00017385204081632653,
- "loss": 1.6686,
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
"step": 205
},
{
- "epoch": 4.17,
- "learning_rate": 0.0001737244897959184,
- "loss": 1.6684,
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
"step": 206
},
{
- "epoch": 4.19,
- "learning_rate": 0.00017359693877551022,
- "loss": 1.6724,
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
"step": 207
},
{
- "epoch": 4.21,
- "learning_rate": 0.00017346938775510205,
- "loss": 1.7361,
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
"step": 208
},
{
- "epoch": 4.23,
- "learning_rate": 0.00017334183673469388,
- "loss": 1.7167,
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
"step": 209
},
{
- "epoch": 4.25,
- "learning_rate": 0.00017321428571428574,
- "loss": 1.7226,
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
"step": 210
},
{
- "epoch": 4.27,
- "learning_rate": 0.00017308673469387754,
- "loss": 1.7133,
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
"step": 211
},
{
- "epoch": 4.29,
- "learning_rate": 0.0001729591836734694,
- "loss": 1.649,
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
"step": 212
},
{
- "epoch": 4.31,
- "learning_rate": 0.00017283163265306123,
- "loss": 1.7104,
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
"step": 213
},
{
- "epoch": 4.33,
- "learning_rate": 0.00017270408163265306,
- "loss": 1.6861,
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
"step": 214
},
{
- "epoch": 4.35,
- "learning_rate": 0.0001725765306122449,
- "loss": 1.648,
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
"step": 215
},
{
- "epoch": 4.37,
- "learning_rate": 0.00017244897959183675,
- "loss": 1.6215,
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
"step": 216
},
{
- "epoch": 4.39,
- "learning_rate": 0.00017232142857142858,
- "loss": 1.6334,
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
"step": 217
},
{
- "epoch": 4.41,
- "learning_rate": 0.0001721938775510204,
- "loss": 1.6283,
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
"step": 218
},
{
- "epoch": 4.43,
- "learning_rate": 0.00017206632653061224,
- "loss": 1.6462,
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
"step": 219
},
{
- "epoch": 4.45,
- "learning_rate": 0.0001719387755102041,
- "loss": 1.7233,
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
"step": 220
},
{
- "epoch": 4.47,
- "learning_rate": 0.0001718112244897959,
- "loss": 1.7839,
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
"step": 221
},
{
- "epoch": 4.49,
- "learning_rate": 0.00017168367346938776,
- "loss": 1.7204,
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
"step": 222
},
{
- "epoch": 4.51,
- "learning_rate": 0.0001715561224489796,
- "loss": 1.7671,
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
"step": 223
},
{
- "epoch": 4.53,
- "learning_rate": 0.00017142857142857143,
- "loss": 1.6824,
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
"step": 224
},
{
- "epoch": 4.55,
- "learning_rate": 0.00017130102040816328,
- "loss": 1.7068,
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
"step": 225
},
{
- "epoch": 4.57,
- "learning_rate": 0.00017117346938775511,
- "loss": 1.6515,
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
"step": 226
},
{
- "epoch": 4.59,
- "learning_rate": 0.00017104591836734694,
- "loss": 1.6586,
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
"step": 227
},
{
- "epoch": 4.61,
- "learning_rate": 0.00017091836734693878,
- "loss": 1.6355,
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
"step": 228
},
{
- "epoch": 4.63,
- "learning_rate": 0.00017079081632653063,
- "loss": 1.7173,
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
"step": 229
},
{
- "epoch": 4.65,
- "learning_rate": 0.00017066326530612246,
- "loss": 1.6585,
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
"step": 230
},
{
- "epoch": 4.67,
- "learning_rate": 0.0001705357142857143,
- "loss": 1.5856,
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
"step": 231
},
{
- "epoch": 4.69,
- "learning_rate": 0.00017040816326530613,
- "loss": 1.5923,
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
"step": 232
},
{
- "epoch": 4.71,
- "learning_rate": 0.00017028061224489798,
- "loss": 1.7128,
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
"step": 233
},
{
- "epoch": 4.73,
- "learning_rate": 0.0001701530612244898,
- "loss": 1.6971,
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
"step": 234
},
{
- "epoch": 4.75,
- "learning_rate": 0.00017002551020408165,
- "loss": 1.6416,
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
"step": 235
},
{
- "epoch": 4.78,
- "learning_rate": 0.00016989795918367348,
- "loss": 1.645,
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
"step": 236
},
{
- "epoch": 4.8,
- "learning_rate": 0.0001697704081632653,
- "loss": 1.6792,
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
"step": 237
},
{
- "epoch": 4.82,
- "learning_rate": 0.00016964285714285714,
- "loss": 1.6522,
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
"step": 238
},
{
- "epoch": 4.84,
- "learning_rate": 0.000169515306122449,
- "loss": 1.6315,
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
"step": 239
},
{
- "epoch": 4.86,
- "learning_rate": 0.00016938775510204083,
- "loss": 1.6622,
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
"step": 240
},
{
- "epoch": 4.88,
- "learning_rate": 0.00016926020408163266,
- "loss": 1.6566,
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
"step": 241
},
{
- "epoch": 4.9,
- "learning_rate": 0.0001691326530612245,
- "loss": 1.7141,
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
"step": 242
},
{
- "epoch": 4.92,
- "learning_rate": 0.00016900510204081635,
- "loss": 1.5873,
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
"step": 243
},
{
- "epoch": 4.94,
- "learning_rate": 0.00016887755102040818,
- "loss": 1.6571,
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
"step": 244
},
{
- "epoch": 4.96,
- "learning_rate": 0.00016875,
- "loss": 1.6829,
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
"step": 245
},
{
- "epoch": 4.98,
- "learning_rate": 0.00016862244897959184,
- "loss": 1.6935,
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
"step": 246
},
{
- "epoch": 5.0,
- "learning_rate": 0.00016849489795918367,
- "loss": 1.6782,
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
"step": 247
},
{
- "epoch": 5.02,
- "learning_rate": 0.00016836734693877553,
- "loss": 1.622,
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
"step": 248
},
{
- "epoch": 5.04,
- "learning_rate": 0.00016823979591836736,
- "loss": 1.6596,
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
"step": 249
},
{
- "epoch": 5.06,
- "learning_rate": 0.0001681122448979592,
- "loss": 1.5821,
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
"step": 250
},
{
- "epoch": 5.08,
- "learning_rate": 0.00016798469387755102,
- "loss": 1.7292,
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
"step": 251
},
{
- "epoch": 5.1,
- "learning_rate": 0.00016785714285714288,
- "loss": 1.646,
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
"step": 252
},
{
- "epoch": 5.12,
- "learning_rate": 0.0001677295918367347,
- "loss": 1.6969,
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
"step": 253
},
{
- "epoch": 5.14,
- "learning_rate": 0.00016760204081632654,
- "loss": 1.6082,
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
"step": 254
},
{
- "epoch": 5.16,
- "learning_rate": 0.00016747448979591837,
- "loss": 1.5843,
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
"step": 255
},
{
- "epoch": 5.18,
- "learning_rate": 0.00016734693877551023,
- "loss": 1.6827,
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
"step": 256
},
{
- "epoch": 5.2,
- "learning_rate": 0.00016721938775510203,
- "loss": 1.5824,
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
"step": 257
},
{
- "epoch": 5.22,
- "learning_rate": 0.0001670918367346939,
- "loss": 1.6795,
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
"step": 258
},
{
- "epoch": 5.24,
- "learning_rate": 0.00016696428571428572,
- "loss": 1.5639,
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
"step": 259
},
{
- "epoch": 5.26,
- "learning_rate": 0.00016683673469387755,
- "loss": 1.592,
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
"step": 260
},
{
- "epoch": 5.28,
- "learning_rate": 0.00016670918367346938,
- "loss": 1.65,
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
"step": 261
},
{
- "epoch": 5.3,
- "learning_rate": 0.00016658163265306124,
- "loss": 1.5592,
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
"step": 262
},
{
- "epoch": 5.32,
- "learning_rate": 0.00016645408163265305,
- "loss": 1.5091,
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
"step": 263
},
{
- "epoch": 5.34,
- "learning_rate": 0.0001663265306122449,
- "loss": 1.6138,
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
"step": 264
},
{
- "epoch": 5.36,
- "learning_rate": 0.00016619897959183673,
- "loss": 1.625,
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
"step": 265
},
{
- "epoch": 5.38,
- "learning_rate": 0.0001660714285714286,
- "loss": 1.5757,
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
"step": 266
},
{
- "epoch": 5.4,
- "learning_rate": 0.00016594387755102042,
- "loss": 1.6372,
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
"step": 267
},
{
- "epoch": 5.42,
- "learning_rate": 0.00016581632653061225,
- "loss": 1.5891,
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
"step": 268
},
{
- "epoch": 5.44,
- "learning_rate": 0.00016568877551020409,
- "loss": 1.6893,
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
"step": 269
},
{
- "epoch": 5.46,
- "learning_rate": 0.00016556122448979592,
- "loss": 1.6662,
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
"step": 270
},
{
- "epoch": 5.48,
- "learning_rate": 0.00016543367346938777,
- "loss": 1.7132,
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
"step": 271
},
{
- "epoch": 5.5,
- "learning_rate": 0.0001653061224489796,
- "loss": 1.5835,
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
"step": 272
},
{
- "epoch": 5.52,
- "learning_rate": 0.00016517857142857144,
- "loss": 1.6342,
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
"step": 273
},
{
- "epoch": 5.54,
- "learning_rate": 0.00016505102040816327,
- "loss": 1.6717,
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
"step": 274
},
{
- "epoch": 5.56,
- "learning_rate": 0.00016492346938775512,
- "loss": 1.6248,
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
"step": 275
},
{
- "epoch": 5.58,
- "learning_rate": 0.00016479591836734696,
- "loss": 1.6117,
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
"step": 276
},
{
- "epoch": 5.6,
- "learning_rate": 0.0001646683673469388,
- "loss": 1.6798,
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
"step": 277
},
{
- "epoch": 5.63,
- "learning_rate": 0.00016454081632653062,
- "loss": 1.6406,
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
"step": 278
},
{
- "epoch": 5.65,
- "learning_rate": 0.00016441326530612248,
- "loss": 1.6512,
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
"step": 279
},
{
- "epoch": 5.67,
- "learning_rate": 0.00016428571428571428,
- "loss": 1.6102,
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
"step": 280
},
{
- "epoch": 5.69,
- "learning_rate": 0.00016415816326530614,
- "loss": 1.6113,
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
"step": 281
},
{
- "epoch": 5.71,
- "learning_rate": 0.00016403061224489797,
- "loss": 1.7116,
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
"step": 282
},
{
- "epoch": 5.73,
- "learning_rate": 0.0001639030612244898,
- "loss": 1.6846,
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
"step": 283
},
{
- "epoch": 5.75,
- "learning_rate": 0.00016377551020408163,
- "loss": 1.6911,
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
"step": 284
},
{
- "epoch": 5.77,
- "learning_rate": 0.0001636479591836735,
- "loss": 1.6202,
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
"step": 285
},
{
- "epoch": 5.79,
- "learning_rate": 0.0001635204081632653,
- "loss": 1.5715,
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
"step": 286
},
{
- "epoch": 5.81,
- "learning_rate": 0.00016339285714285715,
- "loss": 1.6461,
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
"step": 287
},
{
- "epoch": 5.83,
- "learning_rate": 0.00016326530612244898,
- "loss": 1.6624,
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
"step": 288
},
{
- "epoch": 5.85,
- "learning_rate": 0.00016313775510204084,
- "loss": 1.6535,
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
"step": 289
},
{
- "epoch": 5.87,
- "learning_rate": 0.00016301020408163267,
- "loss": 1.6275,
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
"step": 290
},
{
- "epoch": 5.89,
- "learning_rate": 0.0001628826530612245,
- "loss": 1.6636,
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
"step": 291
},
{
- "epoch": 5.91,
- "learning_rate": 0.00016275510204081633,
- "loss": 1.6546,
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
"step": 292
},
{
- "epoch": 5.93,
- "learning_rate": 0.00016262755102040816,
- "loss": 1.7274,
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
"step": 293
},
{
- "epoch": 5.95,
- "learning_rate": 0.00016250000000000002,
- "loss": 1.5901,
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
"step": 294
},
{
- "epoch": 5.97,
- "learning_rate": 0.00016237244897959185,
- "loss": 1.6046,
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
"step": 295
},
{
- "epoch": 5.99,
- "learning_rate": 0.00016224489795918368,
- "loss": 1.5828,
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
"step": 296
},
{
- "epoch": 6.01,
- "learning_rate": 0.0001621173469387755,
- "loss": 1.6435,
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
"step": 297
},
{
- "epoch": 6.03,
- "learning_rate": 0.00016198979591836737,
- "loss": 1.6263,
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
"step": 298
},
{
- "epoch": 6.05,
- "learning_rate": 0.00016186224489795917,
- "loss": 1.4944,
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
"step": 299
},
{
- "epoch": 6.07,
- "learning_rate": 0.00016173469387755103,
- "loss": 1.6286,
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
"step": 300
},
{
- "epoch": 6.09,
- "learning_rate": 0.00016160714285714286,
- "loss": 1.694,
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
"step": 301
},
{
- "epoch": 6.11,
- "learning_rate": 0.00016147959183673472,
- "loss": 1.6197,
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
"step": 302
},
{
- "epoch": 6.13,
- "learning_rate": 0.00016135204081632652,
- "loss": 1.5597,
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
"step": 303
},
{
- "epoch": 6.15,
- "learning_rate": 0.00016122448979591838,
- "loss": 1.5487,
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
"step": 304
},
{
- "epoch": 6.17,
- "learning_rate": 0.0001610969387755102,
- "loss": 1.5769,
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
"step": 305
},
{
- "epoch": 6.19,
- "learning_rate": 0.00016096938775510204,
- "loss": 1.6367,
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
"step": 306
},
{
- "epoch": 6.21,
- "learning_rate": 0.00016084183673469388,
- "loss": 1.583,
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
"step": 307
},
{
- "epoch": 6.23,
- "learning_rate": 0.00016071428571428573,
- "loss": 1.6201,
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
"step": 308
},
{
- "epoch": 6.25,
- "learning_rate": 0.00016058673469387754,
- "loss": 1.6586,
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
"step": 309
},
{
- "epoch": 6.27,
- "learning_rate": 0.0001604591836734694,
- "loss": 1.6711,
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
"step": 310
},
{
- "epoch": 6.29,
- "learning_rate": 0.00016033163265306123,
- "loss": 1.6402,
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
"step": 311
},
{
- "epoch": 6.31,
- "learning_rate": 0.00016020408163265306,
- "loss": 1.5247,
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
"step": 312
},
{
- "epoch": 6.33,
- "learning_rate": 0.00016007653061224491,
- "loss": 1.5356,
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
"step": 313
},
{
- "epoch": 6.35,
- "learning_rate": 0.00015994897959183675,
- "loss": 1.564,
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
"step": 314
},
{
- "epoch": 6.37,
- "learning_rate": 0.00015982142857142858,
- "loss": 1.563,
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
"step": 315
},
{
- "epoch": 6.39,
- "learning_rate": 0.0001596938775510204,
- "loss": 1.5198,
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
"step": 316
},
{
- "epoch": 6.41,
- "learning_rate": 0.00015956632653061227,
- "loss": 1.6558,
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
"step": 317
},
{
- "epoch": 6.43,
- "learning_rate": 0.0001594387755102041,
- "loss": 1.5534,
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
"step": 318
},
{
- "epoch": 6.45,
- "learning_rate": 0.00015931122448979593,
- "loss": 1.6239,
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
"step": 319
},
{
- "epoch": 6.47,
- "learning_rate": 0.00015918367346938776,
- "loss": 1.5645,
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
"step": 320
},
{
- "epoch": 6.5,
- "learning_rate": 0.00015905612244897962,
- "loss": 1.5713,
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
"step": 321
},
{
- "epoch": 6.52,
- "learning_rate": 0.00015892857142857142,
- "loss": 1.6176,
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
"step": 322
},
{
- "epoch": 6.54,
- "learning_rate": 0.00015880102040816328,
- "loss": 1.502,
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
"step": 323
},
{
- "epoch": 6.56,
- "learning_rate": 0.0001586734693877551,
- "loss": 1.645,
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
"step": 324
},
{
- "epoch": 6.58,
- "learning_rate": 0.00015854591836734697,
- "loss": 1.5904,
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
"step": 325
},
{
- "epoch": 6.6,
- "learning_rate": 0.00015841836734693877,
- "loss": 1.6149,
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
"step": 326
},
{
- "epoch": 6.62,
- "learning_rate": 0.00015829081632653063,
- "loss": 1.6757,
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
"step": 327
},
{
- "epoch": 6.64,
- "learning_rate": 0.00015816326530612246,
- "loss": 1.541,
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
"step": 328
},
{
- "epoch": 6.66,
- "learning_rate": 0.0001580357142857143,
- "loss": 1.5898,
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
"step": 329
},
{
- "epoch": 6.68,
- "learning_rate": 0.00015790816326530612,
- "loss": 1.5441,
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
"step": 330
},
{
- "epoch": 6.7,
- "learning_rate": 0.00015778061224489798,
- "loss": 1.61,
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
"step": 331
},
{
- "epoch": 6.72,
- "learning_rate": 0.00015765306122448978,
- "loss": 1.615,
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
"step": 332
},
{
- "epoch": 6.74,
- "learning_rate": 0.00015752551020408164,
- "loss": 1.6575,
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
"step": 333
},
{
- "epoch": 6.76,
- "learning_rate": 0.00015739795918367347,
- "loss": 1.6702,
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
"step": 334
},
{
- "epoch": 6.78,
- "learning_rate": 0.0001572704081632653,
- "loss": 1.6009,
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
"step": 335
},
{
- "epoch": 6.8,
- "learning_rate": 0.00015714285714285716,
- "loss": 1.5568,
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
"step": 336
},
{
- "epoch": 6.82,
- "learning_rate": 0.000157015306122449,
- "loss": 1.619,
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
"step": 337
},
{
- "epoch": 6.84,
- "learning_rate": 0.00015688775510204082,
- "loss": 1.5563,
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
"step": 338
},
{
- "epoch": 6.86,
- "learning_rate": 0.00015676020408163265,
- "loss": 1.6328,
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
"step": 339
},
{
- "epoch": 6.88,
- "learning_rate": 0.0001566326530612245,
- "loss": 1.5726,
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
"step": 340
},
{
- "epoch": 6.9,
- "learning_rate": 0.00015650510204081634,
- "loss": 1.6199,
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
"step": 341
},
{
- "epoch": 6.92,
- "learning_rate": 0.00015637755102040817,
- "loss": 1.5722,
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
"step": 342
},
{
- "epoch": 6.94,
- "learning_rate": 0.00015625,
- "loss": 1.5685,
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
"step": 343
},
{
- "epoch": 6.96,
- "learning_rate": 0.00015612244897959186,
- "loss": 1.5615,
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
"step": 344
},
{
- "epoch": 6.98,
- "learning_rate": 0.00015599489795918366,
- "loss": 1.5994,
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
"step": 345
},
{
- "epoch": 7.0,
- "learning_rate": 0.00015586734693877552,
- "loss": 1.5579,
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
"step": 346
},
{
- "epoch": 7.02,
- "learning_rate": 0.00015573979591836735,
- "loss": 1.547,
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
"step": 347
},
{
- "epoch": 7.04,
- "learning_rate": 0.00015561224489795918,
- "loss": 1.5292,
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
"step": 348
},
{
- "epoch": 7.06,
- "learning_rate": 0.00015548469387755102,
- "loss": 1.6032,
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
"step": 349
},
{
- "epoch": 7.08,
- "learning_rate": 0.00015535714285714287,
- "loss": 1.5149,
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
"step": 350
},
{
- "epoch": 7.1,
- "learning_rate": 0.0001552295918367347,
- "loss": 1.6093,
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
"step": 351
},
{
- "epoch": 7.12,
- "learning_rate": 0.00015510204081632654,
- "loss": 1.5421,
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
"step": 352
},
{
- "epoch": 7.14,
- "learning_rate": 0.00015497448979591837,
- "loss": 1.5733,
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
"step": 353
},
{
- "epoch": 7.16,
- "learning_rate": 0.00015484693877551022,
- "loss": 1.5703,
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
"step": 354
},
{
- "epoch": 7.18,
- "learning_rate": 0.00015471938775510203,
- "loss": 1.6141,
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
"step": 355
},
{
- "epoch": 7.2,
- "learning_rate": 0.00015459183673469389,
- "loss": 1.5526,
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
"step": 356
},
{
- "epoch": 7.22,
- "learning_rate": 0.00015446428571428572,
- "loss": 1.5347,
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
"step": 357
},
{
- "epoch": 7.24,
- "learning_rate": 0.00015433673469387755,
- "loss": 1.5682,
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
"step": 358
},
{
- "epoch": 7.26,
- "learning_rate": 0.0001542091836734694,
- "loss": 1.5292,
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
"step": 359
},
{
- "epoch": 7.28,
- "learning_rate": 0.00015408163265306124,
- "loss": 1.499,
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
"step": 360
},
{
- "epoch": 7.3,
- "learning_rate": 0.00015395408163265307,
- "loss": 1.5624,
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
"step": 361
},
{
- "epoch": 7.32,
- "learning_rate": 0.0001538265306122449,
- "loss": 1.627,
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
"step": 362
},
{
- "epoch": 7.34,
- "learning_rate": 0.00015369897959183676,
- "loss": 1.5327,
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
"step": 363
},
{
- "epoch": 7.37,
- "learning_rate": 0.0001535714285714286,
- "loss": 1.5622,
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
"step": 364
},
{
- "epoch": 7.39,
- "learning_rate": 0.00015344387755102042,
- "loss": 1.5659,
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
"step": 365
},
{
- "epoch": 7.41,
- "learning_rate": 0.00015331632653061225,
- "loss": 1.5019,
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
"step": 366
},
{
- "epoch": 7.43,
- "learning_rate": 0.0001531887755102041,
- "loss": 1.5921,
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
"step": 367
},
{
- "epoch": 7.45,
- "learning_rate": 0.0001530612244897959,
- "loss": 1.5914,
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
"step": 368
},
{
- "epoch": 7.47,
- "learning_rate": 0.00015293367346938777,
- "loss": 1.5045,
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
"step": 369
},
{
- "epoch": 7.49,
- "learning_rate": 0.0001528061224489796,
- "loss": 1.6209,
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
"step": 370
},
{
- "epoch": 7.51,
- "learning_rate": 0.00015267857142857143,
- "loss": 1.5198,
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
"step": 371
},
{
- "epoch": 7.53,
- "learning_rate": 0.00015255102040816326,
- "loss": 1.5363,
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
"step": 372
},
{
- "epoch": 7.55,
- "learning_rate": 0.00015242346938775512,
- "loss": 1.5391,
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
"step": 373
},
{
- "epoch": 7.57,
- "learning_rate": 0.00015229591836734695,
- "loss": 1.4546,
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
"step": 374
},
{
- "epoch": 7.59,
- "learning_rate": 0.00015216836734693878,
- "loss": 1.5546,
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
"step": 375
},
{
- "epoch": 7.61,
- "learning_rate": 0.0001520408163265306,
- "loss": 1.5629,
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
"step": 376
},
{
- "epoch": 7.63,
- "learning_rate": 0.00015191326530612247,
- "loss": 1.6002,
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
"step": 377
},
{
- "epoch": 7.65,
- "learning_rate": 0.00015178571428571427,
- "loss": 1.5543,
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
"step": 378
},
{
- "epoch": 7.67,
- "learning_rate": 0.00015165816326530613,
- "loss": 1.5925,
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
"step": 379
},
{
- "epoch": 7.69,
- "learning_rate": 0.00015153061224489796,
- "loss": 1.5631,
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
"step": 380
},
{
- "epoch": 7.71,
- "learning_rate": 0.0001514030612244898,
- "loss": 1.5677,
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
"step": 381
},
{
- "epoch": 7.73,
- "learning_rate": 0.00015127551020408165,
- "loss": 1.5828,
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
"step": 382
},
{
- "epoch": 7.75,
- "learning_rate": 0.00015114795918367348,
- "loss": 1.6494,
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
"step": 383
},
{
- "epoch": 7.77,
- "learning_rate": 0.0001510204081632653,
- "loss": 1.553,
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
"step": 384
},
{
- "epoch": 7.79,
- "learning_rate": 0.00015089285714285714,
- "loss": 1.6156,
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
"step": 385
},
{
- "epoch": 7.81,
- "learning_rate": 0.000150765306122449,
- "loss": 1.5001,
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
"step": 386
},
{
- "epoch": 7.83,
- "learning_rate": 0.00015063775510204083,
- "loss": 1.5321,
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
"step": 387
},
{
- "epoch": 7.85,
- "learning_rate": 0.00015051020408163266,
- "loss": 1.5307,
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
"step": 388
},
{
- "epoch": 7.87,
- "learning_rate": 0.0001503826530612245,
- "loss": 1.5639,
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
"step": 389
},
{
- "epoch": 7.89,
- "learning_rate": 0.00015025510204081635,
- "loss": 1.517,
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
"step": 390
},
{
- "epoch": 7.91,
- "learning_rate": 0.00015012755102040816,
- "loss": 1.4776,
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
"step": 391
},
- {
- "epoch": 7.93,
- "learning_rate": 0.00015000000000000001,
- "loss": 1.5368,
+ {
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
"step": 392
},
{
- "epoch": 7.95,
- "learning_rate": 0.00014987244897959184,
- "loss": 1.5636,
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
"step": 393
},
{
- "epoch": 7.97,
- "learning_rate": 0.00014974489795918368,
- "loss": 1.6004,
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
"step": 394
},
{
- "epoch": 7.99,
- "learning_rate": 0.0001496173469387755,
- "loss": 1.5524,
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
"step": 395
},
{
- "epoch": 8.01,
- "learning_rate": 0.00014948979591836736,
- "loss": 1.5307,
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
"step": 396
},
{
- "epoch": 8.03,
- "learning_rate": 0.00014936224489795917,
- "loss": 1.5123,
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
"step": 397
},
{
- "epoch": 8.05,
- "learning_rate": 0.00014923469387755103,
- "loss": 1.5132,
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
"step": 398
},
{
- "epoch": 8.07,
- "learning_rate": 0.00014910714285714286,
- "loss": 1.5109,
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
"step": 399
},
{
- "epoch": 8.09,
- "learning_rate": 0.00014897959183673472,
- "loss": 1.5302,
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
"step": 400
},
{
- "epoch": 8.11,
- "learning_rate": 0.00014885204081632652,
- "loss": 1.5238,
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
"step": 401
},
{
- "epoch": 8.13,
- "learning_rate": 0.00014872448979591838,
- "loss": 1.4781,
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
"step": 402
},
{
- "epoch": 8.15,
- "learning_rate": 0.0001485969387755102,
- "loss": 1.5446,
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
"step": 403
},
{
- "epoch": 8.17,
- "learning_rate": 0.00014846938775510204,
- "loss": 1.5,
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
"step": 404
},
{
- "epoch": 8.19,
- "learning_rate": 0.0001483418367346939,
- "loss": 1.5458,
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
"step": 405
},
{
- "epoch": 8.21,
- "learning_rate": 0.00014821428571428573,
- "loss": 1.5257,
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
"step": 406
},
{
- "epoch": 8.24,
- "learning_rate": 0.00014808673469387756,
- "loss": 1.4607,
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
"step": 407
},
{
- "epoch": 8.26,
- "learning_rate": 0.0001479591836734694,
- "loss": 1.4282,
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
"step": 408
},
{
- "epoch": 8.28,
- "learning_rate": 0.00014783163265306125,
- "loss": 1.4519,
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
"step": 409
},
{
- "epoch": 8.3,
- "learning_rate": 0.00014770408163265305,
- "loss": 1.475,
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
"step": 410
},
{
- "epoch": 8.32,
- "learning_rate": 0.0001475765306122449,
- "loss": 1.5425,
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
"step": 411
},
{
- "epoch": 8.34,
- "learning_rate": 0.00014744897959183674,
- "loss": 1.5407,
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
"step": 412
},
{
- "epoch": 8.36,
- "learning_rate": 0.0001473214285714286,
- "loss": 1.5698,
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
"step": 413
},
{
- "epoch": 8.38,
- "learning_rate": 0.0001471938775510204,
- "loss": 1.4282,
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
"step": 414
},
{
- "epoch": 8.4,
- "learning_rate": 0.00014706632653061226,
- "loss": 1.5301,
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
"step": 415
},
{
- "epoch": 8.42,
- "learning_rate": 0.0001469387755102041,
- "loss": 1.5083,
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
"step": 416
},
{
- "epoch": 8.44,
- "learning_rate": 0.00014681122448979592,
- "loss": 1.5712,
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
"step": 417
},
{
- "epoch": 8.46,
- "learning_rate": 0.00014668367346938775,
- "loss": 1.4363,
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
"step": 418
},
{
- "epoch": 8.48,
- "learning_rate": 0.0001465561224489796,
- "loss": 1.4463,
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
"step": 419
},
{
- "epoch": 8.5,
- "learning_rate": 0.00014642857142857141,
- "loss": 1.4738,
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
"step": 420
},
{
- "epoch": 8.52,
- "learning_rate": 0.00014630102040816327,
- "loss": 1.5396,
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
"step": 421
},
{
- "epoch": 8.54,
- "learning_rate": 0.0001461734693877551,
- "loss": 1.4384,
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
"step": 422
},
{
- "epoch": 8.56,
- "learning_rate": 0.00014604591836734696,
- "loss": 1.5345,
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
"step": 423
},
{
- "epoch": 8.58,
- "learning_rate": 0.0001459183673469388,
- "loss": 1.5355,
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
"step": 424
},
{
- "epoch": 8.6,
- "learning_rate": 0.00014579081632653062,
- "loss": 1.5188,
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
"step": 425
},
{
- "epoch": 8.62,
- "learning_rate": 0.00014566326530612245,
- "loss": 1.5575,
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
"step": 426
},
{
- "epoch": 8.64,
- "learning_rate": 0.00014553571428571428,
- "loss": 1.5279,
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
"step": 427
},
{
- "epoch": 8.66,
- "learning_rate": 0.00014540816326530614,
- "loss": 1.5484,
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
"step": 428
},
{
- "epoch": 8.68,
- "learning_rate": 0.00014528061224489797,
- "loss": 1.4878,
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
"step": 429
},
{
- "epoch": 8.7,
- "learning_rate": 0.0001451530612244898,
- "loss": 1.503,
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
"step": 430
},
{
- "epoch": 8.72,
- "learning_rate": 0.00014502551020408163,
- "loss": 1.4723,
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
"step": 431
},
{
- "epoch": 8.74,
- "learning_rate": 0.0001448979591836735,
- "loss": 1.5579,
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
"step": 432
},
{
- "epoch": 8.76,
- "learning_rate": 0.0001447704081632653,
- "loss": 1.4789,
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
"step": 433
},
{
- "epoch": 8.78,
- "learning_rate": 0.00014464285714285715,
- "loss": 1.5501,
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
"step": 434
},
{
- "epoch": 8.8,
- "learning_rate": 0.00014451530612244899,
- "loss": 1.5204,
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
"step": 435
},
{
- "epoch": 8.82,
- "learning_rate": 0.00014438775510204084,
- "loss": 1.5489,
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
"step": 436
},
{
- "epoch": 8.84,
- "learning_rate": 0.00014426020408163265,
- "loss": 1.5464,
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
"step": 437
},
{
- "epoch": 8.86,
- "learning_rate": 0.0001441326530612245,
- "loss": 1.5896,
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
"step": 438
},
{
- "epoch": 8.88,
- "learning_rate": 0.00014400510204081634,
- "loss": 1.5465,
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
"step": 439
},
{
- "epoch": 8.9,
- "learning_rate": 0.00014387755102040817,
- "loss": 1.5094,
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
"step": 440
},
{
- "epoch": 8.92,
- "learning_rate": 0.00014375,
- "loss": 1.5144,
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
"step": 441
},
{
- "epoch": 8.94,
- "learning_rate": 0.00014362244897959186,
- "loss": 1.4919,
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
"step": 442
},
{
- "epoch": 8.96,
- "learning_rate": 0.00014349489795918366,
- "loss": 1.4702,
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
"step": 443
},
{
- "epoch": 8.98,
- "learning_rate": 0.00014336734693877552,
- "loss": 1.4996,
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
"step": 444
},
{
- "epoch": 9.0,
- "learning_rate": 0.00014323979591836735,
- "loss": 1.5503,
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
"step": 445
},
{
- "epoch": 9.02,
- "learning_rate": 0.00014311224489795918,
- "loss": 1.4125,
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
"step": 446
},
{
- "epoch": 9.04,
- "learning_rate": 0.00014298469387755104,
- "loss": 1.4722,
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
"step": 447
},
{
- "epoch": 9.06,
- "learning_rate": 0.00014285714285714287,
- "loss": 1.5199,
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
"step": 448
},
{
- "epoch": 9.09,
- "learning_rate": 0.0001427295918367347,
- "loss": 1.4571,
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
"step": 449
},
{
- "epoch": 9.11,
- "learning_rate": 0.00014260204081632653,
- "loss": 1.4996,
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
"step": 450
},
{
- "epoch": 9.13,
- "learning_rate": 0.0001424744897959184,
- "loss": 1.4092,
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
"step": 451
},
{
- "epoch": 9.15,
- "learning_rate": 0.00014234693877551022,
- "loss": 1.4198,
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
"step": 452
},
{
- "epoch": 9.17,
- "learning_rate": 0.00014221938775510205,
- "loss": 1.4916,
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
"step": 453
},
{
- "epoch": 9.19,
- "learning_rate": 0.00014209183673469388,
- "loss": 1.5051,
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
"step": 454
},
{
- "epoch": 9.21,
- "learning_rate": 0.00014196428571428574,
- "loss": 1.4321,
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
"step": 455
},
{
- "epoch": 9.23,
- "learning_rate": 0.00014183673469387754,
- "loss": 1.4097,
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
"step": 456
},
{
- "epoch": 9.25,
- "learning_rate": 0.0001417091836734694,
- "loss": 1.4853,
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
"step": 457
},
{
- "epoch": 9.27,
- "learning_rate": 0.00014158163265306123,
- "loss": 1.4593,
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
"step": 458
},
{
- "epoch": 9.29,
- "learning_rate": 0.00014145408163265306,
- "loss": 1.3729,
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
"step": 459
},
{
- "epoch": 9.31,
- "learning_rate": 0.0001413265306122449,
- "loss": 1.4467,
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
"step": 460
},
{
- "epoch": 9.33,
- "learning_rate": 0.00014119897959183675,
- "loss": 1.4467,
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
"step": 461
},
{
- "epoch": 9.35,
- "learning_rate": 0.00014107142857142858,
- "loss": 1.4785,
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
"step": 462
},
{
- "epoch": 9.37,
- "learning_rate": 0.0001409438775510204,
- "loss": 1.4089,
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
"step": 463
},
{
- "epoch": 9.39,
- "learning_rate": 0.00014081632653061224,
- "loss": 1.5026,
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
"step": 464
},
{
- "epoch": 9.41,
- "learning_rate": 0.0001406887755102041,
- "loss": 1.4857,
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
"step": 465
},
{
- "epoch": 9.43,
- "learning_rate": 0.0001405612244897959,
- "loss": 1.3745,
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
"step": 466
},
{
- "epoch": 9.45,
- "learning_rate": 0.00014043367346938776,
- "loss": 1.4733,
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
"step": 467
},
{
- "epoch": 9.47,
- "learning_rate": 0.0001403061224489796,
- "loss": 1.5212,
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
"step": 468
},
{
- "epoch": 9.49,
- "learning_rate": 0.00014017857142857142,
- "loss": 1.5398,
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
"step": 469
},
{
- "epoch": 9.51,
- "learning_rate": 0.00014005102040816328,
- "loss": 1.478,
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
"step": 470
},
{
- "epoch": 9.53,
- "learning_rate": 0.0001399234693877551,
- "loss": 1.496,
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
"step": 471
},
{
- "epoch": 9.55,
- "learning_rate": 0.00013979591836734694,
- "loss": 1.4837,
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
"step": 472
},
{
- "epoch": 9.57,
- "learning_rate": 0.00013966836734693878,
- "loss": 1.4724,
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
"step": 473
},
{
- "epoch": 9.59,
- "learning_rate": 0.00013954081632653063,
- "loss": 1.4828,
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
"step": 474
},
{
- "epoch": 9.61,
- "learning_rate": 0.00013941326530612246,
- "loss": 1.5012,
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
"step": 475
},
{
- "epoch": 9.63,
- "learning_rate": 0.0001392857142857143,
- "loss": 1.4879,
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
"step": 476
},
{
- "epoch": 9.65,
- "learning_rate": 0.00013915816326530613,
- "loss": 1.4196,
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
"step": 477
},
{
- "epoch": 9.67,
- "learning_rate": 0.00013903061224489798,
- "loss": 1.4915,
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
"step": 478
},
{
- "epoch": 9.69,
- "learning_rate": 0.0001389030612244898,
- "loss": 1.3878,
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
"step": 479
},
{
- "epoch": 9.71,
- "learning_rate": 0.00013877551020408165,
- "loss": 1.466,
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
"step": 480
},
{
- "epoch": 9.73,
- "learning_rate": 0.00013864795918367348,
- "loss": 1.4582,
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
"step": 481
},
{
- "epoch": 9.75,
- "learning_rate": 0.0001385204081632653,
- "loss": 1.533,
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
"step": 482
},
{
- "epoch": 9.77,
- "learning_rate": 0.00013839285714285714,
- "loss": 1.4697,
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
"step": 483
},
{
- "epoch": 9.79,
- "learning_rate": 0.000138265306122449,
- "loss": 1.3989,
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
"step": 484
},
{
- "epoch": 9.81,
- "learning_rate": 0.00013813775510204083,
- "loss": 1.4361,
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
"step": 485
},
{
- "epoch": 9.83,
- "learning_rate": 0.00013801020408163266,
- "loss": 1.5271,
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
"step": 486
},
{
- "epoch": 9.85,
- "learning_rate": 0.0001378826530612245,
- "loss": 1.4905,
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
"step": 487
},
{
- "epoch": 9.87,
- "learning_rate": 0.00013775510204081635,
- "loss": 1.4757,
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
"step": 488
},
{
- "epoch": 9.89,
- "learning_rate": 0.00013762755102040815,
- "loss": 1.5485,
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
"step": 489
},
{
- "epoch": 9.91,
- "learning_rate": 0.0001375,
- "loss": 1.4783,
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
"step": 490
},
{
- "epoch": 9.93,
- "learning_rate": 0.00013737244897959184,
- "loss": 1.4849,
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
"step": 491
},
{
- "epoch": 9.96,
- "learning_rate": 0.00013724489795918367,
- "loss": 1.5382,
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
"step": 492
},
{
- "epoch": 9.98,
- "learning_rate": 0.00013711734693877553,
- "loss": 1.4902,
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
"step": 493
},
{
- "epoch": 10.0,
- "learning_rate": 0.00013698979591836736,
- "loss": 1.4865,
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
"step": 494
},
{
- "epoch": 10.02,
- "learning_rate": 0.0001368622448979592,
- "loss": 1.4436,
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
"step": 495
},
{
- "epoch": 10.04,
- "learning_rate": 0.00013673469387755102,
- "loss": 1.408,
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
"step": 496
},
{
- "epoch": 10.06,
- "learning_rate": 0.00013660714285714288,
- "loss": 1.4764,
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
"step": 497
},
{
- "epoch": 10.08,
- "learning_rate": 0.0001364795918367347,
- "loss": 1.4646,
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
"step": 498
},
{
- "epoch": 10.1,
- "learning_rate": 0.00013635204081632654,
- "loss": 1.406,
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
"step": 499
},
{
- "epoch": 10.12,
- "learning_rate": 0.00013622448979591837,
- "loss": 1.4785,
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
"step": 500
},
{
- "epoch": 10.14,
- "learning_rate": 0.00013609693877551023,
- "loss": 1.4117,
+ "epoch": 5.66,
+ "learning_rate": 0.00012883522727272727,
+ "loss": 1.0755,
"step": 501
},
{
- "epoch": 10.16,
- "learning_rate": 0.00013596938775510203,
- "loss": 1.4108,
+ "epoch": 5.67,
+ "learning_rate": 0.00012869318181818183,
+ "loss": 1.0755,
"step": 502
},
{
- "epoch": 10.18,
- "learning_rate": 0.0001358418367346939,
- "loss": 1.4155,
+ "epoch": 5.68,
+ "learning_rate": 0.00012855113636363636,
+ "loss": 1.0869,
"step": 503
},
{
- "epoch": 10.2,
- "learning_rate": 0.00013571428571428572,
- "loss": 1.4021,
+ "epoch": 5.69,
+ "learning_rate": 0.00012840909090909092,
+ "loss": 1.0673,
"step": 504
},
{
- "epoch": 10.22,
- "learning_rate": 0.00013558673469387755,
- "loss": 1.411,
+ "epoch": 5.71,
+ "learning_rate": 0.00012826704545454545,
+ "loss": 1.0692,
"step": 505
},
{
- "epoch": 10.24,
- "learning_rate": 0.00013545918367346938,
- "loss": 1.3851,
+ "epoch": 5.72,
+ "learning_rate": 0.000128125,
+ "loss": 1.0474,
"step": 506
},
{
- "epoch": 10.26,
- "learning_rate": 0.00013533163265306124,
- "loss": 1.387,
+ "epoch": 5.73,
+ "learning_rate": 0.00012798295454545454,
+ "loss": 1.0749,
"step": 507
},
{
- "epoch": 10.28,
- "learning_rate": 0.00013520408163265305,
- "loss": 1.4163,
+ "epoch": 5.74,
+ "learning_rate": 0.0001278409090909091,
+ "loss": 1.0519,
"step": 508
},
{
- "epoch": 10.3,
- "learning_rate": 0.0001350765306122449,
- "loss": 1.3343,
+ "epoch": 5.75,
+ "learning_rate": 0.00012769886363636366,
+ "loss": 1.0566,
"step": 509
},
{
- "epoch": 10.32,
- "learning_rate": 0.00013494897959183673,
- "loss": 1.4811,
+ "epoch": 5.76,
+ "learning_rate": 0.0001275568181818182,
+ "loss": 1.06,
"step": 510
},
{
- "epoch": 10.34,
- "learning_rate": 0.0001348214285714286,
- "loss": 1.4086,
+ "epoch": 5.77,
+ "learning_rate": 0.00012741477272727272,
+ "loss": 1.0618,
"step": 511
},
{
- "epoch": 10.36,
- "learning_rate": 0.0001346938775510204,
- "loss": 1.3879,
+ "epoch": 5.78,
+ "learning_rate": 0.00012727272727272728,
+ "loss": 1.0643,
"step": 512
},
{
- "epoch": 10.38,
- "learning_rate": 0.00013456632653061225,
- "loss": 1.4204,
+ "epoch": 5.8,
+ "learning_rate": 0.0001271306818181818,
+ "loss": 1.026,
"step": 513
},
{
- "epoch": 10.4,
- "learning_rate": 0.00013443877551020408,
- "loss": 1.4158,
+ "epoch": 5.81,
+ "learning_rate": 0.00012698863636363637,
+ "loss": 1.0335,
"step": 514
},
{
- "epoch": 10.42,
- "learning_rate": 0.00013431122448979592,
- "loss": 1.4521,
+ "epoch": 5.82,
+ "learning_rate": 0.00012684659090909093,
+ "loss": 1.0205,
"step": 515
},
{
- "epoch": 10.44,
- "learning_rate": 0.00013418367346938777,
- "loss": 1.4196,
+ "epoch": 5.83,
+ "learning_rate": 0.00012670454545454546,
+ "loss": 1.0594,
"step": 516
},
{
- "epoch": 10.46,
- "learning_rate": 0.0001340561224489796,
- "loss": 1.4361,
+ "epoch": 5.84,
+ "learning_rate": 0.0001265625,
+ "loss": 1.0136,
"step": 517
},
{
- "epoch": 10.48,
- "learning_rate": 0.00013392857142857144,
- "loss": 1.4482,
+ "epoch": 5.85,
+ "learning_rate": 0.00012642045454545455,
+ "loss": 1.0244,
"step": 518
},
{
- "epoch": 10.5,
- "learning_rate": 0.00013380102040816327,
- "loss": 1.4801,
+ "epoch": 5.86,
+ "learning_rate": 0.00012627840909090908,
+ "loss": 1.0569,
"step": 519
},
{
- "epoch": 10.52,
- "learning_rate": 0.00013367346938775512,
- "loss": 1.4556,
+ "epoch": 5.87,
+ "learning_rate": 0.00012613636363636364,
+ "loss": 1.0416,
"step": 520
},
{
- "epoch": 10.54,
- "learning_rate": 0.00013354591836734695,
- "loss": 1.3902,
+ "epoch": 5.89,
+ "learning_rate": 0.0001259943181818182,
+ "loss": 0.9884,
"step": 521
},
{
- "epoch": 10.56,
- "learning_rate": 0.00013341836734693879,
- "loss": 1.4269,
+ "epoch": 5.9,
+ "learning_rate": 0.00012585227272727273,
+ "loss": 1.0351,
"step": 522
},
{
- "epoch": 10.58,
- "learning_rate": 0.00013329081632653062,
- "loss": 1.4899,
+ "epoch": 5.91,
+ "learning_rate": 0.00012571022727272726,
+ "loss": 1.0037,
"step": 523
},
{
- "epoch": 10.6,
- "learning_rate": 0.00013316326530612247,
- "loss": 1.3952,
+ "epoch": 5.92,
+ "learning_rate": 0.00012556818181818182,
+ "loss": 1.0219,
"step": 524
},
{
- "epoch": 10.62,
- "learning_rate": 0.00013303571428571428,
- "loss": 1.4116,
+ "epoch": 5.93,
+ "learning_rate": 0.00012542613636363635,
+ "loss": 1.0533,
"step": 525
},
{
- "epoch": 10.64,
- "learning_rate": 0.00013290816326530614,
- "loss": 1.4583,
+ "epoch": 5.94,
+ "learning_rate": 0.0001252840909090909,
+ "loss": 1.0031,
"step": 526
},
{
- "epoch": 10.66,
- "learning_rate": 0.00013278061224489797,
- "loss": 1.4466,
+ "epoch": 5.95,
+ "learning_rate": 0.00012514204545454547,
+ "loss": 1.0454,
"step": 527
},
{
- "epoch": 10.68,
- "learning_rate": 0.0001326530612244898,
- "loss": 1.4242,
+ "epoch": 5.97,
+ "learning_rate": 0.000125,
+ "loss": 1.0195,
"step": 528
},
{
- "epoch": 10.7,
- "learning_rate": 0.00013252551020408163,
- "loss": 1.3717,
+ "epoch": 5.98,
+ "learning_rate": 0.00012485795454545453,
+ "loss": 1.0076,
"step": 529
},
{
- "epoch": 10.72,
- "learning_rate": 0.0001323979591836735,
- "loss": 1.4583,
+ "epoch": 5.99,
+ "learning_rate": 0.0001247159090909091,
+ "loss": 1.0378,
"step": 530
},
{
- "epoch": 10.74,
- "learning_rate": 0.0001322704081632653,
- "loss": 1.4185,
+ "epoch": 6.0,
+ "learning_rate": 0.00012457386363636365,
+ "loss": 0.9795,
"step": 531
},
{
- "epoch": 10.76,
- "learning_rate": 0.00013214285714285715,
- "loss": 1.4287,
+ "epoch": 6.01,
+ "learning_rate": 0.00012443181818181818,
+ "loss": 0.9405,
"step": 532
},
{
- "epoch": 10.78,
- "learning_rate": 0.00013201530612244898,
- "loss": 1.4385,
+ "epoch": 6.02,
+ "learning_rate": 0.00012428977272727274,
+ "loss": 0.9503,
"step": 533
},
{
- "epoch": 10.8,
- "learning_rate": 0.00013188775510204084,
- "loss": 1.453,
+ "epoch": 6.03,
+ "learning_rate": 0.00012414772727272727,
+ "loss": 0.9456,
"step": 534
},
{
- "epoch": 10.83,
- "learning_rate": 0.00013176020408163264,
- "loss": 1.4161,
+ "epoch": 6.04,
+ "learning_rate": 0.0001240056818181818,
+ "loss": 0.9536,
"step": 535
},
{
- "epoch": 10.85,
- "learning_rate": 0.0001316326530612245,
- "loss": 1.457,
+ "epoch": 6.06,
+ "learning_rate": 0.00012386363636363636,
+ "loss": 0.9412,
"step": 536
},
{
- "epoch": 10.87,
- "learning_rate": 0.00013150510204081633,
- "loss": 1.4367,
+ "epoch": 6.07,
+ "learning_rate": 0.00012372159090909092,
+ "loss": 0.9315,
"step": 537
},
{
- "epoch": 10.89,
- "learning_rate": 0.00013137755102040816,
- "loss": 1.4256,
+ "epoch": 6.08,
+ "learning_rate": 0.00012357954545454545,
+ "loss": 0.9486,
"step": 538
},
{
- "epoch": 10.91,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.424,
+ "epoch": 6.09,
+ "learning_rate": 0.0001234375,
+ "loss": 0.9405,
"step": 539
},
{
- "epoch": 10.93,
- "learning_rate": 0.00013112244897959185,
- "loss": 1.3923,
+ "epoch": 6.1,
+ "learning_rate": 0.00012329545454545454,
+ "loss": 0.9269,
"step": 540
},
{
- "epoch": 10.95,
- "learning_rate": 0.00013099489795918368,
- "loss": 1.4225,
+ "epoch": 6.11,
+ "learning_rate": 0.0001231534090909091,
+ "loss": 0.9378,
"step": 541
},
{
- "epoch": 10.97,
- "learning_rate": 0.0001308673469387755,
- "loss": 1.3969,
+ "epoch": 6.12,
+ "learning_rate": 0.00012301136363636366,
+ "loss": 0.9431,
"step": 542
},
{
- "epoch": 10.99,
- "learning_rate": 0.00013073979591836737,
- "loss": 1.4446,
+ "epoch": 6.13,
+ "learning_rate": 0.0001228693181818182,
+ "loss": 0.9256,
"step": 543
},
{
- "epoch": 11.01,
- "learning_rate": 0.00013061224489795917,
- "loss": 1.4375,
+ "epoch": 6.15,
+ "learning_rate": 0.00012272727272727272,
+ "loss": 0.919,
"step": 544
},
{
- "epoch": 11.03,
- "learning_rate": 0.00013048469387755103,
- "loss": 1.4064,
+ "epoch": 6.16,
+ "learning_rate": 0.00012258522727272728,
+ "loss": 0.9188,
"step": 545
},
{
- "epoch": 11.05,
- "learning_rate": 0.00013035714285714286,
- "loss": 1.3454,
+ "epoch": 6.17,
+ "learning_rate": 0.00012244318181818181,
+ "loss": 0.9447,
"step": 546
},
{
- "epoch": 11.07,
- "learning_rate": 0.00013022959183673472,
- "loss": 1.3234,
+ "epoch": 6.18,
+ "learning_rate": 0.00012230113636363637,
+ "loss": 0.9261,
"step": 547
},
{
- "epoch": 11.09,
- "learning_rate": 0.00013010204081632652,
- "loss": 1.3759,
+ "epoch": 6.19,
+ "learning_rate": 0.00012215909090909093,
+ "loss": 0.9302,
"step": 548
},
{
- "epoch": 11.11,
- "learning_rate": 0.00012997448979591838,
- "loss": 1.4221,
+ "epoch": 6.2,
+ "learning_rate": 0.00012201704545454546,
+ "loss": 0.9161,
"step": 549
},
{
- "epoch": 11.13,
- "learning_rate": 0.0001298469387755102,
- "loss": 1.4261,
+ "epoch": 6.21,
+ "learning_rate": 0.00012187500000000001,
+ "loss": 0.9521,
"step": 550
},
{
- "epoch": 11.15,
- "learning_rate": 0.00012971938775510204,
- "loss": 1.3341,
+ "epoch": 6.22,
+ "learning_rate": 0.00012173295454545455,
+ "loss": 0.9026,
"step": 551
},
{
- "epoch": 11.17,
- "learning_rate": 0.00012959183673469387,
- "loss": 1.3994,
+ "epoch": 6.24,
+ "learning_rate": 0.00012159090909090908,
+ "loss": 0.9361,
"step": 552
},
{
- "epoch": 11.19,
- "learning_rate": 0.00012946428571428573,
- "loss": 1.3894,
+ "epoch": 6.25,
+ "learning_rate": 0.00012144886363636366,
+ "loss": 0.8944,
"step": 553
},
{
- "epoch": 11.21,
- "learning_rate": 0.00012933673469387754,
- "loss": 1.3585,
+ "epoch": 6.26,
+ "learning_rate": 0.00012130681818181819,
+ "loss": 0.895,
"step": 554
},
{
- "epoch": 11.23,
- "learning_rate": 0.0001292091836734694,
- "loss": 1.3763,
+ "epoch": 6.27,
+ "learning_rate": 0.00012116477272727273,
+ "loss": 0.8956,
"step": 555
},
{
- "epoch": 11.25,
- "learning_rate": 0.00012908163265306123,
- "loss": 1.3623,
+ "epoch": 6.28,
+ "learning_rate": 0.00012102272727272728,
+ "loss": 0.8998,
"step": 556
},
{
- "epoch": 11.27,
- "learning_rate": 0.00012895408163265306,
- "loss": 1.3907,
+ "epoch": 6.29,
+ "learning_rate": 0.00012088068181818182,
+ "loss": 0.915,
"step": 557
},
{
- "epoch": 11.29,
- "learning_rate": 0.0001288265306122449,
- "loss": 1.3807,
+ "epoch": 6.3,
+ "learning_rate": 0.00012073863636363636,
+ "loss": 0.9282,
"step": 558
},
{
- "epoch": 11.31,
- "learning_rate": 0.00012869897959183674,
- "loss": 1.4045,
+ "epoch": 6.32,
+ "learning_rate": 0.00012059659090909093,
+ "loss": 0.8938,
"step": 559
},
{
- "epoch": 11.33,
- "learning_rate": 0.00012857142857142858,
- "loss": 1.4038,
+ "epoch": 6.33,
+ "learning_rate": 0.00012045454545454546,
+ "loss": 0.8886,
"step": 560
},
{
- "epoch": 11.35,
- "learning_rate": 0.0001284438775510204,
- "loss": 1.3466,
+ "epoch": 6.34,
+ "learning_rate": 0.0001203125,
+ "loss": 0.8988,
"step": 561
},
{
- "epoch": 11.37,
- "learning_rate": 0.00012831632653061226,
- "loss": 1.3449,
+ "epoch": 6.35,
+ "learning_rate": 0.00012017045454545455,
+ "loss": 0.8852,
"step": 562
},
{
- "epoch": 11.39,
- "learning_rate": 0.0001281887755102041,
- "loss": 1.3866,
+ "epoch": 6.36,
+ "learning_rate": 0.0001200284090909091,
+ "loss": 0.8818,
"step": 563
},
{
- "epoch": 11.41,
- "learning_rate": 0.00012806122448979593,
- "loss": 1.3106,
+ "epoch": 6.37,
+ "learning_rate": 0.00011988636363636365,
+ "loss": 0.8881,
"step": 564
},
{
- "epoch": 11.43,
- "learning_rate": 0.00012793367346938776,
- "loss": 1.4414,
+ "epoch": 6.38,
+ "learning_rate": 0.0001197443181818182,
+ "loss": 0.9226,
"step": 565
},
{
- "epoch": 11.45,
- "learning_rate": 0.00012780612244897962,
- "loss": 1.3737,
+ "epoch": 6.39,
+ "learning_rate": 0.00011960227272727273,
+ "loss": 0.8849,
"step": 566
},
{
- "epoch": 11.47,
- "learning_rate": 0.00012767857142857142,
- "loss": 1.4053,
+ "epoch": 6.41,
+ "learning_rate": 0.00011946022727272727,
+ "loss": 0.8894,
"step": 567
},
{
- "epoch": 11.49,
- "learning_rate": 0.00012755102040816328,
- "loss": 1.4561,
+ "epoch": 6.42,
+ "learning_rate": 0.00011931818181818182,
+ "loss": 0.9207,
"step": 568
},
{
- "epoch": 11.51,
- "learning_rate": 0.0001274234693877551,
- "loss": 1.3684,
+ "epoch": 6.43,
+ "learning_rate": 0.00011917613636363636,
+ "loss": 0.9105,
"step": 569
},
{
- "epoch": 11.53,
- "learning_rate": 0.00012729591836734697,
- "loss": 1.3117,
+ "epoch": 6.44,
+ "learning_rate": 0.00011903409090909092,
+ "loss": 0.8762,
"step": 570
},
{
- "epoch": 11.55,
- "learning_rate": 0.00012716836734693877,
- "loss": 1.3474,
+ "epoch": 6.45,
+ "learning_rate": 0.00011889204545454547,
+ "loss": 0.8926,
"step": 571
},
{
- "epoch": 11.57,
- "learning_rate": 0.00012704081632653063,
- "loss": 1.3804,
+ "epoch": 6.46,
+ "learning_rate": 0.00011875,
+ "loss": 0.8719,
"step": 572
},
{
- "epoch": 11.59,
- "learning_rate": 0.00012691326530612246,
- "loss": 1.3656,
+ "epoch": 6.47,
+ "learning_rate": 0.00011860795454545454,
+ "loss": 0.9198,
"step": 573
},
{
- "epoch": 11.61,
- "learning_rate": 0.0001267857142857143,
- "loss": 1.3133,
+ "epoch": 6.48,
+ "learning_rate": 0.00011846590909090909,
+ "loss": 0.8846,
"step": 574
},
{
- "epoch": 11.63,
- "learning_rate": 0.00012665816326530612,
- "loss": 1.4077,
+ "epoch": 6.5,
+ "learning_rate": 0.00011832386363636365,
+ "loss": 0.8495,
"step": 575
},
{
- "epoch": 11.65,
- "learning_rate": 0.00012653061224489798,
- "loss": 1.4087,
+ "epoch": 6.51,
+ "learning_rate": 0.0001181818181818182,
+ "loss": 0.8953,
"step": 576
},
{
- "epoch": 11.67,
- "learning_rate": 0.00012640306122448978,
- "loss": 1.3524,
+ "epoch": 6.52,
+ "learning_rate": 0.00011803977272727274,
+ "loss": 0.8686,
"step": 577
},
{
- "epoch": 11.7,
- "learning_rate": 0.00012627551020408164,
- "loss": 1.3481,
+ "epoch": 6.53,
+ "learning_rate": 0.00011789772727272727,
+ "loss": 0.8841,
"step": 578
},
{
- "epoch": 11.72,
- "learning_rate": 0.00012614795918367347,
- "loss": 1.4497,
+ "epoch": 6.54,
+ "learning_rate": 0.00011775568181818182,
+ "loss": 0.8681,
"step": 579
},
{
- "epoch": 11.74,
- "learning_rate": 0.0001260204081632653,
- "loss": 1.3866,
+ "epoch": 6.55,
+ "learning_rate": 0.00011761363636363636,
+ "loss": 0.8732,
"step": 580
},
{
- "epoch": 11.76,
- "learning_rate": 0.00012589285714285713,
- "loss": 1.42,
+ "epoch": 6.56,
+ "learning_rate": 0.00011747159090909092,
+ "loss": 0.8582,
"step": 581
},
{
- "epoch": 11.78,
- "learning_rate": 0.000125765306122449,
- "loss": 1.3562,
+ "epoch": 6.58,
+ "learning_rate": 0.00011732954545454546,
+ "loss": 0.8744,
"step": 582
},
{
- "epoch": 11.8,
- "learning_rate": 0.00012563775510204082,
- "loss": 1.3249,
+ "epoch": 6.59,
+ "learning_rate": 0.00011718750000000001,
+ "loss": 0.8694,
"step": 583
},
{
- "epoch": 11.82,
- "learning_rate": 0.00012551020408163265,
- "loss": 1.4277,
+ "epoch": 6.6,
+ "learning_rate": 0.00011704545454545454,
+ "loss": 0.8565,
"step": 584
},
{
- "epoch": 11.84,
- "learning_rate": 0.0001253826530612245,
- "loss": 1.3734,
+ "epoch": 6.61,
+ "learning_rate": 0.00011690340909090909,
+ "loss": 0.8584,
"step": 585
},
{
- "epoch": 11.86,
- "learning_rate": 0.00012525510204081634,
- "loss": 1.3765,
+ "epoch": 6.62,
+ "learning_rate": 0.00011676136363636366,
+ "loss": 0.8859,
"step": 586
},
{
- "epoch": 11.88,
- "learning_rate": 0.00012512755102040817,
- "loss": 1.4153,
+ "epoch": 6.63,
+ "learning_rate": 0.00011661931818181819,
+ "loss": 0.8452,
"step": 587
},
{
- "epoch": 11.9,
- "learning_rate": 0.000125,
- "loss": 1.3847,
+ "epoch": 6.64,
+ "learning_rate": 0.00011647727272727273,
+ "loss": 0.8323,
"step": 588
},
{
- "epoch": 11.92,
- "learning_rate": 0.00012487244897959186,
- "loss": 1.3824,
+ "epoch": 6.65,
+ "learning_rate": 0.00011633522727272728,
+ "loss": 0.8548,
"step": 589
},
{
- "epoch": 11.94,
- "learning_rate": 0.00012474489795918366,
- "loss": 1.3938,
+ "epoch": 6.67,
+ "learning_rate": 0.00011619318181818181,
+ "loss": 0.8506,
"step": 590
},
{
- "epoch": 11.96,
- "learning_rate": 0.00012461734693877552,
- "loss": 1.4143,
+ "epoch": 6.68,
+ "learning_rate": 0.00011605113636363636,
+ "loss": 0.8556,
"step": 591
},
{
- "epoch": 11.98,
- "learning_rate": 0.00012448979591836735,
- "loss": 1.3794,
+ "epoch": 6.69,
+ "learning_rate": 0.00011590909090909093,
+ "loss": 0.8459,
"step": 592
},
{
- "epoch": 12.0,
- "learning_rate": 0.00012436224489795918,
- "loss": 1.3755,
+ "epoch": 6.7,
+ "learning_rate": 0.00011576704545454546,
+ "loss": 0.8432,
"step": 593
},
{
- "epoch": 12.02,
- "learning_rate": 0.00012423469387755101,
- "loss": 1.3736,
+ "epoch": 6.71,
+ "learning_rate": 0.000115625,
+ "loss": 0.8645,
"step": 594
},
{
- "epoch": 12.04,
- "learning_rate": 0.00012410714285714287,
- "loss": 1.2957,
+ "epoch": 6.72,
+ "learning_rate": 0.00011548295454545455,
+ "loss": 0.86,
"step": 595
},
{
- "epoch": 12.06,
- "learning_rate": 0.0001239795918367347,
- "loss": 1.2996,
+ "epoch": 6.73,
+ "learning_rate": 0.00011534090909090908,
+ "loss": 0.8161,
"step": 596
},
{
- "epoch": 12.08,
- "learning_rate": 0.00012385204081632653,
- "loss": 1.3648,
+ "epoch": 6.74,
+ "learning_rate": 0.00011519886363636365,
+ "loss": 0.8133,
"step": 597
},
{
- "epoch": 12.1,
- "learning_rate": 0.00012372448979591837,
- "loss": 1.3031,
+ "epoch": 6.76,
+ "learning_rate": 0.0001150568181818182,
+ "loss": 0.8372,
"step": 598
},
{
- "epoch": 12.12,
- "learning_rate": 0.00012359693877551022,
- "loss": 1.2933,
+ "epoch": 6.77,
+ "learning_rate": 0.00011491477272727273,
+ "loss": 0.8222,
"step": 599
},
{
- "epoch": 12.14,
- "learning_rate": 0.00012346938775510203,
- "loss": 1.322,
+ "epoch": 6.78,
+ "learning_rate": 0.00011477272727272728,
+ "loss": 0.8372,
"step": 600
},
{
- "epoch": 12.16,
- "learning_rate": 0.00012334183673469389,
- "loss": 1.3123,
+ "epoch": 6.79,
+ "learning_rate": 0.00011463068181818182,
+ "loss": 0.837,
"step": 601
},
{
- "epoch": 12.18,
- "learning_rate": 0.00012321428571428572,
- "loss": 1.3187,
+ "epoch": 6.8,
+ "learning_rate": 0.00011448863636363637,
+ "loss": 0.8406,
"step": 602
},
{
- "epoch": 12.2,
- "learning_rate": 0.00012308673469387755,
- "loss": 1.3353,
+ "epoch": 6.81,
+ "learning_rate": 0.00011434659090909092,
+ "loss": 0.836,
"step": 603
},
{
- "epoch": 12.22,
- "learning_rate": 0.0001229591836734694,
- "loss": 1.3221,
+ "epoch": 6.82,
+ "learning_rate": 0.00011420454545454547,
+ "loss": 0.8476,
"step": 604
},
{
- "epoch": 12.24,
- "learning_rate": 0.00012283163265306124,
- "loss": 1.3458,
+ "epoch": 6.83,
+ "learning_rate": 0.0001140625,
+ "loss": 0.8368,
"step": 605
},
{
- "epoch": 12.26,
- "learning_rate": 0.00012270408163265307,
- "loss": 1.275,
+ "epoch": 6.85,
+ "learning_rate": 0.00011392045454545455,
+ "loss": 0.822,
"step": 606
},
{
- "epoch": 12.28,
- "learning_rate": 0.0001225765306122449,
- "loss": 1.3455,
+ "epoch": 6.86,
+ "learning_rate": 0.00011377840909090909,
+ "loss": 0.8107,
"step": 607
},
{
- "epoch": 12.3,
- "learning_rate": 0.00012244897959183676,
- "loss": 1.2769,
+ "epoch": 6.87,
+ "learning_rate": 0.00011363636363636365,
+ "loss": 0.8395,
"step": 608
},
{
- "epoch": 12.32,
- "learning_rate": 0.00012232142857142859,
- "loss": 1.3201,
+ "epoch": 6.88,
+ "learning_rate": 0.0001134943181818182,
+ "loss": 0.8083,
"step": 609
},
{
- "epoch": 12.34,
- "learning_rate": 0.00012219387755102042,
- "loss": 1.3073,
+ "epoch": 6.89,
+ "learning_rate": 0.00011335227272727274,
+ "loss": 0.828,
"step": 610
},
{
- "epoch": 12.36,
- "learning_rate": 0.00012206632653061225,
- "loss": 1.3103,
+ "epoch": 6.9,
+ "learning_rate": 0.00011321022727272727,
+ "loss": 0.8494,
"step": 611
},
{
- "epoch": 12.38,
- "learning_rate": 0.00012193877551020409,
- "loss": 1.4437,
+ "epoch": 6.91,
+ "learning_rate": 0.00011306818181818182,
+ "loss": 0.8169,
"step": 612
},
{
- "epoch": 12.4,
- "learning_rate": 0.00012181122448979591,
- "loss": 1.3086,
+ "epoch": 6.93,
+ "learning_rate": 0.00011292613636363636,
+ "loss": 0.8224,
"step": 613
},
{
- "epoch": 12.42,
- "learning_rate": 0.00012168367346938775,
- "loss": 1.3867,
+ "epoch": 6.94,
+ "learning_rate": 0.00011278409090909092,
+ "loss": 0.8173,
"step": 614
},
{
- "epoch": 12.44,
- "learning_rate": 0.0001215561224489796,
- "loss": 1.2565,
+ "epoch": 6.95,
+ "learning_rate": 0.00011264204545454547,
+ "loss": 0.7961,
"step": 615
},
{
- "epoch": 12.46,
- "learning_rate": 0.00012142857142857143,
- "loss": 1.335,
+ "epoch": 6.96,
+ "learning_rate": 0.00011250000000000001,
+ "loss": 0.7948,
"step": 616
},
{
- "epoch": 12.48,
- "learning_rate": 0.00012130102040816327,
- "loss": 1.3423,
+ "epoch": 6.97,
+ "learning_rate": 0.00011235795454545454,
+ "loss": 0.7746,
"step": 617
},
{
- "epoch": 12.5,
- "learning_rate": 0.00012117346938775512,
- "loss": 1.3433,
+ "epoch": 6.98,
+ "learning_rate": 0.00011221590909090909,
+ "loss": 0.8325,
"step": 618
},
{
- "epoch": 12.52,
- "learning_rate": 0.00012104591836734695,
- "loss": 1.3387,
+ "epoch": 6.99,
+ "learning_rate": 0.00011207386363636365,
+ "loss": 0.8149,
"step": 619
},
{
- "epoch": 12.55,
- "learning_rate": 0.00012091836734693878,
- "loss": 1.3923,
+ "epoch": 7.0,
+ "learning_rate": 0.00011193181818181819,
+ "loss": 0.7516,
"step": 620
},
{
- "epoch": 12.57,
- "learning_rate": 0.00012079081632653062,
- "loss": 1.3774,
+ "epoch": 7.02,
+ "learning_rate": 0.00011178977272727274,
+ "loss": 0.7571,
"step": 621
},
{
- "epoch": 12.59,
- "learning_rate": 0.00012066326530612247,
- "loss": 1.3203,
+ "epoch": 7.03,
+ "learning_rate": 0.00011164772727272728,
+ "loss": 0.7397,
"step": 622
},
{
- "epoch": 12.61,
- "learning_rate": 0.00012053571428571429,
- "loss": 1.2924,
+ "epoch": 7.04,
+ "learning_rate": 0.00011150568181818181,
+ "loss": 0.761,
"step": 623
},
{
- "epoch": 12.63,
- "learning_rate": 0.00012040816326530613,
- "loss": 1.3292,
+ "epoch": 7.05,
+ "learning_rate": 0.00011136363636363636,
+ "loss": 0.7783,
"step": 624
},
{
- "epoch": 12.65,
- "learning_rate": 0.00012028061224489798,
- "loss": 1.3161,
+ "epoch": 7.06,
+ "learning_rate": 0.00011122159090909092,
+ "loss": 0.7571,
"step": 625
},
{
- "epoch": 12.67,
- "learning_rate": 0.00012015306122448979,
- "loss": 1.352,
+ "epoch": 7.07,
+ "learning_rate": 0.00011107954545454546,
+ "loss": 0.7628,
"step": 626
},
{
- "epoch": 12.69,
- "learning_rate": 0.00012002551020408164,
- "loss": 1.3577,
+ "epoch": 7.08,
+ "learning_rate": 0.0001109375,
+ "loss": 0.7561,
"step": 627
},
{
- "epoch": 12.71,
- "learning_rate": 0.00011989795918367348,
- "loss": 1.3575,
+ "epoch": 7.09,
+ "learning_rate": 0.00011079545454545455,
+ "loss": 0.7432,
"step": 628
},
{
- "epoch": 12.73,
- "learning_rate": 0.0001197704081632653,
- "loss": 1.3727,
+ "epoch": 7.11,
+ "learning_rate": 0.00011065340909090908,
+ "loss": 0.7245,
"step": 629
},
{
- "epoch": 12.75,
- "learning_rate": 0.00011964285714285714,
- "loss": 1.3312,
+ "epoch": 7.12,
+ "learning_rate": 0.00011051136363636366,
+ "loss": 0.7279,
"step": 630
},
{
- "epoch": 12.77,
- "learning_rate": 0.00011951530612244899,
- "loss": 1.3378,
+ "epoch": 7.13,
+ "learning_rate": 0.00011036931818181819,
+ "loss": 0.7347,
"step": 631
},
{
- "epoch": 12.79,
- "learning_rate": 0.00011938775510204083,
- "loss": 1.295,
+ "epoch": 7.14,
+ "learning_rate": 0.00011022727272727273,
+ "loss": 0.7427,
"step": 632
},
{
- "epoch": 12.81,
- "learning_rate": 0.00011926020408163265,
- "loss": 1.3447,
+ "epoch": 7.15,
+ "learning_rate": 0.00011008522727272728,
+ "loss": 0.7339,
"step": 633
},
{
- "epoch": 12.83,
- "learning_rate": 0.0001191326530612245,
- "loss": 1.3835,
+ "epoch": 7.16,
+ "learning_rate": 0.00010994318181818182,
+ "loss": 0.7375,
"step": 634
},
{
- "epoch": 12.85,
- "learning_rate": 0.00011900510204081634,
- "loss": 1.3222,
+ "epoch": 7.17,
+ "learning_rate": 0.00010980113636363635,
+ "loss": 0.7182,
"step": 635
},
{
- "epoch": 12.87,
- "learning_rate": 0.00011887755102040817,
- "loss": 1.2851,
+ "epoch": 7.19,
+ "learning_rate": 0.00010965909090909093,
+ "loss": 0.7452,
"step": 636
},
{
- "epoch": 12.89,
- "learning_rate": 0.00011875,
- "loss": 1.2723,
+ "epoch": 7.2,
+ "learning_rate": 0.00010951704545454546,
+ "loss": 0.7565,
"step": 637
},
{
- "epoch": 12.91,
- "learning_rate": 0.00011862244897959184,
- "loss": 1.3924,
+ "epoch": 7.21,
+ "learning_rate": 0.000109375,
+ "loss": 0.7296,
"step": 638
},
{
- "epoch": 12.93,
- "learning_rate": 0.00011849489795918368,
- "loss": 1.4625,
+ "epoch": 7.22,
+ "learning_rate": 0.00010923295454545455,
+ "loss": 0.7484,
"step": 639
},
{
- "epoch": 12.95,
- "learning_rate": 0.00011836734693877552,
- "loss": 1.3245,
+ "epoch": 7.23,
+ "learning_rate": 0.00010909090909090909,
+ "loss": 0.732,
"step": 640
},
{
- "epoch": 12.97,
- "learning_rate": 0.00011823979591836736,
- "loss": 1.4042,
+ "epoch": 7.24,
+ "learning_rate": 0.00010894886363636365,
+ "loss": 0.7415,
"step": 641
},
{
- "epoch": 12.99,
- "learning_rate": 0.00011811224489795918,
- "loss": 1.3761,
+ "epoch": 7.25,
+ "learning_rate": 0.0001088068181818182,
+ "loss": 0.7344,
"step": 642
},
{
- "epoch": 13.01,
- "learning_rate": 0.00011798469387755103,
- "loss": 1.3376,
+ "epoch": 7.26,
+ "learning_rate": 0.00010866477272727274,
+ "loss": 0.7267,
"step": 643
},
{
- "epoch": 13.03,
- "learning_rate": 0.00011785714285714287,
- "loss": 1.2174,
+ "epoch": 7.28,
+ "learning_rate": 0.00010852272727272727,
+ "loss": 0.7543,
"step": 644
},
{
- "epoch": 13.05,
- "learning_rate": 0.00011772959183673471,
- "loss": 1.3602,
+ "epoch": 7.29,
+ "learning_rate": 0.00010838068181818182,
+ "loss": 0.7266,
"step": 645
},
{
- "epoch": 13.07,
- "learning_rate": 0.00011760204081632653,
- "loss": 1.3002,
+ "epoch": 7.3,
+ "learning_rate": 0.00010823863636363636,
+ "loss": 0.7449,
"step": 646
},
{
- "epoch": 13.09,
- "learning_rate": 0.00011747448979591838,
- "loss": 1.2262,
+ "epoch": 7.31,
+ "learning_rate": 0.00010809659090909092,
+ "loss": 0.7324,
"step": 647
},
{
- "epoch": 13.11,
- "learning_rate": 0.00011734693877551022,
- "loss": 1.3048,
+ "epoch": 7.32,
+ "learning_rate": 0.00010795454545454547,
+ "loss": 0.7268,
"step": 648
},
{
- "epoch": 13.13,
- "learning_rate": 0.00011721938775510204,
- "loss": 1.2231,
+ "epoch": 7.33,
+ "learning_rate": 0.00010781250000000001,
+ "loss": 0.7172,
"step": 649
},
{
- "epoch": 13.15,
- "learning_rate": 0.00011709183673469388,
- "loss": 1.2996,
+ "epoch": 7.34,
+ "learning_rate": 0.00010767045454545454,
+ "loss": 0.7169,
"step": 650
},
{
- "epoch": 13.17,
- "learning_rate": 0.00011696428571428573,
- "loss": 1.2708,
+ "epoch": 7.35,
+ "learning_rate": 0.00010752840909090909,
+ "loss": 0.7194,
"step": 651
},
{
- "epoch": 13.19,
- "learning_rate": 0.00011683673469387754,
- "loss": 1.2776,
+ "epoch": 7.37,
+ "learning_rate": 0.00010738636363636365,
+ "loss": 0.7223,
"step": 652
},
{
- "epoch": 13.21,
- "learning_rate": 0.00011670918367346939,
- "loss": 1.248,
+ "epoch": 7.38,
+ "learning_rate": 0.00010724431818181819,
+ "loss": 0.7158,
"step": 653
},
{
- "epoch": 13.23,
- "learning_rate": 0.00011658163265306123,
- "loss": 1.2582,
+ "epoch": 7.39,
+ "learning_rate": 0.00010710227272727274,
+ "loss": 0.7122,
"step": 654
},
{
- "epoch": 13.25,
- "learning_rate": 0.00011645408163265305,
- "loss": 1.3011,
+ "epoch": 7.4,
+ "learning_rate": 0.00010696022727272728,
+ "loss": 0.7225,
"step": 655
},
{
- "epoch": 13.27,
- "learning_rate": 0.0001163265306122449,
- "loss": 1.2969,
+ "epoch": 7.41,
+ "learning_rate": 0.00010681818181818181,
+ "loss": 0.7102,
"step": 656
},
{
- "epoch": 13.29,
- "learning_rate": 0.00011619897959183674,
- "loss": 1.2454,
+ "epoch": 7.42,
+ "learning_rate": 0.00010667613636363636,
+ "loss": 0.7251,
"step": 657
},
{
- "epoch": 13.31,
- "learning_rate": 0.00011607142857142858,
- "loss": 1.1914,
+ "epoch": 7.43,
+ "learning_rate": 0.00010653409090909092,
+ "loss": 0.7191,
"step": 658
},
{
- "epoch": 13.33,
- "learning_rate": 0.00011594387755102041,
- "loss": 1.34,
+ "epoch": 7.45,
+ "learning_rate": 0.00010639204545454546,
+ "loss": 0.7015,
"step": 659
},
{
- "epoch": 13.35,
- "learning_rate": 0.00011581632653061225,
- "loss": 1.2828,
+ "epoch": 7.46,
+ "learning_rate": 0.00010625000000000001,
+ "loss": 0.693,
"step": 660
},
{
- "epoch": 13.37,
- "learning_rate": 0.00011568877551020409,
- "loss": 1.2962,
+ "epoch": 7.47,
+ "learning_rate": 0.00010610795454545455,
+ "loss": 0.7039,
"step": 661
},
{
- "epoch": 13.39,
- "learning_rate": 0.00011556122448979592,
- "loss": 1.3334,
+ "epoch": 7.48,
+ "learning_rate": 0.00010596590909090908,
+ "loss": 0.7305,
"step": 662
},
{
- "epoch": 13.42,
- "learning_rate": 0.00011543367346938776,
- "loss": 1.2832,
+ "epoch": 7.49,
+ "learning_rate": 0.00010582386363636366,
+ "loss": 0.6978,
"step": 663
},
{
- "epoch": 13.44,
- "learning_rate": 0.00011530612244897961,
- "loss": 1.3012,
+ "epoch": 7.5,
+ "learning_rate": 0.00010568181818181819,
+ "loss": 0.7219,
"step": 664
},
{
- "epoch": 13.46,
- "learning_rate": 0.00011517857142857143,
- "loss": 1.2857,
+ "epoch": 7.51,
+ "learning_rate": 0.00010553977272727273,
+ "loss": 0.7199,
"step": 665
},
{
- "epoch": 13.48,
- "learning_rate": 0.00011505102040816327,
- "loss": 1.2855,
+ "epoch": 7.52,
+ "learning_rate": 0.00010539772727272728,
+ "loss": 0.6979,
"step": 666
},
{
- "epoch": 13.5,
- "learning_rate": 0.00011492346938775512,
- "loss": 1.3077,
+ "epoch": 7.54,
+ "learning_rate": 0.00010525568181818182,
+ "loss": 0.7058,
"step": 667
},
{
- "epoch": 13.52,
- "learning_rate": 0.00011479591836734696,
- "loss": 1.3139,
+ "epoch": 7.55,
+ "learning_rate": 0.00010511363636363635,
+ "loss": 0.6994,
"step": 668
},
{
- "epoch": 13.54,
- "learning_rate": 0.00011466836734693878,
- "loss": 1.3138,
+ "epoch": 7.56,
+ "learning_rate": 0.00010497159090909093,
+ "loss": 0.7141,
"step": 669
},
{
- "epoch": 13.56,
- "learning_rate": 0.00011454081632653062,
- "loss": 1.2808,
+ "epoch": 7.57,
+ "learning_rate": 0.00010482954545454546,
+ "loss": 0.7092,
"step": 670
},
{
- "epoch": 13.58,
- "learning_rate": 0.00011441326530612247,
- "loss": 1.2492,
+ "epoch": 7.58,
+ "learning_rate": 0.0001046875,
+ "loss": 0.7059,
"step": 671
},
{
- "epoch": 13.6,
- "learning_rate": 0.00011428571428571428,
- "loss": 1.2027,
+ "epoch": 7.59,
+ "learning_rate": 0.00010454545454545455,
+ "loss": 0.6904,
"step": 672
},
{
- "epoch": 13.62,
- "learning_rate": 0.00011415816326530613,
- "loss": 1.33,
+ "epoch": 7.6,
+ "learning_rate": 0.0001044034090909091,
+ "loss": 0.7115,
"step": 673
},
{
- "epoch": 13.64,
- "learning_rate": 0.00011403061224489797,
- "loss": 1.3112,
+ "epoch": 7.61,
+ "learning_rate": 0.00010426136363636365,
+ "loss": 0.7254,
"step": 674
},
{
- "epoch": 13.66,
- "learning_rate": 0.00011390306122448979,
- "loss": 1.2772,
+ "epoch": 7.63,
+ "learning_rate": 0.0001041193181818182,
+ "loss": 0.7181,
"step": 675
},
{
- "epoch": 13.68,
- "learning_rate": 0.00011377551020408163,
- "loss": 1.2701,
+ "epoch": 7.64,
+ "learning_rate": 0.00010397727272727273,
+ "loss": 0.6867,
"step": 676
},
{
- "epoch": 13.7,
- "learning_rate": 0.00011364795918367348,
- "loss": 1.1973,
+ "epoch": 7.65,
+ "learning_rate": 0.00010383522727272727,
+ "loss": 0.6917,
"step": 677
},
{
- "epoch": 13.72,
- "learning_rate": 0.0001135204081632653,
- "loss": 1.3124,
+ "epoch": 7.66,
+ "learning_rate": 0.00010369318181818182,
+ "loss": 0.6908,
"step": 678
},
{
- "epoch": 13.74,
- "learning_rate": 0.00011339285714285714,
- "loss": 1.3085,
+ "epoch": 7.67,
+ "learning_rate": 0.00010355113636363636,
+ "loss": 0.6871,
"step": 679
},
{
- "epoch": 13.76,
- "learning_rate": 0.00011326530612244898,
- "loss": 1.3457,
+ "epoch": 7.68,
+ "learning_rate": 0.00010340909090909092,
+ "loss": 0.682,
"step": 680
},
{
- "epoch": 13.78,
- "learning_rate": 0.00011313775510204083,
- "loss": 1.3338,
+ "epoch": 7.69,
+ "learning_rate": 0.00010326704545454547,
+ "loss": 0.6737,
"step": 681
},
{
- "epoch": 13.8,
- "learning_rate": 0.00011301020408163266,
- "loss": 1.2753,
+ "epoch": 7.7,
+ "learning_rate": 0.000103125,
+ "loss": 0.7023,
"step": 682
},
{
- "epoch": 13.82,
- "learning_rate": 0.00011288265306122449,
- "loss": 1.2786,
+ "epoch": 7.72,
+ "learning_rate": 0.00010298295454545454,
+ "loss": 0.7079,
"step": 683
},
{
- "epoch": 13.84,
- "learning_rate": 0.00011275510204081634,
- "loss": 1.2584,
+ "epoch": 7.73,
+ "learning_rate": 0.00010284090909090909,
+ "loss": 0.6954,
"step": 684
},
{
- "epoch": 13.86,
- "learning_rate": 0.00011262755102040817,
- "loss": 1.2779,
+ "epoch": 7.74,
+ "learning_rate": 0.00010269886363636365,
+ "loss": 0.6834,
"step": 685
},
{
- "epoch": 13.88,
- "learning_rate": 0.00011250000000000001,
- "loss": 1.3502,
+ "epoch": 7.75,
+ "learning_rate": 0.0001025568181818182,
+ "loss": 0.6706,
"step": 686
},
{
- "epoch": 13.9,
- "learning_rate": 0.00011237244897959185,
- "loss": 1.3251,
+ "epoch": 7.76,
+ "learning_rate": 0.00010241477272727274,
+ "loss": 0.6706,
"step": 687
},
{
- "epoch": 13.92,
- "learning_rate": 0.00011224489795918367,
- "loss": 1.273,
+ "epoch": 7.77,
+ "learning_rate": 0.00010227272727272727,
+ "loss": 0.681,
"step": 688
},
{
- "epoch": 13.94,
- "learning_rate": 0.00011211734693877552,
- "loss": 1.3341,
+ "epoch": 7.78,
+ "learning_rate": 0.00010213068181818182,
+ "loss": 0.6853,
"step": 689
},
{
- "epoch": 13.96,
- "learning_rate": 0.00011198979591836736,
- "loss": 1.2654,
+ "epoch": 7.8,
+ "learning_rate": 0.00010198863636363636,
+ "loss": 0.6772,
"step": 690
},
{
- "epoch": 13.98,
- "learning_rate": 0.00011186224489795918,
- "loss": 1.3333,
+ "epoch": 7.81,
+ "learning_rate": 0.00010184659090909092,
+ "loss": 0.6635,
"step": 691
},
{
- "epoch": 14.0,
- "learning_rate": 0.00011173469387755102,
- "loss": 1.3246,
+ "epoch": 7.82,
+ "learning_rate": 0.00010170454545454546,
+ "loss": 0.6712,
"step": 692
},
{
- "epoch": 14.02,
- "learning_rate": 0.00011160714285714287,
- "loss": 1.2547,
+ "epoch": 7.83,
+ "learning_rate": 0.00010156250000000001,
+ "loss": 0.6884,
"step": 693
},
{
- "epoch": 14.04,
- "learning_rate": 0.00011147959183673471,
- "loss": 1.208,
+ "epoch": 7.84,
+ "learning_rate": 0.00010142045454545454,
+ "loss": 0.6641,
"step": 694
},
{
- "epoch": 14.06,
- "learning_rate": 0.00011135204081632653,
- "loss": 1.223,
+ "epoch": 7.85,
+ "learning_rate": 0.00010127840909090909,
+ "loss": 0.6838,
"step": 695
},
{
- "epoch": 14.08,
- "learning_rate": 0.00011122448979591837,
- "loss": 1.2483,
+ "epoch": 7.86,
+ "learning_rate": 0.00010113636363636366,
+ "loss": 0.675,
"step": 696
},
{
- "epoch": 14.1,
- "learning_rate": 0.00011109693877551022,
- "loss": 1.2823,
+ "epoch": 7.87,
+ "learning_rate": 0.00010099431818181819,
+ "loss": 0.6626,
"step": 697
},
{
- "epoch": 14.12,
- "learning_rate": 0.00011096938775510204,
- "loss": 1.2013,
+ "epoch": 7.89,
+ "learning_rate": 0.00010085227272727273,
+ "loss": 0.6605,
"step": 698
},
{
- "epoch": 14.14,
- "learning_rate": 0.00011084183673469388,
- "loss": 1.1883,
+ "epoch": 7.9,
+ "learning_rate": 0.00010071022727272728,
+ "loss": 0.6777,
"step": 699
},
{
- "epoch": 14.16,
- "learning_rate": 0.00011071428571428572,
- "loss": 1.2364,
+ "epoch": 7.91,
+ "learning_rate": 0.00010056818181818181,
+ "loss": 0.6347,
"step": 700
},
{
- "epoch": 14.18,
- "learning_rate": 0.00011058673469387754,
- "loss": 1.2069,
+ "epoch": 7.92,
+ "learning_rate": 0.00010042613636363636,
+ "loss": 0.6857,
"step": 701
},
{
- "epoch": 14.2,
- "learning_rate": 0.00011045918367346939,
- "loss": 1.1968,
+ "epoch": 7.93,
+ "learning_rate": 0.00010028409090909093,
+ "loss": 0.6677,
"step": 702
},
{
- "epoch": 14.22,
- "learning_rate": 0.00011033163265306123,
- "loss": 1.2236,
+ "epoch": 7.94,
+ "learning_rate": 0.00010014204545454546,
+ "loss": 0.6697,
"step": 703
},
{
- "epoch": 14.24,
- "learning_rate": 0.00011020408163265306,
- "loss": 1.1942,
+ "epoch": 7.95,
+ "learning_rate": 0.0001,
+ "loss": 0.6375,
"step": 704
},
{
- "epoch": 14.26,
- "learning_rate": 0.0001100765306122449,
- "loss": 1.2561,
+ "epoch": 7.96,
+ "learning_rate": 9.985795454545455e-05,
+ "loss": 0.6572,
"step": 705
},
{
- "epoch": 14.29,
- "learning_rate": 0.00010994897959183674,
- "loss": 1.1839,
+ "epoch": 7.98,
+ "learning_rate": 9.97159090909091e-05,
+ "loss": 0.668,
"step": 706
},
{
- "epoch": 14.31,
- "learning_rate": 0.00010982142857142858,
- "loss": 1.2128,
+ "epoch": 7.99,
+ "learning_rate": 9.957386363636364e-05,
+ "loss": 0.6797,
"step": 707
},
{
- "epoch": 14.33,
- "learning_rate": 0.00010969387755102041,
- "loss": 1.3086,
+ "epoch": 8.0,
+ "learning_rate": 9.943181818181819e-05,
+ "loss": 0.6784,
"step": 708
},
{
- "epoch": 14.35,
- "learning_rate": 0.00010956632653061226,
- "loss": 1.2379,
+ "epoch": 8.01,
+ "learning_rate": 9.928977272727273e-05,
+ "loss": 0.6192,
"step": 709
},
{
- "epoch": 14.37,
- "learning_rate": 0.0001094387755102041,
- "loss": 1.176,
+ "epoch": 8.02,
+ "learning_rate": 9.914772727272728e-05,
+ "loss": 0.6287,
"step": 710
},
{
- "epoch": 14.39,
- "learning_rate": 0.00010931122448979592,
- "loss": 1.2105,
+ "epoch": 8.03,
+ "learning_rate": 9.900568181818183e-05,
+ "loss": 0.6034,
"step": 711
},
{
- "epoch": 14.41,
- "learning_rate": 0.00010918367346938776,
- "loss": 1.2149,
+ "epoch": 8.04,
+ "learning_rate": 9.886363636363637e-05,
+ "loss": 0.6167,
"step": 712
},
{
- "epoch": 14.43,
- "learning_rate": 0.0001090561224489796,
- "loss": 1.2392,
+ "epoch": 8.06,
+ "learning_rate": 9.872159090909091e-05,
+ "loss": 0.6353,
"step": 713
},
{
- "epoch": 14.45,
- "learning_rate": 0.00010892857142857142,
- "loss": 1.2471,
+ "epoch": 8.07,
+ "learning_rate": 9.857954545454547e-05,
+ "loss": 0.6222,
"step": 714
},
{
- "epoch": 14.47,
- "learning_rate": 0.00010880102040816327,
- "loss": 1.2561,
+ "epoch": 8.08,
+ "learning_rate": 9.84375e-05,
+ "loss": 0.5963,
"step": 715
},
{
- "epoch": 14.49,
- "learning_rate": 0.00010867346938775511,
- "loss": 1.2179,
+ "epoch": 8.09,
+ "learning_rate": 9.829545454545455e-05,
+ "loss": 0.6042,
"step": 716
},
{
- "epoch": 14.51,
- "learning_rate": 0.00010854591836734696,
- "loss": 1.2459,
+ "epoch": 8.1,
+ "learning_rate": 9.81534090909091e-05,
+ "loss": 0.612,
"step": 717
},
{
- "epoch": 14.53,
- "learning_rate": 0.00010841836734693877,
- "loss": 1.2933,
+ "epoch": 8.11,
+ "learning_rate": 9.801136363636364e-05,
+ "loss": 0.6069,
"step": 718
},
{
- "epoch": 14.55,
- "learning_rate": 0.00010829081632653062,
- "loss": 1.2862,
+ "epoch": 8.12,
+ "learning_rate": 9.786931818181818e-05,
+ "loss": 0.6001,
"step": 719
},
{
- "epoch": 14.57,
- "learning_rate": 0.00010816326530612246,
- "loss": 1.2976,
+ "epoch": 8.13,
+ "learning_rate": 9.772727272727274e-05,
+ "loss": 0.6007,
"step": 720
},
{
- "epoch": 14.59,
- "learning_rate": 0.00010803571428571428,
- "loss": 1.231,
+ "epoch": 8.15,
+ "learning_rate": 9.758522727272727e-05,
+ "loss": 0.6079,
"step": 721
},
{
- "epoch": 14.61,
- "learning_rate": 0.00010790816326530613,
- "loss": 1.2464,
+ "epoch": 8.16,
+ "learning_rate": 9.744318181818183e-05,
+ "loss": 0.6216,
"step": 722
},
{
- "epoch": 14.63,
- "learning_rate": 0.00010778061224489797,
- "loss": 1.2181,
+ "epoch": 8.17,
+ "learning_rate": 9.730113636363637e-05,
+ "loss": 0.6321,
"step": 723
},
{
- "epoch": 14.65,
- "learning_rate": 0.00010765306122448979,
- "loss": 1.3307,
+ "epoch": 8.18,
+ "learning_rate": 9.71590909090909e-05,
+ "loss": 0.6044,
"step": 724
},
{
- "epoch": 14.67,
- "learning_rate": 0.00010752551020408163,
- "loss": 1.1723,
+ "epoch": 8.19,
+ "learning_rate": 9.701704545454547e-05,
+ "loss": 0.6028,
"step": 725
},
{
- "epoch": 14.69,
- "learning_rate": 0.00010739795918367348,
- "loss": 1.1528,
+ "epoch": 8.2,
+ "learning_rate": 9.687500000000001e-05,
+ "loss": 0.6098,
"step": 726
},
{
- "epoch": 14.71,
- "learning_rate": 0.0001072704081632653,
- "loss": 1.215,
+ "epoch": 8.21,
+ "learning_rate": 9.673295454545454e-05,
+ "loss": 0.6032,
"step": 727
},
{
- "epoch": 14.73,
- "learning_rate": 0.00010714285714285715,
- "loss": 1.2624,
+ "epoch": 8.22,
+ "learning_rate": 9.65909090909091e-05,
+ "loss": 0.6298,
"step": 728
},
{
- "epoch": 14.75,
- "learning_rate": 0.00010701530612244898,
- "loss": 1.3117,
+ "epoch": 8.24,
+ "learning_rate": 9.644886363636365e-05,
+ "loss": 0.6115,
"step": 729
},
{
- "epoch": 14.77,
- "learning_rate": 0.00010688775510204083,
- "loss": 1.2572,
+ "epoch": 8.25,
+ "learning_rate": 9.630681818181818e-05,
+ "loss": 0.6052,
"step": 730
},
{
- "epoch": 14.79,
- "learning_rate": 0.00010676020408163266,
- "loss": 1.222,
+ "epoch": 8.26,
+ "learning_rate": 9.616477272727274e-05,
+ "loss": 0.6097,
"step": 731
},
{
- "epoch": 14.81,
- "learning_rate": 0.0001066326530612245,
- "loss": 1.2881,
+ "epoch": 8.27,
+ "learning_rate": 9.602272727272728e-05,
+ "loss": 0.6062,
"step": 732
},
{
- "epoch": 14.83,
- "learning_rate": 0.00010650510204081635,
- "loss": 1.2676,
+ "epoch": 8.28,
+ "learning_rate": 9.588068181818183e-05,
+ "loss": 0.5984,
"step": 733
},
{
- "epoch": 14.85,
- "learning_rate": 0.00010637755102040816,
- "loss": 1.2734,
+ "epoch": 8.29,
+ "learning_rate": 9.573863636363637e-05,
+ "loss": 0.6432,
"step": 734
},
{
- "epoch": 14.87,
- "learning_rate": 0.00010625000000000001,
- "loss": 1.2885,
+ "epoch": 8.3,
+ "learning_rate": 9.559659090909092e-05,
+ "loss": 0.5814,
"step": 735
},
{
- "epoch": 14.89,
- "learning_rate": 0.00010612244897959185,
- "loss": 1.2764,
+ "epoch": 8.31,
+ "learning_rate": 9.545454545454546e-05,
+ "loss": 0.5965,
"step": 736
},
{
- "epoch": 14.91,
- "learning_rate": 0.00010599489795918367,
- "loss": 1.3267,
+ "epoch": 8.33,
+ "learning_rate": 9.53125e-05,
+ "loss": 0.6102,
"step": 737
},
{
- "epoch": 14.93,
- "learning_rate": 0.00010586734693877551,
- "loss": 1.2445,
+ "epoch": 8.34,
+ "learning_rate": 9.517045454545455e-05,
+ "loss": 0.5849,
"step": 738
},
{
- "epoch": 14.95,
- "learning_rate": 0.00010573979591836736,
- "loss": 1.3359,
+ "epoch": 8.35,
+ "learning_rate": 9.50284090909091e-05,
+ "loss": 0.6062,
"step": 739
},
{
- "epoch": 14.97,
- "learning_rate": 0.00010561224489795918,
- "loss": 1.2508,
+ "epoch": 8.36,
+ "learning_rate": 9.488636363636364e-05,
+ "loss": 0.6031,
"step": 740
},
{
- "epoch": 14.99,
- "learning_rate": 0.00010548469387755102,
- "loss": 1.2227,
+ "epoch": 8.37,
+ "learning_rate": 9.474431818181819e-05,
+ "loss": 0.5932,
"step": 741
},
{
- "epoch": 15.01,
- "learning_rate": 0.00010535714285714286,
- "loss": 1.1889,
+ "epoch": 8.38,
+ "learning_rate": 9.460227272727273e-05,
+ "loss": 0.589,
"step": 742
},
{
- "epoch": 15.03,
- "learning_rate": 0.00010522959183673471,
- "loss": 1.1919,
+ "epoch": 8.39,
+ "learning_rate": 9.446022727272728e-05,
+ "loss": 0.6096,
"step": 743
},
{
- "epoch": 15.05,
- "learning_rate": 0.00010510204081632653,
- "loss": 1.2383,
+ "epoch": 8.41,
+ "learning_rate": 9.431818181818182e-05,
+ "loss": 0.601,
"step": 744
},
{
- "epoch": 15.07,
- "learning_rate": 0.00010497448979591837,
- "loss": 1.2401,
+ "epoch": 8.42,
+ "learning_rate": 9.417613636363637e-05,
+ "loss": 0.5798,
"step": 745
},
{
- "epoch": 15.09,
- "learning_rate": 0.00010484693877551021,
- "loss": 1.2015,
+ "epoch": 8.43,
+ "learning_rate": 9.403409090909091e-05,
+ "loss": 0.59,
"step": 746
},
{
- "epoch": 15.11,
- "learning_rate": 0.00010471938775510203,
- "loss": 1.1509,
+ "epoch": 8.44,
+ "learning_rate": 9.389204545454546e-05,
+ "loss": 0.5988,
"step": 747
},
{
- "epoch": 15.13,
- "learning_rate": 0.00010459183673469388,
- "loss": 1.1878,
+ "epoch": 8.45,
+ "learning_rate": 9.375e-05,
+ "loss": 0.5591,
"step": 748
},
{
- "epoch": 15.16,
- "learning_rate": 0.00010446428571428572,
- "loss": 1.1706,
+ "epoch": 8.46,
+ "learning_rate": 9.360795454545455e-05,
+ "loss": 0.5939,
"step": 749
},
{
- "epoch": 15.18,
- "learning_rate": 0.00010433673469387755,
- "loss": 1.1285,
+ "epoch": 8.47,
+ "learning_rate": 9.346590909090909e-05,
+ "loss": 0.5886,
"step": 750
},
{
- "epoch": 15.2,
- "learning_rate": 0.0001042091836734694,
- "loss": 1.1608,
+ "epoch": 8.48,
+ "learning_rate": 9.332386363636364e-05,
+ "loss": 0.5994,
"step": 751
},
{
- "epoch": 15.22,
- "learning_rate": 0.00010408163265306123,
- "loss": 1.1178,
+ "epoch": 8.5,
+ "learning_rate": 9.318181818181818e-05,
+ "loss": 0.5821,
"step": 752
},
{
- "epoch": 15.24,
- "learning_rate": 0.00010395408163265306,
- "loss": 1.1293,
+ "epoch": 8.51,
+ "learning_rate": 9.303977272727273e-05,
+ "loss": 0.602,
"step": 753
},
{
- "epoch": 15.26,
- "learning_rate": 0.0001038265306122449,
- "loss": 1.2306,
+ "epoch": 8.52,
+ "learning_rate": 9.289772727272727e-05,
+ "loss": 0.5708,
"step": 754
},
{
- "epoch": 15.28,
- "learning_rate": 0.00010369897959183675,
- "loss": 1.1541,
+ "epoch": 8.53,
+ "learning_rate": 9.275568181818183e-05,
+ "loss": 0.5902,
"step": 755
},
{
- "epoch": 15.3,
- "learning_rate": 0.00010357142857142859,
- "loss": 1.1702,
+ "epoch": 8.54,
+ "learning_rate": 9.261363636363636e-05,
+ "loss": 0.6053,
"step": 756
},
{
- "epoch": 15.32,
- "learning_rate": 0.00010344387755102041,
- "loss": 1.2119,
+ "epoch": 8.55,
+ "learning_rate": 9.247159090909091e-05,
+ "loss": 0.5797,
"step": 757
},
{
- "epoch": 15.34,
- "learning_rate": 0.00010331632653061225,
- "loss": 1.2239,
+ "epoch": 8.56,
+ "learning_rate": 9.232954545454547e-05,
+ "loss": 0.5965,
"step": 758
},
{
- "epoch": 15.36,
- "learning_rate": 0.0001031887755102041,
- "loss": 1.2019,
+ "epoch": 8.57,
+ "learning_rate": 9.21875e-05,
+ "loss": 0.5738,
"step": 759
},
{
- "epoch": 15.38,
- "learning_rate": 0.00010306122448979591,
- "loss": 1.2197,
+ "epoch": 8.59,
+ "learning_rate": 9.204545454545454e-05,
+ "loss": 0.5819,
"step": 760
},
{
- "epoch": 15.4,
- "learning_rate": 0.00010293367346938776,
- "loss": 1.1769,
+ "epoch": 8.6,
+ "learning_rate": 9.19034090909091e-05,
+ "loss": 0.5994,
"step": 761
},
{
- "epoch": 15.42,
- "learning_rate": 0.0001028061224489796,
- "loss": 1.1907,
+ "epoch": 8.61,
+ "learning_rate": 9.176136363636363e-05,
+ "loss": 0.5738,
"step": 762
},
{
- "epoch": 15.44,
- "learning_rate": 0.00010267857142857142,
- "loss": 1.2089,
+ "epoch": 8.62,
+ "learning_rate": 9.161931818181818e-05,
+ "loss": 0.5663,
"step": 763
},
{
- "epoch": 15.46,
- "learning_rate": 0.00010255102040816327,
- "loss": 1.1335,
+ "epoch": 8.63,
+ "learning_rate": 9.147727272727274e-05,
+ "loss": 0.5798,
"step": 764
},
{
- "epoch": 15.48,
- "learning_rate": 0.00010242346938775511,
- "loss": 1.1633,
+ "epoch": 8.64,
+ "learning_rate": 9.133522727272727e-05,
+ "loss": 0.5705,
"step": 765
},
{
- "epoch": 15.5,
- "learning_rate": 0.00010229591836734695,
- "loss": 1.1578,
+ "epoch": 8.65,
+ "learning_rate": 9.119318181818183e-05,
+ "loss": 0.5943,
"step": 766
},
{
- "epoch": 15.52,
- "learning_rate": 0.00010216836734693877,
- "loss": 1.2236,
+ "epoch": 8.67,
+ "learning_rate": 9.105113636363637e-05,
+ "loss": 0.6019,
"step": 767
},
{
- "epoch": 15.54,
- "learning_rate": 0.00010204081632653062,
- "loss": 1.1941,
+ "epoch": 8.68,
+ "learning_rate": 9.090909090909092e-05,
+ "loss": 0.5733,
"step": 768
},
{
- "epoch": 15.56,
- "learning_rate": 0.00010191326530612246,
- "loss": 1.2666,
+ "epoch": 8.69,
+ "learning_rate": 9.076704545454546e-05,
+ "loss": 0.575,
"step": 769
},
{
- "epoch": 15.58,
- "learning_rate": 0.00010178571428571428,
- "loss": 1.1232,
+ "epoch": 8.7,
+ "learning_rate": 9.062500000000001e-05,
+ "loss": 0.5675,
"step": 770
},
{
- "epoch": 15.6,
- "learning_rate": 0.00010165816326530612,
- "loss": 1.2242,
+ "epoch": 8.71,
+ "learning_rate": 9.048295454545455e-05,
+ "loss": 0.566,
"step": 771
},
{
- "epoch": 15.62,
- "learning_rate": 0.00010153061224489797,
- "loss": 1.1852,
+ "epoch": 8.72,
+ "learning_rate": 9.03409090909091e-05,
+ "loss": 0.5513,
"step": 772
},
{
- "epoch": 15.64,
- "learning_rate": 0.0001014030612244898,
- "loss": 1.2626,
+ "epoch": 8.73,
+ "learning_rate": 9.019886363636364e-05,
+ "loss": 0.5682,
"step": 773
},
{
- "epoch": 15.66,
- "learning_rate": 0.00010127551020408164,
- "loss": 1.1873,
+ "epoch": 8.74,
+ "learning_rate": 9.005681818181819e-05,
+ "loss": 0.5508,
"step": 774
},
{
- "epoch": 15.68,
- "learning_rate": 0.00010114795918367349,
- "loss": 1.3005,
+ "epoch": 8.76,
+ "learning_rate": 8.991477272727273e-05,
+ "loss": 0.5668,
"step": 775
},
{
- "epoch": 15.7,
- "learning_rate": 0.0001010204081632653,
- "loss": 1.1904,
+ "epoch": 8.77,
+ "learning_rate": 8.977272727272728e-05,
+ "loss": 0.569,
"step": 776
},
{
- "epoch": 15.72,
- "learning_rate": 0.00010089285714285715,
- "loss": 1.2927,
+ "epoch": 8.78,
+ "learning_rate": 8.963068181818182e-05,
+ "loss": 0.5897,
"step": 777
},
{
- "epoch": 15.74,
- "learning_rate": 0.00010076530612244899,
- "loss": 1.179,
+ "epoch": 8.79,
+ "learning_rate": 8.948863636363637e-05,
+ "loss": 0.5738,
"step": 778
},
{
- "epoch": 15.76,
- "learning_rate": 0.00010063775510204084,
- "loss": 1.2027,
+ "epoch": 8.8,
+ "learning_rate": 8.934659090909091e-05,
+ "loss": 0.5511,
"step": 779
},
{
- "epoch": 15.78,
- "learning_rate": 0.00010051020408163265,
- "loss": 1.2428,
+ "epoch": 8.81,
+ "learning_rate": 8.920454545454546e-05,
+ "loss": 0.5659,
"step": 780
},
{
- "epoch": 15.8,
- "learning_rate": 0.0001003826530612245,
- "loss": 1.2324,
+ "epoch": 8.82,
+ "learning_rate": 8.90625e-05,
+ "loss": 0.5649,
"step": 781
},
{
- "epoch": 15.82,
- "learning_rate": 0.00010025510204081634,
- "loss": 1.1251,
+ "epoch": 8.83,
+ "learning_rate": 8.892045454545455e-05,
+ "loss": 0.5618,
"step": 782
},
{
- "epoch": 15.84,
- "learning_rate": 0.00010012755102040816,
- "loss": 1.2405,
+ "epoch": 8.85,
+ "learning_rate": 8.87784090909091e-05,
+ "loss": 0.5602,
"step": 783
},
{
- "epoch": 15.86,
- "learning_rate": 0.0001,
- "loss": 1.2005,
+ "epoch": 8.86,
+ "learning_rate": 8.863636363636364e-05,
+ "loss": 0.5723,
"step": 784
},
{
- "epoch": 15.88,
- "learning_rate": 9.987244897959184e-05,
- "loss": 1.2259,
+ "epoch": 8.87,
+ "learning_rate": 8.849431818181818e-05,
+ "loss": 0.5816,
"step": 785
},
{
- "epoch": 15.9,
- "learning_rate": 9.974489795918368e-05,
- "loss": 1.1576,
+ "epoch": 8.88,
+ "learning_rate": 8.835227272727273e-05,
+ "loss": 0.555,
"step": 786
},
{
- "epoch": 15.92,
- "learning_rate": 9.961734693877551e-05,
- "loss": 1.1834,
+ "epoch": 8.89,
+ "learning_rate": 8.821022727272727e-05,
+ "loss": 0.5563,
"step": 787
},
{
- "epoch": 15.94,
- "learning_rate": 9.948979591836736e-05,
- "loss": 1.2396,
+ "epoch": 8.9,
+ "learning_rate": 8.806818181818183e-05,
+ "loss": 0.554,
"step": 788
},
{
- "epoch": 15.96,
- "learning_rate": 9.936224489795919e-05,
- "loss": 1.1865,
+ "epoch": 8.91,
+ "learning_rate": 8.792613636363636e-05,
+ "loss": 0.5671,
"step": 789
},
{
- "epoch": 15.98,
- "learning_rate": 9.923469387755102e-05,
- "loss": 1.2356,
+ "epoch": 8.92,
+ "learning_rate": 8.778409090909091e-05,
+ "loss": 0.5485,
"step": 790
},
{
- "epoch": 16.01,
- "learning_rate": 9.910714285714286e-05,
- "loss": 1.2639,
+ "epoch": 8.94,
+ "learning_rate": 8.764204545454547e-05,
+ "loss": 0.5712,
"step": 791
},
{
- "epoch": 16.03,
- "learning_rate": 9.897959183673469e-05,
- "loss": 1.1216,
+ "epoch": 8.95,
+ "learning_rate": 8.75e-05,
+ "loss": 0.5507,
"step": 792
},
{
- "epoch": 16.05,
- "learning_rate": 9.885204081632652e-05,
- "loss": 1.1051,
+ "epoch": 8.96,
+ "learning_rate": 8.735795454545454e-05,
+ "loss": 0.5718,
"step": 793
},
{
- "epoch": 16.07,
- "learning_rate": 9.872448979591837e-05,
- "loss": 1.0864,
+ "epoch": 8.97,
+ "learning_rate": 8.72159090909091e-05,
+ "loss": 0.5585,
"step": 794
},
{
- "epoch": 16.09,
- "learning_rate": 9.859693877551021e-05,
- "loss": 1.182,
+ "epoch": 8.98,
+ "learning_rate": 8.707386363636363e-05,
+ "loss": 0.5563,
"step": 795
},
{
- "epoch": 16.11,
- "learning_rate": 9.846938775510204e-05,
- "loss": 1.1272,
+ "epoch": 8.99,
+ "learning_rate": 8.693181818181818e-05,
+ "loss": 0.581,
"step": 796
},
{
- "epoch": 16.13,
- "learning_rate": 9.834183673469389e-05,
- "loss": 1.1946,
+ "epoch": 9.0,
+ "learning_rate": 8.678977272727274e-05,
+ "loss": 0.5511,
"step": 797
},
{
- "epoch": 16.15,
- "learning_rate": 9.821428571428572e-05,
- "loss": 1.0875,
+ "epoch": 9.02,
+ "learning_rate": 8.664772727272727e-05,
+ "loss": 0.5103,
"step": 798
},
{
- "epoch": 16.17,
- "learning_rate": 9.808673469387756e-05,
- "loss": 1.1671,
+ "epoch": 9.03,
+ "learning_rate": 8.650568181818183e-05,
+ "loss": 0.5323,
"step": 799
},
{
- "epoch": 16.19,
- "learning_rate": 9.79591836734694e-05,
- "loss": 1.1502,
+ "epoch": 9.04,
+ "learning_rate": 8.636363636363637e-05,
+ "loss": 0.5092,
"step": 800
},
{
- "epoch": 16.21,
- "learning_rate": 9.783163265306124e-05,
- "loss": 1.19,
+ "epoch": 9.05,
+ "learning_rate": 8.62215909090909e-05,
+ "loss": 0.5247,
"step": 801
},
{
- "epoch": 16.23,
- "learning_rate": 9.770408163265307e-05,
- "loss": 1.1258,
+ "epoch": 9.06,
+ "learning_rate": 8.607954545454546e-05,
+ "loss": 0.5403,
"step": 802
},
{
- "epoch": 16.25,
- "learning_rate": 9.75765306122449e-05,
- "loss": 1.1765,
+ "epoch": 9.07,
+ "learning_rate": 8.593750000000001e-05,
+ "loss": 0.5252,
"step": 803
},
{
- "epoch": 16.27,
- "learning_rate": 9.744897959183674e-05,
- "loss": 1.1217,
+ "epoch": 9.08,
+ "learning_rate": 8.579545454545454e-05,
+ "loss": 0.5296,
"step": 804
},
{
- "epoch": 16.29,
- "learning_rate": 9.732142857142858e-05,
- "loss": 1.1293,
+ "epoch": 9.09,
+ "learning_rate": 8.56534090909091e-05,
+ "loss": 0.5223,
"step": 805
},
{
- "epoch": 16.31,
- "learning_rate": 9.719387755102042e-05,
- "loss": 1.17,
+ "epoch": 9.11,
+ "learning_rate": 8.551136363636364e-05,
+ "loss": 0.4972,
"step": 806
},
{
- "epoch": 16.33,
- "learning_rate": 9.706632653061225e-05,
- "loss": 1.17,
+ "epoch": 9.12,
+ "learning_rate": 8.536931818181818e-05,
+ "loss": 0.5005,
"step": 807
},
{
- "epoch": 16.35,
- "learning_rate": 9.693877551020408e-05,
- "loss": 1.2004,
+ "epoch": 9.13,
+ "learning_rate": 8.522727272727273e-05,
+ "loss": 0.5249,
"step": 808
},
{
- "epoch": 16.37,
- "learning_rate": 9.681122448979593e-05,
- "loss": 1.1648,
+ "epoch": 9.14,
+ "learning_rate": 8.508522727272728e-05,
+ "loss": 0.5135,
"step": 809
},
{
- "epoch": 16.39,
- "learning_rate": 9.668367346938776e-05,
- "loss": 1.0688,
+ "epoch": 9.15,
+ "learning_rate": 8.494318181818182e-05,
+ "loss": 0.5053,
"step": 810
},
{
- "epoch": 16.41,
- "learning_rate": 9.655612244897959e-05,
- "loss": 1.1607,
+ "epoch": 9.16,
+ "learning_rate": 8.480113636363637e-05,
+ "loss": 0.5158,
"step": 811
},
{
- "epoch": 16.43,
- "learning_rate": 9.642857142857143e-05,
- "loss": 1.1298,
+ "epoch": 9.17,
+ "learning_rate": 8.465909090909091e-05,
+ "loss": 0.5061,
"step": 812
},
{
- "epoch": 16.45,
- "learning_rate": 9.630102040816326e-05,
- "loss": 1.1064,
+ "epoch": 9.18,
+ "learning_rate": 8.451704545454546e-05,
+ "loss": 0.4988,
"step": 813
},
{
- "epoch": 16.47,
- "learning_rate": 9.617346938775511e-05,
- "loss": 1.1472,
+ "epoch": 9.2,
+ "learning_rate": 8.4375e-05,
+ "loss": 0.5273,
"step": 814
},
{
- "epoch": 16.49,
- "learning_rate": 9.604591836734694e-05,
- "loss": 1.1577,
+ "epoch": 9.21,
+ "learning_rate": 8.423295454545455e-05,
+ "loss": 0.5332,
"step": 815
},
{
- "epoch": 16.51,
- "learning_rate": 9.591836734693878e-05,
- "loss": 1.1436,
+ "epoch": 9.22,
+ "learning_rate": 8.40909090909091e-05,
+ "loss": 0.5181,
"step": 816
},
{
- "epoch": 16.53,
- "learning_rate": 9.579081632653061e-05,
- "loss": 1.1657,
+ "epoch": 9.23,
+ "learning_rate": 8.394886363636364e-05,
+ "loss": 0.5085,
"step": 817
},
{
- "epoch": 16.55,
- "learning_rate": 9.566326530612246e-05,
- "loss": 1.1147,
+ "epoch": 9.24,
+ "learning_rate": 8.380681818181818e-05,
+ "loss": 0.5137,
"step": 818
},
{
- "epoch": 16.57,
- "learning_rate": 9.553571428571429e-05,
- "loss": 1.1839,
+ "epoch": 9.25,
+ "learning_rate": 8.366477272727273e-05,
+ "loss": 0.5195,
"step": 819
},
{
- "epoch": 16.59,
- "learning_rate": 9.540816326530613e-05,
- "loss": 1.1298,
+ "epoch": 9.26,
+ "learning_rate": 8.352272727272727e-05,
+ "loss": 0.5077,
"step": 820
},
{
- "epoch": 16.61,
- "learning_rate": 9.528061224489796e-05,
- "loss": 1.2141,
+ "epoch": 9.28,
+ "learning_rate": 8.338068181818183e-05,
+ "loss": 0.5074,
"step": 821
},
{
- "epoch": 16.63,
- "learning_rate": 9.515306122448981e-05,
- "loss": 1.2045,
+ "epoch": 9.29,
+ "learning_rate": 8.323863636363637e-05,
+ "loss": 0.5142,
"step": 822
},
{
- "epoch": 16.65,
- "learning_rate": 9.502551020408164e-05,
- "loss": 1.1791,
+ "epoch": 9.3,
+ "learning_rate": 8.309659090909091e-05,
+ "loss": 0.5116,
"step": 823
},
{
- "epoch": 16.67,
- "learning_rate": 9.489795918367348e-05,
- "loss": 1.1137,
+ "epoch": 9.31,
+ "learning_rate": 8.295454545454547e-05,
+ "loss": 0.4974,
"step": 824
},
{
- "epoch": 16.69,
- "learning_rate": 9.477040816326531e-05,
- "loss": 1.1312,
+ "epoch": 9.32,
+ "learning_rate": 8.28125e-05,
+ "loss": 0.5117,
"step": 825
},
{
- "epoch": 16.71,
- "learning_rate": 9.464285714285715e-05,
- "loss": 1.1102,
+ "epoch": 9.33,
+ "learning_rate": 8.267045454545455e-05,
+ "loss": 0.5114,
"step": 826
},
{
- "epoch": 16.73,
- "learning_rate": 9.451530612244899e-05,
- "loss": 1.1865,
+ "epoch": 9.34,
+ "learning_rate": 8.25284090909091e-05,
+ "loss": 0.5039,
"step": 827
},
{
- "epoch": 16.75,
- "learning_rate": 9.438775510204082e-05,
- "loss": 1.1232,
+ "epoch": 9.35,
+ "learning_rate": 8.238636363636364e-05,
+ "loss": 0.498,
"step": 828
},
{
- "epoch": 16.77,
- "learning_rate": 9.426020408163265e-05,
- "loss": 1.2068,
+ "epoch": 9.37,
+ "learning_rate": 8.224431818181818e-05,
+ "loss": 0.5042,
"step": 829
},
{
- "epoch": 16.79,
- "learning_rate": 9.41326530612245e-05,
- "loss": 1.1864,
+ "epoch": 9.38,
+ "learning_rate": 8.210227272727274e-05,
+ "loss": 0.5049,
"step": 830
},
{
- "epoch": 16.81,
- "learning_rate": 9.400510204081633e-05,
- "loss": 1.2195,
+ "epoch": 9.39,
+ "learning_rate": 8.196022727272727e-05,
+ "loss": 0.5123,
"step": 831
},
{
- "epoch": 16.83,
- "learning_rate": 9.387755102040817e-05,
- "loss": 1.2063,
+ "epoch": 9.4,
+ "learning_rate": 8.181818181818183e-05,
+ "loss": 0.4907,
"step": 832
},
{
- "epoch": 16.85,
- "learning_rate": 9.375e-05,
- "loss": 1.1455,
+ "epoch": 9.41,
+ "learning_rate": 8.167613636363637e-05,
+ "loss": 0.5267,
"step": 833
},
{
- "epoch": 16.88,
- "learning_rate": 9.362244897959183e-05,
- "loss": 1.1819,
+ "epoch": 9.42,
+ "learning_rate": 8.15340909090909e-05,
+ "loss": 0.5314,
"step": 834
},
{
- "epoch": 16.9,
- "learning_rate": 9.349489795918368e-05,
- "loss": 1.1887,
+ "epoch": 9.43,
+ "learning_rate": 8.139204545454546e-05,
+ "loss": 0.4952,
"step": 835
},
{
- "epoch": 16.92,
- "learning_rate": 9.336734693877551e-05,
- "loss": 1.1557,
+ "epoch": 9.44,
+ "learning_rate": 8.125000000000001e-05,
+ "loss": 0.5014,
"step": 836
},
{
- "epoch": 16.94,
- "learning_rate": 9.323979591836735e-05,
- "loss": 1.2094,
+ "epoch": 9.46,
+ "learning_rate": 8.110795454545454e-05,
+ "loss": 0.4967,
"step": 837
},
{
- "epoch": 16.96,
- "learning_rate": 9.311224489795918e-05,
- "loss": 1.1512,
+ "epoch": 9.47,
+ "learning_rate": 8.09659090909091e-05,
+ "loss": 0.5116,
"step": 838
},
{
- "epoch": 16.98,
- "learning_rate": 9.298469387755103e-05,
- "loss": 1.1463,
+ "epoch": 9.48,
+ "learning_rate": 8.082386363636365e-05,
+ "loss": 0.5119,
"step": 839
},
{
- "epoch": 17.0,
- "learning_rate": 9.285714285714286e-05,
- "loss": 1.155,
+ "epoch": 9.49,
+ "learning_rate": 8.068181818181818e-05,
+ "loss": 0.4987,
"step": 840
},
{
- "epoch": 17.02,
- "learning_rate": 9.27295918367347e-05,
- "loss": 1.1292,
+ "epoch": 9.5,
+ "learning_rate": 8.053977272727274e-05,
+ "loss": 0.5063,
"step": 841
},
{
- "epoch": 17.04,
- "learning_rate": 9.260204081632653e-05,
- "loss": 1.0996,
+ "epoch": 9.51,
+ "learning_rate": 8.039772727272728e-05,
+ "loss": 0.5019,
"step": 842
},
{
- "epoch": 17.06,
- "learning_rate": 9.247448979591838e-05,
- "loss": 1.0662,
+ "epoch": 9.52,
+ "learning_rate": 8.025568181818183e-05,
+ "loss": 0.5272,
"step": 843
},
{
- "epoch": 17.08,
- "learning_rate": 9.234693877551021e-05,
- "loss": 1.0931,
+ "epoch": 9.54,
+ "learning_rate": 8.011363636363637e-05,
+ "loss": 0.4969,
"step": 844
},
{
- "epoch": 17.1,
- "learning_rate": 9.221938775510205e-05,
- "loss": 1.0727,
+ "epoch": 9.55,
+ "learning_rate": 7.997159090909092e-05,
+ "loss": 0.5222,
"step": 845
},
{
- "epoch": 17.12,
- "learning_rate": 9.209183673469388e-05,
- "loss": 1.1043,
+ "epoch": 9.56,
+ "learning_rate": 7.982954545454546e-05,
+ "loss": 0.4729,
"step": 846
},
{
- "epoch": 17.14,
- "learning_rate": 9.196428571428572e-05,
- "loss": 1.0594,
+ "epoch": 9.57,
+ "learning_rate": 7.96875e-05,
+ "loss": 0.4976,
"step": 847
},
{
- "epoch": 17.16,
- "learning_rate": 9.183673469387756e-05,
- "loss": 1.0952,
+ "epoch": 9.58,
+ "learning_rate": 7.954545454545455e-05,
+ "loss": 0.4974,
"step": 848
},
{
- "epoch": 17.18,
- "learning_rate": 9.170918367346939e-05,
- "loss": 1.0639,
+ "epoch": 9.59,
+ "learning_rate": 7.94034090909091e-05,
+ "loss": 0.4849,
"step": 849
},
{
- "epoch": 17.2,
- "learning_rate": 9.158163265306124e-05,
- "loss": 1.132,
+ "epoch": 9.6,
+ "learning_rate": 7.926136363636364e-05,
+ "loss": 0.4897,
"step": 850
},
{
- "epoch": 17.22,
- "learning_rate": 9.145408163265307e-05,
- "loss": 1.1083,
+ "epoch": 9.61,
+ "learning_rate": 7.911931818181819e-05,
+ "loss": 0.4962,
"step": 851
},
{
- "epoch": 17.24,
- "learning_rate": 9.13265306122449e-05,
- "loss": 1.1282,
+ "epoch": 9.63,
+ "learning_rate": 7.897727272727273e-05,
+ "loss": 0.4877,
"step": 852
},
{
- "epoch": 17.26,
- "learning_rate": 9.119897959183674e-05,
- "loss": 1.0474,
+ "epoch": 9.64,
+ "learning_rate": 7.883522727272728e-05,
+ "loss": 0.4921,
"step": 853
},
{
- "epoch": 17.28,
- "learning_rate": 9.107142857142857e-05,
- "loss": 1.1138,
+ "epoch": 9.65,
+ "learning_rate": 7.869318181818182e-05,
+ "loss": 0.4969,
"step": 854
},
{
- "epoch": 17.3,
- "learning_rate": 9.094387755102042e-05,
- "loss": 1.1025,
+ "epoch": 9.66,
+ "learning_rate": 7.855113636363637e-05,
+ "loss": 0.5045,
"step": 855
},
{
- "epoch": 17.32,
- "learning_rate": 9.081632653061225e-05,
- "loss": 1.0968,
+ "epoch": 9.67,
+ "learning_rate": 7.840909090909091e-05,
+ "loss": 0.5207,
"step": 856
},
{
- "epoch": 17.34,
- "learning_rate": 9.068877551020408e-05,
- "loss": 1.1683,
+ "epoch": 9.68,
+ "learning_rate": 7.826704545454546e-05,
+ "loss": 0.5098,
"step": 857
},
{
- "epoch": 17.36,
- "learning_rate": 9.056122448979592e-05,
- "loss": 1.0975,
+ "epoch": 9.69,
+ "learning_rate": 7.8125e-05,
+ "loss": 0.5005,
"step": 858
},
{
- "epoch": 17.38,
- "learning_rate": 9.043367346938775e-05,
- "loss": 1.1274,
+ "epoch": 9.7,
+ "learning_rate": 7.798295454545455e-05,
+ "loss": 0.5028,
"step": 859
},
{
- "epoch": 17.4,
- "learning_rate": 9.030612244897958e-05,
- "loss": 1.0916,
+ "epoch": 9.72,
+ "learning_rate": 7.784090909090909e-05,
+ "loss": 0.5067,
"step": 860
},
{
- "epoch": 17.42,
- "learning_rate": 9.017857142857143e-05,
- "loss": 1.0912,
+ "epoch": 9.73,
+ "learning_rate": 7.769886363636364e-05,
+ "loss": 0.484,
"step": 861
},
{
- "epoch": 17.44,
- "learning_rate": 9.005102040816327e-05,
- "loss": 1.0875,
+ "epoch": 9.74,
+ "learning_rate": 7.755681818181818e-05,
+ "loss": 0.5029,
"step": 862
},
{
- "epoch": 17.46,
- "learning_rate": 8.99234693877551e-05,
- "loss": 1.05,
+ "epoch": 9.75,
+ "learning_rate": 7.741477272727273e-05,
+ "loss": 0.5077,
"step": 863
},
{
- "epoch": 17.48,
- "learning_rate": 8.979591836734695e-05,
- "loss": 1.1418,
+ "epoch": 9.76,
+ "learning_rate": 7.727272727272727e-05,
+ "loss": 0.5091,
"step": 864
},
{
- "epoch": 17.5,
- "learning_rate": 8.966836734693878e-05,
- "loss": 1.0609,
+ "epoch": 9.77,
+ "learning_rate": 7.713068181818183e-05,
+ "loss": 0.4781,
"step": 865
},
{
- "epoch": 17.52,
- "learning_rate": 8.954081632653062e-05,
- "loss": 1.1611,
+ "epoch": 9.78,
+ "learning_rate": 7.698863636363636e-05,
+ "loss": 0.5124,
"step": 866
},
{
- "epoch": 17.54,
- "learning_rate": 8.941326530612245e-05,
- "loss": 1.1065,
+ "epoch": 9.79,
+ "learning_rate": 7.684659090909091e-05,
+ "loss": 0.4859,
"step": 867
},
{
- "epoch": 17.56,
- "learning_rate": 8.92857142857143e-05,
- "loss": 1.1611,
+ "epoch": 9.81,
+ "learning_rate": 7.670454545454547e-05,
+ "loss": 0.4872,
"step": 868
},
{
- "epoch": 17.58,
- "learning_rate": 8.915816326530613e-05,
- "loss": 1.1398,
+ "epoch": 9.82,
+ "learning_rate": 7.65625e-05,
+ "loss": 0.4675,
"step": 869
},
{
- "epoch": 17.6,
- "learning_rate": 8.903061224489796e-05,
- "loss": 1.1055,
+ "epoch": 9.83,
+ "learning_rate": 7.642045454545454e-05,
+ "loss": 0.5056,
"step": 870
},
{
- "epoch": 17.62,
- "learning_rate": 8.89030612244898e-05,
- "loss": 1.1314,
+ "epoch": 9.84,
+ "learning_rate": 7.62784090909091e-05,
+ "loss": 0.4868,
"step": 871
},
{
- "epoch": 17.64,
- "learning_rate": 8.877551020408164e-05,
- "loss": 1.1084,
+ "epoch": 9.85,
+ "learning_rate": 7.613636363636363e-05,
+ "loss": 0.4907,
"step": 872
},
{
- "epoch": 17.66,
- "learning_rate": 8.864795918367348e-05,
- "loss": 1.1254,
+ "epoch": 9.86,
+ "learning_rate": 7.599431818181818e-05,
+ "loss": 0.474,
"step": 873
},
{
- "epoch": 17.68,
- "learning_rate": 8.852040816326531e-05,
- "loss": 1.142,
+ "epoch": 9.87,
+ "learning_rate": 7.585227272727274e-05,
+ "loss": 0.4813,
"step": 874
},
{
- "epoch": 17.7,
- "learning_rate": 8.839285714285714e-05,
- "loss": 1.1371,
+ "epoch": 9.89,
+ "learning_rate": 7.571022727272727e-05,
+ "loss": 0.4838,
"step": 875
},
{
- "epoch": 17.72,
- "learning_rate": 8.826530612244899e-05,
- "loss": 1.1092,
+ "epoch": 9.9,
+ "learning_rate": 7.556818181818183e-05,
+ "loss": 0.4935,
"step": 876
},
{
- "epoch": 17.75,
- "learning_rate": 8.813775510204082e-05,
- "loss": 1.161,
+ "epoch": 9.91,
+ "learning_rate": 7.542613636363637e-05,
+ "loss": 0.4884,
"step": 877
},
{
- "epoch": 17.77,
- "learning_rate": 8.801020408163265e-05,
- "loss": 1.1044,
+ "epoch": 9.92,
+ "learning_rate": 7.52840909090909e-05,
+ "loss": 0.4797,
"step": 878
},
{
- "epoch": 17.79,
- "learning_rate": 8.788265306122449e-05,
- "loss": 1.117,
+ "epoch": 9.93,
+ "learning_rate": 7.514204545454546e-05,
+ "loss": 0.479,
"step": 879
},
{
- "epoch": 17.81,
- "learning_rate": 8.775510204081632e-05,
- "loss": 1.1262,
+ "epoch": 9.94,
+ "learning_rate": 7.500000000000001e-05,
+ "loss": 0.4727,
"step": 880
},
{
- "epoch": 17.83,
- "learning_rate": 8.762755102040817e-05,
- "loss": 1.0829,
+ "epoch": 9.95,
+ "learning_rate": 7.485795454545454e-05,
+ "loss": 0.4758,
"step": 881
},
{
- "epoch": 17.85,
- "learning_rate": 8.75e-05,
- "loss": 1.1393,
+ "epoch": 9.96,
+ "learning_rate": 7.47159090909091e-05,
+ "loss": 0.482,
"step": 882
},
{
- "epoch": 17.87,
- "learning_rate": 8.737244897959183e-05,
- "loss": 1.1781,
+ "epoch": 9.98,
+ "learning_rate": 7.457386363636364e-05,
+ "loss": 0.4951,
"step": 883
},
{
- "epoch": 17.89,
- "learning_rate": 8.724489795918367e-05,
- "loss": 1.1582,
+ "epoch": 9.99,
+ "learning_rate": 7.443181818181817e-05,
+ "loss": 0.4823,
"step": 884
},
{
- "epoch": 17.91,
- "learning_rate": 8.711734693877552e-05,
- "loss": 1.1469,
+ "epoch": 10.0,
+ "learning_rate": 7.428977272727273e-05,
+ "loss": 0.4638,
"step": 885
},
{
- "epoch": 17.93,
- "learning_rate": 8.698979591836735e-05,
- "loss": 1.1494,
+ "epoch": 10.01,
+ "learning_rate": 7.414772727272728e-05,
+ "loss": 0.4715,
"step": 886
},
{
- "epoch": 17.95,
- "learning_rate": 8.68622448979592e-05,
- "loss": 1.1251,
+ "epoch": 10.02,
+ "learning_rate": 7.400568181818182e-05,
+ "loss": 0.461,
"step": 887
},
{
- "epoch": 17.97,
- "learning_rate": 8.673469387755102e-05,
- "loss": 1.1624,
+ "epoch": 10.03,
+ "learning_rate": 7.386363636363637e-05,
+ "loss": 0.4429,
"step": 888
},
{
- "epoch": 17.99,
- "learning_rate": 8.660714285714287e-05,
- "loss": 1.0842,
+ "epoch": 10.04,
+ "learning_rate": 7.372159090909091e-05,
+ "loss": 0.4403,
"step": 889
},
{
- "epoch": 18.01,
- "learning_rate": 8.64795918367347e-05,
- "loss": 1.1944,
+ "epoch": 10.05,
+ "learning_rate": 7.357954545454546e-05,
+ "loss": 0.4519,
"step": 890
},
{
- "epoch": 18.03,
- "learning_rate": 8.635204081632653e-05,
- "loss": 1.0642,
+ "epoch": 10.07,
+ "learning_rate": 7.34375e-05,
+ "loss": 0.4611,
"step": 891
},
{
- "epoch": 18.05,
- "learning_rate": 8.622448979591838e-05,
- "loss": 1.0459,
+ "epoch": 10.08,
+ "learning_rate": 7.329545454545455e-05,
+ "loss": 0.4543,
"step": 892
},
{
- "epoch": 18.07,
- "learning_rate": 8.60969387755102e-05,
- "loss": 1.0941,
+ "epoch": 10.09,
+ "learning_rate": 7.315340909090909e-05,
+ "loss": 0.4528,
"step": 893
},
{
- "epoch": 18.09,
- "learning_rate": 8.596938775510205e-05,
- "loss": 1.0457,
+ "epoch": 10.1,
+ "learning_rate": 7.301136363636364e-05,
+ "loss": 0.4586,
"step": 894
},
{
- "epoch": 18.11,
- "learning_rate": 8.584183673469388e-05,
- "loss": 1.1033,
+ "epoch": 10.11,
+ "learning_rate": 7.286931818181818e-05,
+ "loss": 0.4418,
"step": 895
},
{
- "epoch": 18.13,
- "learning_rate": 8.571428571428571e-05,
- "loss": 1.0756,
+ "epoch": 10.12,
+ "learning_rate": 7.272727272727273e-05,
+ "loss": 0.4435,
"step": 896
},
{
- "epoch": 18.15,
- "learning_rate": 8.558673469387756e-05,
- "loss": 1.0615,
+ "epoch": 10.13,
+ "learning_rate": 7.258522727272727e-05,
+ "loss": 0.44,
"step": 897
},
{
- "epoch": 18.17,
- "learning_rate": 8.545918367346939e-05,
- "loss": 1.0828,
+ "epoch": 10.15,
+ "learning_rate": 7.244318181818183e-05,
+ "loss": 0.4589,
"step": 898
},
{
- "epoch": 18.19,
- "learning_rate": 8.533163265306123e-05,
- "loss": 1.1158,
+ "epoch": 10.16,
+ "learning_rate": 7.230113636363636e-05,
+ "loss": 0.4597,
"step": 899
},
{
- "epoch": 18.21,
- "learning_rate": 8.520408163265306e-05,
- "loss": 1.0133,
+ "epoch": 10.17,
+ "learning_rate": 7.215909090909091e-05,
+ "loss": 0.4479,
"step": 900
},
{
- "epoch": 18.23,
- "learning_rate": 8.50765306122449e-05,
- "loss": 1.0437,
+ "epoch": 10.18,
+ "learning_rate": 7.201704545454547e-05,
+ "loss": 0.4477,
"step": 901
},
{
- "epoch": 18.25,
- "learning_rate": 8.494897959183674e-05,
- "loss": 1.0372,
+ "epoch": 10.19,
+ "learning_rate": 7.1875e-05,
+ "loss": 0.446,
"step": 902
},
{
- "epoch": 18.27,
- "learning_rate": 8.482142857142857e-05,
- "loss": 1.1012,
+ "epoch": 10.2,
+ "learning_rate": 7.173295454545454e-05,
+ "loss": 0.4546,
"step": 903
},
{
- "epoch": 18.29,
- "learning_rate": 8.469387755102041e-05,
- "loss": 1.0777,
+ "epoch": 10.21,
+ "learning_rate": 7.15909090909091e-05,
+ "loss": 0.4347,
"step": 904
},
{
- "epoch": 18.31,
- "learning_rate": 8.456632653061224e-05,
- "loss": 1.0799,
+ "epoch": 10.22,
+ "learning_rate": 7.144886363636363e-05,
+ "loss": 0.452,
"step": 905
},
{
- "epoch": 18.33,
- "learning_rate": 8.443877551020409e-05,
- "loss": 0.9846,
+ "epoch": 10.24,
+ "learning_rate": 7.130681818181818e-05,
+ "loss": 0.4536,
"step": 906
},
{
- "epoch": 18.35,
- "learning_rate": 8.431122448979592e-05,
- "loss": 1.1,
+ "epoch": 10.25,
+ "learning_rate": 7.116477272727274e-05,
+ "loss": 0.4492,
"step": 907
},
{
- "epoch": 18.37,
- "learning_rate": 8.418367346938776e-05,
- "loss": 1.0787,
+ "epoch": 10.26,
+ "learning_rate": 7.102272727272727e-05,
+ "loss": 0.4401,
"step": 908
},
{
- "epoch": 18.39,
- "learning_rate": 8.40561224489796e-05,
- "loss": 1.0647,
+ "epoch": 10.27,
+ "learning_rate": 7.088068181818183e-05,
+ "loss": 0.4609,
"step": 909
},
{
- "epoch": 18.41,
- "learning_rate": 8.392857142857144e-05,
- "loss": 1.056,
+ "epoch": 10.28,
+ "learning_rate": 7.073863636363637e-05,
+ "loss": 0.4544,
"step": 910
},
{
- "epoch": 18.43,
- "learning_rate": 8.380102040816327e-05,
- "loss": 1.1131,
+ "epoch": 10.29,
+ "learning_rate": 7.05965909090909e-05,
+ "loss": 0.4477,
"step": 911
},
{
- "epoch": 18.45,
- "learning_rate": 8.367346938775511e-05,
- "loss": 1.0825,
+ "epoch": 10.3,
+ "learning_rate": 7.045454545454546e-05,
+ "loss": 0.4445,
"step": 912
},
{
- "epoch": 18.47,
- "learning_rate": 8.354591836734695e-05,
- "loss": 1.0681,
+ "epoch": 10.31,
+ "learning_rate": 7.031250000000001e-05,
+ "loss": 0.4544,
"step": 913
},
{
- "epoch": 18.49,
- "learning_rate": 8.341836734693878e-05,
- "loss": 1.0479,
+ "epoch": 10.33,
+ "learning_rate": 7.017045454545454e-05,
+ "loss": 0.4634,
"step": 914
},
{
- "epoch": 18.51,
- "learning_rate": 8.329081632653062e-05,
- "loss": 1.0921,
+ "epoch": 10.34,
+ "learning_rate": 7.00284090909091e-05,
+ "loss": 0.4499,
"step": 915
},
{
- "epoch": 18.53,
- "learning_rate": 8.316326530612245e-05,
- "loss": 1.0626,
+ "epoch": 10.35,
+ "learning_rate": 6.988636363636364e-05,
+ "loss": 0.4354,
"step": 916
},
{
- "epoch": 18.55,
- "learning_rate": 8.30357142857143e-05,
- "loss": 1.0518,
+ "epoch": 10.36,
+ "learning_rate": 6.974431818181818e-05,
+ "loss": 0.454,
"step": 917
},
{
- "epoch": 18.57,
- "learning_rate": 8.290816326530613e-05,
- "loss": 1.0557,
+ "epoch": 10.37,
+ "learning_rate": 6.960227272727273e-05,
+ "loss": 0.4473,
"step": 918
},
{
- "epoch": 18.6,
- "learning_rate": 8.278061224489796e-05,
- "loss": 1.0831,
+ "epoch": 10.38,
+ "learning_rate": 6.946022727272728e-05,
+ "loss": 0.4347,
"step": 919
},
{
- "epoch": 18.62,
- "learning_rate": 8.26530612244898e-05,
- "loss": 1.0307,
+ "epoch": 10.39,
+ "learning_rate": 6.931818181818182e-05,
+ "loss": 0.441,
"step": 920
},
{
- "epoch": 18.64,
- "learning_rate": 8.252551020408163e-05,
- "loss": 1.0455,
+ "epoch": 10.4,
+ "learning_rate": 6.917613636363637e-05,
+ "loss": 0.4545,
"step": 921
},
{
- "epoch": 18.66,
- "learning_rate": 8.239795918367348e-05,
- "loss": 1.0667,
+ "epoch": 10.42,
+ "learning_rate": 6.903409090909091e-05,
+ "loss": 0.458,
"step": 922
},
{
- "epoch": 18.68,
- "learning_rate": 8.227040816326531e-05,
- "loss": 1.0736,
+ "epoch": 10.43,
+ "learning_rate": 6.889204545454546e-05,
+ "loss": 0.4381,
"step": 923
},
{
- "epoch": 18.7,
- "learning_rate": 8.214285714285714e-05,
- "loss": 1.0108,
+ "epoch": 10.44,
+ "learning_rate": 6.875e-05,
+ "loss": 0.441,
"step": 924
},
{
- "epoch": 18.72,
- "learning_rate": 8.201530612244898e-05,
- "loss": 1.0458,
+ "epoch": 10.45,
+ "learning_rate": 6.860795454545455e-05,
+ "loss": 0.4446,
"step": 925
},
{
- "epoch": 18.74,
- "learning_rate": 8.188775510204081e-05,
- "loss": 1.0852,
+ "epoch": 10.46,
+ "learning_rate": 6.84659090909091e-05,
+ "loss": 0.4548,
"step": 926
},
{
- "epoch": 18.76,
- "learning_rate": 8.176020408163265e-05,
- "loss": 1.1207,
+ "epoch": 10.47,
+ "learning_rate": 6.832386363636364e-05,
+ "loss": 0.4404,
"step": 927
},
{
- "epoch": 18.78,
- "learning_rate": 8.163265306122449e-05,
- "loss": 1.0914,
+ "epoch": 10.48,
+ "learning_rate": 6.818181818181818e-05,
+ "loss": 0.4446,
"step": 928
},
{
- "epoch": 18.8,
- "learning_rate": 8.150510204081633e-05,
- "loss": 1.1108,
+ "epoch": 10.5,
+ "learning_rate": 6.803977272727273e-05,
+ "loss": 0.4434,
"step": 929
},
{
- "epoch": 18.82,
- "learning_rate": 8.137755102040817e-05,
- "loss": 1.1394,
+ "epoch": 10.51,
+ "learning_rate": 6.789772727272727e-05,
+ "loss": 0.4778,
"step": 930
},
{
- "epoch": 18.84,
- "learning_rate": 8.125000000000001e-05,
- "loss": 1.029,
+ "epoch": 10.52,
+ "learning_rate": 6.775568181818182e-05,
+ "loss": 0.4356,
"step": 931
},
{
- "epoch": 18.86,
- "learning_rate": 8.112244897959184e-05,
- "loss": 1.0661,
+ "epoch": 10.53,
+ "learning_rate": 6.761363636363636e-05,
+ "loss": 0.4464,
"step": 932
},
{
- "epoch": 18.88,
- "learning_rate": 8.099489795918369e-05,
- "loss": 1.0303,
+ "epoch": 10.54,
+ "learning_rate": 6.747159090909091e-05,
+ "loss": 0.4387,
"step": 933
},
{
- "epoch": 18.9,
- "learning_rate": 8.086734693877552e-05,
- "loss": 1.1144,
+ "epoch": 10.55,
+ "learning_rate": 6.732954545454547e-05,
+ "loss": 0.456,
"step": 934
},
{
- "epoch": 18.92,
- "learning_rate": 8.073979591836736e-05,
- "loss": 1.1096,
+ "epoch": 10.56,
+ "learning_rate": 6.71875e-05,
+ "loss": 0.453,
"step": 935
},
{
- "epoch": 18.94,
- "learning_rate": 8.061224489795919e-05,
- "loss": 1.123,
+ "epoch": 10.57,
+ "learning_rate": 6.704545454545455e-05,
+ "loss": 0.4611,
"step": 936
},
{
- "epoch": 18.96,
- "learning_rate": 8.048469387755102e-05,
- "loss": 1.1002,
+ "epoch": 10.59,
+ "learning_rate": 6.69034090909091e-05,
+ "loss": 0.4354,
"step": 937
},
{
- "epoch": 18.98,
- "learning_rate": 8.035714285714287e-05,
- "loss": 1.1016,
+ "epoch": 10.6,
+ "learning_rate": 6.676136363636364e-05,
+ "loss": 0.4519,
"step": 938
},
{
- "epoch": 19.0,
- "learning_rate": 8.02295918367347e-05,
- "loss": 1.0847,
+ "epoch": 10.61,
+ "learning_rate": 6.661931818181818e-05,
+ "loss": 0.4435,
"step": 939
},
{
- "epoch": 19.02,
- "learning_rate": 8.010204081632653e-05,
- "loss": 1.1029,
+ "epoch": 10.62,
+ "learning_rate": 6.647727272727274e-05,
+ "loss": 0.4422,
"step": 940
},
{
- "epoch": 19.04,
- "learning_rate": 7.997448979591837e-05,
- "loss": 1.041,
+ "epoch": 10.63,
+ "learning_rate": 6.633522727272727e-05,
+ "loss": 0.4344,
"step": 941
},
{
- "epoch": 19.06,
- "learning_rate": 7.98469387755102e-05,
- "loss": 1.01,
+ "epoch": 10.64,
+ "learning_rate": 6.619318181818183e-05,
+ "loss": 0.4419,
"step": 942
},
{
- "epoch": 19.08,
- "learning_rate": 7.971938775510205e-05,
- "loss": 1.0197,
+ "epoch": 10.65,
+ "learning_rate": 6.605113636363637e-05,
+ "loss": 0.4308,
"step": 943
},
{
- "epoch": 19.1,
- "learning_rate": 7.959183673469388e-05,
- "loss": 1.0543,
+ "epoch": 10.66,
+ "learning_rate": 6.59090909090909e-05,
+ "loss": 0.4043,
"step": 944
},
{
- "epoch": 19.12,
- "learning_rate": 7.946428571428571e-05,
- "loss": 1.0369,
+ "epoch": 10.68,
+ "learning_rate": 6.576704545454546e-05,
+ "loss": 0.4626,
"step": 945
},
{
- "epoch": 19.14,
- "learning_rate": 7.933673469387755e-05,
- "loss": 1.0154,
+ "epoch": 10.69,
+ "learning_rate": 6.562500000000001e-05,
+ "loss": 0.4365,
"step": 946
},
{
- "epoch": 19.16,
- "learning_rate": 7.920918367346939e-05,
- "loss": 0.9546,
+ "epoch": 10.7,
+ "learning_rate": 6.548295454545454e-05,
+ "loss": 0.4397,
"step": 947
},
{
- "epoch": 19.18,
- "learning_rate": 7.908163265306123e-05,
- "loss": 0.9982,
+ "epoch": 10.71,
+ "learning_rate": 6.53409090909091e-05,
+ "loss": 0.4463,
"step": 948
},
{
- "epoch": 19.2,
- "learning_rate": 7.895408163265306e-05,
- "loss": 1.0748,
+ "epoch": 10.72,
+ "learning_rate": 6.519886363636364e-05,
+ "loss": 0.4394,
"step": 949
},
{
- "epoch": 19.22,
- "learning_rate": 7.882653061224489e-05,
- "loss": 1.0562,
+ "epoch": 10.73,
+ "learning_rate": 6.505681818181818e-05,
+ "loss": 0.45,
"step": 950
},
{
- "epoch": 19.24,
- "learning_rate": 7.869897959183674e-05,
- "loss": 1.0352,
+ "epoch": 10.74,
+ "learning_rate": 6.491477272727273e-05,
+ "loss": 0.4363,
"step": 951
},
{
- "epoch": 19.26,
- "learning_rate": 7.857142857142858e-05,
- "loss": 0.9976,
+ "epoch": 10.76,
+ "learning_rate": 6.477272727272728e-05,
+ "loss": 0.4566,
"step": 952
},
{
- "epoch": 19.28,
- "learning_rate": 7.844387755102041e-05,
- "loss": 1.0221,
+ "epoch": 10.77,
+ "learning_rate": 6.463068181818183e-05,
+ "loss": 0.4235,
"step": 953
},
{
- "epoch": 19.3,
- "learning_rate": 7.831632653061226e-05,
- "loss": 1.0119,
+ "epoch": 10.78,
+ "learning_rate": 6.448863636363637e-05,
+ "loss": 0.4458,
"step": 954
},
{
- "epoch": 19.32,
- "learning_rate": 7.818877551020409e-05,
- "loss": 1.0657,
+ "epoch": 10.79,
+ "learning_rate": 6.434659090909092e-05,
+ "loss": 0.423,
"step": 955
},
{
- "epoch": 19.34,
- "learning_rate": 7.806122448979593e-05,
- "loss": 0.9591,
+ "epoch": 10.8,
+ "learning_rate": 6.420454545454546e-05,
+ "loss": 0.445,
"step": 956
},
{
- "epoch": 19.36,
- "learning_rate": 7.793367346938776e-05,
- "loss": 1.0101,
+ "epoch": 10.81,
+ "learning_rate": 6.40625e-05,
+ "loss": 0.424,
"step": 957
},
{
- "epoch": 19.38,
- "learning_rate": 7.780612244897959e-05,
- "loss": 1.0453,
+ "epoch": 10.82,
+ "learning_rate": 6.392045454545455e-05,
+ "loss": 0.4224,
"step": 958
},
{
- "epoch": 19.4,
- "learning_rate": 7.767857142857144e-05,
- "loss": 1.0461,
+ "epoch": 10.83,
+ "learning_rate": 6.37784090909091e-05,
+ "loss": 0.4223,
"step": 959
},
{
- "epoch": 19.42,
- "learning_rate": 7.755102040816327e-05,
- "loss": 1.0959,
+ "epoch": 10.85,
+ "learning_rate": 6.363636363636364e-05,
+ "loss": 0.4314,
"step": 960
},
{
- "epoch": 19.44,
- "learning_rate": 7.742346938775511e-05,
- "loss": 1.0608,
+ "epoch": 10.86,
+ "learning_rate": 6.349431818181819e-05,
+ "loss": 0.4488,
"step": 961
},
{
- "epoch": 19.47,
- "learning_rate": 7.729591836734694e-05,
- "loss": 1.1177,
+ "epoch": 10.87,
+ "learning_rate": 6.335227272727273e-05,
+ "loss": 0.423,
"step": 962
},
{
- "epoch": 19.49,
- "learning_rate": 7.716836734693877e-05,
- "loss": 1.0354,
+ "epoch": 10.88,
+ "learning_rate": 6.321022727272728e-05,
+ "loss": 0.4416,
"step": 963
},
{
- "epoch": 19.51,
- "learning_rate": 7.704081632653062e-05,
- "loss": 1.0507,
+ "epoch": 10.89,
+ "learning_rate": 6.306818181818182e-05,
+ "loss": 0.423,
"step": 964
},
{
- "epoch": 19.53,
- "learning_rate": 7.691326530612245e-05,
- "loss": 1.0313,
+ "epoch": 10.9,
+ "learning_rate": 6.292613636363637e-05,
+ "loss": 0.4502,
"step": 965
},
{
- "epoch": 19.55,
- "learning_rate": 7.67857142857143e-05,
- "loss": 1.0569,
+ "epoch": 10.91,
+ "learning_rate": 6.278409090909091e-05,
+ "loss": 0.4266,
"step": 966
},
{
- "epoch": 19.57,
- "learning_rate": 7.665816326530612e-05,
- "loss": 1.0862,
+ "epoch": 10.92,
+ "learning_rate": 6.264204545454546e-05,
+ "loss": 0.4344,
"step": 967
},
{
- "epoch": 19.59,
- "learning_rate": 7.653061224489796e-05,
- "loss": 1.0593,
+ "epoch": 10.94,
+ "learning_rate": 6.25e-05,
+ "loss": 0.434,
"step": 968
},
{
- "epoch": 19.61,
- "learning_rate": 7.64030612244898e-05,
- "loss": 1.0602,
+ "epoch": 10.95,
+ "learning_rate": 6.235795454545455e-05,
+ "loss": 0.4269,
"step": 969
},
{
- "epoch": 19.63,
- "learning_rate": 7.627551020408163e-05,
- "loss": 1.0048,
+ "epoch": 10.96,
+ "learning_rate": 6.221590909090909e-05,
+ "loss": 0.4158,
"step": 970
},
{
- "epoch": 19.65,
- "learning_rate": 7.614795918367347e-05,
- "loss": 1.0346,
+ "epoch": 10.97,
+ "learning_rate": 6.207386363636364e-05,
+ "loss": 0.4231,
"step": 971
},
{
- "epoch": 19.67,
- "learning_rate": 7.60204081632653e-05,
- "loss": 1.0172,
+ "epoch": 10.98,
+ "learning_rate": 6.193181818181818e-05,
+ "loss": 0.4235,
"step": 972
},
{
- "epoch": 19.69,
- "learning_rate": 7.589285714285714e-05,
- "loss": 1.02,
+ "epoch": 10.99,
+ "learning_rate": 6.178977272727273e-05,
+ "loss": 0.4504,
"step": 973
},
{
- "epoch": 19.71,
- "learning_rate": 7.576530612244898e-05,
- "loss": 1.0028,
+ "epoch": 11.0,
+ "learning_rate": 6.164772727272727e-05,
+ "loss": 0.4394,
"step": 974
},
{
- "epoch": 19.73,
- "learning_rate": 7.563775510204083e-05,
- "loss": 1.08,
+ "epoch": 11.02,
+ "learning_rate": 6.150568181818183e-05,
+ "loss": 0.4333,
"step": 975
},
{
- "epoch": 19.75,
- "learning_rate": 7.551020408163266e-05,
- "loss": 1.0402,
+ "epoch": 11.03,
+ "learning_rate": 6.136363636363636e-05,
+ "loss": 0.3936,
"step": 976
},
{
- "epoch": 19.77,
- "learning_rate": 7.53826530612245e-05,
- "loss": 1.0567,
+ "epoch": 11.04,
+ "learning_rate": 6.122159090909091e-05,
+ "loss": 0.3933,
"step": 977
},
{
- "epoch": 19.79,
- "learning_rate": 7.525510204081633e-05,
- "loss": 1.0169,
+ "epoch": 11.05,
+ "learning_rate": 6.107954545454547e-05,
+ "loss": 0.4161,
"step": 978
},
{
- "epoch": 19.81,
- "learning_rate": 7.512755102040818e-05,
- "loss": 0.9881,
+ "epoch": 11.06,
+ "learning_rate": 6.0937500000000004e-05,
+ "loss": 0.4097,
"step": 979
},
{
- "epoch": 19.83,
- "learning_rate": 7.500000000000001e-05,
- "loss": 1.0677,
+ "epoch": 11.07,
+ "learning_rate": 6.079545454545454e-05,
+ "loss": 0.412,
"step": 980
},
{
- "epoch": 19.85,
- "learning_rate": 7.487244897959184e-05,
- "loss": 1.1026,
+ "epoch": 11.08,
+ "learning_rate": 6.0653409090909094e-05,
+ "loss": 0.4104,
"step": 981
},
{
- "epoch": 19.87,
- "learning_rate": 7.474489795918368e-05,
- "loss": 1.0101,
+ "epoch": 11.09,
+ "learning_rate": 6.051136363636364e-05,
+ "loss": 0.4152,
"step": 982
},
{
- "epoch": 19.89,
- "learning_rate": 7.461734693877551e-05,
- "loss": 1.069,
+ "epoch": 11.11,
+ "learning_rate": 6.036931818181818e-05,
+ "loss": 0.4037,
"step": 983
},
{
- "epoch": 19.91,
- "learning_rate": 7.448979591836736e-05,
- "loss": 1.0493,
+ "epoch": 11.12,
+ "learning_rate": 6.022727272727273e-05,
+ "loss": 0.413,
"step": 984
},
{
- "epoch": 19.93,
- "learning_rate": 7.436224489795919e-05,
- "loss": 1.0858,
+ "epoch": 11.13,
+ "learning_rate": 6.0085227272727274e-05,
+ "loss": 0.4413,
"step": 985
},
{
- "epoch": 19.95,
- "learning_rate": 7.423469387755102e-05,
- "loss": 1.0734,
+ "epoch": 11.14,
+ "learning_rate": 5.9943181818181826e-05,
+ "loss": 0.3908,
"step": 986
},
{
- "epoch": 19.97,
- "learning_rate": 7.410714285714286e-05,
- "loss": 1.0203,
+ "epoch": 11.15,
+ "learning_rate": 5.9801136363636365e-05,
+ "loss": 0.3982,
"step": 987
},
{
- "epoch": 19.99,
- "learning_rate": 7.39795918367347e-05,
- "loss": 1.0285,
+ "epoch": 11.16,
+ "learning_rate": 5.965909090909091e-05,
+ "loss": 0.4109,
"step": 988
},
{
- "epoch": 20.01,
- "learning_rate": 7.385204081632653e-05,
- "loss": 0.9446,
+ "epoch": 11.17,
+ "learning_rate": 5.951704545454546e-05,
+ "loss": 0.3923,
"step": 989
},
{
- "epoch": 20.03,
- "learning_rate": 7.372448979591837e-05,
- "loss": 0.9915,
+ "epoch": 11.18,
+ "learning_rate": 5.9375e-05,
+ "loss": 0.4107,
"step": 990
},
{
- "epoch": 20.05,
- "learning_rate": 7.35969387755102e-05,
- "loss": 0.9882,
+ "epoch": 11.2,
+ "learning_rate": 5.9232954545454545e-05,
+ "loss": 0.4099,
"step": 991
},
{
- "epoch": 20.07,
- "learning_rate": 7.346938775510205e-05,
- "loss": 0.9338,
+ "epoch": 11.21,
+ "learning_rate": 5.90909090909091e-05,
+ "loss": 0.4163,
"step": 992
},
{
- "epoch": 20.09,
- "learning_rate": 7.334183673469388e-05,
- "loss": 0.942,
+ "epoch": 11.22,
+ "learning_rate": 5.8948863636363635e-05,
+ "loss": 0.4189,
"step": 993
},
{
- "epoch": 20.11,
- "learning_rate": 7.321428571428571e-05,
- "loss": 0.9725,
+ "epoch": 11.23,
+ "learning_rate": 5.880681818181818e-05,
+ "loss": 0.3889,
"step": 994
},
{
- "epoch": 20.13,
- "learning_rate": 7.308673469387755e-05,
- "loss": 1.027,
+ "epoch": 11.24,
+ "learning_rate": 5.866477272727273e-05,
+ "loss": 0.3988,
"step": 995
},
{
- "epoch": 20.15,
- "learning_rate": 7.29591836734694e-05,
- "loss": 1.0081,
+ "epoch": 11.25,
+ "learning_rate": 5.852272727272727e-05,
+ "loss": 0.4215,
"step": 996
},
{
- "epoch": 20.17,
- "learning_rate": 7.283163265306123e-05,
- "loss": 1.0117,
+ "epoch": 11.26,
+ "learning_rate": 5.838068181818183e-05,
+ "loss": 0.4207,
"step": 997
},
{
- "epoch": 20.19,
- "learning_rate": 7.270408163265307e-05,
- "loss": 0.969,
+ "epoch": 11.27,
+ "learning_rate": 5.823863636363637e-05,
+ "loss": 0.413,
"step": 998
},
{
- "epoch": 20.21,
- "learning_rate": 7.25765306122449e-05,
- "loss": 1.0024,
+ "epoch": 11.29,
+ "learning_rate": 5.8096590909090906e-05,
+ "loss": 0.4057,
"step": 999
},
{
- "epoch": 20.23,
- "learning_rate": 7.244897959183675e-05,
- "loss": 0.994,
+ "epoch": 11.3,
+ "learning_rate": 5.7954545454545464e-05,
+ "loss": 0.3939,
"step": 1000
}
],
"logging_steps": 1,
- "max_steps": 1568,
- "num_train_epochs": 32,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
"save_steps": 100,
- "total_flos": 1.4801648710853222e+18,
+ "total_flos": 1.3647437694522778e+18,
"trial_name": null,
"trial_params": null
}
diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin
index db23e07d097c18532e52f58a70eb72d22e39c8c1..ee7ddb867f05d9a969f71467a8eb88994865cf51 100644
--- a/checkpoint-1000/training_args.bin
+++ b/checkpoint-1000/training_args.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
size 4155
diff --git a/checkpoint-1100/adapter_model.bin b/checkpoint-1100/adapter_model.bin
index 7dcf0dc8d5443bd22121bd973b23076054b3ffc1..b0c372ea5e6bb9ba9144e31528b00cbe54585c4a 100644
--- a/checkpoint-1100/adapter_model.bin
+++ b/checkpoint-1100/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:475f2b2ac94b5181337d2afa8e4c9ca58b6bb0a30162d0174dc0d849d31a30b0
+oid sha256:5c4d9203c081d3cd793800a0facc03411d40e2f93788f5b95bdfa968eb1645c1
size 39409357
diff --git a/checkpoint-1100/optimizer.pt b/checkpoint-1100/optimizer.pt
index b17fb83a70f4d6556bd2414b6993be01bb4b300d..96da47b35aa614dc0d2fd08e71e7090e8060f156 100644
--- a/checkpoint-1100/optimizer.pt
+++ b/checkpoint-1100/optimizer.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:c2866f6f91b96afb3514ac044018e0555e8cbf2349cf0707fcab04ed3fddf495
+oid sha256:a9dba50b77a684018228b1b562dc170ee8a5e6c31c67ed3f1963e3e85f7adbe1
size 78844421
diff --git a/checkpoint-1100/rng_state.pth b/checkpoint-1100/rng_state.pth
index 6c28f5beeeb3e640e81e05216ffbd6b8723d5723..961069ec281e351c01eb6735b97b75dd3d8d33b7 100644
--- a/checkpoint-1100/rng_state.pth
+++ b/checkpoint-1100/rng_state.pth
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:8a2ce2e2326ca04fc964861061399d5335411f688384a0f62f8f943f1fff584e
+oid sha256:696b4cef517e79a03215d5c5fccde0c73d2d962fe70ebab1e472f650136142b2
size 14575
diff --git a/checkpoint-1100/scheduler.pt b/checkpoint-1100/scheduler.pt
index 93a79f6932abedd9808abc7ecd95a072e0a7d19f..3fb997f5b184a72c73e1ed47a3a47b72638b4cbf 100644
--- a/checkpoint-1100/scheduler.pt
+++ b/checkpoint-1100/scheduler.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:4088610c769d87bd694b880357ee2736f8d9456a674ba2deac6ae25ba56fffaa
+oid sha256:bf976c23393d274589d6444fcab30c2d19ead89a0a911884f99807904f62c00b
size 627
diff --git a/checkpoint-1100/trainer_state.json b/checkpoint-1100/trainer_state.json
index aaf6a541ca340e29c7cd0e489d61a46e1a63d6b3..4b3079060bc1fe55aee51170296a362fc0f30c31 100644
--- a/checkpoint-1100/trainer_state.json
+++ b/checkpoint-1100/trainer_state.json
@@ -1,7 +1,7 @@
{
"best_metric": null,
"best_model_checkpoint": null,
- "epoch": 22.25735061650332,
+ "epoch": 12.427184466019417,
"eval_steps": 500,
"global_step": 1100,
"is_hyper_param_search": false,
@@ -9,6611 +9,6611 @@
"is_world_process_zero": true,
"log_history": [
{
- "epoch": 0.02,
- "learning_rate": 0.00019987244897959184,
- "loss": 3.2215,
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
"step": 1
},
{
- "epoch": 0.04,
- "learning_rate": 0.00019974489795918367,
- "loss": 2.8365,
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
"step": 2
},
{
- "epoch": 0.06,
- "learning_rate": 0.00019961734693877553,
- "loss": 2.602,
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
"step": 3
},
{
- "epoch": 0.08,
- "learning_rate": 0.00019948979591836736,
- "loss": 2.4196,
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
"step": 4
},
{
- "epoch": 0.1,
- "learning_rate": 0.0001993622448979592,
- "loss": 2.2574,
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
"step": 5
},
{
- "epoch": 0.12,
- "learning_rate": 0.00019923469387755102,
- "loss": 2.2239,
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
"step": 6
},
{
- "epoch": 0.14,
- "learning_rate": 0.00019910714285714288,
- "loss": 2.1661,
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
"step": 7
},
{
- "epoch": 0.16,
- "learning_rate": 0.0001989795918367347,
- "loss": 2.0987,
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
"step": 8
},
{
- "epoch": 0.18,
- "learning_rate": 0.00019885204081632654,
- "loss": 2.015,
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
"step": 9
},
{
- "epoch": 0.2,
- "learning_rate": 0.00019872448979591837,
- "loss": 1.9771,
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
"step": 10
},
{
- "epoch": 0.22,
- "learning_rate": 0.00019859693877551023,
- "loss": 2.0271,
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
"step": 11
},
{
- "epoch": 0.24,
- "learning_rate": 0.00019846938775510203,
- "loss": 1.9812,
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
"step": 12
},
{
- "epoch": 0.26,
- "learning_rate": 0.0001983418367346939,
- "loss": 2.0834,
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
"step": 13
},
{
- "epoch": 0.28,
- "learning_rate": 0.00019821428571428572,
- "loss": 1.9174,
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
"step": 14
},
{
- "epoch": 0.3,
- "learning_rate": 0.00019808673469387755,
- "loss": 1.8409,
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
"step": 15
},
{
- "epoch": 0.32,
- "learning_rate": 0.00019795918367346938,
- "loss": 1.929,
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
"step": 16
},
{
- "epoch": 0.34,
- "learning_rate": 0.00019783163265306124,
- "loss": 2.0041,
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
"step": 17
},
{
- "epoch": 0.36,
- "learning_rate": 0.00019770408163265305,
- "loss": 1.9385,
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
"step": 18
},
{
- "epoch": 0.38,
- "learning_rate": 0.0001975765306122449,
- "loss": 1.9592,
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
"step": 19
},
{
- "epoch": 0.4,
- "learning_rate": 0.00019744897959183674,
- "loss": 1.9701,
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
"step": 20
},
{
- "epoch": 0.42,
- "learning_rate": 0.0001973214285714286,
- "loss": 1.9277,
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
"step": 21
},
{
- "epoch": 0.45,
- "learning_rate": 0.00019719387755102042,
- "loss": 1.8394,
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
"step": 22
},
{
- "epoch": 0.47,
- "learning_rate": 0.00019706632653061226,
- "loss": 1.8666,
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
"step": 23
},
{
- "epoch": 0.49,
- "learning_rate": 0.00019693877551020409,
- "loss": 1.8997,
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
"step": 24
},
{
- "epoch": 0.51,
- "learning_rate": 0.00019681122448979592,
- "loss": 1.9432,
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
"step": 25
},
{
- "epoch": 0.53,
- "learning_rate": 0.00019668367346938777,
- "loss": 1.9137,
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
"step": 26
},
{
- "epoch": 0.55,
- "learning_rate": 0.0001965561224489796,
- "loss": 1.905,
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
"step": 27
},
{
- "epoch": 0.57,
- "learning_rate": 0.00019642857142857144,
- "loss": 1.8708,
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
"step": 28
},
{
- "epoch": 0.59,
- "learning_rate": 0.00019630102040816327,
- "loss": 1.9097,
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
"step": 29
},
{
- "epoch": 0.61,
- "learning_rate": 0.00019617346938775513,
- "loss": 1.896,
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
"step": 30
},
{
- "epoch": 0.63,
- "learning_rate": 0.00019604591836734696,
- "loss": 1.8834,
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
"step": 31
},
{
- "epoch": 0.65,
- "learning_rate": 0.0001959183673469388,
- "loss": 1.8323,
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
"step": 32
},
{
- "epoch": 0.67,
- "learning_rate": 0.00019579081632653062,
- "loss": 1.804,
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
"step": 33
},
{
- "epoch": 0.69,
- "learning_rate": 0.00019566326530612248,
- "loss": 1.8906,
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
"step": 34
},
{
- "epoch": 0.71,
- "learning_rate": 0.00019553571428571428,
- "loss": 1.8693,
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
"step": 35
},
{
- "epoch": 0.73,
- "learning_rate": 0.00019540816326530614,
- "loss": 1.9308,
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
"step": 36
},
{
- "epoch": 0.75,
- "learning_rate": 0.00019528061224489797,
- "loss": 1.8082,
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
"step": 37
},
{
- "epoch": 0.77,
- "learning_rate": 0.0001951530612244898,
- "loss": 1.848,
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
"step": 38
},
{
- "epoch": 0.79,
- "learning_rate": 0.00019502551020408163,
- "loss": 1.8866,
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
"step": 39
},
{
- "epoch": 0.81,
- "learning_rate": 0.0001948979591836735,
- "loss": 1.7844,
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
"step": 40
},
{
- "epoch": 0.83,
- "learning_rate": 0.0001947704081632653,
- "loss": 1.8485,
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
"step": 41
},
{
- "epoch": 0.85,
- "learning_rate": 0.00019464285714285715,
- "loss": 1.7917,
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
"step": 42
},
{
- "epoch": 0.87,
- "learning_rate": 0.00019451530612244898,
- "loss": 1.7342,
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
"step": 43
},
{
- "epoch": 0.89,
- "learning_rate": 0.00019438775510204084,
- "loss": 1.8479,
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
"step": 44
},
{
- "epoch": 0.91,
- "learning_rate": 0.00019426020408163267,
- "loss": 1.8639,
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
"step": 45
},
{
- "epoch": 0.93,
- "learning_rate": 0.0001941326530612245,
- "loss": 1.8166,
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
"step": 46
},
{
- "epoch": 0.95,
- "learning_rate": 0.00019400510204081633,
- "loss": 1.7566,
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
"step": 47
},
{
- "epoch": 0.97,
- "learning_rate": 0.00019387755102040816,
- "loss": 1.8071,
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
"step": 48
},
{
- "epoch": 0.99,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.8612,
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
"step": 49
},
{
- "epoch": 1.01,
- "learning_rate": 0.00019362244897959185,
- "loss": 1.7819,
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
"step": 50
},
{
- "epoch": 1.03,
- "learning_rate": 0.00019349489795918368,
- "loss": 1.8647,
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
"step": 51
},
{
- "epoch": 1.05,
- "learning_rate": 0.0001933673469387755,
- "loss": 1.8196,
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
"step": 52
},
{
- "epoch": 1.07,
- "learning_rate": 0.00019323979591836737,
- "loss": 1.8027,
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
"step": 53
},
{
- "epoch": 1.09,
- "learning_rate": 0.00019311224489795917,
- "loss": 1.8927,
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
"step": 54
},
{
- "epoch": 1.11,
- "learning_rate": 0.00019298469387755103,
- "loss": 1.8481,
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
"step": 55
},
{
- "epoch": 1.13,
- "learning_rate": 0.00019285714285714286,
- "loss": 1.7781,
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
"step": 56
},
{
- "epoch": 1.15,
- "learning_rate": 0.00019272959183673472,
- "loss": 1.8101,
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
"step": 57
},
{
- "epoch": 1.17,
- "learning_rate": 0.00019260204081632653,
- "loss": 1.7257,
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
"step": 58
},
{
- "epoch": 1.19,
- "learning_rate": 0.00019247448979591838,
- "loss": 1.8185,
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
"step": 59
},
{
- "epoch": 1.21,
- "learning_rate": 0.00019234693877551021,
- "loss": 1.8557,
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
"step": 60
},
{
- "epoch": 1.23,
- "learning_rate": 0.00019221938775510204,
- "loss": 1.7418,
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
"step": 61
},
{
- "epoch": 1.25,
- "learning_rate": 0.00019209183673469388,
- "loss": 1.6879,
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
"step": 62
},
{
- "epoch": 1.27,
- "learning_rate": 0.00019196428571428573,
- "loss": 1.7651,
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
"step": 63
},
{
- "epoch": 1.29,
- "learning_rate": 0.00019183673469387756,
- "loss": 1.7759,
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
"step": 64
},
{
- "epoch": 1.32,
- "learning_rate": 0.0001917091836734694,
- "loss": 1.7691,
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
"step": 65
},
{
- "epoch": 1.34,
- "learning_rate": 0.00019158163265306123,
- "loss": 1.7794,
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
"step": 66
},
{
- "epoch": 1.36,
- "learning_rate": 0.00019145408163265306,
- "loss": 1.8152,
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
"step": 67
},
{
- "epoch": 1.38,
- "learning_rate": 0.00019132653061224492,
- "loss": 1.8052,
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
"step": 68
},
{
- "epoch": 1.4,
- "learning_rate": 0.00019119897959183675,
- "loss": 1.8054,
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
"step": 69
},
{
- "epoch": 1.42,
- "learning_rate": 0.00019107142857142858,
- "loss": 1.8114,
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
"step": 70
},
{
- "epoch": 1.44,
- "learning_rate": 0.0001909438775510204,
- "loss": 1.7749,
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
"step": 71
},
{
- "epoch": 1.46,
- "learning_rate": 0.00019081632653061227,
- "loss": 1.777,
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
"step": 72
},
{
- "epoch": 1.48,
- "learning_rate": 0.0001906887755102041,
- "loss": 1.7896,
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
"step": 73
},
{
- "epoch": 1.5,
- "learning_rate": 0.00019056122448979593,
- "loss": 1.8335,
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
"step": 74
},
{
- "epoch": 1.52,
- "learning_rate": 0.00019043367346938776,
- "loss": 1.8155,
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
"step": 75
},
{
- "epoch": 1.54,
- "learning_rate": 0.00019030612244897962,
- "loss": 1.8224,
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
"step": 76
},
{
- "epoch": 1.56,
- "learning_rate": 0.00019017857142857142,
- "loss": 1.7889,
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
"step": 77
},
{
- "epoch": 1.58,
- "learning_rate": 0.00019005102040816328,
- "loss": 1.8866,
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
"step": 78
},
{
- "epoch": 1.6,
- "learning_rate": 0.0001899234693877551,
- "loss": 1.8439,
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
"step": 79
},
{
- "epoch": 1.62,
- "learning_rate": 0.00018979591836734697,
- "loss": 1.7906,
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
"step": 80
},
{
- "epoch": 1.64,
- "learning_rate": 0.00018966836734693877,
- "loss": 1.8627,
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
"step": 81
},
{
- "epoch": 1.66,
- "learning_rate": 0.00018954081632653063,
- "loss": 1.7497,
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
"step": 82
},
{
- "epoch": 1.68,
- "learning_rate": 0.00018941326530612246,
- "loss": 1.7936,
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
"step": 83
},
{
- "epoch": 1.7,
- "learning_rate": 0.0001892857142857143,
- "loss": 1.8341,
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
"step": 84
},
{
- "epoch": 1.72,
- "learning_rate": 0.00018915816326530612,
- "loss": 1.7868,
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
"step": 85
},
{
- "epoch": 1.74,
- "learning_rate": 0.00018903061224489798,
- "loss": 1.7493,
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
"step": 86
},
{
- "epoch": 1.76,
- "learning_rate": 0.0001889030612244898,
- "loss": 1.7926,
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
"step": 87
},
{
- "epoch": 1.78,
- "learning_rate": 0.00018877551020408164,
- "loss": 1.8278,
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
"step": 88
},
{
- "epoch": 1.8,
- "learning_rate": 0.00018864795918367347,
- "loss": 1.7387,
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
"step": 89
},
{
- "epoch": 1.82,
- "learning_rate": 0.0001885204081632653,
- "loss": 1.7669,
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
"step": 90
},
{
- "epoch": 1.84,
- "learning_rate": 0.00018839285714285716,
- "loss": 1.7686,
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
"step": 91
},
{
- "epoch": 1.86,
- "learning_rate": 0.000188265306122449,
- "loss": 1.7759,
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
"step": 92
},
{
- "epoch": 1.88,
- "learning_rate": 0.00018813775510204082,
- "loss": 1.7016,
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
"step": 93
},
{
- "epoch": 1.9,
- "learning_rate": 0.00018801020408163265,
- "loss": 1.8123,
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
"step": 94
},
{
- "epoch": 1.92,
- "learning_rate": 0.0001878826530612245,
- "loss": 1.8315,
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
"step": 95
},
{
- "epoch": 1.94,
- "learning_rate": 0.00018775510204081634,
- "loss": 1.7679,
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
"step": 96
},
{
- "epoch": 1.96,
- "learning_rate": 0.00018762755102040817,
- "loss": 1.7874,
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
"step": 97
},
{
- "epoch": 1.98,
- "learning_rate": 0.0001875,
- "loss": 1.8008,
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
"step": 98
},
{
- "epoch": 2.0,
- "learning_rate": 0.00018737244897959186,
- "loss": 1.7177,
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
"step": 99
},
{
- "epoch": 2.02,
- "learning_rate": 0.00018724489795918367,
- "loss": 1.7272,
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
"step": 100
},
{
- "epoch": 2.04,
- "learning_rate": 0.00018711734693877552,
- "loss": 1.7848,
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
"step": 101
},
{
- "epoch": 2.06,
- "learning_rate": 0.00018698979591836735,
- "loss": 1.744,
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
"step": 102
},
{
- "epoch": 2.08,
- "learning_rate": 0.00018686224489795919,
- "loss": 1.7005,
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
"step": 103
},
{
- "epoch": 2.1,
- "learning_rate": 0.00018673469387755102,
- "loss": 1.8247,
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
"step": 104
},
{
- "epoch": 2.12,
- "learning_rate": 0.00018660714285714287,
- "loss": 1.6855,
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
"step": 105
},
{
- "epoch": 2.14,
- "learning_rate": 0.0001864795918367347,
- "loss": 1.7627,
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
"step": 106
},
{
- "epoch": 2.17,
- "learning_rate": 0.00018635204081632654,
- "loss": 1.7564,
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
"step": 107
},
{
- "epoch": 2.19,
- "learning_rate": 0.00018622448979591837,
- "loss": 1.8237,
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
"step": 108
},
{
- "epoch": 2.21,
- "learning_rate": 0.00018609693877551022,
- "loss": 1.7421,
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
"step": 109
},
{
- "epoch": 2.23,
- "learning_rate": 0.00018596938775510206,
- "loss": 1.7517,
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
"step": 110
},
{
- "epoch": 2.25,
- "learning_rate": 0.0001858418367346939,
- "loss": 1.7515,
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
"step": 111
},
{
- "epoch": 2.27,
- "learning_rate": 0.00018571428571428572,
- "loss": 1.7842,
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
"step": 112
},
{
- "epoch": 2.29,
- "learning_rate": 0.00018558673469387755,
- "loss": 1.8001,
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
"step": 113
},
{
- "epoch": 2.31,
- "learning_rate": 0.0001854591836734694,
- "loss": 1.7653,
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
"step": 114
},
{
- "epoch": 2.33,
- "learning_rate": 0.00018533163265306124,
- "loss": 1.694,
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
"step": 115
},
{
- "epoch": 2.35,
- "learning_rate": 0.00018520408163265307,
- "loss": 1.7457,
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
"step": 116
},
{
- "epoch": 2.37,
- "learning_rate": 0.0001850765306122449,
- "loss": 1.7899,
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
"step": 117
},
{
- "epoch": 2.39,
- "learning_rate": 0.00018494897959183676,
- "loss": 1.7473,
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
"step": 118
},
{
- "epoch": 2.41,
- "learning_rate": 0.0001848214285714286,
- "loss": 1.6639,
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
"step": 119
},
{
- "epoch": 2.43,
- "learning_rate": 0.00018469387755102042,
- "loss": 1.762,
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
"step": 120
},
{
- "epoch": 2.45,
- "learning_rate": 0.00018456632653061225,
- "loss": 1.7378,
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
"step": 121
},
{
- "epoch": 2.47,
- "learning_rate": 0.0001844387755102041,
- "loss": 1.672,
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
"step": 122
},
{
- "epoch": 2.49,
- "learning_rate": 0.0001843112244897959,
- "loss": 1.7267,
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
"step": 123
},
{
- "epoch": 2.51,
- "learning_rate": 0.00018418367346938777,
- "loss": 1.7825,
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
"step": 124
},
{
- "epoch": 2.53,
- "learning_rate": 0.0001840561224489796,
- "loss": 1.7566,
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
"step": 125
},
{
- "epoch": 2.55,
- "learning_rate": 0.00018392857142857143,
- "loss": 1.8169,
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
"step": 126
},
{
- "epoch": 2.57,
- "learning_rate": 0.00018380102040816326,
- "loss": 1.6801,
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
"step": 127
},
{
- "epoch": 2.59,
- "learning_rate": 0.00018367346938775512,
- "loss": 1.7292,
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
"step": 128
},
{
- "epoch": 2.61,
- "learning_rate": 0.00018354591836734695,
- "loss": 1.737,
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
"step": 129
},
{
- "epoch": 2.63,
- "learning_rate": 0.00018341836734693878,
- "loss": 1.7696,
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
"step": 130
},
{
- "epoch": 2.65,
- "learning_rate": 0.0001832908163265306,
- "loss": 1.7239,
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
"step": 131
},
{
- "epoch": 2.67,
- "learning_rate": 0.00018316326530612247,
- "loss": 1.7441,
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
"step": 132
},
{
- "epoch": 2.69,
- "learning_rate": 0.0001830357142857143,
- "loss": 1.7825,
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
"step": 133
},
{
- "epoch": 2.71,
- "learning_rate": 0.00018290816326530613,
- "loss": 1.7411,
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
"step": 134
},
{
- "epoch": 2.73,
- "learning_rate": 0.00018278061224489796,
- "loss": 1.7119,
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
"step": 135
},
{
- "epoch": 2.75,
- "learning_rate": 0.0001826530612244898,
- "loss": 1.7443,
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
"step": 136
},
{
- "epoch": 2.77,
- "learning_rate": 0.00018252551020408165,
- "loss": 1.7197,
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
"step": 137
},
{
- "epoch": 2.79,
- "learning_rate": 0.00018239795918367348,
- "loss": 1.7273,
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
"step": 138
},
{
- "epoch": 2.81,
- "learning_rate": 0.0001822704081632653,
- "loss": 1.7681,
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
"step": 139
},
{
- "epoch": 2.83,
- "learning_rate": 0.00018214285714285714,
- "loss": 1.8088,
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
"step": 140
},
{
- "epoch": 2.85,
- "learning_rate": 0.000182015306122449,
- "loss": 1.7301,
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
"step": 141
},
{
- "epoch": 2.87,
- "learning_rate": 0.00018188775510204083,
- "loss": 1.6853,
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
"step": 142
},
{
- "epoch": 2.89,
- "learning_rate": 0.00018176020408163266,
- "loss": 1.6966,
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
"step": 143
},
{
- "epoch": 2.91,
- "learning_rate": 0.0001816326530612245,
- "loss": 1.7938,
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
"step": 144
},
{
- "epoch": 2.93,
- "learning_rate": 0.00018150510204081635,
- "loss": 1.7639,
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
"step": 145
},
{
- "epoch": 2.95,
- "learning_rate": 0.00018137755102040816,
- "loss": 1.7527,
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
"step": 146
},
{
- "epoch": 2.97,
- "learning_rate": 0.00018125000000000001,
- "loss": 1.7386,
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
"step": 147
},
{
- "epoch": 2.99,
- "learning_rate": 0.00018112244897959185,
- "loss": 1.7223,
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
"step": 148
},
{
- "epoch": 3.01,
- "learning_rate": 0.00018099489795918368,
- "loss": 1.7571,
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
"step": 149
},
{
- "epoch": 3.04,
- "learning_rate": 0.0001808673469387755,
- "loss": 1.7054,
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
"step": 150
},
{
- "epoch": 3.06,
- "learning_rate": 0.00018073979591836737,
- "loss": 1.6581,
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
"step": 151
},
{
- "epoch": 3.08,
- "learning_rate": 0.00018061224489795917,
- "loss": 1.681,
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
"step": 152
},
{
- "epoch": 3.1,
- "learning_rate": 0.00018048469387755103,
- "loss": 1.7425,
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
"step": 153
},
{
- "epoch": 3.12,
- "learning_rate": 0.00018035714285714286,
- "loss": 1.7108,
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
"step": 154
},
{
- "epoch": 3.14,
- "learning_rate": 0.00018022959183673472,
- "loss": 1.7194,
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
"step": 155
},
{
- "epoch": 3.16,
- "learning_rate": 0.00018010204081632655,
- "loss": 1.6953,
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
"step": 156
},
{
- "epoch": 3.18,
- "learning_rate": 0.00017997448979591838,
- "loss": 1.669,
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
"step": 157
},
{
- "epoch": 3.2,
- "learning_rate": 0.0001798469387755102,
- "loss": 1.744,
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
"step": 158
},
{
- "epoch": 3.22,
- "learning_rate": 0.00017971938775510204,
- "loss": 1.6467,
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
"step": 159
},
{
- "epoch": 3.24,
- "learning_rate": 0.0001795918367346939,
- "loss": 1.7103,
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
"step": 160
},
{
- "epoch": 3.26,
- "learning_rate": 0.00017946428571428573,
- "loss": 1.6662,
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
"step": 161
},
{
- "epoch": 3.28,
- "learning_rate": 0.00017933673469387756,
- "loss": 1.6657,
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
"step": 162
},
{
- "epoch": 3.3,
- "learning_rate": 0.0001792091836734694,
- "loss": 1.791,
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
"step": 163
},
{
- "epoch": 3.32,
- "learning_rate": 0.00017908163265306125,
- "loss": 1.7704,
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
"step": 164
},
{
- "epoch": 3.34,
- "learning_rate": 0.00017895408163265305,
- "loss": 1.7229,
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
"step": 165
},
{
- "epoch": 3.36,
- "learning_rate": 0.0001788265306122449,
- "loss": 1.76,
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
"step": 166
},
{
- "epoch": 3.38,
- "learning_rate": 0.00017869897959183674,
- "loss": 1.6482,
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
"step": 167
},
{
- "epoch": 3.4,
- "learning_rate": 0.0001785714285714286,
- "loss": 1.8076,
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
"step": 168
},
{
- "epoch": 3.42,
- "learning_rate": 0.0001784438775510204,
- "loss": 1.7368,
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
"step": 169
},
{
- "epoch": 3.44,
- "learning_rate": 0.00017831632653061226,
- "loss": 1.6264,
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
"step": 170
},
{
- "epoch": 3.46,
- "learning_rate": 0.0001781887755102041,
- "loss": 1.6289,
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
"step": 171
},
{
- "epoch": 3.48,
- "learning_rate": 0.00017806122448979592,
- "loss": 1.7913,
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
"step": 172
},
{
- "epoch": 3.5,
- "learning_rate": 0.00017793367346938775,
- "loss": 1.6985,
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
"step": 173
},
{
- "epoch": 3.52,
- "learning_rate": 0.0001778061224489796,
- "loss": 1.6936,
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
"step": 174
},
{
- "epoch": 3.54,
- "learning_rate": 0.00017767857142857141,
- "loss": 1.8068,
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
"step": 175
},
{
- "epoch": 3.56,
- "learning_rate": 0.00017755102040816327,
- "loss": 1.7243,
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
"step": 176
},
{
- "epoch": 3.58,
- "learning_rate": 0.0001774234693877551,
- "loss": 1.6893,
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
"step": 177
},
{
- "epoch": 3.6,
- "learning_rate": 0.00017729591836734696,
- "loss": 1.8122,
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
"step": 178
},
{
- "epoch": 3.62,
- "learning_rate": 0.0001771683673469388,
- "loss": 1.6562,
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
"step": 179
},
{
- "epoch": 3.64,
- "learning_rate": 0.00017704081632653062,
- "loss": 1.6999,
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
"step": 180
},
{
- "epoch": 3.66,
- "learning_rate": 0.00017691326530612245,
- "loss": 1.7229,
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
"step": 181
},
{
- "epoch": 3.68,
- "learning_rate": 0.00017678571428571428,
- "loss": 1.6764,
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
"step": 182
},
{
- "epoch": 3.7,
- "learning_rate": 0.00017665816326530614,
- "loss": 1.6982,
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
"step": 183
},
{
- "epoch": 3.72,
- "learning_rate": 0.00017653061224489797,
- "loss": 1.696,
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
"step": 184
},
{
- "epoch": 3.74,
- "learning_rate": 0.0001764030612244898,
- "loss": 1.6797,
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
"step": 185
},
{
- "epoch": 3.76,
- "learning_rate": 0.00017627551020408164,
- "loss": 1.637,
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
"step": 186
},
{
- "epoch": 3.78,
- "learning_rate": 0.0001761479591836735,
- "loss": 1.7074,
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
"step": 187
},
{
- "epoch": 3.8,
- "learning_rate": 0.0001760204081632653,
- "loss": 1.705,
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
"step": 188
},
{
- "epoch": 3.82,
- "learning_rate": 0.00017589285714285716,
- "loss": 1.6153,
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
"step": 189
},
{
- "epoch": 3.84,
- "learning_rate": 0.00017576530612244899,
- "loss": 1.7354,
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
"step": 190
},
{
- "epoch": 3.86,
- "learning_rate": 0.00017563775510204084,
- "loss": 1.6941,
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
"step": 191
},
{
- "epoch": 3.88,
- "learning_rate": 0.00017551020408163265,
- "loss": 1.7231,
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
"step": 192
},
{
- "epoch": 3.91,
- "learning_rate": 0.0001753826530612245,
- "loss": 1.7663,
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
"step": 193
},
{
- "epoch": 3.93,
- "learning_rate": 0.00017525510204081634,
- "loss": 1.6532,
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
"step": 194
},
{
- "epoch": 3.95,
- "learning_rate": 0.00017512755102040817,
- "loss": 1.7115,
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
"step": 195
},
{
- "epoch": 3.97,
- "learning_rate": 0.000175,
- "loss": 1.6955,
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
"step": 196
},
{
- "epoch": 3.99,
- "learning_rate": 0.00017487244897959186,
- "loss": 1.6863,
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
"step": 197
},
{
- "epoch": 4.01,
- "learning_rate": 0.00017474489795918366,
- "loss": 1.7012,
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
"step": 198
},
{
- "epoch": 4.03,
- "learning_rate": 0.00017461734693877552,
- "loss": 1.5927,
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
"step": 199
},
{
- "epoch": 4.05,
- "learning_rate": 0.00017448979591836735,
- "loss": 1.6272,
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
"step": 200
},
{
- "epoch": 4.07,
- "learning_rate": 0.00017436224489795918,
- "loss": 1.5994,
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
"step": 201
},
{
- "epoch": 4.09,
- "learning_rate": 0.00017423469387755104,
- "loss": 1.7141,
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
"step": 202
},
{
- "epoch": 4.11,
- "learning_rate": 0.00017410714285714287,
- "loss": 1.7547,
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
"step": 203
},
{
- "epoch": 4.13,
- "learning_rate": 0.0001739795918367347,
- "loss": 1.6254,
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
"step": 204
},
{
- "epoch": 4.15,
- "learning_rate": 0.00017385204081632653,
- "loss": 1.6686,
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
"step": 205
},
{
- "epoch": 4.17,
- "learning_rate": 0.0001737244897959184,
- "loss": 1.6684,
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
"step": 206
},
{
- "epoch": 4.19,
- "learning_rate": 0.00017359693877551022,
- "loss": 1.6724,
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
"step": 207
},
{
- "epoch": 4.21,
- "learning_rate": 0.00017346938775510205,
- "loss": 1.7361,
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
"step": 208
},
{
- "epoch": 4.23,
- "learning_rate": 0.00017334183673469388,
- "loss": 1.7167,
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
"step": 209
},
{
- "epoch": 4.25,
- "learning_rate": 0.00017321428571428574,
- "loss": 1.7226,
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
"step": 210
},
{
- "epoch": 4.27,
- "learning_rate": 0.00017308673469387754,
- "loss": 1.7133,
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
"step": 211
},
{
- "epoch": 4.29,
- "learning_rate": 0.0001729591836734694,
- "loss": 1.649,
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
"step": 212
},
{
- "epoch": 4.31,
- "learning_rate": 0.00017283163265306123,
- "loss": 1.7104,
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
"step": 213
},
{
- "epoch": 4.33,
- "learning_rate": 0.00017270408163265306,
- "loss": 1.6861,
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
"step": 214
},
{
- "epoch": 4.35,
- "learning_rate": 0.0001725765306122449,
- "loss": 1.648,
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
"step": 215
},
{
- "epoch": 4.37,
- "learning_rate": 0.00017244897959183675,
- "loss": 1.6215,
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
"step": 216
},
{
- "epoch": 4.39,
- "learning_rate": 0.00017232142857142858,
- "loss": 1.6334,
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
"step": 217
},
{
- "epoch": 4.41,
- "learning_rate": 0.0001721938775510204,
- "loss": 1.6283,
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
"step": 218
},
{
- "epoch": 4.43,
- "learning_rate": 0.00017206632653061224,
- "loss": 1.6462,
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
"step": 219
},
{
- "epoch": 4.45,
- "learning_rate": 0.0001719387755102041,
- "loss": 1.7233,
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
"step": 220
},
{
- "epoch": 4.47,
- "learning_rate": 0.0001718112244897959,
- "loss": 1.7839,
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
"step": 221
},
{
- "epoch": 4.49,
- "learning_rate": 0.00017168367346938776,
- "loss": 1.7204,
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
"step": 222
},
{
- "epoch": 4.51,
- "learning_rate": 0.0001715561224489796,
- "loss": 1.7671,
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
"step": 223
},
{
- "epoch": 4.53,
- "learning_rate": 0.00017142857142857143,
- "loss": 1.6824,
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
"step": 224
},
{
- "epoch": 4.55,
- "learning_rate": 0.00017130102040816328,
- "loss": 1.7068,
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
"step": 225
},
{
- "epoch": 4.57,
- "learning_rate": 0.00017117346938775511,
- "loss": 1.6515,
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
"step": 226
},
{
- "epoch": 4.59,
- "learning_rate": 0.00017104591836734694,
- "loss": 1.6586,
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
"step": 227
},
{
- "epoch": 4.61,
- "learning_rate": 0.00017091836734693878,
- "loss": 1.6355,
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
"step": 228
},
{
- "epoch": 4.63,
- "learning_rate": 0.00017079081632653063,
- "loss": 1.7173,
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
"step": 229
},
{
- "epoch": 4.65,
- "learning_rate": 0.00017066326530612246,
- "loss": 1.6585,
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
"step": 230
},
{
- "epoch": 4.67,
- "learning_rate": 0.0001705357142857143,
- "loss": 1.5856,
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
"step": 231
},
{
- "epoch": 4.69,
- "learning_rate": 0.00017040816326530613,
- "loss": 1.5923,
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
"step": 232
},
{
- "epoch": 4.71,
- "learning_rate": 0.00017028061224489798,
- "loss": 1.7128,
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
"step": 233
},
{
- "epoch": 4.73,
- "learning_rate": 0.0001701530612244898,
- "loss": 1.6971,
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
"step": 234
},
{
- "epoch": 4.75,
- "learning_rate": 0.00017002551020408165,
- "loss": 1.6416,
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
"step": 235
},
{
- "epoch": 4.78,
- "learning_rate": 0.00016989795918367348,
- "loss": 1.645,
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
"step": 236
},
{
- "epoch": 4.8,
- "learning_rate": 0.0001697704081632653,
- "loss": 1.6792,
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
"step": 237
},
{
- "epoch": 4.82,
- "learning_rate": 0.00016964285714285714,
- "loss": 1.6522,
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
"step": 238
},
{
- "epoch": 4.84,
- "learning_rate": 0.000169515306122449,
- "loss": 1.6315,
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
"step": 239
},
{
- "epoch": 4.86,
- "learning_rate": 0.00016938775510204083,
- "loss": 1.6622,
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
"step": 240
},
{
- "epoch": 4.88,
- "learning_rate": 0.00016926020408163266,
- "loss": 1.6566,
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
"step": 241
},
{
- "epoch": 4.9,
- "learning_rate": 0.0001691326530612245,
- "loss": 1.7141,
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
"step": 242
},
{
- "epoch": 4.92,
- "learning_rate": 0.00016900510204081635,
- "loss": 1.5873,
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
"step": 243
},
{
- "epoch": 4.94,
- "learning_rate": 0.00016887755102040818,
- "loss": 1.6571,
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
"step": 244
},
{
- "epoch": 4.96,
- "learning_rate": 0.00016875,
- "loss": 1.6829,
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
"step": 245
},
{
- "epoch": 4.98,
- "learning_rate": 0.00016862244897959184,
- "loss": 1.6935,
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
"step": 246
},
{
- "epoch": 5.0,
- "learning_rate": 0.00016849489795918367,
- "loss": 1.6782,
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
"step": 247
},
{
- "epoch": 5.02,
- "learning_rate": 0.00016836734693877553,
- "loss": 1.622,
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
"step": 248
},
{
- "epoch": 5.04,
- "learning_rate": 0.00016823979591836736,
- "loss": 1.6596,
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
"step": 249
},
{
- "epoch": 5.06,
- "learning_rate": 0.0001681122448979592,
- "loss": 1.5821,
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
"step": 250
},
{
- "epoch": 5.08,
- "learning_rate": 0.00016798469387755102,
- "loss": 1.7292,
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
"step": 251
},
{
- "epoch": 5.1,
- "learning_rate": 0.00016785714285714288,
- "loss": 1.646,
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
"step": 252
},
{
- "epoch": 5.12,
- "learning_rate": 0.0001677295918367347,
- "loss": 1.6969,
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
"step": 253
},
{
- "epoch": 5.14,
- "learning_rate": 0.00016760204081632654,
- "loss": 1.6082,
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
"step": 254
},
{
- "epoch": 5.16,
- "learning_rate": 0.00016747448979591837,
- "loss": 1.5843,
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
"step": 255
},
{
- "epoch": 5.18,
- "learning_rate": 0.00016734693877551023,
- "loss": 1.6827,
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
"step": 256
},
{
- "epoch": 5.2,
- "learning_rate": 0.00016721938775510203,
- "loss": 1.5824,
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
"step": 257
},
{
- "epoch": 5.22,
- "learning_rate": 0.0001670918367346939,
- "loss": 1.6795,
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
"step": 258
},
{
- "epoch": 5.24,
- "learning_rate": 0.00016696428571428572,
- "loss": 1.5639,
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
"step": 259
},
{
- "epoch": 5.26,
- "learning_rate": 0.00016683673469387755,
- "loss": 1.592,
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
"step": 260
},
{
- "epoch": 5.28,
- "learning_rate": 0.00016670918367346938,
- "loss": 1.65,
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
"step": 261
},
{
- "epoch": 5.3,
- "learning_rate": 0.00016658163265306124,
- "loss": 1.5592,
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
"step": 262
},
{
- "epoch": 5.32,
- "learning_rate": 0.00016645408163265305,
- "loss": 1.5091,
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
"step": 263
},
{
- "epoch": 5.34,
- "learning_rate": 0.0001663265306122449,
- "loss": 1.6138,
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
"step": 264
},
{
- "epoch": 5.36,
- "learning_rate": 0.00016619897959183673,
- "loss": 1.625,
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
"step": 265
},
{
- "epoch": 5.38,
- "learning_rate": 0.0001660714285714286,
- "loss": 1.5757,
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
"step": 266
},
{
- "epoch": 5.4,
- "learning_rate": 0.00016594387755102042,
- "loss": 1.6372,
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
"step": 267
},
{
- "epoch": 5.42,
- "learning_rate": 0.00016581632653061225,
- "loss": 1.5891,
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
"step": 268
},
{
- "epoch": 5.44,
- "learning_rate": 0.00016568877551020409,
- "loss": 1.6893,
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
"step": 269
},
{
- "epoch": 5.46,
- "learning_rate": 0.00016556122448979592,
- "loss": 1.6662,
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
"step": 270
},
{
- "epoch": 5.48,
- "learning_rate": 0.00016543367346938777,
- "loss": 1.7132,
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
"step": 271
},
{
- "epoch": 5.5,
- "learning_rate": 0.0001653061224489796,
- "loss": 1.5835,
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
"step": 272
},
{
- "epoch": 5.52,
- "learning_rate": 0.00016517857142857144,
- "loss": 1.6342,
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
"step": 273
},
{
- "epoch": 5.54,
- "learning_rate": 0.00016505102040816327,
- "loss": 1.6717,
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
"step": 274
},
{
- "epoch": 5.56,
- "learning_rate": 0.00016492346938775512,
- "loss": 1.6248,
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
"step": 275
},
{
- "epoch": 5.58,
- "learning_rate": 0.00016479591836734696,
- "loss": 1.6117,
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
"step": 276
},
{
- "epoch": 5.6,
- "learning_rate": 0.0001646683673469388,
- "loss": 1.6798,
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
"step": 277
},
{
- "epoch": 5.63,
- "learning_rate": 0.00016454081632653062,
- "loss": 1.6406,
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
"step": 278
},
{
- "epoch": 5.65,
- "learning_rate": 0.00016441326530612248,
- "loss": 1.6512,
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
"step": 279
},
{
- "epoch": 5.67,
- "learning_rate": 0.00016428571428571428,
- "loss": 1.6102,
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
"step": 280
},
{
- "epoch": 5.69,
- "learning_rate": 0.00016415816326530614,
- "loss": 1.6113,
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
"step": 281
},
{
- "epoch": 5.71,
- "learning_rate": 0.00016403061224489797,
- "loss": 1.7116,
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
"step": 282
},
{
- "epoch": 5.73,
- "learning_rate": 0.0001639030612244898,
- "loss": 1.6846,
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
"step": 283
},
{
- "epoch": 5.75,
- "learning_rate": 0.00016377551020408163,
- "loss": 1.6911,
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
"step": 284
},
{
- "epoch": 5.77,
- "learning_rate": 0.0001636479591836735,
- "loss": 1.6202,
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
"step": 285
},
{
- "epoch": 5.79,
- "learning_rate": 0.0001635204081632653,
- "loss": 1.5715,
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
"step": 286
},
{
- "epoch": 5.81,
- "learning_rate": 0.00016339285714285715,
- "loss": 1.6461,
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
"step": 287
},
{
- "epoch": 5.83,
- "learning_rate": 0.00016326530612244898,
- "loss": 1.6624,
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
"step": 288
},
{
- "epoch": 5.85,
- "learning_rate": 0.00016313775510204084,
- "loss": 1.6535,
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
"step": 289
},
{
- "epoch": 5.87,
- "learning_rate": 0.00016301020408163267,
- "loss": 1.6275,
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
"step": 290
},
{
- "epoch": 5.89,
- "learning_rate": 0.0001628826530612245,
- "loss": 1.6636,
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
"step": 291
},
{
- "epoch": 5.91,
- "learning_rate": 0.00016275510204081633,
- "loss": 1.6546,
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
"step": 292
},
{
- "epoch": 5.93,
- "learning_rate": 0.00016262755102040816,
- "loss": 1.7274,
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
"step": 293
},
{
- "epoch": 5.95,
- "learning_rate": 0.00016250000000000002,
- "loss": 1.5901,
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
"step": 294
},
{
- "epoch": 5.97,
- "learning_rate": 0.00016237244897959185,
- "loss": 1.6046,
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
"step": 295
},
{
- "epoch": 5.99,
- "learning_rate": 0.00016224489795918368,
- "loss": 1.5828,
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
"step": 296
},
{
- "epoch": 6.01,
- "learning_rate": 0.0001621173469387755,
- "loss": 1.6435,
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
"step": 297
},
{
- "epoch": 6.03,
- "learning_rate": 0.00016198979591836737,
- "loss": 1.6263,
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
"step": 298
},
{
- "epoch": 6.05,
- "learning_rate": 0.00016186224489795917,
- "loss": 1.4944,
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
"step": 299
},
{
- "epoch": 6.07,
- "learning_rate": 0.00016173469387755103,
- "loss": 1.6286,
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
"step": 300
},
{
- "epoch": 6.09,
- "learning_rate": 0.00016160714285714286,
- "loss": 1.694,
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
"step": 301
},
{
- "epoch": 6.11,
- "learning_rate": 0.00016147959183673472,
- "loss": 1.6197,
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
"step": 302
},
{
- "epoch": 6.13,
- "learning_rate": 0.00016135204081632652,
- "loss": 1.5597,
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
"step": 303
},
{
- "epoch": 6.15,
- "learning_rate": 0.00016122448979591838,
- "loss": 1.5487,
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
"step": 304
},
{
- "epoch": 6.17,
- "learning_rate": 0.0001610969387755102,
- "loss": 1.5769,
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
"step": 305
},
{
- "epoch": 6.19,
- "learning_rate": 0.00016096938775510204,
- "loss": 1.6367,
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
"step": 306
},
{
- "epoch": 6.21,
- "learning_rate": 0.00016084183673469388,
- "loss": 1.583,
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
"step": 307
},
{
- "epoch": 6.23,
- "learning_rate": 0.00016071428571428573,
- "loss": 1.6201,
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
"step": 308
},
{
- "epoch": 6.25,
- "learning_rate": 0.00016058673469387754,
- "loss": 1.6586,
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
"step": 309
},
{
- "epoch": 6.27,
- "learning_rate": 0.0001604591836734694,
- "loss": 1.6711,
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
"step": 310
},
{
- "epoch": 6.29,
- "learning_rate": 0.00016033163265306123,
- "loss": 1.6402,
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
"step": 311
},
{
- "epoch": 6.31,
- "learning_rate": 0.00016020408163265306,
- "loss": 1.5247,
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
"step": 312
},
{
- "epoch": 6.33,
- "learning_rate": 0.00016007653061224491,
- "loss": 1.5356,
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
"step": 313
},
{
- "epoch": 6.35,
- "learning_rate": 0.00015994897959183675,
- "loss": 1.564,
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
"step": 314
},
{
- "epoch": 6.37,
- "learning_rate": 0.00015982142857142858,
- "loss": 1.563,
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
"step": 315
},
{
- "epoch": 6.39,
- "learning_rate": 0.0001596938775510204,
- "loss": 1.5198,
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
"step": 316
},
{
- "epoch": 6.41,
- "learning_rate": 0.00015956632653061227,
- "loss": 1.6558,
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
"step": 317
},
{
- "epoch": 6.43,
- "learning_rate": 0.0001594387755102041,
- "loss": 1.5534,
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
"step": 318
},
{
- "epoch": 6.45,
- "learning_rate": 0.00015931122448979593,
- "loss": 1.6239,
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
"step": 319
},
{
- "epoch": 6.47,
- "learning_rate": 0.00015918367346938776,
- "loss": 1.5645,
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
"step": 320
},
{
- "epoch": 6.5,
- "learning_rate": 0.00015905612244897962,
- "loss": 1.5713,
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
"step": 321
},
{
- "epoch": 6.52,
- "learning_rate": 0.00015892857142857142,
- "loss": 1.6176,
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
"step": 322
},
{
- "epoch": 6.54,
- "learning_rate": 0.00015880102040816328,
- "loss": 1.502,
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
"step": 323
},
{
- "epoch": 6.56,
- "learning_rate": 0.0001586734693877551,
- "loss": 1.645,
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
"step": 324
},
{
- "epoch": 6.58,
- "learning_rate": 0.00015854591836734697,
- "loss": 1.5904,
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
"step": 325
},
{
- "epoch": 6.6,
- "learning_rate": 0.00015841836734693877,
- "loss": 1.6149,
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
"step": 326
},
{
- "epoch": 6.62,
- "learning_rate": 0.00015829081632653063,
- "loss": 1.6757,
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
"step": 327
},
{
- "epoch": 6.64,
- "learning_rate": 0.00015816326530612246,
- "loss": 1.541,
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
"step": 328
},
{
- "epoch": 6.66,
- "learning_rate": 0.0001580357142857143,
- "loss": 1.5898,
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
"step": 329
},
{
- "epoch": 6.68,
- "learning_rate": 0.00015790816326530612,
- "loss": 1.5441,
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
"step": 330
},
{
- "epoch": 6.7,
- "learning_rate": 0.00015778061224489798,
- "loss": 1.61,
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
"step": 331
},
{
- "epoch": 6.72,
- "learning_rate": 0.00015765306122448978,
- "loss": 1.615,
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
"step": 332
},
{
- "epoch": 6.74,
- "learning_rate": 0.00015752551020408164,
- "loss": 1.6575,
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
"step": 333
},
{
- "epoch": 6.76,
- "learning_rate": 0.00015739795918367347,
- "loss": 1.6702,
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
"step": 334
},
{
- "epoch": 6.78,
- "learning_rate": 0.0001572704081632653,
- "loss": 1.6009,
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
"step": 335
},
{
- "epoch": 6.8,
- "learning_rate": 0.00015714285714285716,
- "loss": 1.5568,
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
"step": 336
},
{
- "epoch": 6.82,
- "learning_rate": 0.000157015306122449,
- "loss": 1.619,
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
"step": 337
},
{
- "epoch": 6.84,
- "learning_rate": 0.00015688775510204082,
- "loss": 1.5563,
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
"step": 338
},
{
- "epoch": 6.86,
- "learning_rate": 0.00015676020408163265,
- "loss": 1.6328,
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
"step": 339
},
{
- "epoch": 6.88,
- "learning_rate": 0.0001566326530612245,
- "loss": 1.5726,
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
"step": 340
},
{
- "epoch": 6.9,
- "learning_rate": 0.00015650510204081634,
- "loss": 1.6199,
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
"step": 341
},
{
- "epoch": 6.92,
- "learning_rate": 0.00015637755102040817,
- "loss": 1.5722,
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
"step": 342
},
{
- "epoch": 6.94,
- "learning_rate": 0.00015625,
- "loss": 1.5685,
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
"step": 343
},
{
- "epoch": 6.96,
- "learning_rate": 0.00015612244897959186,
- "loss": 1.5615,
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
"step": 344
},
{
- "epoch": 6.98,
- "learning_rate": 0.00015599489795918366,
- "loss": 1.5994,
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
"step": 345
},
{
- "epoch": 7.0,
- "learning_rate": 0.00015586734693877552,
- "loss": 1.5579,
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
"step": 346
},
{
- "epoch": 7.02,
- "learning_rate": 0.00015573979591836735,
- "loss": 1.547,
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
"step": 347
},
{
- "epoch": 7.04,
- "learning_rate": 0.00015561224489795918,
- "loss": 1.5292,
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
"step": 348
},
{
- "epoch": 7.06,
- "learning_rate": 0.00015548469387755102,
- "loss": 1.6032,
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
"step": 349
},
{
- "epoch": 7.08,
- "learning_rate": 0.00015535714285714287,
- "loss": 1.5149,
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
"step": 350
},
{
- "epoch": 7.1,
- "learning_rate": 0.0001552295918367347,
- "loss": 1.6093,
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
"step": 351
},
{
- "epoch": 7.12,
- "learning_rate": 0.00015510204081632654,
- "loss": 1.5421,
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
"step": 352
},
{
- "epoch": 7.14,
- "learning_rate": 0.00015497448979591837,
- "loss": 1.5733,
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
"step": 353
},
{
- "epoch": 7.16,
- "learning_rate": 0.00015484693877551022,
- "loss": 1.5703,
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
"step": 354
},
{
- "epoch": 7.18,
- "learning_rate": 0.00015471938775510203,
- "loss": 1.6141,
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
"step": 355
},
{
- "epoch": 7.2,
- "learning_rate": 0.00015459183673469389,
- "loss": 1.5526,
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
"step": 356
},
{
- "epoch": 7.22,
- "learning_rate": 0.00015446428571428572,
- "loss": 1.5347,
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
"step": 357
},
{
- "epoch": 7.24,
- "learning_rate": 0.00015433673469387755,
- "loss": 1.5682,
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
"step": 358
},
{
- "epoch": 7.26,
- "learning_rate": 0.0001542091836734694,
- "loss": 1.5292,
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
"step": 359
},
{
- "epoch": 7.28,
- "learning_rate": 0.00015408163265306124,
- "loss": 1.499,
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
"step": 360
},
{
- "epoch": 7.3,
- "learning_rate": 0.00015395408163265307,
- "loss": 1.5624,
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
"step": 361
},
{
- "epoch": 7.32,
- "learning_rate": 0.0001538265306122449,
- "loss": 1.627,
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
"step": 362
},
{
- "epoch": 7.34,
- "learning_rate": 0.00015369897959183676,
- "loss": 1.5327,
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
"step": 363
},
{
- "epoch": 7.37,
- "learning_rate": 0.0001535714285714286,
- "loss": 1.5622,
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
"step": 364
},
{
- "epoch": 7.39,
- "learning_rate": 0.00015344387755102042,
- "loss": 1.5659,
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
"step": 365
},
{
- "epoch": 7.41,
- "learning_rate": 0.00015331632653061225,
- "loss": 1.5019,
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
"step": 366
},
{
- "epoch": 7.43,
- "learning_rate": 0.0001531887755102041,
- "loss": 1.5921,
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
"step": 367
},
{
- "epoch": 7.45,
- "learning_rate": 0.0001530612244897959,
- "loss": 1.5914,
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
"step": 368
},
{
- "epoch": 7.47,
- "learning_rate": 0.00015293367346938777,
- "loss": 1.5045,
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
"step": 369
},
{
- "epoch": 7.49,
- "learning_rate": 0.0001528061224489796,
- "loss": 1.6209,
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
"step": 370
},
{
- "epoch": 7.51,
- "learning_rate": 0.00015267857142857143,
- "loss": 1.5198,
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
"step": 371
},
{
- "epoch": 7.53,
- "learning_rate": 0.00015255102040816326,
- "loss": 1.5363,
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
"step": 372
},
{
- "epoch": 7.55,
- "learning_rate": 0.00015242346938775512,
- "loss": 1.5391,
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
"step": 373
},
{
- "epoch": 7.57,
- "learning_rate": 0.00015229591836734695,
- "loss": 1.4546,
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
"step": 374
},
{
- "epoch": 7.59,
- "learning_rate": 0.00015216836734693878,
- "loss": 1.5546,
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
"step": 375
},
{
- "epoch": 7.61,
- "learning_rate": 0.0001520408163265306,
- "loss": 1.5629,
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
"step": 376
},
{
- "epoch": 7.63,
- "learning_rate": 0.00015191326530612247,
- "loss": 1.6002,
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
"step": 377
},
{
- "epoch": 7.65,
- "learning_rate": 0.00015178571428571427,
- "loss": 1.5543,
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
"step": 378
},
{
- "epoch": 7.67,
- "learning_rate": 0.00015165816326530613,
- "loss": 1.5925,
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
"step": 379
},
{
- "epoch": 7.69,
- "learning_rate": 0.00015153061224489796,
- "loss": 1.5631,
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
"step": 380
},
{
- "epoch": 7.71,
- "learning_rate": 0.0001514030612244898,
- "loss": 1.5677,
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
"step": 381
},
{
- "epoch": 7.73,
- "learning_rate": 0.00015127551020408165,
- "loss": 1.5828,
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
"step": 382
},
{
- "epoch": 7.75,
- "learning_rate": 0.00015114795918367348,
- "loss": 1.6494,
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
"step": 383
},
{
- "epoch": 7.77,
- "learning_rate": 0.0001510204081632653,
- "loss": 1.553,
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
"step": 384
},
{
- "epoch": 7.79,
- "learning_rate": 0.00015089285714285714,
- "loss": 1.6156,
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
"step": 385
},
{
- "epoch": 7.81,
- "learning_rate": 0.000150765306122449,
- "loss": 1.5001,
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
"step": 386
},
{
- "epoch": 7.83,
- "learning_rate": 0.00015063775510204083,
- "loss": 1.5321,
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
"step": 387
},
{
- "epoch": 7.85,
- "learning_rate": 0.00015051020408163266,
- "loss": 1.5307,
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
"step": 388
},
{
- "epoch": 7.87,
- "learning_rate": 0.0001503826530612245,
- "loss": 1.5639,
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
"step": 389
},
{
- "epoch": 7.89,
- "learning_rate": 0.00015025510204081635,
- "loss": 1.517,
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
"step": 390
},
{
- "epoch": 7.91,
- "learning_rate": 0.00015012755102040816,
- "loss": 1.4776,
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
"step": 391
},
{
- "epoch": 7.93,
- "learning_rate": 0.00015000000000000001,
- "loss": 1.5368,
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
"step": 392
},
{
- "epoch": 7.95,
- "learning_rate": 0.00014987244897959184,
- "loss": 1.5636,
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
"step": 393
},
{
- "epoch": 7.97,
- "learning_rate": 0.00014974489795918368,
- "loss": 1.6004,
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
"step": 394
},
{
- "epoch": 7.99,
- "learning_rate": 0.0001496173469387755,
- "loss": 1.5524,
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
"step": 395
},
{
- "epoch": 8.01,
- "learning_rate": 0.00014948979591836736,
- "loss": 1.5307,
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
"step": 396
},
{
- "epoch": 8.03,
- "learning_rate": 0.00014936224489795917,
- "loss": 1.5123,
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
"step": 397
},
{
- "epoch": 8.05,
- "learning_rate": 0.00014923469387755103,
- "loss": 1.5132,
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
"step": 398
},
{
- "epoch": 8.07,
- "learning_rate": 0.00014910714285714286,
- "loss": 1.5109,
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
"step": 399
},
{
- "epoch": 8.09,
- "learning_rate": 0.00014897959183673472,
- "loss": 1.5302,
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
"step": 400
},
{
- "epoch": 8.11,
- "learning_rate": 0.00014885204081632652,
- "loss": 1.5238,
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
"step": 401
},
{
- "epoch": 8.13,
- "learning_rate": 0.00014872448979591838,
- "loss": 1.4781,
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
"step": 402
},
{
- "epoch": 8.15,
- "learning_rate": 0.0001485969387755102,
- "loss": 1.5446,
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
"step": 403
},
{
- "epoch": 8.17,
- "learning_rate": 0.00014846938775510204,
- "loss": 1.5,
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
"step": 404
},
{
- "epoch": 8.19,
- "learning_rate": 0.0001483418367346939,
- "loss": 1.5458,
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
"step": 405
},
{
- "epoch": 8.21,
- "learning_rate": 0.00014821428571428573,
- "loss": 1.5257,
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
"step": 406
},
{
- "epoch": 8.24,
- "learning_rate": 0.00014808673469387756,
- "loss": 1.4607,
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
"step": 407
},
{
- "epoch": 8.26,
- "learning_rate": 0.0001479591836734694,
- "loss": 1.4282,
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
"step": 408
},
{
- "epoch": 8.28,
- "learning_rate": 0.00014783163265306125,
- "loss": 1.4519,
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
"step": 409
},
{
- "epoch": 8.3,
- "learning_rate": 0.00014770408163265305,
- "loss": 1.475,
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
"step": 410
},
{
- "epoch": 8.32,
- "learning_rate": 0.0001475765306122449,
- "loss": 1.5425,
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
"step": 411
},
{
- "epoch": 8.34,
- "learning_rate": 0.00014744897959183674,
- "loss": 1.5407,
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
"step": 412
},
{
- "epoch": 8.36,
- "learning_rate": 0.0001473214285714286,
- "loss": 1.5698,
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
"step": 413
},
{
- "epoch": 8.38,
- "learning_rate": 0.0001471938775510204,
- "loss": 1.4282,
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
"step": 414
},
{
- "epoch": 8.4,
- "learning_rate": 0.00014706632653061226,
- "loss": 1.5301,
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
"step": 415
},
{
- "epoch": 8.42,
- "learning_rate": 0.0001469387755102041,
- "loss": 1.5083,
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
"step": 416
},
{
- "epoch": 8.44,
- "learning_rate": 0.00014681122448979592,
- "loss": 1.5712,
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
"step": 417
},
{
- "epoch": 8.46,
- "learning_rate": 0.00014668367346938775,
- "loss": 1.4363,
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
"step": 418
},
{
- "epoch": 8.48,
- "learning_rate": 0.0001465561224489796,
- "loss": 1.4463,
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
"step": 419
},
{
- "epoch": 8.5,
- "learning_rate": 0.00014642857142857141,
- "loss": 1.4738,
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
"step": 420
},
{
- "epoch": 8.52,
- "learning_rate": 0.00014630102040816327,
- "loss": 1.5396,
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
"step": 421
},
{
- "epoch": 8.54,
- "learning_rate": 0.0001461734693877551,
- "loss": 1.4384,
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
"step": 422
},
{
- "epoch": 8.56,
- "learning_rate": 0.00014604591836734696,
- "loss": 1.5345,
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
"step": 423
},
{
- "epoch": 8.58,
- "learning_rate": 0.0001459183673469388,
- "loss": 1.5355,
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
"step": 424
},
{
- "epoch": 8.6,
- "learning_rate": 0.00014579081632653062,
- "loss": 1.5188,
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
"step": 425
},
{
- "epoch": 8.62,
- "learning_rate": 0.00014566326530612245,
- "loss": 1.5575,
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
"step": 426
},
{
- "epoch": 8.64,
- "learning_rate": 0.00014553571428571428,
- "loss": 1.5279,
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
"step": 427
},
{
- "epoch": 8.66,
- "learning_rate": 0.00014540816326530614,
- "loss": 1.5484,
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
"step": 428
},
{
- "epoch": 8.68,
- "learning_rate": 0.00014528061224489797,
- "loss": 1.4878,
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
"step": 429
},
{
- "epoch": 8.7,
- "learning_rate": 0.0001451530612244898,
- "loss": 1.503,
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
"step": 430
},
{
- "epoch": 8.72,
- "learning_rate": 0.00014502551020408163,
- "loss": 1.4723,
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
"step": 431
},
{
- "epoch": 8.74,
- "learning_rate": 0.0001448979591836735,
- "loss": 1.5579,
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
"step": 432
},
{
- "epoch": 8.76,
- "learning_rate": 0.0001447704081632653,
- "loss": 1.4789,
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
"step": 433
},
{
- "epoch": 8.78,
- "learning_rate": 0.00014464285714285715,
- "loss": 1.5501,
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
"step": 434
},
{
- "epoch": 8.8,
- "learning_rate": 0.00014451530612244899,
- "loss": 1.5204,
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
"step": 435
},
{
- "epoch": 8.82,
- "learning_rate": 0.00014438775510204084,
- "loss": 1.5489,
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
"step": 436
},
{
- "epoch": 8.84,
- "learning_rate": 0.00014426020408163265,
- "loss": 1.5464,
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
"step": 437
},
{
- "epoch": 8.86,
- "learning_rate": 0.0001441326530612245,
- "loss": 1.5896,
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
"step": 438
},
{
- "epoch": 8.88,
- "learning_rate": 0.00014400510204081634,
- "loss": 1.5465,
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
"step": 439
},
{
- "epoch": 8.9,
- "learning_rate": 0.00014387755102040817,
- "loss": 1.5094,
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
"step": 440
},
{
- "epoch": 8.92,
- "learning_rate": 0.00014375,
- "loss": 1.5144,
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
"step": 441
},
{
- "epoch": 8.94,
- "learning_rate": 0.00014362244897959186,
- "loss": 1.4919,
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
"step": 442
},
{
- "epoch": 8.96,
- "learning_rate": 0.00014349489795918366,
- "loss": 1.4702,
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
"step": 443
},
{
- "epoch": 8.98,
- "learning_rate": 0.00014336734693877552,
- "loss": 1.4996,
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
"step": 444
},
{
- "epoch": 9.0,
- "learning_rate": 0.00014323979591836735,
- "loss": 1.5503,
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
"step": 445
},
{
- "epoch": 9.02,
- "learning_rate": 0.00014311224489795918,
- "loss": 1.4125,
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
"step": 446
},
{
- "epoch": 9.04,
- "learning_rate": 0.00014298469387755104,
- "loss": 1.4722,
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
"step": 447
},
{
- "epoch": 9.06,
- "learning_rate": 0.00014285714285714287,
- "loss": 1.5199,
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
"step": 448
},
{
- "epoch": 9.09,
- "learning_rate": 0.0001427295918367347,
- "loss": 1.4571,
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
"step": 449
},
{
- "epoch": 9.11,
- "learning_rate": 0.00014260204081632653,
- "loss": 1.4996,
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
"step": 450
},
{
- "epoch": 9.13,
- "learning_rate": 0.0001424744897959184,
- "loss": 1.4092,
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
"step": 451
},
{
- "epoch": 9.15,
- "learning_rate": 0.00014234693877551022,
- "loss": 1.4198,
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
"step": 452
},
{
- "epoch": 9.17,
- "learning_rate": 0.00014221938775510205,
- "loss": 1.4916,
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
"step": 453
},
{
- "epoch": 9.19,
- "learning_rate": 0.00014209183673469388,
- "loss": 1.5051,
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
"step": 454
},
{
- "epoch": 9.21,
- "learning_rate": 0.00014196428571428574,
- "loss": 1.4321,
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
"step": 455
},
{
- "epoch": 9.23,
- "learning_rate": 0.00014183673469387754,
- "loss": 1.4097,
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
"step": 456
},
{
- "epoch": 9.25,
- "learning_rate": 0.0001417091836734694,
- "loss": 1.4853,
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
"step": 457
},
{
- "epoch": 9.27,
- "learning_rate": 0.00014158163265306123,
- "loss": 1.4593,
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
"step": 458
},
{
- "epoch": 9.29,
- "learning_rate": 0.00014145408163265306,
- "loss": 1.3729,
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
"step": 459
},
{
- "epoch": 9.31,
- "learning_rate": 0.0001413265306122449,
- "loss": 1.4467,
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
"step": 460
},
{
- "epoch": 9.33,
- "learning_rate": 0.00014119897959183675,
- "loss": 1.4467,
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
"step": 461
},
{
- "epoch": 9.35,
- "learning_rate": 0.00014107142857142858,
- "loss": 1.4785,
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
"step": 462
},
{
- "epoch": 9.37,
- "learning_rate": 0.0001409438775510204,
- "loss": 1.4089,
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
"step": 463
},
{
- "epoch": 9.39,
- "learning_rate": 0.00014081632653061224,
- "loss": 1.5026,
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
"step": 464
},
{
- "epoch": 9.41,
- "learning_rate": 0.0001406887755102041,
- "loss": 1.4857,
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
"step": 465
},
{
- "epoch": 9.43,
- "learning_rate": 0.0001405612244897959,
- "loss": 1.3745,
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
"step": 466
},
{
- "epoch": 9.45,
- "learning_rate": 0.00014043367346938776,
- "loss": 1.4733,
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
"step": 467
},
{
- "epoch": 9.47,
- "learning_rate": 0.0001403061224489796,
- "loss": 1.5212,
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
"step": 468
},
{
- "epoch": 9.49,
- "learning_rate": 0.00014017857142857142,
- "loss": 1.5398,
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
"step": 469
},
{
- "epoch": 9.51,
- "learning_rate": 0.00014005102040816328,
- "loss": 1.478,
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
"step": 470
},
{
- "epoch": 9.53,
- "learning_rate": 0.0001399234693877551,
- "loss": 1.496,
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
"step": 471
},
{
- "epoch": 9.55,
- "learning_rate": 0.00013979591836734694,
- "loss": 1.4837,
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
"step": 472
},
{
- "epoch": 9.57,
- "learning_rate": 0.00013966836734693878,
- "loss": 1.4724,
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
"step": 473
},
{
- "epoch": 9.59,
- "learning_rate": 0.00013954081632653063,
- "loss": 1.4828,
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
"step": 474
},
{
- "epoch": 9.61,
- "learning_rate": 0.00013941326530612246,
- "loss": 1.5012,
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
"step": 475
},
{
- "epoch": 9.63,
- "learning_rate": 0.0001392857142857143,
- "loss": 1.4879,
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
"step": 476
},
{
- "epoch": 9.65,
- "learning_rate": 0.00013915816326530613,
- "loss": 1.4196,
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
"step": 477
},
{
- "epoch": 9.67,
- "learning_rate": 0.00013903061224489798,
- "loss": 1.4915,
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
"step": 478
},
{
- "epoch": 9.69,
- "learning_rate": 0.0001389030612244898,
- "loss": 1.3878,
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
"step": 479
},
{
- "epoch": 9.71,
- "learning_rate": 0.00013877551020408165,
- "loss": 1.466,
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
"step": 480
},
{
- "epoch": 9.73,
- "learning_rate": 0.00013864795918367348,
- "loss": 1.4582,
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
"step": 481
},
{
- "epoch": 9.75,
- "learning_rate": 0.0001385204081632653,
- "loss": 1.533,
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
"step": 482
},
{
- "epoch": 9.77,
- "learning_rate": 0.00013839285714285714,
- "loss": 1.4697,
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
"step": 483
},
{
- "epoch": 9.79,
- "learning_rate": 0.000138265306122449,
- "loss": 1.3989,
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
"step": 484
},
{
- "epoch": 9.81,
- "learning_rate": 0.00013813775510204083,
- "loss": 1.4361,
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
"step": 485
},
{
- "epoch": 9.83,
- "learning_rate": 0.00013801020408163266,
- "loss": 1.5271,
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
"step": 486
},
{
- "epoch": 9.85,
- "learning_rate": 0.0001378826530612245,
- "loss": 1.4905,
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
"step": 487
},
{
- "epoch": 9.87,
- "learning_rate": 0.00013775510204081635,
- "loss": 1.4757,
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
"step": 488
},
{
- "epoch": 9.89,
- "learning_rate": 0.00013762755102040815,
- "loss": 1.5485,
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
"step": 489
},
{
- "epoch": 9.91,
- "learning_rate": 0.0001375,
- "loss": 1.4783,
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
"step": 490
},
{
- "epoch": 9.93,
- "learning_rate": 0.00013737244897959184,
- "loss": 1.4849,
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
"step": 491
},
{
- "epoch": 9.96,
- "learning_rate": 0.00013724489795918367,
- "loss": 1.5382,
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
"step": 492
},
{
- "epoch": 9.98,
- "learning_rate": 0.00013711734693877553,
- "loss": 1.4902,
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
"step": 493
},
{
- "epoch": 10.0,
- "learning_rate": 0.00013698979591836736,
- "loss": 1.4865,
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
"step": 494
},
{
- "epoch": 10.02,
- "learning_rate": 0.0001368622448979592,
- "loss": 1.4436,
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
"step": 495
},
{
- "epoch": 10.04,
- "learning_rate": 0.00013673469387755102,
- "loss": 1.408,
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
"step": 496
},
{
- "epoch": 10.06,
- "learning_rate": 0.00013660714285714288,
- "loss": 1.4764,
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
"step": 497
},
{
- "epoch": 10.08,
- "learning_rate": 0.0001364795918367347,
- "loss": 1.4646,
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
"step": 498
},
{
- "epoch": 10.1,
- "learning_rate": 0.00013635204081632654,
- "loss": 1.406,
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
"step": 499
},
{
- "epoch": 10.12,
- "learning_rate": 0.00013622448979591837,
- "loss": 1.4785,
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
"step": 500
},
{
- "epoch": 10.14,
- "learning_rate": 0.00013609693877551023,
- "loss": 1.4117,
+ "epoch": 5.66,
+ "learning_rate": 0.00012883522727272727,
+ "loss": 1.0755,
"step": 501
},
{
- "epoch": 10.16,
- "learning_rate": 0.00013596938775510203,
- "loss": 1.4108,
+ "epoch": 5.67,
+ "learning_rate": 0.00012869318181818183,
+ "loss": 1.0755,
"step": 502
},
{
- "epoch": 10.18,
- "learning_rate": 0.0001358418367346939,
- "loss": 1.4155,
+ "epoch": 5.68,
+ "learning_rate": 0.00012855113636363636,
+ "loss": 1.0869,
"step": 503
},
{
- "epoch": 10.2,
- "learning_rate": 0.00013571428571428572,
- "loss": 1.4021,
+ "epoch": 5.69,
+ "learning_rate": 0.00012840909090909092,
+ "loss": 1.0673,
"step": 504
},
{
- "epoch": 10.22,
- "learning_rate": 0.00013558673469387755,
- "loss": 1.411,
+ "epoch": 5.71,
+ "learning_rate": 0.00012826704545454545,
+ "loss": 1.0692,
"step": 505
},
{
- "epoch": 10.24,
- "learning_rate": 0.00013545918367346938,
- "loss": 1.3851,
+ "epoch": 5.72,
+ "learning_rate": 0.000128125,
+ "loss": 1.0474,
"step": 506
},
{
- "epoch": 10.26,
- "learning_rate": 0.00013533163265306124,
- "loss": 1.387,
+ "epoch": 5.73,
+ "learning_rate": 0.00012798295454545454,
+ "loss": 1.0749,
"step": 507
},
{
- "epoch": 10.28,
- "learning_rate": 0.00013520408163265305,
- "loss": 1.4163,
+ "epoch": 5.74,
+ "learning_rate": 0.0001278409090909091,
+ "loss": 1.0519,
"step": 508
},
{
- "epoch": 10.3,
- "learning_rate": 0.0001350765306122449,
- "loss": 1.3343,
+ "epoch": 5.75,
+ "learning_rate": 0.00012769886363636366,
+ "loss": 1.0566,
"step": 509
},
{
- "epoch": 10.32,
- "learning_rate": 0.00013494897959183673,
- "loss": 1.4811,
+ "epoch": 5.76,
+ "learning_rate": 0.0001275568181818182,
+ "loss": 1.06,
"step": 510
},
{
- "epoch": 10.34,
- "learning_rate": 0.0001348214285714286,
- "loss": 1.4086,
+ "epoch": 5.77,
+ "learning_rate": 0.00012741477272727272,
+ "loss": 1.0618,
"step": 511
},
{
- "epoch": 10.36,
- "learning_rate": 0.0001346938775510204,
- "loss": 1.3879,
+ "epoch": 5.78,
+ "learning_rate": 0.00012727272727272728,
+ "loss": 1.0643,
"step": 512
},
{
- "epoch": 10.38,
- "learning_rate": 0.00013456632653061225,
- "loss": 1.4204,
+ "epoch": 5.8,
+ "learning_rate": 0.0001271306818181818,
+ "loss": 1.026,
"step": 513
},
{
- "epoch": 10.4,
- "learning_rate": 0.00013443877551020408,
- "loss": 1.4158,
+ "epoch": 5.81,
+ "learning_rate": 0.00012698863636363637,
+ "loss": 1.0335,
"step": 514
},
{
- "epoch": 10.42,
- "learning_rate": 0.00013431122448979592,
- "loss": 1.4521,
+ "epoch": 5.82,
+ "learning_rate": 0.00012684659090909093,
+ "loss": 1.0205,
"step": 515
},
{
- "epoch": 10.44,
- "learning_rate": 0.00013418367346938777,
- "loss": 1.4196,
+ "epoch": 5.83,
+ "learning_rate": 0.00012670454545454546,
+ "loss": 1.0594,
"step": 516
},
{
- "epoch": 10.46,
- "learning_rate": 0.0001340561224489796,
- "loss": 1.4361,
+ "epoch": 5.84,
+ "learning_rate": 0.0001265625,
+ "loss": 1.0136,
"step": 517
},
{
- "epoch": 10.48,
- "learning_rate": 0.00013392857142857144,
- "loss": 1.4482,
+ "epoch": 5.85,
+ "learning_rate": 0.00012642045454545455,
+ "loss": 1.0244,
"step": 518
},
{
- "epoch": 10.5,
- "learning_rate": 0.00013380102040816327,
- "loss": 1.4801,
+ "epoch": 5.86,
+ "learning_rate": 0.00012627840909090908,
+ "loss": 1.0569,
"step": 519
},
{
- "epoch": 10.52,
- "learning_rate": 0.00013367346938775512,
- "loss": 1.4556,
+ "epoch": 5.87,
+ "learning_rate": 0.00012613636363636364,
+ "loss": 1.0416,
"step": 520
},
{
- "epoch": 10.54,
- "learning_rate": 0.00013354591836734695,
- "loss": 1.3902,
+ "epoch": 5.89,
+ "learning_rate": 0.0001259943181818182,
+ "loss": 0.9884,
"step": 521
},
{
- "epoch": 10.56,
- "learning_rate": 0.00013341836734693879,
- "loss": 1.4269,
+ "epoch": 5.9,
+ "learning_rate": 0.00012585227272727273,
+ "loss": 1.0351,
"step": 522
},
{
- "epoch": 10.58,
- "learning_rate": 0.00013329081632653062,
- "loss": 1.4899,
+ "epoch": 5.91,
+ "learning_rate": 0.00012571022727272726,
+ "loss": 1.0037,
"step": 523
},
{
- "epoch": 10.6,
- "learning_rate": 0.00013316326530612247,
- "loss": 1.3952,
+ "epoch": 5.92,
+ "learning_rate": 0.00012556818181818182,
+ "loss": 1.0219,
"step": 524
},
{
- "epoch": 10.62,
- "learning_rate": 0.00013303571428571428,
- "loss": 1.4116,
+ "epoch": 5.93,
+ "learning_rate": 0.00012542613636363635,
+ "loss": 1.0533,
"step": 525
},
{
- "epoch": 10.64,
- "learning_rate": 0.00013290816326530614,
- "loss": 1.4583,
+ "epoch": 5.94,
+ "learning_rate": 0.0001252840909090909,
+ "loss": 1.0031,
"step": 526
},
{
- "epoch": 10.66,
- "learning_rate": 0.00013278061224489797,
- "loss": 1.4466,
+ "epoch": 5.95,
+ "learning_rate": 0.00012514204545454547,
+ "loss": 1.0454,
"step": 527
},
{
- "epoch": 10.68,
- "learning_rate": 0.0001326530612244898,
- "loss": 1.4242,
+ "epoch": 5.97,
+ "learning_rate": 0.000125,
+ "loss": 1.0195,
"step": 528
},
{
- "epoch": 10.7,
- "learning_rate": 0.00013252551020408163,
- "loss": 1.3717,
+ "epoch": 5.98,
+ "learning_rate": 0.00012485795454545453,
+ "loss": 1.0076,
"step": 529
},
{
- "epoch": 10.72,
- "learning_rate": 0.0001323979591836735,
- "loss": 1.4583,
+ "epoch": 5.99,
+ "learning_rate": 0.0001247159090909091,
+ "loss": 1.0378,
"step": 530
},
{
- "epoch": 10.74,
- "learning_rate": 0.0001322704081632653,
- "loss": 1.4185,
+ "epoch": 6.0,
+ "learning_rate": 0.00012457386363636365,
+ "loss": 0.9795,
"step": 531
},
{
- "epoch": 10.76,
- "learning_rate": 0.00013214285714285715,
- "loss": 1.4287,
+ "epoch": 6.01,
+ "learning_rate": 0.00012443181818181818,
+ "loss": 0.9405,
"step": 532
},
{
- "epoch": 10.78,
- "learning_rate": 0.00013201530612244898,
- "loss": 1.4385,
+ "epoch": 6.02,
+ "learning_rate": 0.00012428977272727274,
+ "loss": 0.9503,
"step": 533
},
{
- "epoch": 10.8,
- "learning_rate": 0.00013188775510204084,
- "loss": 1.453,
+ "epoch": 6.03,
+ "learning_rate": 0.00012414772727272727,
+ "loss": 0.9456,
"step": 534
},
{
- "epoch": 10.83,
- "learning_rate": 0.00013176020408163264,
- "loss": 1.4161,
+ "epoch": 6.04,
+ "learning_rate": 0.0001240056818181818,
+ "loss": 0.9536,
"step": 535
},
{
- "epoch": 10.85,
- "learning_rate": 0.0001316326530612245,
- "loss": 1.457,
+ "epoch": 6.06,
+ "learning_rate": 0.00012386363636363636,
+ "loss": 0.9412,
"step": 536
},
{
- "epoch": 10.87,
- "learning_rate": 0.00013150510204081633,
- "loss": 1.4367,
+ "epoch": 6.07,
+ "learning_rate": 0.00012372159090909092,
+ "loss": 0.9315,
"step": 537
},
{
- "epoch": 10.89,
- "learning_rate": 0.00013137755102040816,
- "loss": 1.4256,
+ "epoch": 6.08,
+ "learning_rate": 0.00012357954545454545,
+ "loss": 0.9486,
"step": 538
},
{
- "epoch": 10.91,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.424,
+ "epoch": 6.09,
+ "learning_rate": 0.0001234375,
+ "loss": 0.9405,
"step": 539
},
{
- "epoch": 10.93,
- "learning_rate": 0.00013112244897959185,
- "loss": 1.3923,
+ "epoch": 6.1,
+ "learning_rate": 0.00012329545454545454,
+ "loss": 0.9269,
"step": 540
},
{
- "epoch": 10.95,
- "learning_rate": 0.00013099489795918368,
- "loss": 1.4225,
+ "epoch": 6.11,
+ "learning_rate": 0.0001231534090909091,
+ "loss": 0.9378,
"step": 541
},
{
- "epoch": 10.97,
- "learning_rate": 0.0001308673469387755,
- "loss": 1.3969,
+ "epoch": 6.12,
+ "learning_rate": 0.00012301136363636366,
+ "loss": 0.9431,
"step": 542
},
{
- "epoch": 10.99,
- "learning_rate": 0.00013073979591836737,
- "loss": 1.4446,
+ "epoch": 6.13,
+ "learning_rate": 0.0001228693181818182,
+ "loss": 0.9256,
"step": 543
},
{
- "epoch": 11.01,
- "learning_rate": 0.00013061224489795917,
- "loss": 1.4375,
+ "epoch": 6.15,
+ "learning_rate": 0.00012272727272727272,
+ "loss": 0.919,
"step": 544
},
{
- "epoch": 11.03,
- "learning_rate": 0.00013048469387755103,
- "loss": 1.4064,
+ "epoch": 6.16,
+ "learning_rate": 0.00012258522727272728,
+ "loss": 0.9188,
"step": 545
},
{
- "epoch": 11.05,
- "learning_rate": 0.00013035714285714286,
- "loss": 1.3454,
+ "epoch": 6.17,
+ "learning_rate": 0.00012244318181818181,
+ "loss": 0.9447,
"step": 546
},
{
- "epoch": 11.07,
- "learning_rate": 0.00013022959183673472,
- "loss": 1.3234,
+ "epoch": 6.18,
+ "learning_rate": 0.00012230113636363637,
+ "loss": 0.9261,
"step": 547
},
{
- "epoch": 11.09,
- "learning_rate": 0.00013010204081632652,
- "loss": 1.3759,
+ "epoch": 6.19,
+ "learning_rate": 0.00012215909090909093,
+ "loss": 0.9302,
"step": 548
},
{
- "epoch": 11.11,
- "learning_rate": 0.00012997448979591838,
- "loss": 1.4221,
+ "epoch": 6.2,
+ "learning_rate": 0.00012201704545454546,
+ "loss": 0.9161,
"step": 549
},
{
- "epoch": 11.13,
- "learning_rate": 0.0001298469387755102,
- "loss": 1.4261,
+ "epoch": 6.21,
+ "learning_rate": 0.00012187500000000001,
+ "loss": 0.9521,
"step": 550
},
{
- "epoch": 11.15,
- "learning_rate": 0.00012971938775510204,
- "loss": 1.3341,
+ "epoch": 6.22,
+ "learning_rate": 0.00012173295454545455,
+ "loss": 0.9026,
"step": 551
},
{
- "epoch": 11.17,
- "learning_rate": 0.00012959183673469387,
- "loss": 1.3994,
+ "epoch": 6.24,
+ "learning_rate": 0.00012159090909090908,
+ "loss": 0.9361,
"step": 552
},
{
- "epoch": 11.19,
- "learning_rate": 0.00012946428571428573,
- "loss": 1.3894,
+ "epoch": 6.25,
+ "learning_rate": 0.00012144886363636366,
+ "loss": 0.8944,
"step": 553
},
{
- "epoch": 11.21,
- "learning_rate": 0.00012933673469387754,
- "loss": 1.3585,
+ "epoch": 6.26,
+ "learning_rate": 0.00012130681818181819,
+ "loss": 0.895,
"step": 554
},
{
- "epoch": 11.23,
- "learning_rate": 0.0001292091836734694,
- "loss": 1.3763,
+ "epoch": 6.27,
+ "learning_rate": 0.00012116477272727273,
+ "loss": 0.8956,
"step": 555
},
{
- "epoch": 11.25,
- "learning_rate": 0.00012908163265306123,
- "loss": 1.3623,
+ "epoch": 6.28,
+ "learning_rate": 0.00012102272727272728,
+ "loss": 0.8998,
"step": 556
},
{
- "epoch": 11.27,
- "learning_rate": 0.00012895408163265306,
- "loss": 1.3907,
+ "epoch": 6.29,
+ "learning_rate": 0.00012088068181818182,
+ "loss": 0.915,
"step": 557
},
{
- "epoch": 11.29,
- "learning_rate": 0.0001288265306122449,
- "loss": 1.3807,
+ "epoch": 6.3,
+ "learning_rate": 0.00012073863636363636,
+ "loss": 0.9282,
"step": 558
},
{
- "epoch": 11.31,
- "learning_rate": 0.00012869897959183674,
- "loss": 1.4045,
+ "epoch": 6.32,
+ "learning_rate": 0.00012059659090909093,
+ "loss": 0.8938,
"step": 559
},
{
- "epoch": 11.33,
- "learning_rate": 0.00012857142857142858,
- "loss": 1.4038,
+ "epoch": 6.33,
+ "learning_rate": 0.00012045454545454546,
+ "loss": 0.8886,
"step": 560
},
{
- "epoch": 11.35,
- "learning_rate": 0.0001284438775510204,
- "loss": 1.3466,
+ "epoch": 6.34,
+ "learning_rate": 0.0001203125,
+ "loss": 0.8988,
"step": 561
},
{
- "epoch": 11.37,
- "learning_rate": 0.00012831632653061226,
- "loss": 1.3449,
+ "epoch": 6.35,
+ "learning_rate": 0.00012017045454545455,
+ "loss": 0.8852,
"step": 562
},
{
- "epoch": 11.39,
- "learning_rate": 0.0001281887755102041,
- "loss": 1.3866,
+ "epoch": 6.36,
+ "learning_rate": 0.0001200284090909091,
+ "loss": 0.8818,
"step": 563
},
{
- "epoch": 11.41,
- "learning_rate": 0.00012806122448979593,
- "loss": 1.3106,
+ "epoch": 6.37,
+ "learning_rate": 0.00011988636363636365,
+ "loss": 0.8881,
"step": 564
},
{
- "epoch": 11.43,
- "learning_rate": 0.00012793367346938776,
- "loss": 1.4414,
+ "epoch": 6.38,
+ "learning_rate": 0.0001197443181818182,
+ "loss": 0.9226,
"step": 565
},
{
- "epoch": 11.45,
- "learning_rate": 0.00012780612244897962,
- "loss": 1.3737,
+ "epoch": 6.39,
+ "learning_rate": 0.00011960227272727273,
+ "loss": 0.8849,
"step": 566
},
{
- "epoch": 11.47,
- "learning_rate": 0.00012767857142857142,
- "loss": 1.4053,
+ "epoch": 6.41,
+ "learning_rate": 0.00011946022727272727,
+ "loss": 0.8894,
"step": 567
},
{
- "epoch": 11.49,
- "learning_rate": 0.00012755102040816328,
- "loss": 1.4561,
+ "epoch": 6.42,
+ "learning_rate": 0.00011931818181818182,
+ "loss": 0.9207,
"step": 568
},
{
- "epoch": 11.51,
- "learning_rate": 0.0001274234693877551,
- "loss": 1.3684,
+ "epoch": 6.43,
+ "learning_rate": 0.00011917613636363636,
+ "loss": 0.9105,
"step": 569
},
{
- "epoch": 11.53,
- "learning_rate": 0.00012729591836734697,
- "loss": 1.3117,
+ "epoch": 6.44,
+ "learning_rate": 0.00011903409090909092,
+ "loss": 0.8762,
"step": 570
},
{
- "epoch": 11.55,
- "learning_rate": 0.00012716836734693877,
- "loss": 1.3474,
+ "epoch": 6.45,
+ "learning_rate": 0.00011889204545454547,
+ "loss": 0.8926,
"step": 571
},
{
- "epoch": 11.57,
- "learning_rate": 0.00012704081632653063,
- "loss": 1.3804,
+ "epoch": 6.46,
+ "learning_rate": 0.00011875,
+ "loss": 0.8719,
"step": 572
},
{
- "epoch": 11.59,
- "learning_rate": 0.00012691326530612246,
- "loss": 1.3656,
+ "epoch": 6.47,
+ "learning_rate": 0.00011860795454545454,
+ "loss": 0.9198,
"step": 573
},
{
- "epoch": 11.61,
- "learning_rate": 0.0001267857142857143,
- "loss": 1.3133,
+ "epoch": 6.48,
+ "learning_rate": 0.00011846590909090909,
+ "loss": 0.8846,
"step": 574
},
{
- "epoch": 11.63,
- "learning_rate": 0.00012665816326530612,
- "loss": 1.4077,
+ "epoch": 6.5,
+ "learning_rate": 0.00011832386363636365,
+ "loss": 0.8495,
"step": 575
},
{
- "epoch": 11.65,
- "learning_rate": 0.00012653061224489798,
- "loss": 1.4087,
+ "epoch": 6.51,
+ "learning_rate": 0.0001181818181818182,
+ "loss": 0.8953,
"step": 576
},
{
- "epoch": 11.67,
- "learning_rate": 0.00012640306122448978,
- "loss": 1.3524,
+ "epoch": 6.52,
+ "learning_rate": 0.00011803977272727274,
+ "loss": 0.8686,
"step": 577
},
{
- "epoch": 11.7,
- "learning_rate": 0.00012627551020408164,
- "loss": 1.3481,
+ "epoch": 6.53,
+ "learning_rate": 0.00011789772727272727,
+ "loss": 0.8841,
"step": 578
},
{
- "epoch": 11.72,
- "learning_rate": 0.00012614795918367347,
- "loss": 1.4497,
+ "epoch": 6.54,
+ "learning_rate": 0.00011775568181818182,
+ "loss": 0.8681,
"step": 579
},
{
- "epoch": 11.74,
- "learning_rate": 0.0001260204081632653,
- "loss": 1.3866,
+ "epoch": 6.55,
+ "learning_rate": 0.00011761363636363636,
+ "loss": 0.8732,
"step": 580
},
{
- "epoch": 11.76,
- "learning_rate": 0.00012589285714285713,
- "loss": 1.42,
+ "epoch": 6.56,
+ "learning_rate": 0.00011747159090909092,
+ "loss": 0.8582,
"step": 581
},
{
- "epoch": 11.78,
- "learning_rate": 0.000125765306122449,
- "loss": 1.3562,
+ "epoch": 6.58,
+ "learning_rate": 0.00011732954545454546,
+ "loss": 0.8744,
"step": 582
},
{
- "epoch": 11.8,
- "learning_rate": 0.00012563775510204082,
- "loss": 1.3249,
+ "epoch": 6.59,
+ "learning_rate": 0.00011718750000000001,
+ "loss": 0.8694,
"step": 583
},
{
- "epoch": 11.82,
- "learning_rate": 0.00012551020408163265,
- "loss": 1.4277,
+ "epoch": 6.6,
+ "learning_rate": 0.00011704545454545454,
+ "loss": 0.8565,
"step": 584
},
{
- "epoch": 11.84,
- "learning_rate": 0.0001253826530612245,
- "loss": 1.3734,
+ "epoch": 6.61,
+ "learning_rate": 0.00011690340909090909,
+ "loss": 0.8584,
"step": 585
},
{
- "epoch": 11.86,
- "learning_rate": 0.00012525510204081634,
- "loss": 1.3765,
+ "epoch": 6.62,
+ "learning_rate": 0.00011676136363636366,
+ "loss": 0.8859,
"step": 586
},
{
- "epoch": 11.88,
- "learning_rate": 0.00012512755102040817,
- "loss": 1.4153,
+ "epoch": 6.63,
+ "learning_rate": 0.00011661931818181819,
+ "loss": 0.8452,
"step": 587
},
{
- "epoch": 11.9,
- "learning_rate": 0.000125,
- "loss": 1.3847,
+ "epoch": 6.64,
+ "learning_rate": 0.00011647727272727273,
+ "loss": 0.8323,
"step": 588
},
{
- "epoch": 11.92,
- "learning_rate": 0.00012487244897959186,
- "loss": 1.3824,
+ "epoch": 6.65,
+ "learning_rate": 0.00011633522727272728,
+ "loss": 0.8548,
"step": 589
},
{
- "epoch": 11.94,
- "learning_rate": 0.00012474489795918366,
- "loss": 1.3938,
+ "epoch": 6.67,
+ "learning_rate": 0.00011619318181818181,
+ "loss": 0.8506,
"step": 590
},
{
- "epoch": 11.96,
- "learning_rate": 0.00012461734693877552,
- "loss": 1.4143,
+ "epoch": 6.68,
+ "learning_rate": 0.00011605113636363636,
+ "loss": 0.8556,
"step": 591
},
{
- "epoch": 11.98,
- "learning_rate": 0.00012448979591836735,
- "loss": 1.3794,
+ "epoch": 6.69,
+ "learning_rate": 0.00011590909090909093,
+ "loss": 0.8459,
"step": 592
},
{
- "epoch": 12.0,
- "learning_rate": 0.00012436224489795918,
- "loss": 1.3755,
+ "epoch": 6.7,
+ "learning_rate": 0.00011576704545454546,
+ "loss": 0.8432,
"step": 593
},
{
- "epoch": 12.02,
- "learning_rate": 0.00012423469387755101,
- "loss": 1.3736,
+ "epoch": 6.71,
+ "learning_rate": 0.000115625,
+ "loss": 0.8645,
"step": 594
},
{
- "epoch": 12.04,
- "learning_rate": 0.00012410714285714287,
- "loss": 1.2957,
+ "epoch": 6.72,
+ "learning_rate": 0.00011548295454545455,
+ "loss": 0.86,
"step": 595
},
{
- "epoch": 12.06,
- "learning_rate": 0.0001239795918367347,
- "loss": 1.2996,
+ "epoch": 6.73,
+ "learning_rate": 0.00011534090909090908,
+ "loss": 0.8161,
"step": 596
},
{
- "epoch": 12.08,
- "learning_rate": 0.00012385204081632653,
- "loss": 1.3648,
+ "epoch": 6.74,
+ "learning_rate": 0.00011519886363636365,
+ "loss": 0.8133,
"step": 597
},
{
- "epoch": 12.1,
- "learning_rate": 0.00012372448979591837,
- "loss": 1.3031,
+ "epoch": 6.76,
+ "learning_rate": 0.0001150568181818182,
+ "loss": 0.8372,
"step": 598
},
{
- "epoch": 12.12,
- "learning_rate": 0.00012359693877551022,
- "loss": 1.2933,
+ "epoch": 6.77,
+ "learning_rate": 0.00011491477272727273,
+ "loss": 0.8222,
"step": 599
},
{
- "epoch": 12.14,
- "learning_rate": 0.00012346938775510203,
- "loss": 1.322,
+ "epoch": 6.78,
+ "learning_rate": 0.00011477272727272728,
+ "loss": 0.8372,
"step": 600
},
{
- "epoch": 12.16,
- "learning_rate": 0.00012334183673469389,
- "loss": 1.3123,
+ "epoch": 6.79,
+ "learning_rate": 0.00011463068181818182,
+ "loss": 0.837,
"step": 601
},
{
- "epoch": 12.18,
- "learning_rate": 0.00012321428571428572,
- "loss": 1.3187,
+ "epoch": 6.8,
+ "learning_rate": 0.00011448863636363637,
+ "loss": 0.8406,
"step": 602
},
{
- "epoch": 12.2,
- "learning_rate": 0.00012308673469387755,
- "loss": 1.3353,
+ "epoch": 6.81,
+ "learning_rate": 0.00011434659090909092,
+ "loss": 0.836,
"step": 603
},
{
- "epoch": 12.22,
- "learning_rate": 0.0001229591836734694,
- "loss": 1.3221,
+ "epoch": 6.82,
+ "learning_rate": 0.00011420454545454547,
+ "loss": 0.8476,
"step": 604
},
{
- "epoch": 12.24,
- "learning_rate": 0.00012283163265306124,
- "loss": 1.3458,
+ "epoch": 6.83,
+ "learning_rate": 0.0001140625,
+ "loss": 0.8368,
"step": 605
},
{
- "epoch": 12.26,
- "learning_rate": 0.00012270408163265307,
- "loss": 1.275,
+ "epoch": 6.85,
+ "learning_rate": 0.00011392045454545455,
+ "loss": 0.822,
"step": 606
},
{
- "epoch": 12.28,
- "learning_rate": 0.0001225765306122449,
- "loss": 1.3455,
+ "epoch": 6.86,
+ "learning_rate": 0.00011377840909090909,
+ "loss": 0.8107,
"step": 607
},
{
- "epoch": 12.3,
- "learning_rate": 0.00012244897959183676,
- "loss": 1.2769,
+ "epoch": 6.87,
+ "learning_rate": 0.00011363636363636365,
+ "loss": 0.8395,
"step": 608
},
{
- "epoch": 12.32,
- "learning_rate": 0.00012232142857142859,
- "loss": 1.3201,
+ "epoch": 6.88,
+ "learning_rate": 0.0001134943181818182,
+ "loss": 0.8083,
"step": 609
},
{
- "epoch": 12.34,
- "learning_rate": 0.00012219387755102042,
- "loss": 1.3073,
+ "epoch": 6.89,
+ "learning_rate": 0.00011335227272727274,
+ "loss": 0.828,
"step": 610
},
{
- "epoch": 12.36,
- "learning_rate": 0.00012206632653061225,
- "loss": 1.3103,
+ "epoch": 6.9,
+ "learning_rate": 0.00011321022727272727,
+ "loss": 0.8494,
"step": 611
},
{
- "epoch": 12.38,
- "learning_rate": 0.00012193877551020409,
- "loss": 1.4437,
+ "epoch": 6.91,
+ "learning_rate": 0.00011306818181818182,
+ "loss": 0.8169,
"step": 612
},
{
- "epoch": 12.4,
- "learning_rate": 0.00012181122448979591,
- "loss": 1.3086,
+ "epoch": 6.93,
+ "learning_rate": 0.00011292613636363636,
+ "loss": 0.8224,
"step": 613
},
{
- "epoch": 12.42,
- "learning_rate": 0.00012168367346938775,
- "loss": 1.3867,
+ "epoch": 6.94,
+ "learning_rate": 0.00011278409090909092,
+ "loss": 0.8173,
"step": 614
},
{
- "epoch": 12.44,
- "learning_rate": 0.0001215561224489796,
- "loss": 1.2565,
+ "epoch": 6.95,
+ "learning_rate": 0.00011264204545454547,
+ "loss": 0.7961,
"step": 615
},
{
- "epoch": 12.46,
- "learning_rate": 0.00012142857142857143,
- "loss": 1.335,
+ "epoch": 6.96,
+ "learning_rate": 0.00011250000000000001,
+ "loss": 0.7948,
"step": 616
},
{
- "epoch": 12.48,
- "learning_rate": 0.00012130102040816327,
- "loss": 1.3423,
+ "epoch": 6.97,
+ "learning_rate": 0.00011235795454545454,
+ "loss": 0.7746,
"step": 617
},
{
- "epoch": 12.5,
- "learning_rate": 0.00012117346938775512,
- "loss": 1.3433,
+ "epoch": 6.98,
+ "learning_rate": 0.00011221590909090909,
+ "loss": 0.8325,
"step": 618
},
{
- "epoch": 12.52,
- "learning_rate": 0.00012104591836734695,
- "loss": 1.3387,
+ "epoch": 6.99,
+ "learning_rate": 0.00011207386363636365,
+ "loss": 0.8149,
"step": 619
},
{
- "epoch": 12.55,
- "learning_rate": 0.00012091836734693878,
- "loss": 1.3923,
+ "epoch": 7.0,
+ "learning_rate": 0.00011193181818181819,
+ "loss": 0.7516,
"step": 620
},
{
- "epoch": 12.57,
- "learning_rate": 0.00012079081632653062,
- "loss": 1.3774,
+ "epoch": 7.02,
+ "learning_rate": 0.00011178977272727274,
+ "loss": 0.7571,
"step": 621
},
{
- "epoch": 12.59,
- "learning_rate": 0.00012066326530612247,
- "loss": 1.3203,
+ "epoch": 7.03,
+ "learning_rate": 0.00011164772727272728,
+ "loss": 0.7397,
"step": 622
},
{
- "epoch": 12.61,
- "learning_rate": 0.00012053571428571429,
- "loss": 1.2924,
+ "epoch": 7.04,
+ "learning_rate": 0.00011150568181818181,
+ "loss": 0.761,
"step": 623
},
{
- "epoch": 12.63,
- "learning_rate": 0.00012040816326530613,
- "loss": 1.3292,
+ "epoch": 7.05,
+ "learning_rate": 0.00011136363636363636,
+ "loss": 0.7783,
"step": 624
},
{
- "epoch": 12.65,
- "learning_rate": 0.00012028061224489798,
- "loss": 1.3161,
+ "epoch": 7.06,
+ "learning_rate": 0.00011122159090909092,
+ "loss": 0.7571,
"step": 625
},
{
- "epoch": 12.67,
- "learning_rate": 0.00012015306122448979,
- "loss": 1.352,
+ "epoch": 7.07,
+ "learning_rate": 0.00011107954545454546,
+ "loss": 0.7628,
"step": 626
},
{
- "epoch": 12.69,
- "learning_rate": 0.00012002551020408164,
- "loss": 1.3577,
+ "epoch": 7.08,
+ "learning_rate": 0.0001109375,
+ "loss": 0.7561,
"step": 627
},
{
- "epoch": 12.71,
- "learning_rate": 0.00011989795918367348,
- "loss": 1.3575,
+ "epoch": 7.09,
+ "learning_rate": 0.00011079545454545455,
+ "loss": 0.7432,
"step": 628
},
{
- "epoch": 12.73,
- "learning_rate": 0.0001197704081632653,
- "loss": 1.3727,
+ "epoch": 7.11,
+ "learning_rate": 0.00011065340909090908,
+ "loss": 0.7245,
"step": 629
},
{
- "epoch": 12.75,
- "learning_rate": 0.00011964285714285714,
- "loss": 1.3312,
+ "epoch": 7.12,
+ "learning_rate": 0.00011051136363636366,
+ "loss": 0.7279,
"step": 630
},
{
- "epoch": 12.77,
- "learning_rate": 0.00011951530612244899,
- "loss": 1.3378,
+ "epoch": 7.13,
+ "learning_rate": 0.00011036931818181819,
+ "loss": 0.7347,
"step": 631
},
{
- "epoch": 12.79,
- "learning_rate": 0.00011938775510204083,
- "loss": 1.295,
+ "epoch": 7.14,
+ "learning_rate": 0.00011022727272727273,
+ "loss": 0.7427,
"step": 632
},
{
- "epoch": 12.81,
- "learning_rate": 0.00011926020408163265,
- "loss": 1.3447,
+ "epoch": 7.15,
+ "learning_rate": 0.00011008522727272728,
+ "loss": 0.7339,
"step": 633
},
{
- "epoch": 12.83,
- "learning_rate": 0.0001191326530612245,
- "loss": 1.3835,
+ "epoch": 7.16,
+ "learning_rate": 0.00010994318181818182,
+ "loss": 0.7375,
"step": 634
},
{
- "epoch": 12.85,
- "learning_rate": 0.00011900510204081634,
- "loss": 1.3222,
+ "epoch": 7.17,
+ "learning_rate": 0.00010980113636363635,
+ "loss": 0.7182,
"step": 635
},
{
- "epoch": 12.87,
- "learning_rate": 0.00011887755102040817,
- "loss": 1.2851,
+ "epoch": 7.19,
+ "learning_rate": 0.00010965909090909093,
+ "loss": 0.7452,
"step": 636
},
{
- "epoch": 12.89,
- "learning_rate": 0.00011875,
- "loss": 1.2723,
+ "epoch": 7.2,
+ "learning_rate": 0.00010951704545454546,
+ "loss": 0.7565,
"step": 637
},
{
- "epoch": 12.91,
- "learning_rate": 0.00011862244897959184,
- "loss": 1.3924,
+ "epoch": 7.21,
+ "learning_rate": 0.000109375,
+ "loss": 0.7296,
"step": 638
},
{
- "epoch": 12.93,
- "learning_rate": 0.00011849489795918368,
- "loss": 1.4625,
+ "epoch": 7.22,
+ "learning_rate": 0.00010923295454545455,
+ "loss": 0.7484,
"step": 639
},
{
- "epoch": 12.95,
- "learning_rate": 0.00011836734693877552,
- "loss": 1.3245,
+ "epoch": 7.23,
+ "learning_rate": 0.00010909090909090909,
+ "loss": 0.732,
"step": 640
},
{
- "epoch": 12.97,
- "learning_rate": 0.00011823979591836736,
- "loss": 1.4042,
+ "epoch": 7.24,
+ "learning_rate": 0.00010894886363636365,
+ "loss": 0.7415,
"step": 641
},
{
- "epoch": 12.99,
- "learning_rate": 0.00011811224489795918,
- "loss": 1.3761,
+ "epoch": 7.25,
+ "learning_rate": 0.0001088068181818182,
+ "loss": 0.7344,
"step": 642
},
{
- "epoch": 13.01,
- "learning_rate": 0.00011798469387755103,
- "loss": 1.3376,
+ "epoch": 7.26,
+ "learning_rate": 0.00010866477272727274,
+ "loss": 0.7267,
"step": 643
},
{
- "epoch": 13.03,
- "learning_rate": 0.00011785714285714287,
- "loss": 1.2174,
+ "epoch": 7.28,
+ "learning_rate": 0.00010852272727272727,
+ "loss": 0.7543,
"step": 644
},
{
- "epoch": 13.05,
- "learning_rate": 0.00011772959183673471,
- "loss": 1.3602,
+ "epoch": 7.29,
+ "learning_rate": 0.00010838068181818182,
+ "loss": 0.7266,
"step": 645
},
{
- "epoch": 13.07,
- "learning_rate": 0.00011760204081632653,
- "loss": 1.3002,
+ "epoch": 7.3,
+ "learning_rate": 0.00010823863636363636,
+ "loss": 0.7449,
"step": 646
},
{
- "epoch": 13.09,
- "learning_rate": 0.00011747448979591838,
- "loss": 1.2262,
+ "epoch": 7.31,
+ "learning_rate": 0.00010809659090909092,
+ "loss": 0.7324,
"step": 647
},
{
- "epoch": 13.11,
- "learning_rate": 0.00011734693877551022,
- "loss": 1.3048,
+ "epoch": 7.32,
+ "learning_rate": 0.00010795454545454547,
+ "loss": 0.7268,
"step": 648
},
{
- "epoch": 13.13,
- "learning_rate": 0.00011721938775510204,
- "loss": 1.2231,
+ "epoch": 7.33,
+ "learning_rate": 0.00010781250000000001,
+ "loss": 0.7172,
"step": 649
},
{
- "epoch": 13.15,
- "learning_rate": 0.00011709183673469388,
- "loss": 1.2996,
+ "epoch": 7.34,
+ "learning_rate": 0.00010767045454545454,
+ "loss": 0.7169,
"step": 650
},
{
- "epoch": 13.17,
- "learning_rate": 0.00011696428571428573,
- "loss": 1.2708,
+ "epoch": 7.35,
+ "learning_rate": 0.00010752840909090909,
+ "loss": 0.7194,
"step": 651
},
{
- "epoch": 13.19,
- "learning_rate": 0.00011683673469387754,
- "loss": 1.2776,
+ "epoch": 7.37,
+ "learning_rate": 0.00010738636363636365,
+ "loss": 0.7223,
"step": 652
},
{
- "epoch": 13.21,
- "learning_rate": 0.00011670918367346939,
- "loss": 1.248,
+ "epoch": 7.38,
+ "learning_rate": 0.00010724431818181819,
+ "loss": 0.7158,
"step": 653
},
{
- "epoch": 13.23,
- "learning_rate": 0.00011658163265306123,
- "loss": 1.2582,
+ "epoch": 7.39,
+ "learning_rate": 0.00010710227272727274,
+ "loss": 0.7122,
"step": 654
},
{
- "epoch": 13.25,
- "learning_rate": 0.00011645408163265305,
- "loss": 1.3011,
+ "epoch": 7.4,
+ "learning_rate": 0.00010696022727272728,
+ "loss": 0.7225,
"step": 655
},
{
- "epoch": 13.27,
- "learning_rate": 0.0001163265306122449,
- "loss": 1.2969,
+ "epoch": 7.41,
+ "learning_rate": 0.00010681818181818181,
+ "loss": 0.7102,
"step": 656
},
{
- "epoch": 13.29,
- "learning_rate": 0.00011619897959183674,
- "loss": 1.2454,
+ "epoch": 7.42,
+ "learning_rate": 0.00010667613636363636,
+ "loss": 0.7251,
"step": 657
},
{
- "epoch": 13.31,
- "learning_rate": 0.00011607142857142858,
- "loss": 1.1914,
+ "epoch": 7.43,
+ "learning_rate": 0.00010653409090909092,
+ "loss": 0.7191,
"step": 658
},
{
- "epoch": 13.33,
- "learning_rate": 0.00011594387755102041,
- "loss": 1.34,
+ "epoch": 7.45,
+ "learning_rate": 0.00010639204545454546,
+ "loss": 0.7015,
"step": 659
},
{
- "epoch": 13.35,
- "learning_rate": 0.00011581632653061225,
- "loss": 1.2828,
+ "epoch": 7.46,
+ "learning_rate": 0.00010625000000000001,
+ "loss": 0.693,
"step": 660
},
{
- "epoch": 13.37,
- "learning_rate": 0.00011568877551020409,
- "loss": 1.2962,
+ "epoch": 7.47,
+ "learning_rate": 0.00010610795454545455,
+ "loss": 0.7039,
"step": 661
},
{
- "epoch": 13.39,
- "learning_rate": 0.00011556122448979592,
- "loss": 1.3334,
+ "epoch": 7.48,
+ "learning_rate": 0.00010596590909090908,
+ "loss": 0.7305,
"step": 662
},
{
- "epoch": 13.42,
- "learning_rate": 0.00011543367346938776,
- "loss": 1.2832,
+ "epoch": 7.49,
+ "learning_rate": 0.00010582386363636366,
+ "loss": 0.6978,
"step": 663
},
{
- "epoch": 13.44,
- "learning_rate": 0.00011530612244897961,
- "loss": 1.3012,
+ "epoch": 7.5,
+ "learning_rate": 0.00010568181818181819,
+ "loss": 0.7219,
"step": 664
},
{
- "epoch": 13.46,
- "learning_rate": 0.00011517857142857143,
- "loss": 1.2857,
+ "epoch": 7.51,
+ "learning_rate": 0.00010553977272727273,
+ "loss": 0.7199,
"step": 665
},
{
- "epoch": 13.48,
- "learning_rate": 0.00011505102040816327,
- "loss": 1.2855,
+ "epoch": 7.52,
+ "learning_rate": 0.00010539772727272728,
+ "loss": 0.6979,
"step": 666
},
{
- "epoch": 13.5,
- "learning_rate": 0.00011492346938775512,
- "loss": 1.3077,
+ "epoch": 7.54,
+ "learning_rate": 0.00010525568181818182,
+ "loss": 0.7058,
"step": 667
},
{
- "epoch": 13.52,
- "learning_rate": 0.00011479591836734696,
- "loss": 1.3139,
+ "epoch": 7.55,
+ "learning_rate": 0.00010511363636363635,
+ "loss": 0.6994,
"step": 668
},
{
- "epoch": 13.54,
- "learning_rate": 0.00011466836734693878,
- "loss": 1.3138,
+ "epoch": 7.56,
+ "learning_rate": 0.00010497159090909093,
+ "loss": 0.7141,
"step": 669
},
{
- "epoch": 13.56,
- "learning_rate": 0.00011454081632653062,
- "loss": 1.2808,
+ "epoch": 7.57,
+ "learning_rate": 0.00010482954545454546,
+ "loss": 0.7092,
"step": 670
},
{
- "epoch": 13.58,
- "learning_rate": 0.00011441326530612247,
- "loss": 1.2492,
+ "epoch": 7.58,
+ "learning_rate": 0.0001046875,
+ "loss": 0.7059,
"step": 671
},
{
- "epoch": 13.6,
- "learning_rate": 0.00011428571428571428,
- "loss": 1.2027,
+ "epoch": 7.59,
+ "learning_rate": 0.00010454545454545455,
+ "loss": 0.6904,
"step": 672
},
{
- "epoch": 13.62,
- "learning_rate": 0.00011415816326530613,
- "loss": 1.33,
+ "epoch": 7.6,
+ "learning_rate": 0.0001044034090909091,
+ "loss": 0.7115,
"step": 673
},
{
- "epoch": 13.64,
- "learning_rate": 0.00011403061224489797,
- "loss": 1.3112,
+ "epoch": 7.61,
+ "learning_rate": 0.00010426136363636365,
+ "loss": 0.7254,
"step": 674
},
{
- "epoch": 13.66,
- "learning_rate": 0.00011390306122448979,
- "loss": 1.2772,
+ "epoch": 7.63,
+ "learning_rate": 0.0001041193181818182,
+ "loss": 0.7181,
"step": 675
},
{
- "epoch": 13.68,
- "learning_rate": 0.00011377551020408163,
- "loss": 1.2701,
+ "epoch": 7.64,
+ "learning_rate": 0.00010397727272727273,
+ "loss": 0.6867,
"step": 676
},
{
- "epoch": 13.7,
- "learning_rate": 0.00011364795918367348,
- "loss": 1.1973,
+ "epoch": 7.65,
+ "learning_rate": 0.00010383522727272727,
+ "loss": 0.6917,
"step": 677
},
{
- "epoch": 13.72,
- "learning_rate": 0.0001135204081632653,
- "loss": 1.3124,
+ "epoch": 7.66,
+ "learning_rate": 0.00010369318181818182,
+ "loss": 0.6908,
"step": 678
},
{
- "epoch": 13.74,
- "learning_rate": 0.00011339285714285714,
- "loss": 1.3085,
+ "epoch": 7.67,
+ "learning_rate": 0.00010355113636363636,
+ "loss": 0.6871,
"step": 679
},
{
- "epoch": 13.76,
- "learning_rate": 0.00011326530612244898,
- "loss": 1.3457,
+ "epoch": 7.68,
+ "learning_rate": 0.00010340909090909092,
+ "loss": 0.682,
"step": 680
},
{
- "epoch": 13.78,
- "learning_rate": 0.00011313775510204083,
- "loss": 1.3338,
+ "epoch": 7.69,
+ "learning_rate": 0.00010326704545454547,
+ "loss": 0.6737,
"step": 681
},
{
- "epoch": 13.8,
- "learning_rate": 0.00011301020408163266,
- "loss": 1.2753,
+ "epoch": 7.7,
+ "learning_rate": 0.000103125,
+ "loss": 0.7023,
"step": 682
},
{
- "epoch": 13.82,
- "learning_rate": 0.00011288265306122449,
- "loss": 1.2786,
+ "epoch": 7.72,
+ "learning_rate": 0.00010298295454545454,
+ "loss": 0.7079,
"step": 683
},
{
- "epoch": 13.84,
- "learning_rate": 0.00011275510204081634,
- "loss": 1.2584,
+ "epoch": 7.73,
+ "learning_rate": 0.00010284090909090909,
+ "loss": 0.6954,
"step": 684
},
{
- "epoch": 13.86,
- "learning_rate": 0.00011262755102040817,
- "loss": 1.2779,
+ "epoch": 7.74,
+ "learning_rate": 0.00010269886363636365,
+ "loss": 0.6834,
"step": 685
},
{
- "epoch": 13.88,
- "learning_rate": 0.00011250000000000001,
- "loss": 1.3502,
+ "epoch": 7.75,
+ "learning_rate": 0.0001025568181818182,
+ "loss": 0.6706,
"step": 686
},
{
- "epoch": 13.9,
- "learning_rate": 0.00011237244897959185,
- "loss": 1.3251,
+ "epoch": 7.76,
+ "learning_rate": 0.00010241477272727274,
+ "loss": 0.6706,
"step": 687
},
{
- "epoch": 13.92,
- "learning_rate": 0.00011224489795918367,
- "loss": 1.273,
+ "epoch": 7.77,
+ "learning_rate": 0.00010227272727272727,
+ "loss": 0.681,
"step": 688
},
{
- "epoch": 13.94,
- "learning_rate": 0.00011211734693877552,
- "loss": 1.3341,
+ "epoch": 7.78,
+ "learning_rate": 0.00010213068181818182,
+ "loss": 0.6853,
"step": 689
},
{
- "epoch": 13.96,
- "learning_rate": 0.00011198979591836736,
- "loss": 1.2654,
+ "epoch": 7.8,
+ "learning_rate": 0.00010198863636363636,
+ "loss": 0.6772,
"step": 690
},
{
- "epoch": 13.98,
- "learning_rate": 0.00011186224489795918,
- "loss": 1.3333,
+ "epoch": 7.81,
+ "learning_rate": 0.00010184659090909092,
+ "loss": 0.6635,
"step": 691
},
{
- "epoch": 14.0,
- "learning_rate": 0.00011173469387755102,
- "loss": 1.3246,
+ "epoch": 7.82,
+ "learning_rate": 0.00010170454545454546,
+ "loss": 0.6712,
"step": 692
},
{
- "epoch": 14.02,
- "learning_rate": 0.00011160714285714287,
- "loss": 1.2547,
+ "epoch": 7.83,
+ "learning_rate": 0.00010156250000000001,
+ "loss": 0.6884,
"step": 693
},
{
- "epoch": 14.04,
- "learning_rate": 0.00011147959183673471,
- "loss": 1.208,
+ "epoch": 7.84,
+ "learning_rate": 0.00010142045454545454,
+ "loss": 0.6641,
"step": 694
},
{
- "epoch": 14.06,
- "learning_rate": 0.00011135204081632653,
- "loss": 1.223,
+ "epoch": 7.85,
+ "learning_rate": 0.00010127840909090909,
+ "loss": 0.6838,
"step": 695
},
{
- "epoch": 14.08,
- "learning_rate": 0.00011122448979591837,
- "loss": 1.2483,
+ "epoch": 7.86,
+ "learning_rate": 0.00010113636363636366,
+ "loss": 0.675,
"step": 696
},
{
- "epoch": 14.1,
- "learning_rate": 0.00011109693877551022,
- "loss": 1.2823,
+ "epoch": 7.87,
+ "learning_rate": 0.00010099431818181819,
+ "loss": 0.6626,
"step": 697
},
{
- "epoch": 14.12,
- "learning_rate": 0.00011096938775510204,
- "loss": 1.2013,
+ "epoch": 7.89,
+ "learning_rate": 0.00010085227272727273,
+ "loss": 0.6605,
"step": 698
},
{
- "epoch": 14.14,
- "learning_rate": 0.00011084183673469388,
- "loss": 1.1883,
+ "epoch": 7.9,
+ "learning_rate": 0.00010071022727272728,
+ "loss": 0.6777,
"step": 699
},
{
- "epoch": 14.16,
- "learning_rate": 0.00011071428571428572,
- "loss": 1.2364,
+ "epoch": 7.91,
+ "learning_rate": 0.00010056818181818181,
+ "loss": 0.6347,
"step": 700
},
{
- "epoch": 14.18,
- "learning_rate": 0.00011058673469387754,
- "loss": 1.2069,
+ "epoch": 7.92,
+ "learning_rate": 0.00010042613636363636,
+ "loss": 0.6857,
"step": 701
},
{
- "epoch": 14.2,
- "learning_rate": 0.00011045918367346939,
- "loss": 1.1968,
+ "epoch": 7.93,
+ "learning_rate": 0.00010028409090909093,
+ "loss": 0.6677,
"step": 702
},
{
- "epoch": 14.22,
- "learning_rate": 0.00011033163265306123,
- "loss": 1.2236,
+ "epoch": 7.94,
+ "learning_rate": 0.00010014204545454546,
+ "loss": 0.6697,
"step": 703
},
{
- "epoch": 14.24,
- "learning_rate": 0.00011020408163265306,
- "loss": 1.1942,
+ "epoch": 7.95,
+ "learning_rate": 0.0001,
+ "loss": 0.6375,
"step": 704
},
{
- "epoch": 14.26,
- "learning_rate": 0.0001100765306122449,
- "loss": 1.2561,
+ "epoch": 7.96,
+ "learning_rate": 9.985795454545455e-05,
+ "loss": 0.6572,
"step": 705
},
{
- "epoch": 14.29,
- "learning_rate": 0.00010994897959183674,
- "loss": 1.1839,
+ "epoch": 7.98,
+ "learning_rate": 9.97159090909091e-05,
+ "loss": 0.668,
"step": 706
},
{
- "epoch": 14.31,
- "learning_rate": 0.00010982142857142858,
- "loss": 1.2128,
+ "epoch": 7.99,
+ "learning_rate": 9.957386363636364e-05,
+ "loss": 0.6797,
"step": 707
},
{
- "epoch": 14.33,
- "learning_rate": 0.00010969387755102041,
- "loss": 1.3086,
+ "epoch": 8.0,
+ "learning_rate": 9.943181818181819e-05,
+ "loss": 0.6784,
"step": 708
},
{
- "epoch": 14.35,
- "learning_rate": 0.00010956632653061226,
- "loss": 1.2379,
+ "epoch": 8.01,
+ "learning_rate": 9.928977272727273e-05,
+ "loss": 0.6192,
"step": 709
},
{
- "epoch": 14.37,
- "learning_rate": 0.0001094387755102041,
- "loss": 1.176,
+ "epoch": 8.02,
+ "learning_rate": 9.914772727272728e-05,
+ "loss": 0.6287,
"step": 710
},
{
- "epoch": 14.39,
- "learning_rate": 0.00010931122448979592,
- "loss": 1.2105,
+ "epoch": 8.03,
+ "learning_rate": 9.900568181818183e-05,
+ "loss": 0.6034,
"step": 711
},
{
- "epoch": 14.41,
- "learning_rate": 0.00010918367346938776,
- "loss": 1.2149,
+ "epoch": 8.04,
+ "learning_rate": 9.886363636363637e-05,
+ "loss": 0.6167,
"step": 712
},
{
- "epoch": 14.43,
- "learning_rate": 0.0001090561224489796,
- "loss": 1.2392,
+ "epoch": 8.06,
+ "learning_rate": 9.872159090909091e-05,
+ "loss": 0.6353,
"step": 713
},
{
- "epoch": 14.45,
- "learning_rate": 0.00010892857142857142,
- "loss": 1.2471,
+ "epoch": 8.07,
+ "learning_rate": 9.857954545454547e-05,
+ "loss": 0.6222,
"step": 714
},
{
- "epoch": 14.47,
- "learning_rate": 0.00010880102040816327,
- "loss": 1.2561,
+ "epoch": 8.08,
+ "learning_rate": 9.84375e-05,
+ "loss": 0.5963,
"step": 715
},
{
- "epoch": 14.49,
- "learning_rate": 0.00010867346938775511,
- "loss": 1.2179,
+ "epoch": 8.09,
+ "learning_rate": 9.829545454545455e-05,
+ "loss": 0.6042,
"step": 716
},
{
- "epoch": 14.51,
- "learning_rate": 0.00010854591836734696,
- "loss": 1.2459,
+ "epoch": 8.1,
+ "learning_rate": 9.81534090909091e-05,
+ "loss": 0.612,
"step": 717
},
{
- "epoch": 14.53,
- "learning_rate": 0.00010841836734693877,
- "loss": 1.2933,
+ "epoch": 8.11,
+ "learning_rate": 9.801136363636364e-05,
+ "loss": 0.6069,
"step": 718
},
{
- "epoch": 14.55,
- "learning_rate": 0.00010829081632653062,
- "loss": 1.2862,
+ "epoch": 8.12,
+ "learning_rate": 9.786931818181818e-05,
+ "loss": 0.6001,
"step": 719
},
{
- "epoch": 14.57,
- "learning_rate": 0.00010816326530612246,
- "loss": 1.2976,
+ "epoch": 8.13,
+ "learning_rate": 9.772727272727274e-05,
+ "loss": 0.6007,
"step": 720
},
{
- "epoch": 14.59,
- "learning_rate": 0.00010803571428571428,
- "loss": 1.231,
+ "epoch": 8.15,
+ "learning_rate": 9.758522727272727e-05,
+ "loss": 0.6079,
"step": 721
},
{
- "epoch": 14.61,
- "learning_rate": 0.00010790816326530613,
- "loss": 1.2464,
+ "epoch": 8.16,
+ "learning_rate": 9.744318181818183e-05,
+ "loss": 0.6216,
"step": 722
},
{
- "epoch": 14.63,
- "learning_rate": 0.00010778061224489797,
- "loss": 1.2181,
+ "epoch": 8.17,
+ "learning_rate": 9.730113636363637e-05,
+ "loss": 0.6321,
"step": 723
},
{
- "epoch": 14.65,
- "learning_rate": 0.00010765306122448979,
- "loss": 1.3307,
+ "epoch": 8.18,
+ "learning_rate": 9.71590909090909e-05,
+ "loss": 0.6044,
"step": 724
},
{
- "epoch": 14.67,
- "learning_rate": 0.00010752551020408163,
- "loss": 1.1723,
+ "epoch": 8.19,
+ "learning_rate": 9.701704545454547e-05,
+ "loss": 0.6028,
"step": 725
},
{
- "epoch": 14.69,
- "learning_rate": 0.00010739795918367348,
- "loss": 1.1528,
+ "epoch": 8.2,
+ "learning_rate": 9.687500000000001e-05,
+ "loss": 0.6098,
"step": 726
},
{
- "epoch": 14.71,
- "learning_rate": 0.0001072704081632653,
- "loss": 1.215,
+ "epoch": 8.21,
+ "learning_rate": 9.673295454545454e-05,
+ "loss": 0.6032,
"step": 727
},
{
- "epoch": 14.73,
- "learning_rate": 0.00010714285714285715,
- "loss": 1.2624,
+ "epoch": 8.22,
+ "learning_rate": 9.65909090909091e-05,
+ "loss": 0.6298,
"step": 728
},
{
- "epoch": 14.75,
- "learning_rate": 0.00010701530612244898,
- "loss": 1.3117,
+ "epoch": 8.24,
+ "learning_rate": 9.644886363636365e-05,
+ "loss": 0.6115,
"step": 729
},
{
- "epoch": 14.77,
- "learning_rate": 0.00010688775510204083,
- "loss": 1.2572,
+ "epoch": 8.25,
+ "learning_rate": 9.630681818181818e-05,
+ "loss": 0.6052,
"step": 730
},
{
- "epoch": 14.79,
- "learning_rate": 0.00010676020408163266,
- "loss": 1.222,
+ "epoch": 8.26,
+ "learning_rate": 9.616477272727274e-05,
+ "loss": 0.6097,
"step": 731
},
{
- "epoch": 14.81,
- "learning_rate": 0.0001066326530612245,
- "loss": 1.2881,
+ "epoch": 8.27,
+ "learning_rate": 9.602272727272728e-05,
+ "loss": 0.6062,
"step": 732
},
{
- "epoch": 14.83,
- "learning_rate": 0.00010650510204081635,
- "loss": 1.2676,
+ "epoch": 8.28,
+ "learning_rate": 9.588068181818183e-05,
+ "loss": 0.5984,
"step": 733
},
{
- "epoch": 14.85,
- "learning_rate": 0.00010637755102040816,
- "loss": 1.2734,
+ "epoch": 8.29,
+ "learning_rate": 9.573863636363637e-05,
+ "loss": 0.6432,
"step": 734
},
{
- "epoch": 14.87,
- "learning_rate": 0.00010625000000000001,
- "loss": 1.2885,
+ "epoch": 8.3,
+ "learning_rate": 9.559659090909092e-05,
+ "loss": 0.5814,
"step": 735
},
{
- "epoch": 14.89,
- "learning_rate": 0.00010612244897959185,
- "loss": 1.2764,
+ "epoch": 8.31,
+ "learning_rate": 9.545454545454546e-05,
+ "loss": 0.5965,
"step": 736
},
{
- "epoch": 14.91,
- "learning_rate": 0.00010599489795918367,
- "loss": 1.3267,
+ "epoch": 8.33,
+ "learning_rate": 9.53125e-05,
+ "loss": 0.6102,
"step": 737
},
{
- "epoch": 14.93,
- "learning_rate": 0.00010586734693877551,
- "loss": 1.2445,
+ "epoch": 8.34,
+ "learning_rate": 9.517045454545455e-05,
+ "loss": 0.5849,
"step": 738
},
{
- "epoch": 14.95,
- "learning_rate": 0.00010573979591836736,
- "loss": 1.3359,
+ "epoch": 8.35,
+ "learning_rate": 9.50284090909091e-05,
+ "loss": 0.6062,
"step": 739
},
{
- "epoch": 14.97,
- "learning_rate": 0.00010561224489795918,
- "loss": 1.2508,
+ "epoch": 8.36,
+ "learning_rate": 9.488636363636364e-05,
+ "loss": 0.6031,
"step": 740
},
{
- "epoch": 14.99,
- "learning_rate": 0.00010548469387755102,
- "loss": 1.2227,
+ "epoch": 8.37,
+ "learning_rate": 9.474431818181819e-05,
+ "loss": 0.5932,
"step": 741
},
{
- "epoch": 15.01,
- "learning_rate": 0.00010535714285714286,
- "loss": 1.1889,
+ "epoch": 8.38,
+ "learning_rate": 9.460227272727273e-05,
+ "loss": 0.589,
"step": 742
},
{
- "epoch": 15.03,
- "learning_rate": 0.00010522959183673471,
- "loss": 1.1919,
+ "epoch": 8.39,
+ "learning_rate": 9.446022727272728e-05,
+ "loss": 0.6096,
"step": 743
},
{
- "epoch": 15.05,
- "learning_rate": 0.00010510204081632653,
- "loss": 1.2383,
+ "epoch": 8.41,
+ "learning_rate": 9.431818181818182e-05,
+ "loss": 0.601,
"step": 744
},
{
- "epoch": 15.07,
- "learning_rate": 0.00010497448979591837,
- "loss": 1.2401,
+ "epoch": 8.42,
+ "learning_rate": 9.417613636363637e-05,
+ "loss": 0.5798,
"step": 745
},
{
- "epoch": 15.09,
- "learning_rate": 0.00010484693877551021,
- "loss": 1.2015,
+ "epoch": 8.43,
+ "learning_rate": 9.403409090909091e-05,
+ "loss": 0.59,
"step": 746
},
{
- "epoch": 15.11,
- "learning_rate": 0.00010471938775510203,
- "loss": 1.1509,
+ "epoch": 8.44,
+ "learning_rate": 9.389204545454546e-05,
+ "loss": 0.5988,
"step": 747
},
{
- "epoch": 15.13,
- "learning_rate": 0.00010459183673469388,
- "loss": 1.1878,
+ "epoch": 8.45,
+ "learning_rate": 9.375e-05,
+ "loss": 0.5591,
"step": 748
},
{
- "epoch": 15.16,
- "learning_rate": 0.00010446428571428572,
- "loss": 1.1706,
+ "epoch": 8.46,
+ "learning_rate": 9.360795454545455e-05,
+ "loss": 0.5939,
"step": 749
},
{
- "epoch": 15.18,
- "learning_rate": 0.00010433673469387755,
- "loss": 1.1285,
+ "epoch": 8.47,
+ "learning_rate": 9.346590909090909e-05,
+ "loss": 0.5886,
"step": 750
},
{
- "epoch": 15.2,
- "learning_rate": 0.0001042091836734694,
- "loss": 1.1608,
+ "epoch": 8.48,
+ "learning_rate": 9.332386363636364e-05,
+ "loss": 0.5994,
"step": 751
},
{
- "epoch": 15.22,
- "learning_rate": 0.00010408163265306123,
- "loss": 1.1178,
+ "epoch": 8.5,
+ "learning_rate": 9.318181818181818e-05,
+ "loss": 0.5821,
"step": 752
},
{
- "epoch": 15.24,
- "learning_rate": 0.00010395408163265306,
- "loss": 1.1293,
+ "epoch": 8.51,
+ "learning_rate": 9.303977272727273e-05,
+ "loss": 0.602,
"step": 753
},
{
- "epoch": 15.26,
- "learning_rate": 0.0001038265306122449,
- "loss": 1.2306,
+ "epoch": 8.52,
+ "learning_rate": 9.289772727272727e-05,
+ "loss": 0.5708,
"step": 754
},
{
- "epoch": 15.28,
- "learning_rate": 0.00010369897959183675,
- "loss": 1.1541,
+ "epoch": 8.53,
+ "learning_rate": 9.275568181818183e-05,
+ "loss": 0.5902,
"step": 755
},
{
- "epoch": 15.3,
- "learning_rate": 0.00010357142857142859,
- "loss": 1.1702,
+ "epoch": 8.54,
+ "learning_rate": 9.261363636363636e-05,
+ "loss": 0.6053,
"step": 756
},
{
- "epoch": 15.32,
- "learning_rate": 0.00010344387755102041,
- "loss": 1.2119,
+ "epoch": 8.55,
+ "learning_rate": 9.247159090909091e-05,
+ "loss": 0.5797,
"step": 757
},
{
- "epoch": 15.34,
- "learning_rate": 0.00010331632653061225,
- "loss": 1.2239,
+ "epoch": 8.56,
+ "learning_rate": 9.232954545454547e-05,
+ "loss": 0.5965,
"step": 758
},
{
- "epoch": 15.36,
- "learning_rate": 0.0001031887755102041,
- "loss": 1.2019,
+ "epoch": 8.57,
+ "learning_rate": 9.21875e-05,
+ "loss": 0.5738,
"step": 759
},
{
- "epoch": 15.38,
- "learning_rate": 0.00010306122448979591,
- "loss": 1.2197,
+ "epoch": 8.59,
+ "learning_rate": 9.204545454545454e-05,
+ "loss": 0.5819,
"step": 760
},
{
- "epoch": 15.4,
- "learning_rate": 0.00010293367346938776,
- "loss": 1.1769,
+ "epoch": 8.6,
+ "learning_rate": 9.19034090909091e-05,
+ "loss": 0.5994,
"step": 761
},
{
- "epoch": 15.42,
- "learning_rate": 0.0001028061224489796,
- "loss": 1.1907,
+ "epoch": 8.61,
+ "learning_rate": 9.176136363636363e-05,
+ "loss": 0.5738,
"step": 762
},
{
- "epoch": 15.44,
- "learning_rate": 0.00010267857142857142,
- "loss": 1.2089,
+ "epoch": 8.62,
+ "learning_rate": 9.161931818181818e-05,
+ "loss": 0.5663,
"step": 763
},
{
- "epoch": 15.46,
- "learning_rate": 0.00010255102040816327,
- "loss": 1.1335,
+ "epoch": 8.63,
+ "learning_rate": 9.147727272727274e-05,
+ "loss": 0.5798,
"step": 764
},
{
- "epoch": 15.48,
- "learning_rate": 0.00010242346938775511,
- "loss": 1.1633,
+ "epoch": 8.64,
+ "learning_rate": 9.133522727272727e-05,
+ "loss": 0.5705,
"step": 765
},
{
- "epoch": 15.5,
- "learning_rate": 0.00010229591836734695,
- "loss": 1.1578,
+ "epoch": 8.65,
+ "learning_rate": 9.119318181818183e-05,
+ "loss": 0.5943,
"step": 766
},
{
- "epoch": 15.52,
- "learning_rate": 0.00010216836734693877,
- "loss": 1.2236,
+ "epoch": 8.67,
+ "learning_rate": 9.105113636363637e-05,
+ "loss": 0.6019,
"step": 767
},
{
- "epoch": 15.54,
- "learning_rate": 0.00010204081632653062,
- "loss": 1.1941,
+ "epoch": 8.68,
+ "learning_rate": 9.090909090909092e-05,
+ "loss": 0.5733,
"step": 768
},
{
- "epoch": 15.56,
- "learning_rate": 0.00010191326530612246,
- "loss": 1.2666,
+ "epoch": 8.69,
+ "learning_rate": 9.076704545454546e-05,
+ "loss": 0.575,
"step": 769
},
{
- "epoch": 15.58,
- "learning_rate": 0.00010178571428571428,
- "loss": 1.1232,
+ "epoch": 8.7,
+ "learning_rate": 9.062500000000001e-05,
+ "loss": 0.5675,
"step": 770
},
{
- "epoch": 15.6,
- "learning_rate": 0.00010165816326530612,
- "loss": 1.2242,
+ "epoch": 8.71,
+ "learning_rate": 9.048295454545455e-05,
+ "loss": 0.566,
"step": 771
},
{
- "epoch": 15.62,
- "learning_rate": 0.00010153061224489797,
- "loss": 1.1852,
+ "epoch": 8.72,
+ "learning_rate": 9.03409090909091e-05,
+ "loss": 0.5513,
"step": 772
},
{
- "epoch": 15.64,
- "learning_rate": 0.0001014030612244898,
- "loss": 1.2626,
+ "epoch": 8.73,
+ "learning_rate": 9.019886363636364e-05,
+ "loss": 0.5682,
"step": 773
},
{
- "epoch": 15.66,
- "learning_rate": 0.00010127551020408164,
- "loss": 1.1873,
+ "epoch": 8.74,
+ "learning_rate": 9.005681818181819e-05,
+ "loss": 0.5508,
"step": 774
},
{
- "epoch": 15.68,
- "learning_rate": 0.00010114795918367349,
- "loss": 1.3005,
+ "epoch": 8.76,
+ "learning_rate": 8.991477272727273e-05,
+ "loss": 0.5668,
"step": 775
},
{
- "epoch": 15.7,
- "learning_rate": 0.0001010204081632653,
- "loss": 1.1904,
+ "epoch": 8.77,
+ "learning_rate": 8.977272727272728e-05,
+ "loss": 0.569,
"step": 776
},
{
- "epoch": 15.72,
- "learning_rate": 0.00010089285714285715,
- "loss": 1.2927,
+ "epoch": 8.78,
+ "learning_rate": 8.963068181818182e-05,
+ "loss": 0.5897,
"step": 777
},
{
- "epoch": 15.74,
- "learning_rate": 0.00010076530612244899,
- "loss": 1.179,
+ "epoch": 8.79,
+ "learning_rate": 8.948863636363637e-05,
+ "loss": 0.5738,
"step": 778
},
{
- "epoch": 15.76,
- "learning_rate": 0.00010063775510204084,
- "loss": 1.2027,
+ "epoch": 8.8,
+ "learning_rate": 8.934659090909091e-05,
+ "loss": 0.5511,
"step": 779
},
{
- "epoch": 15.78,
- "learning_rate": 0.00010051020408163265,
- "loss": 1.2428,
+ "epoch": 8.81,
+ "learning_rate": 8.920454545454546e-05,
+ "loss": 0.5659,
"step": 780
},
{
- "epoch": 15.8,
- "learning_rate": 0.0001003826530612245,
- "loss": 1.2324,
+ "epoch": 8.82,
+ "learning_rate": 8.90625e-05,
+ "loss": 0.5649,
"step": 781
},
{
- "epoch": 15.82,
- "learning_rate": 0.00010025510204081634,
- "loss": 1.1251,
+ "epoch": 8.83,
+ "learning_rate": 8.892045454545455e-05,
+ "loss": 0.5618,
"step": 782
},
{
- "epoch": 15.84,
- "learning_rate": 0.00010012755102040816,
- "loss": 1.2405,
+ "epoch": 8.85,
+ "learning_rate": 8.87784090909091e-05,
+ "loss": 0.5602,
"step": 783
},
{
- "epoch": 15.86,
- "learning_rate": 0.0001,
- "loss": 1.2005,
+ "epoch": 8.86,
+ "learning_rate": 8.863636363636364e-05,
+ "loss": 0.5723,
"step": 784
},
{
- "epoch": 15.88,
- "learning_rate": 9.987244897959184e-05,
- "loss": 1.2259,
+ "epoch": 8.87,
+ "learning_rate": 8.849431818181818e-05,
+ "loss": 0.5816,
"step": 785
},
{
- "epoch": 15.9,
- "learning_rate": 9.974489795918368e-05,
- "loss": 1.1576,
+ "epoch": 8.88,
+ "learning_rate": 8.835227272727273e-05,
+ "loss": 0.555,
"step": 786
},
{
- "epoch": 15.92,
- "learning_rate": 9.961734693877551e-05,
- "loss": 1.1834,
+ "epoch": 8.89,
+ "learning_rate": 8.821022727272727e-05,
+ "loss": 0.5563,
"step": 787
},
{
- "epoch": 15.94,
- "learning_rate": 9.948979591836736e-05,
- "loss": 1.2396,
+ "epoch": 8.9,
+ "learning_rate": 8.806818181818183e-05,
+ "loss": 0.554,
"step": 788
},
{
- "epoch": 15.96,
- "learning_rate": 9.936224489795919e-05,
- "loss": 1.1865,
+ "epoch": 8.91,
+ "learning_rate": 8.792613636363636e-05,
+ "loss": 0.5671,
"step": 789
},
{
- "epoch": 15.98,
- "learning_rate": 9.923469387755102e-05,
- "loss": 1.2356,
+ "epoch": 8.92,
+ "learning_rate": 8.778409090909091e-05,
+ "loss": 0.5485,
"step": 790
},
{
- "epoch": 16.01,
- "learning_rate": 9.910714285714286e-05,
- "loss": 1.2639,
+ "epoch": 8.94,
+ "learning_rate": 8.764204545454547e-05,
+ "loss": 0.5712,
"step": 791
},
{
- "epoch": 16.03,
- "learning_rate": 9.897959183673469e-05,
- "loss": 1.1216,
+ "epoch": 8.95,
+ "learning_rate": 8.75e-05,
+ "loss": 0.5507,
"step": 792
},
{
- "epoch": 16.05,
- "learning_rate": 9.885204081632652e-05,
- "loss": 1.1051,
+ "epoch": 8.96,
+ "learning_rate": 8.735795454545454e-05,
+ "loss": 0.5718,
"step": 793
},
{
- "epoch": 16.07,
- "learning_rate": 9.872448979591837e-05,
- "loss": 1.0864,
+ "epoch": 8.97,
+ "learning_rate": 8.72159090909091e-05,
+ "loss": 0.5585,
"step": 794
},
{
- "epoch": 16.09,
- "learning_rate": 9.859693877551021e-05,
- "loss": 1.182,
+ "epoch": 8.98,
+ "learning_rate": 8.707386363636363e-05,
+ "loss": 0.5563,
"step": 795
},
{
- "epoch": 16.11,
- "learning_rate": 9.846938775510204e-05,
- "loss": 1.1272,
+ "epoch": 8.99,
+ "learning_rate": 8.693181818181818e-05,
+ "loss": 0.581,
"step": 796
},
{
- "epoch": 16.13,
- "learning_rate": 9.834183673469389e-05,
- "loss": 1.1946,
+ "epoch": 9.0,
+ "learning_rate": 8.678977272727274e-05,
+ "loss": 0.5511,
"step": 797
},
{
- "epoch": 16.15,
- "learning_rate": 9.821428571428572e-05,
- "loss": 1.0875,
+ "epoch": 9.02,
+ "learning_rate": 8.664772727272727e-05,
+ "loss": 0.5103,
"step": 798
},
{
- "epoch": 16.17,
- "learning_rate": 9.808673469387756e-05,
- "loss": 1.1671,
+ "epoch": 9.03,
+ "learning_rate": 8.650568181818183e-05,
+ "loss": 0.5323,
"step": 799
},
{
- "epoch": 16.19,
- "learning_rate": 9.79591836734694e-05,
- "loss": 1.1502,
+ "epoch": 9.04,
+ "learning_rate": 8.636363636363637e-05,
+ "loss": 0.5092,
"step": 800
},
{
- "epoch": 16.21,
- "learning_rate": 9.783163265306124e-05,
- "loss": 1.19,
+ "epoch": 9.05,
+ "learning_rate": 8.62215909090909e-05,
+ "loss": 0.5247,
"step": 801
},
{
- "epoch": 16.23,
- "learning_rate": 9.770408163265307e-05,
- "loss": 1.1258,
+ "epoch": 9.06,
+ "learning_rate": 8.607954545454546e-05,
+ "loss": 0.5403,
"step": 802
},
{
- "epoch": 16.25,
- "learning_rate": 9.75765306122449e-05,
- "loss": 1.1765,
+ "epoch": 9.07,
+ "learning_rate": 8.593750000000001e-05,
+ "loss": 0.5252,
"step": 803
},
{
- "epoch": 16.27,
- "learning_rate": 9.744897959183674e-05,
- "loss": 1.1217,
+ "epoch": 9.08,
+ "learning_rate": 8.579545454545454e-05,
+ "loss": 0.5296,
"step": 804
},
{
- "epoch": 16.29,
- "learning_rate": 9.732142857142858e-05,
- "loss": 1.1293,
+ "epoch": 9.09,
+ "learning_rate": 8.56534090909091e-05,
+ "loss": 0.5223,
"step": 805
},
{
- "epoch": 16.31,
- "learning_rate": 9.719387755102042e-05,
- "loss": 1.17,
+ "epoch": 9.11,
+ "learning_rate": 8.551136363636364e-05,
+ "loss": 0.4972,
"step": 806
},
{
- "epoch": 16.33,
- "learning_rate": 9.706632653061225e-05,
- "loss": 1.17,
+ "epoch": 9.12,
+ "learning_rate": 8.536931818181818e-05,
+ "loss": 0.5005,
"step": 807
},
{
- "epoch": 16.35,
- "learning_rate": 9.693877551020408e-05,
- "loss": 1.2004,
+ "epoch": 9.13,
+ "learning_rate": 8.522727272727273e-05,
+ "loss": 0.5249,
"step": 808
},
{
- "epoch": 16.37,
- "learning_rate": 9.681122448979593e-05,
- "loss": 1.1648,
+ "epoch": 9.14,
+ "learning_rate": 8.508522727272728e-05,
+ "loss": 0.5135,
"step": 809
},
{
- "epoch": 16.39,
- "learning_rate": 9.668367346938776e-05,
- "loss": 1.0688,
+ "epoch": 9.15,
+ "learning_rate": 8.494318181818182e-05,
+ "loss": 0.5053,
"step": 810
},
{
- "epoch": 16.41,
- "learning_rate": 9.655612244897959e-05,
- "loss": 1.1607,
+ "epoch": 9.16,
+ "learning_rate": 8.480113636363637e-05,
+ "loss": 0.5158,
"step": 811
},
{
- "epoch": 16.43,
- "learning_rate": 9.642857142857143e-05,
- "loss": 1.1298,
+ "epoch": 9.17,
+ "learning_rate": 8.465909090909091e-05,
+ "loss": 0.5061,
"step": 812
},
{
- "epoch": 16.45,
- "learning_rate": 9.630102040816326e-05,
- "loss": 1.1064,
+ "epoch": 9.18,
+ "learning_rate": 8.451704545454546e-05,
+ "loss": 0.4988,
"step": 813
},
{
- "epoch": 16.47,
- "learning_rate": 9.617346938775511e-05,
- "loss": 1.1472,
+ "epoch": 9.2,
+ "learning_rate": 8.4375e-05,
+ "loss": 0.5273,
"step": 814
},
{
- "epoch": 16.49,
- "learning_rate": 9.604591836734694e-05,
- "loss": 1.1577,
+ "epoch": 9.21,
+ "learning_rate": 8.423295454545455e-05,
+ "loss": 0.5332,
"step": 815
},
{
- "epoch": 16.51,
- "learning_rate": 9.591836734693878e-05,
- "loss": 1.1436,
+ "epoch": 9.22,
+ "learning_rate": 8.40909090909091e-05,
+ "loss": 0.5181,
"step": 816
},
{
- "epoch": 16.53,
- "learning_rate": 9.579081632653061e-05,
- "loss": 1.1657,
+ "epoch": 9.23,
+ "learning_rate": 8.394886363636364e-05,
+ "loss": 0.5085,
"step": 817
},
{
- "epoch": 16.55,
- "learning_rate": 9.566326530612246e-05,
- "loss": 1.1147,
+ "epoch": 9.24,
+ "learning_rate": 8.380681818181818e-05,
+ "loss": 0.5137,
"step": 818
},
{
- "epoch": 16.57,
- "learning_rate": 9.553571428571429e-05,
- "loss": 1.1839,
+ "epoch": 9.25,
+ "learning_rate": 8.366477272727273e-05,
+ "loss": 0.5195,
"step": 819
},
{
- "epoch": 16.59,
- "learning_rate": 9.540816326530613e-05,
- "loss": 1.1298,
+ "epoch": 9.26,
+ "learning_rate": 8.352272727272727e-05,
+ "loss": 0.5077,
"step": 820
},
{
- "epoch": 16.61,
- "learning_rate": 9.528061224489796e-05,
- "loss": 1.2141,
+ "epoch": 9.28,
+ "learning_rate": 8.338068181818183e-05,
+ "loss": 0.5074,
"step": 821
},
{
- "epoch": 16.63,
- "learning_rate": 9.515306122448981e-05,
- "loss": 1.2045,
+ "epoch": 9.29,
+ "learning_rate": 8.323863636363637e-05,
+ "loss": 0.5142,
"step": 822
},
{
- "epoch": 16.65,
- "learning_rate": 9.502551020408164e-05,
- "loss": 1.1791,
+ "epoch": 9.3,
+ "learning_rate": 8.309659090909091e-05,
+ "loss": 0.5116,
"step": 823
},
{
- "epoch": 16.67,
- "learning_rate": 9.489795918367348e-05,
- "loss": 1.1137,
+ "epoch": 9.31,
+ "learning_rate": 8.295454545454547e-05,
+ "loss": 0.4974,
"step": 824
},
{
- "epoch": 16.69,
- "learning_rate": 9.477040816326531e-05,
- "loss": 1.1312,
+ "epoch": 9.32,
+ "learning_rate": 8.28125e-05,
+ "loss": 0.5117,
"step": 825
},
{
- "epoch": 16.71,
- "learning_rate": 9.464285714285715e-05,
- "loss": 1.1102,
+ "epoch": 9.33,
+ "learning_rate": 8.267045454545455e-05,
+ "loss": 0.5114,
"step": 826
},
{
- "epoch": 16.73,
- "learning_rate": 9.451530612244899e-05,
- "loss": 1.1865,
+ "epoch": 9.34,
+ "learning_rate": 8.25284090909091e-05,
+ "loss": 0.5039,
"step": 827
},
{
- "epoch": 16.75,
- "learning_rate": 9.438775510204082e-05,
- "loss": 1.1232,
+ "epoch": 9.35,
+ "learning_rate": 8.238636363636364e-05,
+ "loss": 0.498,
"step": 828
},
{
- "epoch": 16.77,
- "learning_rate": 9.426020408163265e-05,
- "loss": 1.2068,
+ "epoch": 9.37,
+ "learning_rate": 8.224431818181818e-05,
+ "loss": 0.5042,
"step": 829
},
{
- "epoch": 16.79,
- "learning_rate": 9.41326530612245e-05,
- "loss": 1.1864,
+ "epoch": 9.38,
+ "learning_rate": 8.210227272727274e-05,
+ "loss": 0.5049,
"step": 830
},
{
- "epoch": 16.81,
- "learning_rate": 9.400510204081633e-05,
- "loss": 1.2195,
+ "epoch": 9.39,
+ "learning_rate": 8.196022727272727e-05,
+ "loss": 0.5123,
"step": 831
},
{
- "epoch": 16.83,
- "learning_rate": 9.387755102040817e-05,
- "loss": 1.2063,
+ "epoch": 9.4,
+ "learning_rate": 8.181818181818183e-05,
+ "loss": 0.4907,
"step": 832
},
{
- "epoch": 16.85,
- "learning_rate": 9.375e-05,
- "loss": 1.1455,
+ "epoch": 9.41,
+ "learning_rate": 8.167613636363637e-05,
+ "loss": 0.5267,
"step": 833
},
{
- "epoch": 16.88,
- "learning_rate": 9.362244897959183e-05,
- "loss": 1.1819,
+ "epoch": 9.42,
+ "learning_rate": 8.15340909090909e-05,
+ "loss": 0.5314,
"step": 834
},
{
- "epoch": 16.9,
- "learning_rate": 9.349489795918368e-05,
- "loss": 1.1887,
+ "epoch": 9.43,
+ "learning_rate": 8.139204545454546e-05,
+ "loss": 0.4952,
"step": 835
},
{
- "epoch": 16.92,
- "learning_rate": 9.336734693877551e-05,
- "loss": 1.1557,
+ "epoch": 9.44,
+ "learning_rate": 8.125000000000001e-05,
+ "loss": 0.5014,
"step": 836
},
{
- "epoch": 16.94,
- "learning_rate": 9.323979591836735e-05,
- "loss": 1.2094,
+ "epoch": 9.46,
+ "learning_rate": 8.110795454545454e-05,
+ "loss": 0.4967,
"step": 837
},
{
- "epoch": 16.96,
- "learning_rate": 9.311224489795918e-05,
- "loss": 1.1512,
+ "epoch": 9.47,
+ "learning_rate": 8.09659090909091e-05,
+ "loss": 0.5116,
"step": 838
},
{
- "epoch": 16.98,
- "learning_rate": 9.298469387755103e-05,
- "loss": 1.1463,
+ "epoch": 9.48,
+ "learning_rate": 8.082386363636365e-05,
+ "loss": 0.5119,
"step": 839
},
{
- "epoch": 17.0,
- "learning_rate": 9.285714285714286e-05,
- "loss": 1.155,
+ "epoch": 9.49,
+ "learning_rate": 8.068181818181818e-05,
+ "loss": 0.4987,
"step": 840
},
{
- "epoch": 17.02,
- "learning_rate": 9.27295918367347e-05,
- "loss": 1.1292,
+ "epoch": 9.5,
+ "learning_rate": 8.053977272727274e-05,
+ "loss": 0.5063,
"step": 841
},
{
- "epoch": 17.04,
- "learning_rate": 9.260204081632653e-05,
- "loss": 1.0996,
+ "epoch": 9.51,
+ "learning_rate": 8.039772727272728e-05,
+ "loss": 0.5019,
"step": 842
},
{
- "epoch": 17.06,
- "learning_rate": 9.247448979591838e-05,
- "loss": 1.0662,
+ "epoch": 9.52,
+ "learning_rate": 8.025568181818183e-05,
+ "loss": 0.5272,
"step": 843
},
{
- "epoch": 17.08,
- "learning_rate": 9.234693877551021e-05,
- "loss": 1.0931,
+ "epoch": 9.54,
+ "learning_rate": 8.011363636363637e-05,
+ "loss": 0.4969,
"step": 844
},
{
- "epoch": 17.1,
- "learning_rate": 9.221938775510205e-05,
- "loss": 1.0727,
+ "epoch": 9.55,
+ "learning_rate": 7.997159090909092e-05,
+ "loss": 0.5222,
"step": 845
},
{
- "epoch": 17.12,
- "learning_rate": 9.209183673469388e-05,
- "loss": 1.1043,
+ "epoch": 9.56,
+ "learning_rate": 7.982954545454546e-05,
+ "loss": 0.4729,
"step": 846
},
{
- "epoch": 17.14,
- "learning_rate": 9.196428571428572e-05,
- "loss": 1.0594,
+ "epoch": 9.57,
+ "learning_rate": 7.96875e-05,
+ "loss": 0.4976,
"step": 847
},
{
- "epoch": 17.16,
- "learning_rate": 9.183673469387756e-05,
- "loss": 1.0952,
+ "epoch": 9.58,
+ "learning_rate": 7.954545454545455e-05,
+ "loss": 0.4974,
"step": 848
},
{
- "epoch": 17.18,
- "learning_rate": 9.170918367346939e-05,
- "loss": 1.0639,
+ "epoch": 9.59,
+ "learning_rate": 7.94034090909091e-05,
+ "loss": 0.4849,
"step": 849
},
{
- "epoch": 17.2,
- "learning_rate": 9.158163265306124e-05,
- "loss": 1.132,
+ "epoch": 9.6,
+ "learning_rate": 7.926136363636364e-05,
+ "loss": 0.4897,
"step": 850
},
{
- "epoch": 17.22,
- "learning_rate": 9.145408163265307e-05,
- "loss": 1.1083,
+ "epoch": 9.61,
+ "learning_rate": 7.911931818181819e-05,
+ "loss": 0.4962,
"step": 851
},
{
- "epoch": 17.24,
- "learning_rate": 9.13265306122449e-05,
- "loss": 1.1282,
+ "epoch": 9.63,
+ "learning_rate": 7.897727272727273e-05,
+ "loss": 0.4877,
"step": 852
},
{
- "epoch": 17.26,
- "learning_rate": 9.119897959183674e-05,
- "loss": 1.0474,
+ "epoch": 9.64,
+ "learning_rate": 7.883522727272728e-05,
+ "loss": 0.4921,
"step": 853
},
{
- "epoch": 17.28,
- "learning_rate": 9.107142857142857e-05,
- "loss": 1.1138,
+ "epoch": 9.65,
+ "learning_rate": 7.869318181818182e-05,
+ "loss": 0.4969,
"step": 854
},
{
- "epoch": 17.3,
- "learning_rate": 9.094387755102042e-05,
- "loss": 1.1025,
+ "epoch": 9.66,
+ "learning_rate": 7.855113636363637e-05,
+ "loss": 0.5045,
"step": 855
},
{
- "epoch": 17.32,
- "learning_rate": 9.081632653061225e-05,
- "loss": 1.0968,
+ "epoch": 9.67,
+ "learning_rate": 7.840909090909091e-05,
+ "loss": 0.5207,
"step": 856
},
{
- "epoch": 17.34,
- "learning_rate": 9.068877551020408e-05,
- "loss": 1.1683,
+ "epoch": 9.68,
+ "learning_rate": 7.826704545454546e-05,
+ "loss": 0.5098,
"step": 857
},
{
- "epoch": 17.36,
- "learning_rate": 9.056122448979592e-05,
- "loss": 1.0975,
+ "epoch": 9.69,
+ "learning_rate": 7.8125e-05,
+ "loss": 0.5005,
"step": 858
},
{
- "epoch": 17.38,
- "learning_rate": 9.043367346938775e-05,
- "loss": 1.1274,
+ "epoch": 9.7,
+ "learning_rate": 7.798295454545455e-05,
+ "loss": 0.5028,
"step": 859
},
{
- "epoch": 17.4,
- "learning_rate": 9.030612244897958e-05,
- "loss": 1.0916,
+ "epoch": 9.72,
+ "learning_rate": 7.784090909090909e-05,
+ "loss": 0.5067,
"step": 860
},
{
- "epoch": 17.42,
- "learning_rate": 9.017857142857143e-05,
- "loss": 1.0912,
+ "epoch": 9.73,
+ "learning_rate": 7.769886363636364e-05,
+ "loss": 0.484,
"step": 861
},
{
- "epoch": 17.44,
- "learning_rate": 9.005102040816327e-05,
- "loss": 1.0875,
+ "epoch": 9.74,
+ "learning_rate": 7.755681818181818e-05,
+ "loss": 0.5029,
"step": 862
},
{
- "epoch": 17.46,
- "learning_rate": 8.99234693877551e-05,
- "loss": 1.05,
+ "epoch": 9.75,
+ "learning_rate": 7.741477272727273e-05,
+ "loss": 0.5077,
"step": 863
},
{
- "epoch": 17.48,
- "learning_rate": 8.979591836734695e-05,
- "loss": 1.1418,
+ "epoch": 9.76,
+ "learning_rate": 7.727272727272727e-05,
+ "loss": 0.5091,
"step": 864
},
{
- "epoch": 17.5,
- "learning_rate": 8.966836734693878e-05,
- "loss": 1.0609,
+ "epoch": 9.77,
+ "learning_rate": 7.713068181818183e-05,
+ "loss": 0.4781,
"step": 865
},
{
- "epoch": 17.52,
- "learning_rate": 8.954081632653062e-05,
- "loss": 1.1611,
+ "epoch": 9.78,
+ "learning_rate": 7.698863636363636e-05,
+ "loss": 0.5124,
"step": 866
},
{
- "epoch": 17.54,
- "learning_rate": 8.941326530612245e-05,
- "loss": 1.1065,
+ "epoch": 9.79,
+ "learning_rate": 7.684659090909091e-05,
+ "loss": 0.4859,
"step": 867
},
{
- "epoch": 17.56,
- "learning_rate": 8.92857142857143e-05,
- "loss": 1.1611,
+ "epoch": 9.81,
+ "learning_rate": 7.670454545454547e-05,
+ "loss": 0.4872,
"step": 868
},
{
- "epoch": 17.58,
- "learning_rate": 8.915816326530613e-05,
- "loss": 1.1398,
+ "epoch": 9.82,
+ "learning_rate": 7.65625e-05,
+ "loss": 0.4675,
"step": 869
},
{
- "epoch": 17.6,
- "learning_rate": 8.903061224489796e-05,
- "loss": 1.1055,
+ "epoch": 9.83,
+ "learning_rate": 7.642045454545454e-05,
+ "loss": 0.5056,
"step": 870
},
{
- "epoch": 17.62,
- "learning_rate": 8.89030612244898e-05,
- "loss": 1.1314,
+ "epoch": 9.84,
+ "learning_rate": 7.62784090909091e-05,
+ "loss": 0.4868,
"step": 871
},
{
- "epoch": 17.64,
- "learning_rate": 8.877551020408164e-05,
- "loss": 1.1084,
+ "epoch": 9.85,
+ "learning_rate": 7.613636363636363e-05,
+ "loss": 0.4907,
"step": 872
},
{
- "epoch": 17.66,
- "learning_rate": 8.864795918367348e-05,
- "loss": 1.1254,
+ "epoch": 9.86,
+ "learning_rate": 7.599431818181818e-05,
+ "loss": 0.474,
"step": 873
},
{
- "epoch": 17.68,
- "learning_rate": 8.852040816326531e-05,
- "loss": 1.142,
+ "epoch": 9.87,
+ "learning_rate": 7.585227272727274e-05,
+ "loss": 0.4813,
"step": 874
},
{
- "epoch": 17.7,
- "learning_rate": 8.839285714285714e-05,
- "loss": 1.1371,
+ "epoch": 9.89,
+ "learning_rate": 7.571022727272727e-05,
+ "loss": 0.4838,
"step": 875
},
{
- "epoch": 17.72,
- "learning_rate": 8.826530612244899e-05,
- "loss": 1.1092,
+ "epoch": 9.9,
+ "learning_rate": 7.556818181818183e-05,
+ "loss": 0.4935,
"step": 876
},
{
- "epoch": 17.75,
- "learning_rate": 8.813775510204082e-05,
- "loss": 1.161,
+ "epoch": 9.91,
+ "learning_rate": 7.542613636363637e-05,
+ "loss": 0.4884,
"step": 877
},
{
- "epoch": 17.77,
- "learning_rate": 8.801020408163265e-05,
- "loss": 1.1044,
+ "epoch": 9.92,
+ "learning_rate": 7.52840909090909e-05,
+ "loss": 0.4797,
"step": 878
},
{
- "epoch": 17.79,
- "learning_rate": 8.788265306122449e-05,
- "loss": 1.117,
+ "epoch": 9.93,
+ "learning_rate": 7.514204545454546e-05,
+ "loss": 0.479,
"step": 879
},
{
- "epoch": 17.81,
- "learning_rate": 8.775510204081632e-05,
- "loss": 1.1262,
+ "epoch": 9.94,
+ "learning_rate": 7.500000000000001e-05,
+ "loss": 0.4727,
"step": 880
},
{
- "epoch": 17.83,
- "learning_rate": 8.762755102040817e-05,
- "loss": 1.0829,
+ "epoch": 9.95,
+ "learning_rate": 7.485795454545454e-05,
+ "loss": 0.4758,
"step": 881
},
{
- "epoch": 17.85,
- "learning_rate": 8.75e-05,
- "loss": 1.1393,
+ "epoch": 9.96,
+ "learning_rate": 7.47159090909091e-05,
+ "loss": 0.482,
"step": 882
},
{
- "epoch": 17.87,
- "learning_rate": 8.737244897959183e-05,
- "loss": 1.1781,
+ "epoch": 9.98,
+ "learning_rate": 7.457386363636364e-05,
+ "loss": 0.4951,
"step": 883
},
{
- "epoch": 17.89,
- "learning_rate": 8.724489795918367e-05,
- "loss": 1.1582,
+ "epoch": 9.99,
+ "learning_rate": 7.443181818181817e-05,
+ "loss": 0.4823,
"step": 884
},
{
- "epoch": 17.91,
- "learning_rate": 8.711734693877552e-05,
- "loss": 1.1469,
+ "epoch": 10.0,
+ "learning_rate": 7.428977272727273e-05,
+ "loss": 0.4638,
"step": 885
},
{
- "epoch": 17.93,
- "learning_rate": 8.698979591836735e-05,
- "loss": 1.1494,
+ "epoch": 10.01,
+ "learning_rate": 7.414772727272728e-05,
+ "loss": 0.4715,
"step": 886
},
{
- "epoch": 17.95,
- "learning_rate": 8.68622448979592e-05,
- "loss": 1.1251,
+ "epoch": 10.02,
+ "learning_rate": 7.400568181818182e-05,
+ "loss": 0.461,
"step": 887
},
{
- "epoch": 17.97,
- "learning_rate": 8.673469387755102e-05,
- "loss": 1.1624,
+ "epoch": 10.03,
+ "learning_rate": 7.386363636363637e-05,
+ "loss": 0.4429,
"step": 888
},
{
- "epoch": 17.99,
- "learning_rate": 8.660714285714287e-05,
- "loss": 1.0842,
+ "epoch": 10.04,
+ "learning_rate": 7.372159090909091e-05,
+ "loss": 0.4403,
"step": 889
},
{
- "epoch": 18.01,
- "learning_rate": 8.64795918367347e-05,
- "loss": 1.1944,
+ "epoch": 10.05,
+ "learning_rate": 7.357954545454546e-05,
+ "loss": 0.4519,
"step": 890
},
{
- "epoch": 18.03,
- "learning_rate": 8.635204081632653e-05,
- "loss": 1.0642,
+ "epoch": 10.07,
+ "learning_rate": 7.34375e-05,
+ "loss": 0.4611,
"step": 891
},
{
- "epoch": 18.05,
- "learning_rate": 8.622448979591838e-05,
- "loss": 1.0459,
+ "epoch": 10.08,
+ "learning_rate": 7.329545454545455e-05,
+ "loss": 0.4543,
"step": 892
},
{
- "epoch": 18.07,
- "learning_rate": 8.60969387755102e-05,
- "loss": 1.0941,
+ "epoch": 10.09,
+ "learning_rate": 7.315340909090909e-05,
+ "loss": 0.4528,
"step": 893
},
{
- "epoch": 18.09,
- "learning_rate": 8.596938775510205e-05,
- "loss": 1.0457,
+ "epoch": 10.1,
+ "learning_rate": 7.301136363636364e-05,
+ "loss": 0.4586,
"step": 894
},
{
- "epoch": 18.11,
- "learning_rate": 8.584183673469388e-05,
- "loss": 1.1033,
+ "epoch": 10.11,
+ "learning_rate": 7.286931818181818e-05,
+ "loss": 0.4418,
"step": 895
},
{
- "epoch": 18.13,
- "learning_rate": 8.571428571428571e-05,
- "loss": 1.0756,
+ "epoch": 10.12,
+ "learning_rate": 7.272727272727273e-05,
+ "loss": 0.4435,
"step": 896
},
{
- "epoch": 18.15,
- "learning_rate": 8.558673469387756e-05,
- "loss": 1.0615,
+ "epoch": 10.13,
+ "learning_rate": 7.258522727272727e-05,
+ "loss": 0.44,
"step": 897
},
{
- "epoch": 18.17,
- "learning_rate": 8.545918367346939e-05,
- "loss": 1.0828,
+ "epoch": 10.15,
+ "learning_rate": 7.244318181818183e-05,
+ "loss": 0.4589,
"step": 898
},
{
- "epoch": 18.19,
- "learning_rate": 8.533163265306123e-05,
- "loss": 1.1158,
+ "epoch": 10.16,
+ "learning_rate": 7.230113636363636e-05,
+ "loss": 0.4597,
"step": 899
},
{
- "epoch": 18.21,
- "learning_rate": 8.520408163265306e-05,
- "loss": 1.0133,
+ "epoch": 10.17,
+ "learning_rate": 7.215909090909091e-05,
+ "loss": 0.4479,
"step": 900
},
{
- "epoch": 18.23,
- "learning_rate": 8.50765306122449e-05,
- "loss": 1.0437,
+ "epoch": 10.18,
+ "learning_rate": 7.201704545454547e-05,
+ "loss": 0.4477,
"step": 901
},
{
- "epoch": 18.25,
- "learning_rate": 8.494897959183674e-05,
- "loss": 1.0372,
+ "epoch": 10.19,
+ "learning_rate": 7.1875e-05,
+ "loss": 0.446,
"step": 902
},
{
- "epoch": 18.27,
- "learning_rate": 8.482142857142857e-05,
- "loss": 1.1012,
+ "epoch": 10.2,
+ "learning_rate": 7.173295454545454e-05,
+ "loss": 0.4546,
"step": 903
},
{
- "epoch": 18.29,
- "learning_rate": 8.469387755102041e-05,
- "loss": 1.0777,
+ "epoch": 10.21,
+ "learning_rate": 7.15909090909091e-05,
+ "loss": 0.4347,
"step": 904
},
{
- "epoch": 18.31,
- "learning_rate": 8.456632653061224e-05,
- "loss": 1.0799,
+ "epoch": 10.22,
+ "learning_rate": 7.144886363636363e-05,
+ "loss": 0.452,
"step": 905
},
{
- "epoch": 18.33,
- "learning_rate": 8.443877551020409e-05,
- "loss": 0.9846,
+ "epoch": 10.24,
+ "learning_rate": 7.130681818181818e-05,
+ "loss": 0.4536,
"step": 906
},
{
- "epoch": 18.35,
- "learning_rate": 8.431122448979592e-05,
- "loss": 1.1,
+ "epoch": 10.25,
+ "learning_rate": 7.116477272727274e-05,
+ "loss": 0.4492,
"step": 907
},
{
- "epoch": 18.37,
- "learning_rate": 8.418367346938776e-05,
- "loss": 1.0787,
+ "epoch": 10.26,
+ "learning_rate": 7.102272727272727e-05,
+ "loss": 0.4401,
"step": 908
},
{
- "epoch": 18.39,
- "learning_rate": 8.40561224489796e-05,
- "loss": 1.0647,
+ "epoch": 10.27,
+ "learning_rate": 7.088068181818183e-05,
+ "loss": 0.4609,
"step": 909
},
{
- "epoch": 18.41,
- "learning_rate": 8.392857142857144e-05,
- "loss": 1.056,
+ "epoch": 10.28,
+ "learning_rate": 7.073863636363637e-05,
+ "loss": 0.4544,
"step": 910
},
{
- "epoch": 18.43,
- "learning_rate": 8.380102040816327e-05,
- "loss": 1.1131,
+ "epoch": 10.29,
+ "learning_rate": 7.05965909090909e-05,
+ "loss": 0.4477,
"step": 911
},
{
- "epoch": 18.45,
- "learning_rate": 8.367346938775511e-05,
- "loss": 1.0825,
+ "epoch": 10.3,
+ "learning_rate": 7.045454545454546e-05,
+ "loss": 0.4445,
"step": 912
},
{
- "epoch": 18.47,
- "learning_rate": 8.354591836734695e-05,
- "loss": 1.0681,
+ "epoch": 10.31,
+ "learning_rate": 7.031250000000001e-05,
+ "loss": 0.4544,
"step": 913
},
{
- "epoch": 18.49,
- "learning_rate": 8.341836734693878e-05,
- "loss": 1.0479,
+ "epoch": 10.33,
+ "learning_rate": 7.017045454545454e-05,
+ "loss": 0.4634,
"step": 914
},
{
- "epoch": 18.51,
- "learning_rate": 8.329081632653062e-05,
- "loss": 1.0921,
+ "epoch": 10.34,
+ "learning_rate": 7.00284090909091e-05,
+ "loss": 0.4499,
"step": 915
},
{
- "epoch": 18.53,
- "learning_rate": 8.316326530612245e-05,
- "loss": 1.0626,
+ "epoch": 10.35,
+ "learning_rate": 6.988636363636364e-05,
+ "loss": 0.4354,
"step": 916
},
{
- "epoch": 18.55,
- "learning_rate": 8.30357142857143e-05,
- "loss": 1.0518,
+ "epoch": 10.36,
+ "learning_rate": 6.974431818181818e-05,
+ "loss": 0.454,
"step": 917
},
{
- "epoch": 18.57,
- "learning_rate": 8.290816326530613e-05,
- "loss": 1.0557,
+ "epoch": 10.37,
+ "learning_rate": 6.960227272727273e-05,
+ "loss": 0.4473,
"step": 918
},
{
- "epoch": 18.6,
- "learning_rate": 8.278061224489796e-05,
- "loss": 1.0831,
+ "epoch": 10.38,
+ "learning_rate": 6.946022727272728e-05,
+ "loss": 0.4347,
"step": 919
},
{
- "epoch": 18.62,
- "learning_rate": 8.26530612244898e-05,
- "loss": 1.0307,
+ "epoch": 10.39,
+ "learning_rate": 6.931818181818182e-05,
+ "loss": 0.441,
"step": 920
},
{
- "epoch": 18.64,
- "learning_rate": 8.252551020408163e-05,
- "loss": 1.0455,
+ "epoch": 10.4,
+ "learning_rate": 6.917613636363637e-05,
+ "loss": 0.4545,
"step": 921
},
{
- "epoch": 18.66,
- "learning_rate": 8.239795918367348e-05,
- "loss": 1.0667,
+ "epoch": 10.42,
+ "learning_rate": 6.903409090909091e-05,
+ "loss": 0.458,
"step": 922
},
{
- "epoch": 18.68,
- "learning_rate": 8.227040816326531e-05,
- "loss": 1.0736,
+ "epoch": 10.43,
+ "learning_rate": 6.889204545454546e-05,
+ "loss": 0.4381,
"step": 923
},
{
- "epoch": 18.7,
- "learning_rate": 8.214285714285714e-05,
- "loss": 1.0108,
+ "epoch": 10.44,
+ "learning_rate": 6.875e-05,
+ "loss": 0.441,
"step": 924
},
{
- "epoch": 18.72,
- "learning_rate": 8.201530612244898e-05,
- "loss": 1.0458,
+ "epoch": 10.45,
+ "learning_rate": 6.860795454545455e-05,
+ "loss": 0.4446,
"step": 925
},
{
- "epoch": 18.74,
- "learning_rate": 8.188775510204081e-05,
- "loss": 1.0852,
+ "epoch": 10.46,
+ "learning_rate": 6.84659090909091e-05,
+ "loss": 0.4548,
"step": 926
},
{
- "epoch": 18.76,
- "learning_rate": 8.176020408163265e-05,
- "loss": 1.1207,
+ "epoch": 10.47,
+ "learning_rate": 6.832386363636364e-05,
+ "loss": 0.4404,
"step": 927
},
{
- "epoch": 18.78,
- "learning_rate": 8.163265306122449e-05,
- "loss": 1.0914,
+ "epoch": 10.48,
+ "learning_rate": 6.818181818181818e-05,
+ "loss": 0.4446,
"step": 928
},
{
- "epoch": 18.8,
- "learning_rate": 8.150510204081633e-05,
- "loss": 1.1108,
+ "epoch": 10.5,
+ "learning_rate": 6.803977272727273e-05,
+ "loss": 0.4434,
"step": 929
},
{
- "epoch": 18.82,
- "learning_rate": 8.137755102040817e-05,
- "loss": 1.1394,
+ "epoch": 10.51,
+ "learning_rate": 6.789772727272727e-05,
+ "loss": 0.4778,
"step": 930
},
{
- "epoch": 18.84,
- "learning_rate": 8.125000000000001e-05,
- "loss": 1.029,
+ "epoch": 10.52,
+ "learning_rate": 6.775568181818182e-05,
+ "loss": 0.4356,
"step": 931
},
{
- "epoch": 18.86,
- "learning_rate": 8.112244897959184e-05,
- "loss": 1.0661,
+ "epoch": 10.53,
+ "learning_rate": 6.761363636363636e-05,
+ "loss": 0.4464,
"step": 932
},
{
- "epoch": 18.88,
- "learning_rate": 8.099489795918369e-05,
- "loss": 1.0303,
+ "epoch": 10.54,
+ "learning_rate": 6.747159090909091e-05,
+ "loss": 0.4387,
"step": 933
},
{
- "epoch": 18.9,
- "learning_rate": 8.086734693877552e-05,
- "loss": 1.1144,
+ "epoch": 10.55,
+ "learning_rate": 6.732954545454547e-05,
+ "loss": 0.456,
"step": 934
},
{
- "epoch": 18.92,
- "learning_rate": 8.073979591836736e-05,
- "loss": 1.1096,
+ "epoch": 10.56,
+ "learning_rate": 6.71875e-05,
+ "loss": 0.453,
"step": 935
},
{
- "epoch": 18.94,
- "learning_rate": 8.061224489795919e-05,
- "loss": 1.123,
+ "epoch": 10.57,
+ "learning_rate": 6.704545454545455e-05,
+ "loss": 0.4611,
"step": 936
},
{
- "epoch": 18.96,
- "learning_rate": 8.048469387755102e-05,
- "loss": 1.1002,
+ "epoch": 10.59,
+ "learning_rate": 6.69034090909091e-05,
+ "loss": 0.4354,
"step": 937
},
{
- "epoch": 18.98,
- "learning_rate": 8.035714285714287e-05,
- "loss": 1.1016,
+ "epoch": 10.6,
+ "learning_rate": 6.676136363636364e-05,
+ "loss": 0.4519,
"step": 938
},
{
- "epoch": 19.0,
- "learning_rate": 8.02295918367347e-05,
- "loss": 1.0847,
+ "epoch": 10.61,
+ "learning_rate": 6.661931818181818e-05,
+ "loss": 0.4435,
"step": 939
},
{
- "epoch": 19.02,
- "learning_rate": 8.010204081632653e-05,
- "loss": 1.1029,
+ "epoch": 10.62,
+ "learning_rate": 6.647727272727274e-05,
+ "loss": 0.4422,
"step": 940
},
{
- "epoch": 19.04,
- "learning_rate": 7.997448979591837e-05,
- "loss": 1.041,
+ "epoch": 10.63,
+ "learning_rate": 6.633522727272727e-05,
+ "loss": 0.4344,
"step": 941
},
{
- "epoch": 19.06,
- "learning_rate": 7.98469387755102e-05,
- "loss": 1.01,
+ "epoch": 10.64,
+ "learning_rate": 6.619318181818183e-05,
+ "loss": 0.4419,
"step": 942
},
{
- "epoch": 19.08,
- "learning_rate": 7.971938775510205e-05,
- "loss": 1.0197,
+ "epoch": 10.65,
+ "learning_rate": 6.605113636363637e-05,
+ "loss": 0.4308,
"step": 943
},
{
- "epoch": 19.1,
- "learning_rate": 7.959183673469388e-05,
- "loss": 1.0543,
+ "epoch": 10.66,
+ "learning_rate": 6.59090909090909e-05,
+ "loss": 0.4043,
"step": 944
},
{
- "epoch": 19.12,
- "learning_rate": 7.946428571428571e-05,
- "loss": 1.0369,
+ "epoch": 10.68,
+ "learning_rate": 6.576704545454546e-05,
+ "loss": 0.4626,
"step": 945
},
{
- "epoch": 19.14,
- "learning_rate": 7.933673469387755e-05,
- "loss": 1.0154,
+ "epoch": 10.69,
+ "learning_rate": 6.562500000000001e-05,
+ "loss": 0.4365,
"step": 946
},
{
- "epoch": 19.16,
- "learning_rate": 7.920918367346939e-05,
- "loss": 0.9546,
+ "epoch": 10.7,
+ "learning_rate": 6.548295454545454e-05,
+ "loss": 0.4397,
"step": 947
},
{
- "epoch": 19.18,
- "learning_rate": 7.908163265306123e-05,
- "loss": 0.9982,
+ "epoch": 10.71,
+ "learning_rate": 6.53409090909091e-05,
+ "loss": 0.4463,
"step": 948
},
{
- "epoch": 19.2,
- "learning_rate": 7.895408163265306e-05,
- "loss": 1.0748,
+ "epoch": 10.72,
+ "learning_rate": 6.519886363636364e-05,
+ "loss": 0.4394,
"step": 949
},
{
- "epoch": 19.22,
- "learning_rate": 7.882653061224489e-05,
- "loss": 1.0562,
+ "epoch": 10.73,
+ "learning_rate": 6.505681818181818e-05,
+ "loss": 0.45,
"step": 950
},
{
- "epoch": 19.24,
- "learning_rate": 7.869897959183674e-05,
- "loss": 1.0352,
+ "epoch": 10.74,
+ "learning_rate": 6.491477272727273e-05,
+ "loss": 0.4363,
"step": 951
},
{
- "epoch": 19.26,
- "learning_rate": 7.857142857142858e-05,
- "loss": 0.9976,
+ "epoch": 10.76,
+ "learning_rate": 6.477272727272728e-05,
+ "loss": 0.4566,
"step": 952
},
{
- "epoch": 19.28,
- "learning_rate": 7.844387755102041e-05,
- "loss": 1.0221,
+ "epoch": 10.77,
+ "learning_rate": 6.463068181818183e-05,
+ "loss": 0.4235,
"step": 953
},
{
- "epoch": 19.3,
- "learning_rate": 7.831632653061226e-05,
- "loss": 1.0119,
+ "epoch": 10.78,
+ "learning_rate": 6.448863636363637e-05,
+ "loss": 0.4458,
"step": 954
},
{
- "epoch": 19.32,
- "learning_rate": 7.818877551020409e-05,
- "loss": 1.0657,
+ "epoch": 10.79,
+ "learning_rate": 6.434659090909092e-05,
+ "loss": 0.423,
"step": 955
},
{
- "epoch": 19.34,
- "learning_rate": 7.806122448979593e-05,
- "loss": 0.9591,
+ "epoch": 10.8,
+ "learning_rate": 6.420454545454546e-05,
+ "loss": 0.445,
"step": 956
},
{
- "epoch": 19.36,
- "learning_rate": 7.793367346938776e-05,
- "loss": 1.0101,
+ "epoch": 10.81,
+ "learning_rate": 6.40625e-05,
+ "loss": 0.424,
"step": 957
},
{
- "epoch": 19.38,
- "learning_rate": 7.780612244897959e-05,
- "loss": 1.0453,
+ "epoch": 10.82,
+ "learning_rate": 6.392045454545455e-05,
+ "loss": 0.4224,
"step": 958
},
{
- "epoch": 19.4,
- "learning_rate": 7.767857142857144e-05,
- "loss": 1.0461,
+ "epoch": 10.83,
+ "learning_rate": 6.37784090909091e-05,
+ "loss": 0.4223,
"step": 959
},
{
- "epoch": 19.42,
- "learning_rate": 7.755102040816327e-05,
- "loss": 1.0959,
+ "epoch": 10.85,
+ "learning_rate": 6.363636363636364e-05,
+ "loss": 0.4314,
"step": 960
},
{
- "epoch": 19.44,
- "learning_rate": 7.742346938775511e-05,
- "loss": 1.0608,
+ "epoch": 10.86,
+ "learning_rate": 6.349431818181819e-05,
+ "loss": 0.4488,
"step": 961
},
{
- "epoch": 19.47,
- "learning_rate": 7.729591836734694e-05,
- "loss": 1.1177,
+ "epoch": 10.87,
+ "learning_rate": 6.335227272727273e-05,
+ "loss": 0.423,
"step": 962
},
{
- "epoch": 19.49,
- "learning_rate": 7.716836734693877e-05,
- "loss": 1.0354,
+ "epoch": 10.88,
+ "learning_rate": 6.321022727272728e-05,
+ "loss": 0.4416,
"step": 963
},
{
- "epoch": 19.51,
- "learning_rate": 7.704081632653062e-05,
- "loss": 1.0507,
+ "epoch": 10.89,
+ "learning_rate": 6.306818181818182e-05,
+ "loss": 0.423,
"step": 964
},
{
- "epoch": 19.53,
- "learning_rate": 7.691326530612245e-05,
- "loss": 1.0313,
+ "epoch": 10.9,
+ "learning_rate": 6.292613636363637e-05,
+ "loss": 0.4502,
"step": 965
},
{
- "epoch": 19.55,
- "learning_rate": 7.67857142857143e-05,
- "loss": 1.0569,
+ "epoch": 10.91,
+ "learning_rate": 6.278409090909091e-05,
+ "loss": 0.4266,
"step": 966
},
{
- "epoch": 19.57,
- "learning_rate": 7.665816326530612e-05,
- "loss": 1.0862,
+ "epoch": 10.92,
+ "learning_rate": 6.264204545454546e-05,
+ "loss": 0.4344,
"step": 967
},
{
- "epoch": 19.59,
- "learning_rate": 7.653061224489796e-05,
- "loss": 1.0593,
+ "epoch": 10.94,
+ "learning_rate": 6.25e-05,
+ "loss": 0.434,
"step": 968
},
{
- "epoch": 19.61,
- "learning_rate": 7.64030612244898e-05,
- "loss": 1.0602,
+ "epoch": 10.95,
+ "learning_rate": 6.235795454545455e-05,
+ "loss": 0.4269,
"step": 969
},
{
- "epoch": 19.63,
- "learning_rate": 7.627551020408163e-05,
- "loss": 1.0048,
+ "epoch": 10.96,
+ "learning_rate": 6.221590909090909e-05,
+ "loss": 0.4158,
"step": 970
},
{
- "epoch": 19.65,
- "learning_rate": 7.614795918367347e-05,
- "loss": 1.0346,
+ "epoch": 10.97,
+ "learning_rate": 6.207386363636364e-05,
+ "loss": 0.4231,
"step": 971
},
{
- "epoch": 19.67,
- "learning_rate": 7.60204081632653e-05,
- "loss": 1.0172,
+ "epoch": 10.98,
+ "learning_rate": 6.193181818181818e-05,
+ "loss": 0.4235,
"step": 972
},
{
- "epoch": 19.69,
- "learning_rate": 7.589285714285714e-05,
- "loss": 1.02,
+ "epoch": 10.99,
+ "learning_rate": 6.178977272727273e-05,
+ "loss": 0.4504,
"step": 973
},
{
- "epoch": 19.71,
- "learning_rate": 7.576530612244898e-05,
- "loss": 1.0028,
+ "epoch": 11.0,
+ "learning_rate": 6.164772727272727e-05,
+ "loss": 0.4394,
"step": 974
},
{
- "epoch": 19.73,
- "learning_rate": 7.563775510204083e-05,
- "loss": 1.08,
+ "epoch": 11.02,
+ "learning_rate": 6.150568181818183e-05,
+ "loss": 0.4333,
"step": 975
},
{
- "epoch": 19.75,
- "learning_rate": 7.551020408163266e-05,
- "loss": 1.0402,
+ "epoch": 11.03,
+ "learning_rate": 6.136363636363636e-05,
+ "loss": 0.3936,
"step": 976
},
{
- "epoch": 19.77,
- "learning_rate": 7.53826530612245e-05,
- "loss": 1.0567,
+ "epoch": 11.04,
+ "learning_rate": 6.122159090909091e-05,
+ "loss": 0.3933,
"step": 977
},
{
- "epoch": 19.79,
- "learning_rate": 7.525510204081633e-05,
- "loss": 1.0169,
+ "epoch": 11.05,
+ "learning_rate": 6.107954545454547e-05,
+ "loss": 0.4161,
"step": 978
},
{
- "epoch": 19.81,
- "learning_rate": 7.512755102040818e-05,
- "loss": 0.9881,
+ "epoch": 11.06,
+ "learning_rate": 6.0937500000000004e-05,
+ "loss": 0.4097,
"step": 979
},
{
- "epoch": 19.83,
- "learning_rate": 7.500000000000001e-05,
- "loss": 1.0677,
+ "epoch": 11.07,
+ "learning_rate": 6.079545454545454e-05,
+ "loss": 0.412,
"step": 980
},
{
- "epoch": 19.85,
- "learning_rate": 7.487244897959184e-05,
- "loss": 1.1026,
+ "epoch": 11.08,
+ "learning_rate": 6.0653409090909094e-05,
+ "loss": 0.4104,
"step": 981
},
{
- "epoch": 19.87,
- "learning_rate": 7.474489795918368e-05,
- "loss": 1.0101,
+ "epoch": 11.09,
+ "learning_rate": 6.051136363636364e-05,
+ "loss": 0.4152,
"step": 982
},
{
- "epoch": 19.89,
- "learning_rate": 7.461734693877551e-05,
- "loss": 1.069,
+ "epoch": 11.11,
+ "learning_rate": 6.036931818181818e-05,
+ "loss": 0.4037,
"step": 983
},
{
- "epoch": 19.91,
- "learning_rate": 7.448979591836736e-05,
- "loss": 1.0493,
+ "epoch": 11.12,
+ "learning_rate": 6.022727272727273e-05,
+ "loss": 0.413,
"step": 984
},
{
- "epoch": 19.93,
- "learning_rate": 7.436224489795919e-05,
- "loss": 1.0858,
+ "epoch": 11.13,
+ "learning_rate": 6.0085227272727274e-05,
+ "loss": 0.4413,
"step": 985
},
{
- "epoch": 19.95,
- "learning_rate": 7.423469387755102e-05,
- "loss": 1.0734,
+ "epoch": 11.14,
+ "learning_rate": 5.9943181818181826e-05,
+ "loss": 0.3908,
"step": 986
},
{
- "epoch": 19.97,
- "learning_rate": 7.410714285714286e-05,
- "loss": 1.0203,
+ "epoch": 11.15,
+ "learning_rate": 5.9801136363636365e-05,
+ "loss": 0.3982,
"step": 987
},
{
- "epoch": 19.99,
- "learning_rate": 7.39795918367347e-05,
- "loss": 1.0285,
+ "epoch": 11.16,
+ "learning_rate": 5.965909090909091e-05,
+ "loss": 0.4109,
"step": 988
},
{
- "epoch": 20.01,
- "learning_rate": 7.385204081632653e-05,
- "loss": 0.9446,
+ "epoch": 11.17,
+ "learning_rate": 5.951704545454546e-05,
+ "loss": 0.3923,
"step": 989
},
{
- "epoch": 20.03,
- "learning_rate": 7.372448979591837e-05,
- "loss": 0.9915,
+ "epoch": 11.18,
+ "learning_rate": 5.9375e-05,
+ "loss": 0.4107,
"step": 990
},
{
- "epoch": 20.05,
- "learning_rate": 7.35969387755102e-05,
- "loss": 0.9882,
+ "epoch": 11.2,
+ "learning_rate": 5.9232954545454545e-05,
+ "loss": 0.4099,
"step": 991
},
{
- "epoch": 20.07,
- "learning_rate": 7.346938775510205e-05,
- "loss": 0.9338,
+ "epoch": 11.21,
+ "learning_rate": 5.90909090909091e-05,
+ "loss": 0.4163,
"step": 992
},
{
- "epoch": 20.09,
- "learning_rate": 7.334183673469388e-05,
- "loss": 0.942,
+ "epoch": 11.22,
+ "learning_rate": 5.8948863636363635e-05,
+ "loss": 0.4189,
"step": 993
},
{
- "epoch": 20.11,
- "learning_rate": 7.321428571428571e-05,
- "loss": 0.9725,
+ "epoch": 11.23,
+ "learning_rate": 5.880681818181818e-05,
+ "loss": 0.3889,
"step": 994
},
{
- "epoch": 20.13,
- "learning_rate": 7.308673469387755e-05,
- "loss": 1.027,
+ "epoch": 11.24,
+ "learning_rate": 5.866477272727273e-05,
+ "loss": 0.3988,
"step": 995
},
{
- "epoch": 20.15,
- "learning_rate": 7.29591836734694e-05,
- "loss": 1.0081,
+ "epoch": 11.25,
+ "learning_rate": 5.852272727272727e-05,
+ "loss": 0.4215,
"step": 996
},
{
- "epoch": 20.17,
- "learning_rate": 7.283163265306123e-05,
- "loss": 1.0117,
+ "epoch": 11.26,
+ "learning_rate": 5.838068181818183e-05,
+ "loss": 0.4207,
"step": 997
},
{
- "epoch": 20.19,
- "learning_rate": 7.270408163265307e-05,
- "loss": 0.969,
+ "epoch": 11.27,
+ "learning_rate": 5.823863636363637e-05,
+ "loss": 0.413,
"step": 998
},
{
- "epoch": 20.21,
- "learning_rate": 7.25765306122449e-05,
- "loss": 1.0024,
+ "epoch": 11.29,
+ "learning_rate": 5.8096590909090906e-05,
+ "loss": 0.4057,
"step": 999
},
{
- "epoch": 20.23,
- "learning_rate": 7.244897959183675e-05,
- "loss": 0.994,
+ "epoch": 11.3,
+ "learning_rate": 5.7954545454545464e-05,
+ "loss": 0.3939,
"step": 1000
},
{
- "epoch": 20.25,
- "learning_rate": 7.232142857142858e-05,
- "loss": 1.0248,
+ "epoch": 11.31,
+ "learning_rate": 5.78125e-05,
+ "loss": 0.4199,
"step": 1001
},
{
- "epoch": 20.27,
- "learning_rate": 7.219387755102042e-05,
- "loss": 1.0493,
+ "epoch": 11.32,
+ "learning_rate": 5.767045454545454e-05,
+ "loss": 0.4076,
"step": 1002
},
{
- "epoch": 20.29,
- "learning_rate": 7.206632653061225e-05,
- "loss": 1.0011,
+ "epoch": 11.33,
+ "learning_rate": 5.75284090909091e-05,
+ "loss": 0.4079,
"step": 1003
},
{
- "epoch": 20.31,
- "learning_rate": 7.193877551020408e-05,
- "loss": 0.9874,
+ "epoch": 11.34,
+ "learning_rate": 5.738636363636364e-05,
+ "loss": 0.4002,
"step": 1004
},
{
- "epoch": 20.34,
- "learning_rate": 7.181122448979593e-05,
- "loss": 1.0049,
+ "epoch": 11.35,
+ "learning_rate": 5.724431818181818e-05,
+ "loss": 0.3801,
"step": 1005
},
{
- "epoch": 20.36,
- "learning_rate": 7.168367346938776e-05,
- "loss": 1.0314,
+ "epoch": 11.37,
+ "learning_rate": 5.7102272727272735e-05,
+ "loss": 0.3939,
"step": 1006
},
{
- "epoch": 20.38,
- "learning_rate": 7.155612244897959e-05,
- "loss": 0.9742,
+ "epoch": 11.38,
+ "learning_rate": 5.696022727272727e-05,
+ "loss": 0.3904,
"step": 1007
},
{
- "epoch": 20.4,
- "learning_rate": 7.142857142857143e-05,
- "loss": 1.0621,
+ "epoch": 11.39,
+ "learning_rate": 5.6818181818181825e-05,
+ "loss": 0.406,
"step": 1008
},
{
- "epoch": 20.42,
- "learning_rate": 7.130102040816326e-05,
- "loss": 0.9672,
+ "epoch": 11.4,
+ "learning_rate": 5.667613636363637e-05,
+ "loss": 0.4185,
"step": 1009
},
{
- "epoch": 20.44,
- "learning_rate": 7.117346938775511e-05,
- "loss": 1.0018,
+ "epoch": 11.41,
+ "learning_rate": 5.653409090909091e-05,
+ "loss": 0.3976,
"step": 1010
},
{
- "epoch": 20.46,
- "learning_rate": 7.104591836734694e-05,
- "loss": 1.0045,
+ "epoch": 11.42,
+ "learning_rate": 5.639204545454546e-05,
+ "loss": 0.3907,
"step": 1011
},
{
- "epoch": 20.48,
- "learning_rate": 7.091836734693877e-05,
- "loss": 0.9675,
+ "epoch": 11.43,
+ "learning_rate": 5.6250000000000005e-05,
+ "loss": 0.4065,
"step": 1012
},
{
- "epoch": 20.5,
- "learning_rate": 7.079081632653062e-05,
- "loss": 0.976,
+ "epoch": 11.44,
+ "learning_rate": 5.6107954545454544e-05,
+ "loss": 0.4069,
"step": 1013
},
{
- "epoch": 20.52,
- "learning_rate": 7.066326530612245e-05,
- "loss": 1.0523,
+ "epoch": 11.46,
+ "learning_rate": 5.5965909090909095e-05,
+ "loss": 0.3964,
"step": 1014
},
{
- "epoch": 20.54,
- "learning_rate": 7.053571428571429e-05,
- "loss": 1.052,
+ "epoch": 11.47,
+ "learning_rate": 5.582386363636364e-05,
+ "loss": 0.3912,
"step": 1015
},
{
- "epoch": 20.56,
- "learning_rate": 7.040816326530612e-05,
- "loss": 0.9903,
+ "epoch": 11.48,
+ "learning_rate": 5.568181818181818e-05,
+ "loss": 0.3944,
"step": 1016
},
{
- "epoch": 20.58,
- "learning_rate": 7.028061224489795e-05,
- "loss": 1.0337,
+ "epoch": 11.49,
+ "learning_rate": 5.553977272727273e-05,
+ "loss": 0.4197,
"step": 1017
},
{
- "epoch": 20.6,
- "learning_rate": 7.01530612244898e-05,
- "loss": 1.1122,
+ "epoch": 11.5,
+ "learning_rate": 5.5397727272727276e-05,
+ "loss": 0.4064,
"step": 1018
},
{
- "epoch": 20.62,
- "learning_rate": 7.002551020408164e-05,
- "loss": 1.0133,
+ "epoch": 11.51,
+ "learning_rate": 5.525568181818183e-05,
+ "loss": 0.4054,
"step": 1019
},
{
- "epoch": 20.64,
- "learning_rate": 6.989795918367347e-05,
- "loss": 0.9588,
+ "epoch": 11.52,
+ "learning_rate": 5.5113636363636366e-05,
+ "loss": 0.4128,
"step": 1020
},
{
- "epoch": 20.66,
- "learning_rate": 6.977040816326532e-05,
- "loss": 0.9892,
+ "epoch": 11.53,
+ "learning_rate": 5.497159090909091e-05,
+ "loss": 0.3976,
"step": 1021
},
{
- "epoch": 20.68,
- "learning_rate": 6.964285714285715e-05,
- "loss": 1.025,
+ "epoch": 11.55,
+ "learning_rate": 5.482954545454546e-05,
+ "loss": 0.3863,
"step": 1022
},
{
- "epoch": 20.7,
- "learning_rate": 6.951530612244899e-05,
- "loss": 1.0196,
+ "epoch": 11.56,
+ "learning_rate": 5.46875e-05,
+ "loss": 0.3994,
"step": 1023
},
{
- "epoch": 20.72,
- "learning_rate": 6.938775510204082e-05,
- "loss": 1.0146,
+ "epoch": 11.57,
+ "learning_rate": 5.4545454545454546e-05,
+ "loss": 0.401,
"step": 1024
},
{
- "epoch": 20.74,
- "learning_rate": 6.926020408163265e-05,
- "loss": 1.0656,
+ "epoch": 11.58,
+ "learning_rate": 5.44034090909091e-05,
+ "loss": 0.3948,
"step": 1025
},
{
- "epoch": 20.76,
- "learning_rate": 6.91326530612245e-05,
- "loss": 0.9584,
+ "epoch": 11.59,
+ "learning_rate": 5.4261363636363636e-05,
+ "loss": 0.3967,
"step": 1026
},
{
- "epoch": 20.78,
- "learning_rate": 6.900510204081633e-05,
- "loss": 0.9877,
+ "epoch": 11.6,
+ "learning_rate": 5.411931818181818e-05,
+ "loss": 0.413,
"step": 1027
},
{
- "epoch": 20.8,
- "learning_rate": 6.887755102040817e-05,
- "loss": 1.0607,
+ "epoch": 11.61,
+ "learning_rate": 5.397727272727273e-05,
+ "loss": 0.4032,
"step": 1028
},
{
- "epoch": 20.82,
- "learning_rate": 6.875e-05,
- "loss": 0.9969,
+ "epoch": 11.63,
+ "learning_rate": 5.383522727272727e-05,
+ "loss": 0.3905,
"step": 1029
},
{
- "epoch": 20.84,
- "learning_rate": 6.862244897959184e-05,
- "loss": 0.9506,
+ "epoch": 11.64,
+ "learning_rate": 5.3693181818181823e-05,
+ "loss": 0.4041,
"step": 1030
},
{
- "epoch": 20.86,
- "learning_rate": 6.849489795918368e-05,
- "loss": 1.0576,
+ "epoch": 11.65,
+ "learning_rate": 5.355113636363637e-05,
+ "loss": 0.392,
"step": 1031
},
{
- "epoch": 20.88,
- "learning_rate": 6.836734693877551e-05,
- "loss": 1.0094,
+ "epoch": 11.66,
+ "learning_rate": 5.340909090909091e-05,
+ "loss": 0.3942,
"step": 1032
},
{
- "epoch": 20.9,
- "learning_rate": 6.823979591836735e-05,
- "loss": 0.9872,
+ "epoch": 11.67,
+ "learning_rate": 5.326704545454546e-05,
+ "loss": 0.3946,
"step": 1033
},
{
- "epoch": 20.92,
- "learning_rate": 6.811224489795919e-05,
- "loss": 1.0544,
+ "epoch": 11.68,
+ "learning_rate": 5.3125000000000004e-05,
+ "loss": 0.3989,
"step": 1034
},
{
- "epoch": 20.94,
- "learning_rate": 6.798469387755102e-05,
- "loss": 1.0194,
+ "epoch": 11.69,
+ "learning_rate": 5.298295454545454e-05,
+ "loss": 0.4101,
"step": 1035
},
{
- "epoch": 20.96,
- "learning_rate": 6.785714285714286e-05,
- "loss": 1.0009,
+ "epoch": 11.7,
+ "learning_rate": 5.2840909090909094e-05,
+ "loss": 0.4033,
"step": 1036
},
{
- "epoch": 20.98,
- "learning_rate": 6.772959183673469e-05,
- "loss": 0.9727,
+ "epoch": 11.72,
+ "learning_rate": 5.269886363636364e-05,
+ "loss": 0.3937,
"step": 1037
},
{
- "epoch": 21.0,
- "learning_rate": 6.760204081632652e-05,
- "loss": 0.9754,
+ "epoch": 11.73,
+ "learning_rate": 5.255681818181818e-05,
+ "loss": 0.3873,
"step": 1038
},
{
- "epoch": 21.02,
- "learning_rate": 6.747448979591837e-05,
- "loss": 0.9953,
+ "epoch": 11.74,
+ "learning_rate": 5.241477272727273e-05,
+ "loss": 0.3922,
"step": 1039
},
{
- "epoch": 21.04,
- "learning_rate": 6.73469387755102e-05,
- "loss": 0.9307,
+ "epoch": 11.75,
+ "learning_rate": 5.2272727272727274e-05,
+ "loss": 0.4016,
"step": 1040
},
{
- "epoch": 21.06,
- "learning_rate": 6.721938775510204e-05,
- "loss": 0.9151,
+ "epoch": 11.76,
+ "learning_rate": 5.2130681818181826e-05,
+ "loss": 0.3892,
"step": 1041
},
{
- "epoch": 21.08,
- "learning_rate": 6.709183673469389e-05,
- "loss": 0.9474,
+ "epoch": 11.77,
+ "learning_rate": 5.1988636363636364e-05,
+ "loss": 0.3974,
"step": 1042
},
{
- "epoch": 21.1,
- "learning_rate": 6.696428571428572e-05,
- "loss": 0.9697,
+ "epoch": 11.78,
+ "learning_rate": 5.184659090909091e-05,
+ "loss": 0.4024,
"step": 1043
},
{
- "epoch": 21.12,
- "learning_rate": 6.683673469387756e-05,
- "loss": 0.9423,
+ "epoch": 11.79,
+ "learning_rate": 5.170454545454546e-05,
+ "loss": 0.3889,
"step": 1044
},
{
- "epoch": 21.14,
- "learning_rate": 6.670918367346939e-05,
- "loss": 0.9797,
+ "epoch": 11.81,
+ "learning_rate": 5.15625e-05,
+ "loss": 0.4097,
"step": 1045
},
{
- "epoch": 21.16,
- "learning_rate": 6.658163265306124e-05,
- "loss": 0.919,
+ "epoch": 11.82,
+ "learning_rate": 5.1420454545454545e-05,
+ "loss": 0.4047,
"step": 1046
},
{
- "epoch": 21.18,
- "learning_rate": 6.645408163265307e-05,
- "loss": 0.9743,
+ "epoch": 11.83,
+ "learning_rate": 5.12784090909091e-05,
+ "loss": 0.4033,
"step": 1047
},
{
- "epoch": 21.21,
- "learning_rate": 6.63265306122449e-05,
- "loss": 0.9575,
+ "epoch": 11.84,
+ "learning_rate": 5.1136363636363635e-05,
+ "loss": 0.3774,
"step": 1048
},
{
- "epoch": 21.23,
- "learning_rate": 6.619897959183674e-05,
- "loss": 0.9861,
+ "epoch": 11.85,
+ "learning_rate": 5.099431818181818e-05,
+ "loss": 0.405,
"step": 1049
},
{
- "epoch": 21.25,
- "learning_rate": 6.607142857142857e-05,
- "loss": 0.9103,
+ "epoch": 11.86,
+ "learning_rate": 5.085227272727273e-05,
+ "loss": 0.3996,
"step": 1050
},
{
- "epoch": 21.27,
- "learning_rate": 6.594387755102042e-05,
- "loss": 0.993,
+ "epoch": 11.87,
+ "learning_rate": 5.071022727272727e-05,
+ "loss": 0.3885,
"step": 1051
},
{
- "epoch": 21.29,
- "learning_rate": 6.581632653061225e-05,
- "loss": 0.9668,
+ "epoch": 11.88,
+ "learning_rate": 5.056818181818183e-05,
+ "loss": 0.3914,
"step": 1052
},
{
- "epoch": 21.31,
- "learning_rate": 6.568877551020408e-05,
- "loss": 1.0008,
+ "epoch": 11.9,
+ "learning_rate": 5.042613636363637e-05,
+ "loss": 0.3908,
"step": 1053
},
{
- "epoch": 21.33,
- "learning_rate": 6.556122448979592e-05,
- "loss": 0.9825,
+ "epoch": 11.91,
+ "learning_rate": 5.0284090909090905e-05,
+ "loss": 0.3921,
"step": 1054
},
{
- "epoch": 21.35,
- "learning_rate": 6.543367346938776e-05,
- "loss": 1.0174,
+ "epoch": 11.92,
+ "learning_rate": 5.0142045454545464e-05,
+ "loss": 0.4077,
"step": 1055
},
{
- "epoch": 21.37,
- "learning_rate": 6.530612244897959e-05,
- "loss": 0.9685,
+ "epoch": 11.93,
+ "learning_rate": 5e-05,
+ "loss": 0.3973,
"step": 1056
},
{
- "epoch": 21.39,
- "learning_rate": 6.517857142857143e-05,
- "loss": 0.9265,
+ "epoch": 11.94,
+ "learning_rate": 4.985795454545455e-05,
+ "loss": 0.3986,
"step": 1057
},
{
- "epoch": 21.41,
- "learning_rate": 6.505102040816326e-05,
- "loss": 0.9495,
+ "epoch": 11.95,
+ "learning_rate": 4.971590909090909e-05,
+ "loss": 0.3938,
"step": 1058
},
{
- "epoch": 21.43,
- "learning_rate": 6.49234693877551e-05,
- "loss": 0.9541,
+ "epoch": 11.96,
+ "learning_rate": 4.957386363636364e-05,
+ "loss": 0.3897,
"step": 1059
},
{
- "epoch": 21.45,
- "learning_rate": 6.479591836734694e-05,
- "loss": 0.9299,
+ "epoch": 11.98,
+ "learning_rate": 4.943181818181818e-05,
+ "loss": 0.3965,
"step": 1060
},
{
- "epoch": 21.47,
- "learning_rate": 6.466836734693877e-05,
- "loss": 0.9625,
+ "epoch": 11.99,
+ "learning_rate": 4.9289772727272735e-05,
+ "loss": 0.3999,
"step": 1061
},
{
- "epoch": 21.49,
- "learning_rate": 6.454081632653061e-05,
- "loss": 1.0054,
+ "epoch": 12.0,
+ "learning_rate": 4.914772727272727e-05,
+ "loss": 0.3814,
"step": 1062
},
{
- "epoch": 21.51,
- "learning_rate": 6.441326530612244e-05,
- "loss": 0.9893,
+ "epoch": 12.01,
+ "learning_rate": 4.900568181818182e-05,
+ "loss": 0.3879,
"step": 1063
},
{
- "epoch": 21.53,
- "learning_rate": 6.428571428571429e-05,
- "loss": 0.9906,
+ "epoch": 12.02,
+ "learning_rate": 4.886363636363637e-05,
+ "loss": 0.3768,
"step": 1064
},
{
- "epoch": 21.55,
- "learning_rate": 6.415816326530613e-05,
- "loss": 0.9487,
+ "epoch": 12.03,
+ "learning_rate": 4.8721590909090915e-05,
+ "loss": 0.3813,
"step": 1065
},
{
- "epoch": 21.57,
- "learning_rate": 6.403061224489796e-05,
- "loss": 0.9728,
+ "epoch": 12.04,
+ "learning_rate": 4.857954545454545e-05,
+ "loss": 0.3759,
"step": 1066
},
{
- "epoch": 21.59,
- "learning_rate": 6.390306122448981e-05,
- "loss": 0.9883,
+ "epoch": 12.05,
+ "learning_rate": 4.8437500000000005e-05,
+ "loss": 0.3817,
"step": 1067
},
{
- "epoch": 21.61,
- "learning_rate": 6.377551020408164e-05,
- "loss": 1.053,
+ "epoch": 12.07,
+ "learning_rate": 4.829545454545455e-05,
+ "loss": 0.3773,
"step": 1068
},
{
- "epoch": 21.63,
- "learning_rate": 6.364795918367348e-05,
- "loss": 1.012,
+ "epoch": 12.08,
+ "learning_rate": 4.815340909090909e-05,
+ "loss": 0.3807,
"step": 1069
},
{
- "epoch": 21.65,
- "learning_rate": 6.352040816326531e-05,
- "loss": 0.962,
+ "epoch": 12.09,
+ "learning_rate": 4.801136363636364e-05,
+ "loss": 0.3757,
"step": 1070
},
{
- "epoch": 21.67,
- "learning_rate": 6.339285714285714e-05,
- "loss": 0.9955,
+ "epoch": 12.1,
+ "learning_rate": 4.7869318181818185e-05,
+ "loss": 0.3819,
"step": 1071
},
{
- "epoch": 21.69,
- "learning_rate": 6.326530612244899e-05,
- "loss": 0.9908,
+ "epoch": 12.11,
+ "learning_rate": 4.772727272727273e-05,
+ "loss": 0.3731,
"step": 1072
},
{
- "epoch": 21.71,
- "learning_rate": 6.313775510204082e-05,
- "loss": 1.0327,
+ "epoch": 12.12,
+ "learning_rate": 4.7585227272727276e-05,
+ "loss": 0.3706,
"step": 1073
},
{
- "epoch": 21.73,
- "learning_rate": 6.301020408163265e-05,
- "loss": 0.9255,
+ "epoch": 12.13,
+ "learning_rate": 4.744318181818182e-05,
+ "loss": 0.3762,
"step": 1074
},
{
- "epoch": 21.75,
- "learning_rate": 6.28826530612245e-05,
- "loss": 0.9268,
+ "epoch": 12.14,
+ "learning_rate": 4.7301136363636366e-05,
+ "loss": 0.3749,
"step": 1075
},
{
- "epoch": 21.77,
- "learning_rate": 6.275510204081633e-05,
- "loss": 0.9204,
+ "epoch": 12.16,
+ "learning_rate": 4.715909090909091e-05,
+ "loss": 0.3884,
"step": 1076
},
{
- "epoch": 21.79,
- "learning_rate": 6.262755102040817e-05,
- "loss": 0.9838,
+ "epoch": 12.17,
+ "learning_rate": 4.7017045454545456e-05,
+ "loss": 0.373,
"step": 1077
},
{
- "epoch": 21.81,
- "learning_rate": 6.25e-05,
- "loss": 0.954,
+ "epoch": 12.18,
+ "learning_rate": 4.6875e-05,
+ "loss": 0.374,
"step": 1078
},
{
- "epoch": 21.83,
- "learning_rate": 6.237244897959183e-05,
- "loss": 1.0102,
+ "epoch": 12.19,
+ "learning_rate": 4.6732954545454546e-05,
+ "loss": 0.3813,
"step": 1079
},
{
- "epoch": 21.85,
- "learning_rate": 6.224489795918368e-05,
- "loss": 0.916,
+ "epoch": 12.2,
+ "learning_rate": 4.659090909090909e-05,
+ "loss": 0.3745,
"step": 1080
},
{
- "epoch": 21.87,
- "learning_rate": 6.211734693877551e-05,
- "loss": 0.9939,
+ "epoch": 12.21,
+ "learning_rate": 4.6448863636363636e-05,
+ "loss": 0.3646,
"step": 1081
},
{
- "epoch": 21.89,
- "learning_rate": 6.198979591836735e-05,
- "loss": 0.9675,
+ "epoch": 12.22,
+ "learning_rate": 4.630681818181818e-05,
+ "loss": 0.3729,
"step": 1082
},
{
- "epoch": 21.91,
- "learning_rate": 6.186224489795918e-05,
- "loss": 0.9666,
+ "epoch": 12.24,
+ "learning_rate": 4.616477272727273e-05,
+ "loss": 0.3701,
"step": 1083
},
{
- "epoch": 21.93,
- "learning_rate": 6.173469387755101e-05,
- "loss": 0.9919,
+ "epoch": 12.25,
+ "learning_rate": 4.602272727272727e-05,
+ "loss": 0.3655,
"step": 1084
},
{
- "epoch": 21.95,
- "learning_rate": 6.160714285714286e-05,
- "loss": 1.0106,
+ "epoch": 12.26,
+ "learning_rate": 4.5880681818181817e-05,
+ "loss": 0.3758,
"step": 1085
},
{
- "epoch": 21.97,
- "learning_rate": 6.14795918367347e-05,
- "loss": 0.9982,
+ "epoch": 12.27,
+ "learning_rate": 4.573863636363637e-05,
+ "loss": 0.3682,
"step": 1086
},
{
- "epoch": 21.99,
- "learning_rate": 6.135204081632653e-05,
- "loss": 1.0137,
+ "epoch": 12.28,
+ "learning_rate": 4.5596590909090913e-05,
+ "loss": 0.3865,
"step": 1087
},
{
- "epoch": 22.01,
- "learning_rate": 6.122448979591838e-05,
- "loss": 0.9331,
+ "epoch": 12.29,
+ "learning_rate": 4.545454545454546e-05,
+ "loss": 0.363,
"step": 1088
},
{
- "epoch": 22.03,
- "learning_rate": 6.109693877551021e-05,
- "loss": 0.8834,
+ "epoch": 12.3,
+ "learning_rate": 4.5312500000000004e-05,
+ "loss": 0.3727,
"step": 1089
},
{
- "epoch": 22.06,
- "learning_rate": 6.0969387755102046e-05,
- "loss": 0.9757,
+ "epoch": 12.31,
+ "learning_rate": 4.517045454545455e-05,
+ "loss": 0.3827,
"step": 1090
},
{
- "epoch": 22.08,
- "learning_rate": 6.084183673469388e-05,
- "loss": 0.9038,
+ "epoch": 12.33,
+ "learning_rate": 4.5028409090909094e-05,
+ "loss": 0.3658,
"step": 1091
},
{
- "epoch": 22.1,
- "learning_rate": 6.0714285714285715e-05,
- "loss": 0.9097,
+ "epoch": 12.34,
+ "learning_rate": 4.488636363636364e-05,
+ "loss": 0.3844,
"step": 1092
},
{
- "epoch": 22.12,
- "learning_rate": 6.058673469387756e-05,
- "loss": 0.8972,
+ "epoch": 12.35,
+ "learning_rate": 4.4744318181818184e-05,
+ "loss": 0.3731,
"step": 1093
},
{
- "epoch": 22.14,
- "learning_rate": 6.045918367346939e-05,
- "loss": 0.8825,
+ "epoch": 12.36,
+ "learning_rate": 4.460227272727273e-05,
+ "loss": 0.3767,
"step": 1094
},
{
- "epoch": 22.16,
- "learning_rate": 6.0331632653061234e-05,
- "loss": 0.9814,
+ "epoch": 12.37,
+ "learning_rate": 4.4460227272727274e-05,
+ "loss": 0.3751,
"step": 1095
},
{
- "epoch": 22.18,
- "learning_rate": 6.0204081632653065e-05,
- "loss": 0.9874,
+ "epoch": 12.38,
+ "learning_rate": 4.431818181818182e-05,
+ "loss": 0.3718,
"step": 1096
},
{
- "epoch": 22.2,
- "learning_rate": 6.0076530612244896e-05,
- "loss": 0.912,
+ "epoch": 12.39,
+ "learning_rate": 4.4176136363636364e-05,
+ "loss": 0.3833,
"step": 1097
},
{
- "epoch": 22.22,
- "learning_rate": 5.994897959183674e-05,
- "loss": 0.9206,
+ "epoch": 12.4,
+ "learning_rate": 4.4034090909090916e-05,
+ "loss": 0.3673,
"step": 1098
},
{
- "epoch": 22.24,
- "learning_rate": 5.982142857142857e-05,
- "loss": 0.9497,
+ "epoch": 12.42,
+ "learning_rate": 4.3892045454545454e-05,
+ "loss": 0.3799,
"step": 1099
},
{
- "epoch": 22.26,
- "learning_rate": 5.9693877551020416e-05,
- "loss": 0.9269,
+ "epoch": 12.43,
+ "learning_rate": 4.375e-05,
+ "loss": 0.3661,
"step": 1100
}
],
"logging_steps": 1,
- "max_steps": 1568,
- "num_train_epochs": 32,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
"save_steps": 100,
- "total_flos": 1.628705955351122e+18,
+ "total_flos": 1.5012226913684582e+18,
"trial_name": null,
"trial_params": null
}
diff --git a/checkpoint-1100/training_args.bin b/checkpoint-1100/training_args.bin
index db23e07d097c18532e52f58a70eb72d22e39c8c1..ee7ddb867f05d9a969f71467a8eb88994865cf51 100644
--- a/checkpoint-1100/training_args.bin
+++ b/checkpoint-1100/training_args.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
size 4155
diff --git a/checkpoint-1200/adapter_model.bin b/checkpoint-1200/adapter_model.bin
index fe838bfb517b69e550de232754730118ea65bb04..ca33c973443b9a5cdd1321d0b918f881e3c41940 100644
--- a/checkpoint-1200/adapter_model.bin
+++ b/checkpoint-1200/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:d13f1953081527a4a05ac5762a6e373fae509922a72baa18bfbc0ea2fdd0db77
+oid sha256:65fdc6611558f201789c26daf35ebf132a5b6ddfa2a80501271c771a95626898
size 39409357
diff --git a/checkpoint-1200/optimizer.pt b/checkpoint-1200/optimizer.pt
index 2a557a97984c4cc74844fb337ee8e2cc0c298b34..1d1ed4505caa26ad2874c065eaafeea062885ba7 100644
--- a/checkpoint-1200/optimizer.pt
+++ b/checkpoint-1200/optimizer.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:4b4d37b67055d94cd6568b24b76e241acc964153f215407a64e94710d00d1e06
+oid sha256:bebd87283ad07af460aa2916048a35363c5b38020c6a8b96378eae6a00b91f6f
size 78844421
diff --git a/checkpoint-1200/rng_state.pth b/checkpoint-1200/rng_state.pth
index fead25ae6e1694df464049cc69133704457634ec..60089dd8a0937e03b89f32d15c42d6158dd4df6e 100644
--- a/checkpoint-1200/rng_state.pth
+++ b/checkpoint-1200/rng_state.pth
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b32bbef891dbdd3524f32551a03a56bb081b6c86879cea3d24ae28b3c8f4bc5f
+oid sha256:830e818e6899ff30b431c470cff0e4bafb5e8c7e429469a6fb9dfb5272323c44
size 14575
diff --git a/checkpoint-1200/scheduler.pt b/checkpoint-1200/scheduler.pt
index 6552b7f80e3e5fe7062d2376620abb1ac8c373f3..37c14d25d17272726a6bb3834976522f235cec65 100644
--- a/checkpoint-1200/scheduler.pt
+++ b/checkpoint-1200/scheduler.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:13122a9f43d31f9abd38d193f16e53342905df794d9995e7f5483234c3e54c54
+oid sha256:ffe5c887b5a4ca00db6fe980a4033162925ba89d876b21267ad5ea43ba89dcd3
size 627
diff --git a/checkpoint-1200/trainer_state.json b/checkpoint-1200/trainer_state.json
index e6d8ccf4d007ba938f1e3a0c7b69dfee967403ff..c8ed4c0eb146d2cd0cbfc8eb796bbd79930c275b 100644
--- a/checkpoint-1200/trainer_state.json
+++ b/checkpoint-1200/trainer_state.json
@@ -1,7 +1,7 @@
{
"best_metric": null,
"best_model_checkpoint": null,
- "epoch": 24.28074612709453,
+ "epoch": 13.55692850838482,
"eval_steps": 500,
"global_step": 1200,
"is_hyper_param_search": false,
@@ -9,7211 +9,7211 @@
"is_world_process_zero": true,
"log_history": [
{
- "epoch": 0.02,
- "learning_rate": 0.00019987244897959184,
- "loss": 3.2215,
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
"step": 1
},
{
- "epoch": 0.04,
- "learning_rate": 0.00019974489795918367,
- "loss": 2.8365,
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
"step": 2
},
{
- "epoch": 0.06,
- "learning_rate": 0.00019961734693877553,
- "loss": 2.602,
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
"step": 3
},
{
- "epoch": 0.08,
- "learning_rate": 0.00019948979591836736,
- "loss": 2.4196,
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
"step": 4
},
{
- "epoch": 0.1,
- "learning_rate": 0.0001993622448979592,
- "loss": 2.2574,
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
"step": 5
},
{
- "epoch": 0.12,
- "learning_rate": 0.00019923469387755102,
- "loss": 2.2239,
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
"step": 6
},
{
- "epoch": 0.14,
- "learning_rate": 0.00019910714285714288,
- "loss": 2.1661,
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
"step": 7
},
{
- "epoch": 0.16,
- "learning_rate": 0.0001989795918367347,
- "loss": 2.0987,
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
"step": 8
},
{
- "epoch": 0.18,
- "learning_rate": 0.00019885204081632654,
- "loss": 2.015,
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
"step": 9
},
{
- "epoch": 0.2,
- "learning_rate": 0.00019872448979591837,
- "loss": 1.9771,
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
"step": 10
},
{
- "epoch": 0.22,
- "learning_rate": 0.00019859693877551023,
- "loss": 2.0271,
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
"step": 11
},
{
- "epoch": 0.24,
- "learning_rate": 0.00019846938775510203,
- "loss": 1.9812,
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
"step": 12
},
{
- "epoch": 0.26,
- "learning_rate": 0.0001983418367346939,
- "loss": 2.0834,
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
"step": 13
},
{
- "epoch": 0.28,
- "learning_rate": 0.00019821428571428572,
- "loss": 1.9174,
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
"step": 14
},
{
- "epoch": 0.3,
- "learning_rate": 0.00019808673469387755,
- "loss": 1.8409,
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
"step": 15
},
{
- "epoch": 0.32,
- "learning_rate": 0.00019795918367346938,
- "loss": 1.929,
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
"step": 16
},
{
- "epoch": 0.34,
- "learning_rate": 0.00019783163265306124,
- "loss": 2.0041,
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
"step": 17
},
{
- "epoch": 0.36,
- "learning_rate": 0.00019770408163265305,
- "loss": 1.9385,
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
"step": 18
},
{
- "epoch": 0.38,
- "learning_rate": 0.0001975765306122449,
- "loss": 1.9592,
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
"step": 19
},
{
- "epoch": 0.4,
- "learning_rate": 0.00019744897959183674,
- "loss": 1.9701,
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
"step": 20
},
{
- "epoch": 0.42,
- "learning_rate": 0.0001973214285714286,
- "loss": 1.9277,
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
"step": 21
},
{
- "epoch": 0.45,
- "learning_rate": 0.00019719387755102042,
- "loss": 1.8394,
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
"step": 22
},
{
- "epoch": 0.47,
- "learning_rate": 0.00019706632653061226,
- "loss": 1.8666,
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
"step": 23
},
{
- "epoch": 0.49,
- "learning_rate": 0.00019693877551020409,
- "loss": 1.8997,
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
"step": 24
},
{
- "epoch": 0.51,
- "learning_rate": 0.00019681122448979592,
- "loss": 1.9432,
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
"step": 25
},
{
- "epoch": 0.53,
- "learning_rate": 0.00019668367346938777,
- "loss": 1.9137,
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
"step": 26
},
{
- "epoch": 0.55,
- "learning_rate": 0.0001965561224489796,
- "loss": 1.905,
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
"step": 27
},
{
- "epoch": 0.57,
- "learning_rate": 0.00019642857142857144,
- "loss": 1.8708,
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
"step": 28
},
{
- "epoch": 0.59,
- "learning_rate": 0.00019630102040816327,
- "loss": 1.9097,
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
"step": 29
},
{
- "epoch": 0.61,
- "learning_rate": 0.00019617346938775513,
- "loss": 1.896,
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
"step": 30
},
{
- "epoch": 0.63,
- "learning_rate": 0.00019604591836734696,
- "loss": 1.8834,
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
"step": 31
},
{
- "epoch": 0.65,
- "learning_rate": 0.0001959183673469388,
- "loss": 1.8323,
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
"step": 32
},
{
- "epoch": 0.67,
- "learning_rate": 0.00019579081632653062,
- "loss": 1.804,
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
"step": 33
},
{
- "epoch": 0.69,
- "learning_rate": 0.00019566326530612248,
- "loss": 1.8906,
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
"step": 34
},
{
- "epoch": 0.71,
- "learning_rate": 0.00019553571428571428,
- "loss": 1.8693,
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
"step": 35
},
{
- "epoch": 0.73,
- "learning_rate": 0.00019540816326530614,
- "loss": 1.9308,
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
"step": 36
},
{
- "epoch": 0.75,
- "learning_rate": 0.00019528061224489797,
- "loss": 1.8082,
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
"step": 37
},
{
- "epoch": 0.77,
- "learning_rate": 0.0001951530612244898,
- "loss": 1.848,
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
"step": 38
},
{
- "epoch": 0.79,
- "learning_rate": 0.00019502551020408163,
- "loss": 1.8866,
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
"step": 39
},
{
- "epoch": 0.81,
- "learning_rate": 0.0001948979591836735,
- "loss": 1.7844,
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
"step": 40
},
{
- "epoch": 0.83,
- "learning_rate": 0.0001947704081632653,
- "loss": 1.8485,
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
"step": 41
},
{
- "epoch": 0.85,
- "learning_rate": 0.00019464285714285715,
- "loss": 1.7917,
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
"step": 42
},
{
- "epoch": 0.87,
- "learning_rate": 0.00019451530612244898,
- "loss": 1.7342,
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
"step": 43
},
{
- "epoch": 0.89,
- "learning_rate": 0.00019438775510204084,
- "loss": 1.8479,
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
"step": 44
},
{
- "epoch": 0.91,
- "learning_rate": 0.00019426020408163267,
- "loss": 1.8639,
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
"step": 45
},
{
- "epoch": 0.93,
- "learning_rate": 0.0001941326530612245,
- "loss": 1.8166,
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
"step": 46
},
{
- "epoch": 0.95,
- "learning_rate": 0.00019400510204081633,
- "loss": 1.7566,
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
"step": 47
},
{
- "epoch": 0.97,
- "learning_rate": 0.00019387755102040816,
- "loss": 1.8071,
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
"step": 48
},
{
- "epoch": 0.99,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.8612,
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
"step": 49
},
{
- "epoch": 1.01,
- "learning_rate": 0.00019362244897959185,
- "loss": 1.7819,
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
"step": 50
},
{
- "epoch": 1.03,
- "learning_rate": 0.00019349489795918368,
- "loss": 1.8647,
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
"step": 51
},
{
- "epoch": 1.05,
- "learning_rate": 0.0001933673469387755,
- "loss": 1.8196,
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
"step": 52
},
{
- "epoch": 1.07,
- "learning_rate": 0.00019323979591836737,
- "loss": 1.8027,
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
"step": 53
},
{
- "epoch": 1.09,
- "learning_rate": 0.00019311224489795917,
- "loss": 1.8927,
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
"step": 54
},
{
- "epoch": 1.11,
- "learning_rate": 0.00019298469387755103,
- "loss": 1.8481,
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
"step": 55
},
{
- "epoch": 1.13,
- "learning_rate": 0.00019285714285714286,
- "loss": 1.7781,
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
"step": 56
},
{
- "epoch": 1.15,
- "learning_rate": 0.00019272959183673472,
- "loss": 1.8101,
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
"step": 57
},
{
- "epoch": 1.17,
- "learning_rate": 0.00019260204081632653,
- "loss": 1.7257,
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
"step": 58
},
{
- "epoch": 1.19,
- "learning_rate": 0.00019247448979591838,
- "loss": 1.8185,
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
"step": 59
},
{
- "epoch": 1.21,
- "learning_rate": 0.00019234693877551021,
- "loss": 1.8557,
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
"step": 60
},
{
- "epoch": 1.23,
- "learning_rate": 0.00019221938775510204,
- "loss": 1.7418,
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
"step": 61
},
{
- "epoch": 1.25,
- "learning_rate": 0.00019209183673469388,
- "loss": 1.6879,
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
"step": 62
},
{
- "epoch": 1.27,
- "learning_rate": 0.00019196428571428573,
- "loss": 1.7651,
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
"step": 63
},
{
- "epoch": 1.29,
- "learning_rate": 0.00019183673469387756,
- "loss": 1.7759,
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
"step": 64
},
{
- "epoch": 1.32,
- "learning_rate": 0.0001917091836734694,
- "loss": 1.7691,
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
"step": 65
},
{
- "epoch": 1.34,
- "learning_rate": 0.00019158163265306123,
- "loss": 1.7794,
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
"step": 66
},
{
- "epoch": 1.36,
- "learning_rate": 0.00019145408163265306,
- "loss": 1.8152,
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
"step": 67
},
{
- "epoch": 1.38,
- "learning_rate": 0.00019132653061224492,
- "loss": 1.8052,
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
"step": 68
},
{
- "epoch": 1.4,
- "learning_rate": 0.00019119897959183675,
- "loss": 1.8054,
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
"step": 69
},
{
- "epoch": 1.42,
- "learning_rate": 0.00019107142857142858,
- "loss": 1.8114,
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
"step": 70
},
{
- "epoch": 1.44,
- "learning_rate": 0.0001909438775510204,
- "loss": 1.7749,
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
"step": 71
},
{
- "epoch": 1.46,
- "learning_rate": 0.00019081632653061227,
- "loss": 1.777,
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
"step": 72
},
{
- "epoch": 1.48,
- "learning_rate": 0.0001906887755102041,
- "loss": 1.7896,
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
"step": 73
},
{
- "epoch": 1.5,
- "learning_rate": 0.00019056122448979593,
- "loss": 1.8335,
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
"step": 74
},
{
- "epoch": 1.52,
- "learning_rate": 0.00019043367346938776,
- "loss": 1.8155,
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
"step": 75
},
{
- "epoch": 1.54,
- "learning_rate": 0.00019030612244897962,
- "loss": 1.8224,
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
"step": 76
},
{
- "epoch": 1.56,
- "learning_rate": 0.00019017857142857142,
- "loss": 1.7889,
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
"step": 77
},
{
- "epoch": 1.58,
- "learning_rate": 0.00019005102040816328,
- "loss": 1.8866,
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
"step": 78
},
{
- "epoch": 1.6,
- "learning_rate": 0.0001899234693877551,
- "loss": 1.8439,
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
"step": 79
},
{
- "epoch": 1.62,
- "learning_rate": 0.00018979591836734697,
- "loss": 1.7906,
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
"step": 80
},
{
- "epoch": 1.64,
- "learning_rate": 0.00018966836734693877,
- "loss": 1.8627,
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
"step": 81
},
{
- "epoch": 1.66,
- "learning_rate": 0.00018954081632653063,
- "loss": 1.7497,
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
"step": 82
},
{
- "epoch": 1.68,
- "learning_rate": 0.00018941326530612246,
- "loss": 1.7936,
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
"step": 83
},
{
- "epoch": 1.7,
- "learning_rate": 0.0001892857142857143,
- "loss": 1.8341,
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
"step": 84
},
{
- "epoch": 1.72,
- "learning_rate": 0.00018915816326530612,
- "loss": 1.7868,
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
"step": 85
},
{
- "epoch": 1.74,
- "learning_rate": 0.00018903061224489798,
- "loss": 1.7493,
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
"step": 86
},
{
- "epoch": 1.76,
- "learning_rate": 0.0001889030612244898,
- "loss": 1.7926,
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
"step": 87
},
{
- "epoch": 1.78,
- "learning_rate": 0.00018877551020408164,
- "loss": 1.8278,
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
"step": 88
},
{
- "epoch": 1.8,
- "learning_rate": 0.00018864795918367347,
- "loss": 1.7387,
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
"step": 89
},
{
- "epoch": 1.82,
- "learning_rate": 0.0001885204081632653,
- "loss": 1.7669,
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
"step": 90
},
{
- "epoch": 1.84,
- "learning_rate": 0.00018839285714285716,
- "loss": 1.7686,
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
"step": 91
},
{
- "epoch": 1.86,
- "learning_rate": 0.000188265306122449,
- "loss": 1.7759,
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
"step": 92
},
{
- "epoch": 1.88,
- "learning_rate": 0.00018813775510204082,
- "loss": 1.7016,
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
"step": 93
},
{
- "epoch": 1.9,
- "learning_rate": 0.00018801020408163265,
- "loss": 1.8123,
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
"step": 94
},
{
- "epoch": 1.92,
- "learning_rate": 0.0001878826530612245,
- "loss": 1.8315,
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
"step": 95
},
{
- "epoch": 1.94,
- "learning_rate": 0.00018775510204081634,
- "loss": 1.7679,
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
"step": 96
},
{
- "epoch": 1.96,
- "learning_rate": 0.00018762755102040817,
- "loss": 1.7874,
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
"step": 97
},
{
- "epoch": 1.98,
- "learning_rate": 0.0001875,
- "loss": 1.8008,
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
"step": 98
},
{
- "epoch": 2.0,
- "learning_rate": 0.00018737244897959186,
- "loss": 1.7177,
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
"step": 99
},
{
- "epoch": 2.02,
- "learning_rate": 0.00018724489795918367,
- "loss": 1.7272,
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
"step": 100
},
{
- "epoch": 2.04,
- "learning_rate": 0.00018711734693877552,
- "loss": 1.7848,
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
"step": 101
},
{
- "epoch": 2.06,
- "learning_rate": 0.00018698979591836735,
- "loss": 1.744,
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
"step": 102
},
{
- "epoch": 2.08,
- "learning_rate": 0.00018686224489795919,
- "loss": 1.7005,
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
"step": 103
},
{
- "epoch": 2.1,
- "learning_rate": 0.00018673469387755102,
- "loss": 1.8247,
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
"step": 104
},
{
- "epoch": 2.12,
- "learning_rate": 0.00018660714285714287,
- "loss": 1.6855,
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
"step": 105
},
{
- "epoch": 2.14,
- "learning_rate": 0.0001864795918367347,
- "loss": 1.7627,
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
"step": 106
},
{
- "epoch": 2.17,
- "learning_rate": 0.00018635204081632654,
- "loss": 1.7564,
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
"step": 107
},
{
- "epoch": 2.19,
- "learning_rate": 0.00018622448979591837,
- "loss": 1.8237,
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
"step": 108
},
{
- "epoch": 2.21,
- "learning_rate": 0.00018609693877551022,
- "loss": 1.7421,
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
"step": 109
},
{
- "epoch": 2.23,
- "learning_rate": 0.00018596938775510206,
- "loss": 1.7517,
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
"step": 110
},
{
- "epoch": 2.25,
- "learning_rate": 0.0001858418367346939,
- "loss": 1.7515,
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
"step": 111
},
{
- "epoch": 2.27,
- "learning_rate": 0.00018571428571428572,
- "loss": 1.7842,
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
"step": 112
},
{
- "epoch": 2.29,
- "learning_rate": 0.00018558673469387755,
- "loss": 1.8001,
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
"step": 113
},
{
- "epoch": 2.31,
- "learning_rate": 0.0001854591836734694,
- "loss": 1.7653,
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
"step": 114
},
{
- "epoch": 2.33,
- "learning_rate": 0.00018533163265306124,
- "loss": 1.694,
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
"step": 115
},
{
- "epoch": 2.35,
- "learning_rate": 0.00018520408163265307,
- "loss": 1.7457,
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
"step": 116
},
{
- "epoch": 2.37,
- "learning_rate": 0.0001850765306122449,
- "loss": 1.7899,
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
"step": 117
},
{
- "epoch": 2.39,
- "learning_rate": 0.00018494897959183676,
- "loss": 1.7473,
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
"step": 118
},
{
- "epoch": 2.41,
- "learning_rate": 0.0001848214285714286,
- "loss": 1.6639,
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
"step": 119
},
{
- "epoch": 2.43,
- "learning_rate": 0.00018469387755102042,
- "loss": 1.762,
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
"step": 120
},
{
- "epoch": 2.45,
- "learning_rate": 0.00018456632653061225,
- "loss": 1.7378,
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
"step": 121
},
{
- "epoch": 2.47,
- "learning_rate": 0.0001844387755102041,
- "loss": 1.672,
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
"step": 122
},
{
- "epoch": 2.49,
- "learning_rate": 0.0001843112244897959,
- "loss": 1.7267,
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
"step": 123
},
{
- "epoch": 2.51,
- "learning_rate": 0.00018418367346938777,
- "loss": 1.7825,
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
"step": 124
},
{
- "epoch": 2.53,
- "learning_rate": 0.0001840561224489796,
- "loss": 1.7566,
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
"step": 125
},
{
- "epoch": 2.55,
- "learning_rate": 0.00018392857142857143,
- "loss": 1.8169,
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
"step": 126
},
{
- "epoch": 2.57,
- "learning_rate": 0.00018380102040816326,
- "loss": 1.6801,
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
"step": 127
},
{
- "epoch": 2.59,
- "learning_rate": 0.00018367346938775512,
- "loss": 1.7292,
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
"step": 128
},
{
- "epoch": 2.61,
- "learning_rate": 0.00018354591836734695,
- "loss": 1.737,
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
"step": 129
},
{
- "epoch": 2.63,
- "learning_rate": 0.00018341836734693878,
- "loss": 1.7696,
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
"step": 130
},
{
- "epoch": 2.65,
- "learning_rate": 0.0001832908163265306,
- "loss": 1.7239,
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
"step": 131
},
{
- "epoch": 2.67,
- "learning_rate": 0.00018316326530612247,
- "loss": 1.7441,
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
"step": 132
},
{
- "epoch": 2.69,
- "learning_rate": 0.0001830357142857143,
- "loss": 1.7825,
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
"step": 133
},
{
- "epoch": 2.71,
- "learning_rate": 0.00018290816326530613,
- "loss": 1.7411,
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
"step": 134
},
{
- "epoch": 2.73,
- "learning_rate": 0.00018278061224489796,
- "loss": 1.7119,
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
"step": 135
},
{
- "epoch": 2.75,
- "learning_rate": 0.0001826530612244898,
- "loss": 1.7443,
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
"step": 136
},
{
- "epoch": 2.77,
- "learning_rate": 0.00018252551020408165,
- "loss": 1.7197,
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
"step": 137
},
{
- "epoch": 2.79,
- "learning_rate": 0.00018239795918367348,
- "loss": 1.7273,
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
"step": 138
},
{
- "epoch": 2.81,
- "learning_rate": 0.0001822704081632653,
- "loss": 1.7681,
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
"step": 139
},
{
- "epoch": 2.83,
- "learning_rate": 0.00018214285714285714,
- "loss": 1.8088,
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
"step": 140
},
{
- "epoch": 2.85,
- "learning_rate": 0.000182015306122449,
- "loss": 1.7301,
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
"step": 141
},
{
- "epoch": 2.87,
- "learning_rate": 0.00018188775510204083,
- "loss": 1.6853,
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
"step": 142
},
{
- "epoch": 2.89,
- "learning_rate": 0.00018176020408163266,
- "loss": 1.6966,
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
"step": 143
},
{
- "epoch": 2.91,
- "learning_rate": 0.0001816326530612245,
- "loss": 1.7938,
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
"step": 144
},
{
- "epoch": 2.93,
- "learning_rate": 0.00018150510204081635,
- "loss": 1.7639,
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
"step": 145
},
{
- "epoch": 2.95,
- "learning_rate": 0.00018137755102040816,
- "loss": 1.7527,
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
"step": 146
},
{
- "epoch": 2.97,
- "learning_rate": 0.00018125000000000001,
- "loss": 1.7386,
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
"step": 147
},
{
- "epoch": 2.99,
- "learning_rate": 0.00018112244897959185,
- "loss": 1.7223,
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
"step": 148
},
{
- "epoch": 3.01,
- "learning_rate": 0.00018099489795918368,
- "loss": 1.7571,
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
"step": 149
},
{
- "epoch": 3.04,
- "learning_rate": 0.0001808673469387755,
- "loss": 1.7054,
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
"step": 150
},
{
- "epoch": 3.06,
- "learning_rate": 0.00018073979591836737,
- "loss": 1.6581,
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
"step": 151
},
{
- "epoch": 3.08,
- "learning_rate": 0.00018061224489795917,
- "loss": 1.681,
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
"step": 152
},
{
- "epoch": 3.1,
- "learning_rate": 0.00018048469387755103,
- "loss": 1.7425,
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
"step": 153
},
{
- "epoch": 3.12,
- "learning_rate": 0.00018035714285714286,
- "loss": 1.7108,
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
"step": 154
},
{
- "epoch": 3.14,
- "learning_rate": 0.00018022959183673472,
- "loss": 1.7194,
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
"step": 155
},
{
- "epoch": 3.16,
- "learning_rate": 0.00018010204081632655,
- "loss": 1.6953,
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
"step": 156
},
{
- "epoch": 3.18,
- "learning_rate": 0.00017997448979591838,
- "loss": 1.669,
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
"step": 157
},
{
- "epoch": 3.2,
- "learning_rate": 0.0001798469387755102,
- "loss": 1.744,
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
"step": 158
},
{
- "epoch": 3.22,
- "learning_rate": 0.00017971938775510204,
- "loss": 1.6467,
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
"step": 159
},
{
- "epoch": 3.24,
- "learning_rate": 0.0001795918367346939,
- "loss": 1.7103,
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
"step": 160
},
{
- "epoch": 3.26,
- "learning_rate": 0.00017946428571428573,
- "loss": 1.6662,
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
"step": 161
},
{
- "epoch": 3.28,
- "learning_rate": 0.00017933673469387756,
- "loss": 1.6657,
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
"step": 162
},
{
- "epoch": 3.3,
- "learning_rate": 0.0001792091836734694,
- "loss": 1.791,
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
"step": 163
},
{
- "epoch": 3.32,
- "learning_rate": 0.00017908163265306125,
- "loss": 1.7704,
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
"step": 164
},
{
- "epoch": 3.34,
- "learning_rate": 0.00017895408163265305,
- "loss": 1.7229,
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
"step": 165
},
{
- "epoch": 3.36,
- "learning_rate": 0.0001788265306122449,
- "loss": 1.76,
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
"step": 166
},
{
- "epoch": 3.38,
- "learning_rate": 0.00017869897959183674,
- "loss": 1.6482,
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
"step": 167
},
{
- "epoch": 3.4,
- "learning_rate": 0.0001785714285714286,
- "loss": 1.8076,
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
"step": 168
},
{
- "epoch": 3.42,
- "learning_rate": 0.0001784438775510204,
- "loss": 1.7368,
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
"step": 169
},
{
- "epoch": 3.44,
- "learning_rate": 0.00017831632653061226,
- "loss": 1.6264,
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
"step": 170
},
{
- "epoch": 3.46,
- "learning_rate": 0.0001781887755102041,
- "loss": 1.6289,
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
"step": 171
},
{
- "epoch": 3.48,
- "learning_rate": 0.00017806122448979592,
- "loss": 1.7913,
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
"step": 172
},
{
- "epoch": 3.5,
- "learning_rate": 0.00017793367346938775,
- "loss": 1.6985,
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
"step": 173
},
{
- "epoch": 3.52,
- "learning_rate": 0.0001778061224489796,
- "loss": 1.6936,
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
"step": 174
},
{
- "epoch": 3.54,
- "learning_rate": 0.00017767857142857141,
- "loss": 1.8068,
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
"step": 175
},
{
- "epoch": 3.56,
- "learning_rate": 0.00017755102040816327,
- "loss": 1.7243,
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
"step": 176
},
{
- "epoch": 3.58,
- "learning_rate": 0.0001774234693877551,
- "loss": 1.6893,
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
"step": 177
},
{
- "epoch": 3.6,
- "learning_rate": 0.00017729591836734696,
- "loss": 1.8122,
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
"step": 178
},
{
- "epoch": 3.62,
- "learning_rate": 0.0001771683673469388,
- "loss": 1.6562,
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
"step": 179
},
{
- "epoch": 3.64,
- "learning_rate": 0.00017704081632653062,
- "loss": 1.6999,
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
"step": 180
},
{
- "epoch": 3.66,
- "learning_rate": 0.00017691326530612245,
- "loss": 1.7229,
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
"step": 181
},
{
- "epoch": 3.68,
- "learning_rate": 0.00017678571428571428,
- "loss": 1.6764,
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
"step": 182
},
{
- "epoch": 3.7,
- "learning_rate": 0.00017665816326530614,
- "loss": 1.6982,
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
"step": 183
},
{
- "epoch": 3.72,
- "learning_rate": 0.00017653061224489797,
- "loss": 1.696,
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
"step": 184
},
{
- "epoch": 3.74,
- "learning_rate": 0.0001764030612244898,
- "loss": 1.6797,
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
"step": 185
},
{
- "epoch": 3.76,
- "learning_rate": 0.00017627551020408164,
- "loss": 1.637,
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
"step": 186
},
{
- "epoch": 3.78,
- "learning_rate": 0.0001761479591836735,
- "loss": 1.7074,
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
"step": 187
},
{
- "epoch": 3.8,
- "learning_rate": 0.0001760204081632653,
- "loss": 1.705,
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
"step": 188
},
{
- "epoch": 3.82,
- "learning_rate": 0.00017589285714285716,
- "loss": 1.6153,
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
"step": 189
},
{
- "epoch": 3.84,
- "learning_rate": 0.00017576530612244899,
- "loss": 1.7354,
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
"step": 190
},
{
- "epoch": 3.86,
- "learning_rate": 0.00017563775510204084,
- "loss": 1.6941,
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
"step": 191
},
{
- "epoch": 3.88,
- "learning_rate": 0.00017551020408163265,
- "loss": 1.7231,
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
"step": 192
},
{
- "epoch": 3.91,
- "learning_rate": 0.0001753826530612245,
- "loss": 1.7663,
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
"step": 193
},
{
- "epoch": 3.93,
- "learning_rate": 0.00017525510204081634,
- "loss": 1.6532,
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
"step": 194
},
{
- "epoch": 3.95,
- "learning_rate": 0.00017512755102040817,
- "loss": 1.7115,
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
"step": 195
},
{
- "epoch": 3.97,
- "learning_rate": 0.000175,
- "loss": 1.6955,
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
"step": 196
},
{
- "epoch": 3.99,
- "learning_rate": 0.00017487244897959186,
- "loss": 1.6863,
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
"step": 197
},
{
- "epoch": 4.01,
- "learning_rate": 0.00017474489795918366,
- "loss": 1.7012,
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
"step": 198
},
{
- "epoch": 4.03,
- "learning_rate": 0.00017461734693877552,
- "loss": 1.5927,
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
"step": 199
},
{
- "epoch": 4.05,
- "learning_rate": 0.00017448979591836735,
- "loss": 1.6272,
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
"step": 200
},
{
- "epoch": 4.07,
- "learning_rate": 0.00017436224489795918,
- "loss": 1.5994,
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
"step": 201
},
{
- "epoch": 4.09,
- "learning_rate": 0.00017423469387755104,
- "loss": 1.7141,
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
"step": 202
},
{
- "epoch": 4.11,
- "learning_rate": 0.00017410714285714287,
- "loss": 1.7547,
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
"step": 203
},
{
- "epoch": 4.13,
- "learning_rate": 0.0001739795918367347,
- "loss": 1.6254,
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
"step": 204
},
{
- "epoch": 4.15,
- "learning_rate": 0.00017385204081632653,
- "loss": 1.6686,
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
"step": 205
},
{
- "epoch": 4.17,
- "learning_rate": 0.0001737244897959184,
- "loss": 1.6684,
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
"step": 206
},
{
- "epoch": 4.19,
- "learning_rate": 0.00017359693877551022,
- "loss": 1.6724,
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
"step": 207
},
{
- "epoch": 4.21,
- "learning_rate": 0.00017346938775510205,
- "loss": 1.7361,
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
"step": 208
},
{
- "epoch": 4.23,
- "learning_rate": 0.00017334183673469388,
- "loss": 1.7167,
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
"step": 209
},
{
- "epoch": 4.25,
- "learning_rate": 0.00017321428571428574,
- "loss": 1.7226,
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
"step": 210
},
{
- "epoch": 4.27,
- "learning_rate": 0.00017308673469387754,
- "loss": 1.7133,
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
"step": 211
},
{
- "epoch": 4.29,
- "learning_rate": 0.0001729591836734694,
- "loss": 1.649,
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
"step": 212
},
{
- "epoch": 4.31,
- "learning_rate": 0.00017283163265306123,
- "loss": 1.7104,
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
"step": 213
},
{
- "epoch": 4.33,
- "learning_rate": 0.00017270408163265306,
- "loss": 1.6861,
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
"step": 214
},
{
- "epoch": 4.35,
- "learning_rate": 0.0001725765306122449,
- "loss": 1.648,
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
"step": 215
},
{
- "epoch": 4.37,
- "learning_rate": 0.00017244897959183675,
- "loss": 1.6215,
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
"step": 216
},
{
- "epoch": 4.39,
- "learning_rate": 0.00017232142857142858,
- "loss": 1.6334,
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
"step": 217
},
{
- "epoch": 4.41,
- "learning_rate": 0.0001721938775510204,
- "loss": 1.6283,
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
"step": 218
},
{
- "epoch": 4.43,
- "learning_rate": 0.00017206632653061224,
- "loss": 1.6462,
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
"step": 219
},
{
- "epoch": 4.45,
- "learning_rate": 0.0001719387755102041,
- "loss": 1.7233,
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
"step": 220
},
{
- "epoch": 4.47,
- "learning_rate": 0.0001718112244897959,
- "loss": 1.7839,
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
"step": 221
},
{
- "epoch": 4.49,
- "learning_rate": 0.00017168367346938776,
- "loss": 1.7204,
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
"step": 222
},
{
- "epoch": 4.51,
- "learning_rate": 0.0001715561224489796,
- "loss": 1.7671,
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
"step": 223
},
{
- "epoch": 4.53,
- "learning_rate": 0.00017142857142857143,
- "loss": 1.6824,
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
"step": 224
},
{
- "epoch": 4.55,
- "learning_rate": 0.00017130102040816328,
- "loss": 1.7068,
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
"step": 225
},
{
- "epoch": 4.57,
- "learning_rate": 0.00017117346938775511,
- "loss": 1.6515,
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
"step": 226
},
{
- "epoch": 4.59,
- "learning_rate": 0.00017104591836734694,
- "loss": 1.6586,
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
"step": 227
},
{
- "epoch": 4.61,
- "learning_rate": 0.00017091836734693878,
- "loss": 1.6355,
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
"step": 228
},
{
- "epoch": 4.63,
- "learning_rate": 0.00017079081632653063,
- "loss": 1.7173,
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
"step": 229
},
{
- "epoch": 4.65,
- "learning_rate": 0.00017066326530612246,
- "loss": 1.6585,
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
"step": 230
},
{
- "epoch": 4.67,
- "learning_rate": 0.0001705357142857143,
- "loss": 1.5856,
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
"step": 231
},
{
- "epoch": 4.69,
- "learning_rate": 0.00017040816326530613,
- "loss": 1.5923,
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
"step": 232
},
{
- "epoch": 4.71,
- "learning_rate": 0.00017028061224489798,
- "loss": 1.7128,
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
"step": 233
},
{
- "epoch": 4.73,
- "learning_rate": 0.0001701530612244898,
- "loss": 1.6971,
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
"step": 234
},
{
- "epoch": 4.75,
- "learning_rate": 0.00017002551020408165,
- "loss": 1.6416,
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
"step": 235
},
{
- "epoch": 4.78,
- "learning_rate": 0.00016989795918367348,
- "loss": 1.645,
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
"step": 236
},
{
- "epoch": 4.8,
- "learning_rate": 0.0001697704081632653,
- "loss": 1.6792,
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
"step": 237
},
{
- "epoch": 4.82,
- "learning_rate": 0.00016964285714285714,
- "loss": 1.6522,
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
"step": 238
},
{
- "epoch": 4.84,
- "learning_rate": 0.000169515306122449,
- "loss": 1.6315,
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
"step": 239
},
{
- "epoch": 4.86,
- "learning_rate": 0.00016938775510204083,
- "loss": 1.6622,
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
"step": 240
},
{
- "epoch": 4.88,
- "learning_rate": 0.00016926020408163266,
- "loss": 1.6566,
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
"step": 241
},
{
- "epoch": 4.9,
- "learning_rate": 0.0001691326530612245,
- "loss": 1.7141,
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
"step": 242
},
{
- "epoch": 4.92,
- "learning_rate": 0.00016900510204081635,
- "loss": 1.5873,
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
"step": 243
},
{
- "epoch": 4.94,
- "learning_rate": 0.00016887755102040818,
- "loss": 1.6571,
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
"step": 244
},
{
- "epoch": 4.96,
- "learning_rate": 0.00016875,
- "loss": 1.6829,
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
"step": 245
},
{
- "epoch": 4.98,
- "learning_rate": 0.00016862244897959184,
- "loss": 1.6935,
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
"step": 246
},
{
- "epoch": 5.0,
- "learning_rate": 0.00016849489795918367,
- "loss": 1.6782,
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
"step": 247
},
{
- "epoch": 5.02,
- "learning_rate": 0.00016836734693877553,
- "loss": 1.622,
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
"step": 248
},
{
- "epoch": 5.04,
- "learning_rate": 0.00016823979591836736,
- "loss": 1.6596,
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
"step": 249
},
{
- "epoch": 5.06,
- "learning_rate": 0.0001681122448979592,
- "loss": 1.5821,
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
"step": 250
},
{
- "epoch": 5.08,
- "learning_rate": 0.00016798469387755102,
- "loss": 1.7292,
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
"step": 251
},
{
- "epoch": 5.1,
- "learning_rate": 0.00016785714285714288,
- "loss": 1.646,
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
"step": 252
},
{
- "epoch": 5.12,
- "learning_rate": 0.0001677295918367347,
- "loss": 1.6969,
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
"step": 253
},
{
- "epoch": 5.14,
- "learning_rate": 0.00016760204081632654,
- "loss": 1.6082,
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
"step": 254
},
{
- "epoch": 5.16,
- "learning_rate": 0.00016747448979591837,
- "loss": 1.5843,
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
"step": 255
},
{
- "epoch": 5.18,
- "learning_rate": 0.00016734693877551023,
- "loss": 1.6827,
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
"step": 256
},
{
- "epoch": 5.2,
- "learning_rate": 0.00016721938775510203,
- "loss": 1.5824,
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
"step": 257
},
{
- "epoch": 5.22,
- "learning_rate": 0.0001670918367346939,
- "loss": 1.6795,
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
"step": 258
},
{
- "epoch": 5.24,
- "learning_rate": 0.00016696428571428572,
- "loss": 1.5639,
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
"step": 259
},
{
- "epoch": 5.26,
- "learning_rate": 0.00016683673469387755,
- "loss": 1.592,
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
"step": 260
},
{
- "epoch": 5.28,
- "learning_rate": 0.00016670918367346938,
- "loss": 1.65,
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
"step": 261
},
{
- "epoch": 5.3,
- "learning_rate": 0.00016658163265306124,
- "loss": 1.5592,
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
"step": 262
},
{
- "epoch": 5.32,
- "learning_rate": 0.00016645408163265305,
- "loss": 1.5091,
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
"step": 263
},
{
- "epoch": 5.34,
- "learning_rate": 0.0001663265306122449,
- "loss": 1.6138,
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
"step": 264
},
{
- "epoch": 5.36,
- "learning_rate": 0.00016619897959183673,
- "loss": 1.625,
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
"step": 265
},
{
- "epoch": 5.38,
- "learning_rate": 0.0001660714285714286,
- "loss": 1.5757,
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
"step": 266
},
{
- "epoch": 5.4,
- "learning_rate": 0.00016594387755102042,
- "loss": 1.6372,
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
"step": 267
},
{
- "epoch": 5.42,
- "learning_rate": 0.00016581632653061225,
- "loss": 1.5891,
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
"step": 268
},
{
- "epoch": 5.44,
- "learning_rate": 0.00016568877551020409,
- "loss": 1.6893,
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
"step": 269
},
{
- "epoch": 5.46,
- "learning_rate": 0.00016556122448979592,
- "loss": 1.6662,
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
"step": 270
},
{
- "epoch": 5.48,
- "learning_rate": 0.00016543367346938777,
- "loss": 1.7132,
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
"step": 271
},
{
- "epoch": 5.5,
- "learning_rate": 0.0001653061224489796,
- "loss": 1.5835,
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
"step": 272
},
{
- "epoch": 5.52,
- "learning_rate": 0.00016517857142857144,
- "loss": 1.6342,
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
"step": 273
},
{
- "epoch": 5.54,
- "learning_rate": 0.00016505102040816327,
- "loss": 1.6717,
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
"step": 274
},
{
- "epoch": 5.56,
- "learning_rate": 0.00016492346938775512,
- "loss": 1.6248,
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
"step": 275
},
{
- "epoch": 5.58,
- "learning_rate": 0.00016479591836734696,
- "loss": 1.6117,
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
"step": 276
},
{
- "epoch": 5.6,
- "learning_rate": 0.0001646683673469388,
- "loss": 1.6798,
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
"step": 277
},
{
- "epoch": 5.63,
- "learning_rate": 0.00016454081632653062,
- "loss": 1.6406,
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
"step": 278
},
{
- "epoch": 5.65,
- "learning_rate": 0.00016441326530612248,
- "loss": 1.6512,
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
"step": 279
},
{
- "epoch": 5.67,
- "learning_rate": 0.00016428571428571428,
- "loss": 1.6102,
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
"step": 280
},
{
- "epoch": 5.69,
- "learning_rate": 0.00016415816326530614,
- "loss": 1.6113,
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
"step": 281
},
{
- "epoch": 5.71,
- "learning_rate": 0.00016403061224489797,
- "loss": 1.7116,
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
"step": 282
},
{
- "epoch": 5.73,
- "learning_rate": 0.0001639030612244898,
- "loss": 1.6846,
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
"step": 283
},
{
- "epoch": 5.75,
- "learning_rate": 0.00016377551020408163,
- "loss": 1.6911,
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
"step": 284
},
{
- "epoch": 5.77,
- "learning_rate": 0.0001636479591836735,
- "loss": 1.6202,
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
"step": 285
},
{
- "epoch": 5.79,
- "learning_rate": 0.0001635204081632653,
- "loss": 1.5715,
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
"step": 286
},
{
- "epoch": 5.81,
- "learning_rate": 0.00016339285714285715,
- "loss": 1.6461,
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
"step": 287
},
{
- "epoch": 5.83,
- "learning_rate": 0.00016326530612244898,
- "loss": 1.6624,
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
"step": 288
},
{
- "epoch": 5.85,
- "learning_rate": 0.00016313775510204084,
- "loss": 1.6535,
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
"step": 289
},
{
- "epoch": 5.87,
- "learning_rate": 0.00016301020408163267,
- "loss": 1.6275,
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
"step": 290
},
{
- "epoch": 5.89,
- "learning_rate": 0.0001628826530612245,
- "loss": 1.6636,
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
"step": 291
},
{
- "epoch": 5.91,
- "learning_rate": 0.00016275510204081633,
- "loss": 1.6546,
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
"step": 292
},
{
- "epoch": 5.93,
- "learning_rate": 0.00016262755102040816,
- "loss": 1.7274,
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
"step": 293
},
{
- "epoch": 5.95,
- "learning_rate": 0.00016250000000000002,
- "loss": 1.5901,
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
"step": 294
},
{
- "epoch": 5.97,
- "learning_rate": 0.00016237244897959185,
- "loss": 1.6046,
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
"step": 295
},
{
- "epoch": 5.99,
- "learning_rate": 0.00016224489795918368,
- "loss": 1.5828,
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
"step": 296
},
{
- "epoch": 6.01,
- "learning_rate": 0.0001621173469387755,
- "loss": 1.6435,
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
"step": 297
},
{
- "epoch": 6.03,
- "learning_rate": 0.00016198979591836737,
- "loss": 1.6263,
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
"step": 298
},
{
- "epoch": 6.05,
- "learning_rate": 0.00016186224489795917,
- "loss": 1.4944,
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
"step": 299
},
{
- "epoch": 6.07,
- "learning_rate": 0.00016173469387755103,
- "loss": 1.6286,
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
"step": 300
},
{
- "epoch": 6.09,
- "learning_rate": 0.00016160714285714286,
- "loss": 1.694,
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
"step": 301
},
{
- "epoch": 6.11,
- "learning_rate": 0.00016147959183673472,
- "loss": 1.6197,
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
"step": 302
},
{
- "epoch": 6.13,
- "learning_rate": 0.00016135204081632652,
- "loss": 1.5597,
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
"step": 303
},
{
- "epoch": 6.15,
- "learning_rate": 0.00016122448979591838,
- "loss": 1.5487,
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
"step": 304
},
{
- "epoch": 6.17,
- "learning_rate": 0.0001610969387755102,
- "loss": 1.5769,
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
"step": 305
},
{
- "epoch": 6.19,
- "learning_rate": 0.00016096938775510204,
- "loss": 1.6367,
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
"step": 306
},
{
- "epoch": 6.21,
- "learning_rate": 0.00016084183673469388,
- "loss": 1.583,
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
"step": 307
},
{
- "epoch": 6.23,
- "learning_rate": 0.00016071428571428573,
- "loss": 1.6201,
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
"step": 308
},
{
- "epoch": 6.25,
- "learning_rate": 0.00016058673469387754,
- "loss": 1.6586,
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
"step": 309
},
{
- "epoch": 6.27,
- "learning_rate": 0.0001604591836734694,
- "loss": 1.6711,
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
"step": 310
},
{
- "epoch": 6.29,
- "learning_rate": 0.00016033163265306123,
- "loss": 1.6402,
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
"step": 311
},
{
- "epoch": 6.31,
- "learning_rate": 0.00016020408163265306,
- "loss": 1.5247,
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
"step": 312
},
{
- "epoch": 6.33,
- "learning_rate": 0.00016007653061224491,
- "loss": 1.5356,
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
"step": 313
},
{
- "epoch": 6.35,
- "learning_rate": 0.00015994897959183675,
- "loss": 1.564,
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
"step": 314
},
{
- "epoch": 6.37,
- "learning_rate": 0.00015982142857142858,
- "loss": 1.563,
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
"step": 315
},
{
- "epoch": 6.39,
- "learning_rate": 0.0001596938775510204,
- "loss": 1.5198,
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
"step": 316
},
{
- "epoch": 6.41,
- "learning_rate": 0.00015956632653061227,
- "loss": 1.6558,
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
"step": 317
},
{
- "epoch": 6.43,
- "learning_rate": 0.0001594387755102041,
- "loss": 1.5534,
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
"step": 318
},
{
- "epoch": 6.45,
- "learning_rate": 0.00015931122448979593,
- "loss": 1.6239,
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
"step": 319
},
{
- "epoch": 6.47,
- "learning_rate": 0.00015918367346938776,
- "loss": 1.5645,
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
"step": 320
},
{
- "epoch": 6.5,
- "learning_rate": 0.00015905612244897962,
- "loss": 1.5713,
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
"step": 321
},
{
- "epoch": 6.52,
- "learning_rate": 0.00015892857142857142,
- "loss": 1.6176,
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
"step": 322
},
{
- "epoch": 6.54,
- "learning_rate": 0.00015880102040816328,
- "loss": 1.502,
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
"step": 323
},
{
- "epoch": 6.56,
- "learning_rate": 0.0001586734693877551,
- "loss": 1.645,
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
"step": 324
},
{
- "epoch": 6.58,
- "learning_rate": 0.00015854591836734697,
- "loss": 1.5904,
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
"step": 325
},
{
- "epoch": 6.6,
- "learning_rate": 0.00015841836734693877,
- "loss": 1.6149,
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
"step": 326
},
{
- "epoch": 6.62,
- "learning_rate": 0.00015829081632653063,
- "loss": 1.6757,
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
"step": 327
},
{
- "epoch": 6.64,
- "learning_rate": 0.00015816326530612246,
- "loss": 1.541,
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
"step": 328
},
{
- "epoch": 6.66,
- "learning_rate": 0.0001580357142857143,
- "loss": 1.5898,
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
"step": 329
},
{
- "epoch": 6.68,
- "learning_rate": 0.00015790816326530612,
- "loss": 1.5441,
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
"step": 330
},
{
- "epoch": 6.7,
- "learning_rate": 0.00015778061224489798,
- "loss": 1.61,
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
"step": 331
},
{
- "epoch": 6.72,
- "learning_rate": 0.00015765306122448978,
- "loss": 1.615,
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
"step": 332
},
{
- "epoch": 6.74,
- "learning_rate": 0.00015752551020408164,
- "loss": 1.6575,
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
"step": 333
},
{
- "epoch": 6.76,
- "learning_rate": 0.00015739795918367347,
- "loss": 1.6702,
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
"step": 334
},
{
- "epoch": 6.78,
- "learning_rate": 0.0001572704081632653,
- "loss": 1.6009,
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
"step": 335
},
{
- "epoch": 6.8,
- "learning_rate": 0.00015714285714285716,
- "loss": 1.5568,
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
"step": 336
},
{
- "epoch": 6.82,
- "learning_rate": 0.000157015306122449,
- "loss": 1.619,
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
"step": 337
},
{
- "epoch": 6.84,
- "learning_rate": 0.00015688775510204082,
- "loss": 1.5563,
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
"step": 338
},
{
- "epoch": 6.86,
- "learning_rate": 0.00015676020408163265,
- "loss": 1.6328,
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
"step": 339
},
{
- "epoch": 6.88,
- "learning_rate": 0.0001566326530612245,
- "loss": 1.5726,
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
"step": 340
},
{
- "epoch": 6.9,
- "learning_rate": 0.00015650510204081634,
- "loss": 1.6199,
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
"step": 341
},
{
- "epoch": 6.92,
- "learning_rate": 0.00015637755102040817,
- "loss": 1.5722,
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
"step": 342
},
{
- "epoch": 6.94,
- "learning_rate": 0.00015625,
- "loss": 1.5685,
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
"step": 343
},
{
- "epoch": 6.96,
- "learning_rate": 0.00015612244897959186,
- "loss": 1.5615,
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
"step": 344
},
{
- "epoch": 6.98,
- "learning_rate": 0.00015599489795918366,
- "loss": 1.5994,
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
"step": 345
},
{
- "epoch": 7.0,
- "learning_rate": 0.00015586734693877552,
- "loss": 1.5579,
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
"step": 346
},
{
- "epoch": 7.02,
- "learning_rate": 0.00015573979591836735,
- "loss": 1.547,
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
"step": 347
},
{
- "epoch": 7.04,
- "learning_rate": 0.00015561224489795918,
- "loss": 1.5292,
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
"step": 348
},
{
- "epoch": 7.06,
- "learning_rate": 0.00015548469387755102,
- "loss": 1.6032,
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
"step": 349
},
{
- "epoch": 7.08,
- "learning_rate": 0.00015535714285714287,
- "loss": 1.5149,
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
"step": 350
},
{
- "epoch": 7.1,
- "learning_rate": 0.0001552295918367347,
- "loss": 1.6093,
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
"step": 351
},
{
- "epoch": 7.12,
- "learning_rate": 0.00015510204081632654,
- "loss": 1.5421,
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
"step": 352
},
{
- "epoch": 7.14,
- "learning_rate": 0.00015497448979591837,
- "loss": 1.5733,
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
"step": 353
},
{
- "epoch": 7.16,
- "learning_rate": 0.00015484693877551022,
- "loss": 1.5703,
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
"step": 354
},
{
- "epoch": 7.18,
- "learning_rate": 0.00015471938775510203,
- "loss": 1.6141,
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
"step": 355
},
{
- "epoch": 7.2,
- "learning_rate": 0.00015459183673469389,
- "loss": 1.5526,
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
"step": 356
},
{
- "epoch": 7.22,
- "learning_rate": 0.00015446428571428572,
- "loss": 1.5347,
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
"step": 357
},
{
- "epoch": 7.24,
- "learning_rate": 0.00015433673469387755,
- "loss": 1.5682,
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
"step": 358
},
{
- "epoch": 7.26,
- "learning_rate": 0.0001542091836734694,
- "loss": 1.5292,
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
"step": 359
},
{
- "epoch": 7.28,
- "learning_rate": 0.00015408163265306124,
- "loss": 1.499,
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
"step": 360
},
{
- "epoch": 7.3,
- "learning_rate": 0.00015395408163265307,
- "loss": 1.5624,
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
"step": 361
},
{
- "epoch": 7.32,
- "learning_rate": 0.0001538265306122449,
- "loss": 1.627,
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
"step": 362
},
{
- "epoch": 7.34,
- "learning_rate": 0.00015369897959183676,
- "loss": 1.5327,
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
"step": 363
},
{
- "epoch": 7.37,
- "learning_rate": 0.0001535714285714286,
- "loss": 1.5622,
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
"step": 364
},
{
- "epoch": 7.39,
- "learning_rate": 0.00015344387755102042,
- "loss": 1.5659,
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
"step": 365
},
{
- "epoch": 7.41,
- "learning_rate": 0.00015331632653061225,
- "loss": 1.5019,
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
"step": 366
},
{
- "epoch": 7.43,
- "learning_rate": 0.0001531887755102041,
- "loss": 1.5921,
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
"step": 367
},
{
- "epoch": 7.45,
- "learning_rate": 0.0001530612244897959,
- "loss": 1.5914,
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
"step": 368
},
{
- "epoch": 7.47,
- "learning_rate": 0.00015293367346938777,
- "loss": 1.5045,
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
"step": 369
},
{
- "epoch": 7.49,
- "learning_rate": 0.0001528061224489796,
- "loss": 1.6209,
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
"step": 370
},
{
- "epoch": 7.51,
- "learning_rate": 0.00015267857142857143,
- "loss": 1.5198,
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
"step": 371
},
{
- "epoch": 7.53,
- "learning_rate": 0.00015255102040816326,
- "loss": 1.5363,
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
"step": 372
},
{
- "epoch": 7.55,
- "learning_rate": 0.00015242346938775512,
- "loss": 1.5391,
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
"step": 373
},
{
- "epoch": 7.57,
- "learning_rate": 0.00015229591836734695,
- "loss": 1.4546,
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
"step": 374
},
{
- "epoch": 7.59,
- "learning_rate": 0.00015216836734693878,
- "loss": 1.5546,
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
"step": 375
},
{
- "epoch": 7.61,
- "learning_rate": 0.0001520408163265306,
- "loss": 1.5629,
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
"step": 376
},
{
- "epoch": 7.63,
- "learning_rate": 0.00015191326530612247,
- "loss": 1.6002,
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
"step": 377
},
{
- "epoch": 7.65,
- "learning_rate": 0.00015178571428571427,
- "loss": 1.5543,
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
"step": 378
},
{
- "epoch": 7.67,
- "learning_rate": 0.00015165816326530613,
- "loss": 1.5925,
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
"step": 379
},
{
- "epoch": 7.69,
- "learning_rate": 0.00015153061224489796,
- "loss": 1.5631,
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
"step": 380
},
{
- "epoch": 7.71,
- "learning_rate": 0.0001514030612244898,
- "loss": 1.5677,
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
"step": 381
},
{
- "epoch": 7.73,
- "learning_rate": 0.00015127551020408165,
- "loss": 1.5828,
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
"step": 382
},
{
- "epoch": 7.75,
- "learning_rate": 0.00015114795918367348,
- "loss": 1.6494,
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
"step": 383
},
{
- "epoch": 7.77,
- "learning_rate": 0.0001510204081632653,
- "loss": 1.553,
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
"step": 384
},
{
- "epoch": 7.79,
- "learning_rate": 0.00015089285714285714,
- "loss": 1.6156,
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
"step": 385
},
{
- "epoch": 7.81,
- "learning_rate": 0.000150765306122449,
- "loss": 1.5001,
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
"step": 386
},
{
- "epoch": 7.83,
- "learning_rate": 0.00015063775510204083,
- "loss": 1.5321,
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
"step": 387
},
{
- "epoch": 7.85,
- "learning_rate": 0.00015051020408163266,
- "loss": 1.5307,
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
"step": 388
},
{
- "epoch": 7.87,
- "learning_rate": 0.0001503826530612245,
- "loss": 1.5639,
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
"step": 389
},
{
- "epoch": 7.89,
- "learning_rate": 0.00015025510204081635,
- "loss": 1.517,
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
"step": 390
},
{
- "epoch": 7.91,
- "learning_rate": 0.00015012755102040816,
- "loss": 1.4776,
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
"step": 391
},
{
- "epoch": 7.93,
- "learning_rate": 0.00015000000000000001,
- "loss": 1.5368,
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
"step": 392
},
{
- "epoch": 7.95,
- "learning_rate": 0.00014987244897959184,
- "loss": 1.5636,
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
"step": 393
},
{
- "epoch": 7.97,
- "learning_rate": 0.00014974489795918368,
- "loss": 1.6004,
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
"step": 394
},
{
- "epoch": 7.99,
- "learning_rate": 0.0001496173469387755,
- "loss": 1.5524,
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
"step": 395
},
{
- "epoch": 8.01,
- "learning_rate": 0.00014948979591836736,
- "loss": 1.5307,
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
"step": 396
},
{
- "epoch": 8.03,
- "learning_rate": 0.00014936224489795917,
- "loss": 1.5123,
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
"step": 397
},
{
- "epoch": 8.05,
- "learning_rate": 0.00014923469387755103,
- "loss": 1.5132,
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
"step": 398
},
{
- "epoch": 8.07,
- "learning_rate": 0.00014910714285714286,
- "loss": 1.5109,
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
"step": 399
},
{
- "epoch": 8.09,
- "learning_rate": 0.00014897959183673472,
- "loss": 1.5302,
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
"step": 400
},
{
- "epoch": 8.11,
- "learning_rate": 0.00014885204081632652,
- "loss": 1.5238,
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
"step": 401
},
{
- "epoch": 8.13,
- "learning_rate": 0.00014872448979591838,
- "loss": 1.4781,
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
"step": 402
},
{
- "epoch": 8.15,
- "learning_rate": 0.0001485969387755102,
- "loss": 1.5446,
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
"step": 403
},
{
- "epoch": 8.17,
- "learning_rate": 0.00014846938775510204,
- "loss": 1.5,
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
"step": 404
},
{
- "epoch": 8.19,
- "learning_rate": 0.0001483418367346939,
- "loss": 1.5458,
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
"step": 405
},
{
- "epoch": 8.21,
- "learning_rate": 0.00014821428571428573,
- "loss": 1.5257,
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
"step": 406
},
{
- "epoch": 8.24,
- "learning_rate": 0.00014808673469387756,
- "loss": 1.4607,
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
"step": 407
},
{
- "epoch": 8.26,
- "learning_rate": 0.0001479591836734694,
- "loss": 1.4282,
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
"step": 408
},
{
- "epoch": 8.28,
- "learning_rate": 0.00014783163265306125,
- "loss": 1.4519,
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
"step": 409
},
{
- "epoch": 8.3,
- "learning_rate": 0.00014770408163265305,
- "loss": 1.475,
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
"step": 410
},
{
- "epoch": 8.32,
- "learning_rate": 0.0001475765306122449,
- "loss": 1.5425,
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
"step": 411
},
{
- "epoch": 8.34,
- "learning_rate": 0.00014744897959183674,
- "loss": 1.5407,
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
"step": 412
},
{
- "epoch": 8.36,
- "learning_rate": 0.0001473214285714286,
- "loss": 1.5698,
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
"step": 413
},
{
- "epoch": 8.38,
- "learning_rate": 0.0001471938775510204,
- "loss": 1.4282,
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
"step": 414
},
{
- "epoch": 8.4,
- "learning_rate": 0.00014706632653061226,
- "loss": 1.5301,
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
"step": 415
},
{
- "epoch": 8.42,
- "learning_rate": 0.0001469387755102041,
- "loss": 1.5083,
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
"step": 416
},
{
- "epoch": 8.44,
- "learning_rate": 0.00014681122448979592,
- "loss": 1.5712,
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
"step": 417
},
{
- "epoch": 8.46,
- "learning_rate": 0.00014668367346938775,
- "loss": 1.4363,
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
"step": 418
},
{
- "epoch": 8.48,
- "learning_rate": 0.0001465561224489796,
- "loss": 1.4463,
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
"step": 419
},
{
- "epoch": 8.5,
- "learning_rate": 0.00014642857142857141,
- "loss": 1.4738,
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
"step": 420
},
{
- "epoch": 8.52,
- "learning_rate": 0.00014630102040816327,
- "loss": 1.5396,
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
"step": 421
},
{
- "epoch": 8.54,
- "learning_rate": 0.0001461734693877551,
- "loss": 1.4384,
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
"step": 422
},
{
- "epoch": 8.56,
- "learning_rate": 0.00014604591836734696,
- "loss": 1.5345,
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
"step": 423
},
{
- "epoch": 8.58,
- "learning_rate": 0.0001459183673469388,
- "loss": 1.5355,
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
"step": 424
},
{
- "epoch": 8.6,
- "learning_rate": 0.00014579081632653062,
- "loss": 1.5188,
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
"step": 425
},
{
- "epoch": 8.62,
- "learning_rate": 0.00014566326530612245,
- "loss": 1.5575,
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
"step": 426
},
{
- "epoch": 8.64,
- "learning_rate": 0.00014553571428571428,
- "loss": 1.5279,
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
"step": 427
},
{
- "epoch": 8.66,
- "learning_rate": 0.00014540816326530614,
- "loss": 1.5484,
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
"step": 428
},
{
- "epoch": 8.68,
- "learning_rate": 0.00014528061224489797,
- "loss": 1.4878,
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
"step": 429
},
{
- "epoch": 8.7,
- "learning_rate": 0.0001451530612244898,
- "loss": 1.503,
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
"step": 430
},
{
- "epoch": 8.72,
- "learning_rate": 0.00014502551020408163,
- "loss": 1.4723,
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
"step": 431
},
{
- "epoch": 8.74,
- "learning_rate": 0.0001448979591836735,
- "loss": 1.5579,
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
"step": 432
},
{
- "epoch": 8.76,
- "learning_rate": 0.0001447704081632653,
- "loss": 1.4789,
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
"step": 433
},
{
- "epoch": 8.78,
- "learning_rate": 0.00014464285714285715,
- "loss": 1.5501,
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
"step": 434
},
{
- "epoch": 8.8,
- "learning_rate": 0.00014451530612244899,
- "loss": 1.5204,
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
"step": 435
},
{
- "epoch": 8.82,
- "learning_rate": 0.00014438775510204084,
- "loss": 1.5489,
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
"step": 436
},
{
- "epoch": 8.84,
- "learning_rate": 0.00014426020408163265,
- "loss": 1.5464,
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
"step": 437
},
{
- "epoch": 8.86,
- "learning_rate": 0.0001441326530612245,
- "loss": 1.5896,
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
"step": 438
},
{
- "epoch": 8.88,
- "learning_rate": 0.00014400510204081634,
- "loss": 1.5465,
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
"step": 439
},
{
- "epoch": 8.9,
- "learning_rate": 0.00014387755102040817,
- "loss": 1.5094,
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
"step": 440
},
{
- "epoch": 8.92,
- "learning_rate": 0.00014375,
- "loss": 1.5144,
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
"step": 441
},
{
- "epoch": 8.94,
- "learning_rate": 0.00014362244897959186,
- "loss": 1.4919,
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
"step": 442
},
{
- "epoch": 8.96,
- "learning_rate": 0.00014349489795918366,
- "loss": 1.4702,
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
"step": 443
},
{
- "epoch": 8.98,
- "learning_rate": 0.00014336734693877552,
- "loss": 1.4996,
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
"step": 444
},
{
- "epoch": 9.0,
- "learning_rate": 0.00014323979591836735,
- "loss": 1.5503,
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
"step": 445
},
{
- "epoch": 9.02,
- "learning_rate": 0.00014311224489795918,
- "loss": 1.4125,
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
"step": 446
},
{
- "epoch": 9.04,
- "learning_rate": 0.00014298469387755104,
- "loss": 1.4722,
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
"step": 447
},
{
- "epoch": 9.06,
- "learning_rate": 0.00014285714285714287,
- "loss": 1.5199,
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
"step": 448
},
{
- "epoch": 9.09,
- "learning_rate": 0.0001427295918367347,
- "loss": 1.4571,
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
"step": 449
},
{
- "epoch": 9.11,
- "learning_rate": 0.00014260204081632653,
- "loss": 1.4996,
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
"step": 450
},
{
- "epoch": 9.13,
- "learning_rate": 0.0001424744897959184,
- "loss": 1.4092,
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
"step": 451
},
{
- "epoch": 9.15,
- "learning_rate": 0.00014234693877551022,
- "loss": 1.4198,
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
"step": 452
},
{
- "epoch": 9.17,
- "learning_rate": 0.00014221938775510205,
- "loss": 1.4916,
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
"step": 453
},
{
- "epoch": 9.19,
- "learning_rate": 0.00014209183673469388,
- "loss": 1.5051,
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
"step": 454
},
{
- "epoch": 9.21,
- "learning_rate": 0.00014196428571428574,
- "loss": 1.4321,
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
"step": 455
},
{
- "epoch": 9.23,
- "learning_rate": 0.00014183673469387754,
- "loss": 1.4097,
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
"step": 456
},
{
- "epoch": 9.25,
- "learning_rate": 0.0001417091836734694,
- "loss": 1.4853,
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
"step": 457
},
{
- "epoch": 9.27,
- "learning_rate": 0.00014158163265306123,
- "loss": 1.4593,
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
"step": 458
},
{
- "epoch": 9.29,
- "learning_rate": 0.00014145408163265306,
- "loss": 1.3729,
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
"step": 459
},
{
- "epoch": 9.31,
- "learning_rate": 0.0001413265306122449,
- "loss": 1.4467,
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
"step": 460
},
{
- "epoch": 9.33,
- "learning_rate": 0.00014119897959183675,
- "loss": 1.4467,
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
"step": 461
},
{
- "epoch": 9.35,
- "learning_rate": 0.00014107142857142858,
- "loss": 1.4785,
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
"step": 462
},
{
- "epoch": 9.37,
- "learning_rate": 0.0001409438775510204,
- "loss": 1.4089,
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
"step": 463
},
{
- "epoch": 9.39,
- "learning_rate": 0.00014081632653061224,
- "loss": 1.5026,
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
"step": 464
},
{
- "epoch": 9.41,
- "learning_rate": 0.0001406887755102041,
- "loss": 1.4857,
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
"step": 465
},
{
- "epoch": 9.43,
- "learning_rate": 0.0001405612244897959,
- "loss": 1.3745,
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
"step": 466
},
{
- "epoch": 9.45,
- "learning_rate": 0.00014043367346938776,
- "loss": 1.4733,
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
"step": 467
},
{
- "epoch": 9.47,
- "learning_rate": 0.0001403061224489796,
- "loss": 1.5212,
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
"step": 468
},
{
- "epoch": 9.49,
- "learning_rate": 0.00014017857142857142,
- "loss": 1.5398,
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
"step": 469
},
{
- "epoch": 9.51,
- "learning_rate": 0.00014005102040816328,
- "loss": 1.478,
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
"step": 470
},
{
- "epoch": 9.53,
- "learning_rate": 0.0001399234693877551,
- "loss": 1.496,
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
"step": 471
},
{
- "epoch": 9.55,
- "learning_rate": 0.00013979591836734694,
- "loss": 1.4837,
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
"step": 472
},
{
- "epoch": 9.57,
- "learning_rate": 0.00013966836734693878,
- "loss": 1.4724,
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
"step": 473
},
{
- "epoch": 9.59,
- "learning_rate": 0.00013954081632653063,
- "loss": 1.4828,
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
"step": 474
},
{
- "epoch": 9.61,
- "learning_rate": 0.00013941326530612246,
- "loss": 1.5012,
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
"step": 475
},
{
- "epoch": 9.63,
- "learning_rate": 0.0001392857142857143,
- "loss": 1.4879,
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
"step": 476
},
{
- "epoch": 9.65,
- "learning_rate": 0.00013915816326530613,
- "loss": 1.4196,
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
"step": 477
},
{
- "epoch": 9.67,
- "learning_rate": 0.00013903061224489798,
- "loss": 1.4915,
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
"step": 478
},
{
- "epoch": 9.69,
- "learning_rate": 0.0001389030612244898,
- "loss": 1.3878,
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
"step": 479
},
{
- "epoch": 9.71,
- "learning_rate": 0.00013877551020408165,
- "loss": 1.466,
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
"step": 480
},
{
- "epoch": 9.73,
- "learning_rate": 0.00013864795918367348,
- "loss": 1.4582,
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
"step": 481
},
{
- "epoch": 9.75,
- "learning_rate": 0.0001385204081632653,
- "loss": 1.533,
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
"step": 482
},
{
- "epoch": 9.77,
- "learning_rate": 0.00013839285714285714,
- "loss": 1.4697,
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
"step": 483
},
{
- "epoch": 9.79,
- "learning_rate": 0.000138265306122449,
- "loss": 1.3989,
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
"step": 484
},
{
- "epoch": 9.81,
- "learning_rate": 0.00013813775510204083,
- "loss": 1.4361,
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
"step": 485
},
{
- "epoch": 9.83,
- "learning_rate": 0.00013801020408163266,
- "loss": 1.5271,
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
"step": 486
},
{
- "epoch": 9.85,
- "learning_rate": 0.0001378826530612245,
- "loss": 1.4905,
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
"step": 487
},
{
- "epoch": 9.87,
- "learning_rate": 0.00013775510204081635,
- "loss": 1.4757,
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
"step": 488
},
{
- "epoch": 9.89,
- "learning_rate": 0.00013762755102040815,
- "loss": 1.5485,
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
"step": 489
},
{
- "epoch": 9.91,
- "learning_rate": 0.0001375,
- "loss": 1.4783,
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
"step": 490
},
{
- "epoch": 9.93,
- "learning_rate": 0.00013737244897959184,
- "loss": 1.4849,
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
"step": 491
},
{
- "epoch": 9.96,
- "learning_rate": 0.00013724489795918367,
- "loss": 1.5382,
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
"step": 492
},
{
- "epoch": 9.98,
- "learning_rate": 0.00013711734693877553,
- "loss": 1.4902,
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
"step": 493
},
{
- "epoch": 10.0,
- "learning_rate": 0.00013698979591836736,
- "loss": 1.4865,
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
"step": 494
},
{
- "epoch": 10.02,
- "learning_rate": 0.0001368622448979592,
- "loss": 1.4436,
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
"step": 495
},
{
- "epoch": 10.04,
- "learning_rate": 0.00013673469387755102,
- "loss": 1.408,
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
"step": 496
},
{
- "epoch": 10.06,
- "learning_rate": 0.00013660714285714288,
- "loss": 1.4764,
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
"step": 497
},
{
- "epoch": 10.08,
- "learning_rate": 0.0001364795918367347,
- "loss": 1.4646,
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
"step": 498
},
{
- "epoch": 10.1,
- "learning_rate": 0.00013635204081632654,
- "loss": 1.406,
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
"step": 499
},
{
- "epoch": 10.12,
- "learning_rate": 0.00013622448979591837,
- "loss": 1.4785,
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
"step": 500
},
{
- "epoch": 10.14,
- "learning_rate": 0.00013609693877551023,
- "loss": 1.4117,
+ "epoch": 5.66,
+ "learning_rate": 0.00012883522727272727,
+ "loss": 1.0755,
"step": 501
},
{
- "epoch": 10.16,
- "learning_rate": 0.00013596938775510203,
- "loss": 1.4108,
+ "epoch": 5.67,
+ "learning_rate": 0.00012869318181818183,
+ "loss": 1.0755,
"step": 502
},
{
- "epoch": 10.18,
- "learning_rate": 0.0001358418367346939,
- "loss": 1.4155,
+ "epoch": 5.68,
+ "learning_rate": 0.00012855113636363636,
+ "loss": 1.0869,
"step": 503
},
{
- "epoch": 10.2,
- "learning_rate": 0.00013571428571428572,
- "loss": 1.4021,
+ "epoch": 5.69,
+ "learning_rate": 0.00012840909090909092,
+ "loss": 1.0673,
"step": 504
},
{
- "epoch": 10.22,
- "learning_rate": 0.00013558673469387755,
- "loss": 1.411,
+ "epoch": 5.71,
+ "learning_rate": 0.00012826704545454545,
+ "loss": 1.0692,
"step": 505
},
{
- "epoch": 10.24,
- "learning_rate": 0.00013545918367346938,
- "loss": 1.3851,
+ "epoch": 5.72,
+ "learning_rate": 0.000128125,
+ "loss": 1.0474,
"step": 506
},
{
- "epoch": 10.26,
- "learning_rate": 0.00013533163265306124,
- "loss": 1.387,
+ "epoch": 5.73,
+ "learning_rate": 0.00012798295454545454,
+ "loss": 1.0749,
"step": 507
},
{
- "epoch": 10.28,
- "learning_rate": 0.00013520408163265305,
- "loss": 1.4163,
+ "epoch": 5.74,
+ "learning_rate": 0.0001278409090909091,
+ "loss": 1.0519,
"step": 508
},
{
- "epoch": 10.3,
- "learning_rate": 0.0001350765306122449,
- "loss": 1.3343,
+ "epoch": 5.75,
+ "learning_rate": 0.00012769886363636366,
+ "loss": 1.0566,
"step": 509
},
{
- "epoch": 10.32,
- "learning_rate": 0.00013494897959183673,
- "loss": 1.4811,
+ "epoch": 5.76,
+ "learning_rate": 0.0001275568181818182,
+ "loss": 1.06,
"step": 510
},
{
- "epoch": 10.34,
- "learning_rate": 0.0001348214285714286,
- "loss": 1.4086,
+ "epoch": 5.77,
+ "learning_rate": 0.00012741477272727272,
+ "loss": 1.0618,
"step": 511
},
{
- "epoch": 10.36,
- "learning_rate": 0.0001346938775510204,
- "loss": 1.3879,
+ "epoch": 5.78,
+ "learning_rate": 0.00012727272727272728,
+ "loss": 1.0643,
"step": 512
},
{
- "epoch": 10.38,
- "learning_rate": 0.00013456632653061225,
- "loss": 1.4204,
+ "epoch": 5.8,
+ "learning_rate": 0.0001271306818181818,
+ "loss": 1.026,
"step": 513
},
{
- "epoch": 10.4,
- "learning_rate": 0.00013443877551020408,
- "loss": 1.4158,
+ "epoch": 5.81,
+ "learning_rate": 0.00012698863636363637,
+ "loss": 1.0335,
"step": 514
},
{
- "epoch": 10.42,
- "learning_rate": 0.00013431122448979592,
- "loss": 1.4521,
+ "epoch": 5.82,
+ "learning_rate": 0.00012684659090909093,
+ "loss": 1.0205,
"step": 515
},
{
- "epoch": 10.44,
- "learning_rate": 0.00013418367346938777,
- "loss": 1.4196,
+ "epoch": 5.83,
+ "learning_rate": 0.00012670454545454546,
+ "loss": 1.0594,
"step": 516
},
{
- "epoch": 10.46,
- "learning_rate": 0.0001340561224489796,
- "loss": 1.4361,
+ "epoch": 5.84,
+ "learning_rate": 0.0001265625,
+ "loss": 1.0136,
"step": 517
},
{
- "epoch": 10.48,
- "learning_rate": 0.00013392857142857144,
- "loss": 1.4482,
+ "epoch": 5.85,
+ "learning_rate": 0.00012642045454545455,
+ "loss": 1.0244,
"step": 518
},
{
- "epoch": 10.5,
- "learning_rate": 0.00013380102040816327,
- "loss": 1.4801,
+ "epoch": 5.86,
+ "learning_rate": 0.00012627840909090908,
+ "loss": 1.0569,
"step": 519
},
{
- "epoch": 10.52,
- "learning_rate": 0.00013367346938775512,
- "loss": 1.4556,
+ "epoch": 5.87,
+ "learning_rate": 0.00012613636363636364,
+ "loss": 1.0416,
"step": 520
},
{
- "epoch": 10.54,
- "learning_rate": 0.00013354591836734695,
- "loss": 1.3902,
+ "epoch": 5.89,
+ "learning_rate": 0.0001259943181818182,
+ "loss": 0.9884,
"step": 521
},
{
- "epoch": 10.56,
- "learning_rate": 0.00013341836734693879,
- "loss": 1.4269,
+ "epoch": 5.9,
+ "learning_rate": 0.00012585227272727273,
+ "loss": 1.0351,
"step": 522
},
{
- "epoch": 10.58,
- "learning_rate": 0.00013329081632653062,
- "loss": 1.4899,
+ "epoch": 5.91,
+ "learning_rate": 0.00012571022727272726,
+ "loss": 1.0037,
"step": 523
},
{
- "epoch": 10.6,
- "learning_rate": 0.00013316326530612247,
- "loss": 1.3952,
+ "epoch": 5.92,
+ "learning_rate": 0.00012556818181818182,
+ "loss": 1.0219,
"step": 524
},
{
- "epoch": 10.62,
- "learning_rate": 0.00013303571428571428,
- "loss": 1.4116,
+ "epoch": 5.93,
+ "learning_rate": 0.00012542613636363635,
+ "loss": 1.0533,
"step": 525
},
{
- "epoch": 10.64,
- "learning_rate": 0.00013290816326530614,
- "loss": 1.4583,
+ "epoch": 5.94,
+ "learning_rate": 0.0001252840909090909,
+ "loss": 1.0031,
"step": 526
},
{
- "epoch": 10.66,
- "learning_rate": 0.00013278061224489797,
- "loss": 1.4466,
+ "epoch": 5.95,
+ "learning_rate": 0.00012514204545454547,
+ "loss": 1.0454,
"step": 527
},
{
- "epoch": 10.68,
- "learning_rate": 0.0001326530612244898,
- "loss": 1.4242,
+ "epoch": 5.97,
+ "learning_rate": 0.000125,
+ "loss": 1.0195,
"step": 528
},
{
- "epoch": 10.7,
- "learning_rate": 0.00013252551020408163,
- "loss": 1.3717,
+ "epoch": 5.98,
+ "learning_rate": 0.00012485795454545453,
+ "loss": 1.0076,
"step": 529
},
{
- "epoch": 10.72,
- "learning_rate": 0.0001323979591836735,
- "loss": 1.4583,
+ "epoch": 5.99,
+ "learning_rate": 0.0001247159090909091,
+ "loss": 1.0378,
"step": 530
},
{
- "epoch": 10.74,
- "learning_rate": 0.0001322704081632653,
- "loss": 1.4185,
+ "epoch": 6.0,
+ "learning_rate": 0.00012457386363636365,
+ "loss": 0.9795,
"step": 531
},
{
- "epoch": 10.76,
- "learning_rate": 0.00013214285714285715,
- "loss": 1.4287,
+ "epoch": 6.01,
+ "learning_rate": 0.00012443181818181818,
+ "loss": 0.9405,
"step": 532
},
{
- "epoch": 10.78,
- "learning_rate": 0.00013201530612244898,
- "loss": 1.4385,
+ "epoch": 6.02,
+ "learning_rate": 0.00012428977272727274,
+ "loss": 0.9503,
"step": 533
},
{
- "epoch": 10.8,
- "learning_rate": 0.00013188775510204084,
- "loss": 1.453,
+ "epoch": 6.03,
+ "learning_rate": 0.00012414772727272727,
+ "loss": 0.9456,
"step": 534
},
{
- "epoch": 10.83,
- "learning_rate": 0.00013176020408163264,
- "loss": 1.4161,
+ "epoch": 6.04,
+ "learning_rate": 0.0001240056818181818,
+ "loss": 0.9536,
"step": 535
},
{
- "epoch": 10.85,
- "learning_rate": 0.0001316326530612245,
- "loss": 1.457,
+ "epoch": 6.06,
+ "learning_rate": 0.00012386363636363636,
+ "loss": 0.9412,
"step": 536
},
{
- "epoch": 10.87,
- "learning_rate": 0.00013150510204081633,
- "loss": 1.4367,
+ "epoch": 6.07,
+ "learning_rate": 0.00012372159090909092,
+ "loss": 0.9315,
"step": 537
},
{
- "epoch": 10.89,
- "learning_rate": 0.00013137755102040816,
- "loss": 1.4256,
+ "epoch": 6.08,
+ "learning_rate": 0.00012357954545454545,
+ "loss": 0.9486,
"step": 538
},
{
- "epoch": 10.91,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.424,
+ "epoch": 6.09,
+ "learning_rate": 0.0001234375,
+ "loss": 0.9405,
"step": 539
},
{
- "epoch": 10.93,
- "learning_rate": 0.00013112244897959185,
- "loss": 1.3923,
+ "epoch": 6.1,
+ "learning_rate": 0.00012329545454545454,
+ "loss": 0.9269,
"step": 540
},
{
- "epoch": 10.95,
- "learning_rate": 0.00013099489795918368,
- "loss": 1.4225,
+ "epoch": 6.11,
+ "learning_rate": 0.0001231534090909091,
+ "loss": 0.9378,
"step": 541
},
{
- "epoch": 10.97,
- "learning_rate": 0.0001308673469387755,
- "loss": 1.3969,
+ "epoch": 6.12,
+ "learning_rate": 0.00012301136363636366,
+ "loss": 0.9431,
"step": 542
},
{
- "epoch": 10.99,
- "learning_rate": 0.00013073979591836737,
- "loss": 1.4446,
+ "epoch": 6.13,
+ "learning_rate": 0.0001228693181818182,
+ "loss": 0.9256,
"step": 543
},
{
- "epoch": 11.01,
- "learning_rate": 0.00013061224489795917,
- "loss": 1.4375,
+ "epoch": 6.15,
+ "learning_rate": 0.00012272727272727272,
+ "loss": 0.919,
"step": 544
},
{
- "epoch": 11.03,
- "learning_rate": 0.00013048469387755103,
- "loss": 1.4064,
+ "epoch": 6.16,
+ "learning_rate": 0.00012258522727272728,
+ "loss": 0.9188,
"step": 545
},
{
- "epoch": 11.05,
- "learning_rate": 0.00013035714285714286,
- "loss": 1.3454,
+ "epoch": 6.17,
+ "learning_rate": 0.00012244318181818181,
+ "loss": 0.9447,
"step": 546
},
{
- "epoch": 11.07,
- "learning_rate": 0.00013022959183673472,
- "loss": 1.3234,
+ "epoch": 6.18,
+ "learning_rate": 0.00012230113636363637,
+ "loss": 0.9261,
"step": 547
},
{
- "epoch": 11.09,
- "learning_rate": 0.00013010204081632652,
- "loss": 1.3759,
+ "epoch": 6.19,
+ "learning_rate": 0.00012215909090909093,
+ "loss": 0.9302,
"step": 548
},
{
- "epoch": 11.11,
- "learning_rate": 0.00012997448979591838,
- "loss": 1.4221,
+ "epoch": 6.2,
+ "learning_rate": 0.00012201704545454546,
+ "loss": 0.9161,
"step": 549
},
{
- "epoch": 11.13,
- "learning_rate": 0.0001298469387755102,
- "loss": 1.4261,
+ "epoch": 6.21,
+ "learning_rate": 0.00012187500000000001,
+ "loss": 0.9521,
"step": 550
},
{
- "epoch": 11.15,
- "learning_rate": 0.00012971938775510204,
- "loss": 1.3341,
+ "epoch": 6.22,
+ "learning_rate": 0.00012173295454545455,
+ "loss": 0.9026,
"step": 551
},
{
- "epoch": 11.17,
- "learning_rate": 0.00012959183673469387,
- "loss": 1.3994,
+ "epoch": 6.24,
+ "learning_rate": 0.00012159090909090908,
+ "loss": 0.9361,
"step": 552
},
{
- "epoch": 11.19,
- "learning_rate": 0.00012946428571428573,
- "loss": 1.3894,
+ "epoch": 6.25,
+ "learning_rate": 0.00012144886363636366,
+ "loss": 0.8944,
"step": 553
},
{
- "epoch": 11.21,
- "learning_rate": 0.00012933673469387754,
- "loss": 1.3585,
+ "epoch": 6.26,
+ "learning_rate": 0.00012130681818181819,
+ "loss": 0.895,
"step": 554
},
{
- "epoch": 11.23,
- "learning_rate": 0.0001292091836734694,
- "loss": 1.3763,
+ "epoch": 6.27,
+ "learning_rate": 0.00012116477272727273,
+ "loss": 0.8956,
"step": 555
},
{
- "epoch": 11.25,
- "learning_rate": 0.00012908163265306123,
- "loss": 1.3623,
+ "epoch": 6.28,
+ "learning_rate": 0.00012102272727272728,
+ "loss": 0.8998,
"step": 556
},
{
- "epoch": 11.27,
- "learning_rate": 0.00012895408163265306,
- "loss": 1.3907,
+ "epoch": 6.29,
+ "learning_rate": 0.00012088068181818182,
+ "loss": 0.915,
"step": 557
},
{
- "epoch": 11.29,
- "learning_rate": 0.0001288265306122449,
- "loss": 1.3807,
+ "epoch": 6.3,
+ "learning_rate": 0.00012073863636363636,
+ "loss": 0.9282,
"step": 558
},
{
- "epoch": 11.31,
- "learning_rate": 0.00012869897959183674,
- "loss": 1.4045,
+ "epoch": 6.32,
+ "learning_rate": 0.00012059659090909093,
+ "loss": 0.8938,
"step": 559
},
{
- "epoch": 11.33,
- "learning_rate": 0.00012857142857142858,
- "loss": 1.4038,
+ "epoch": 6.33,
+ "learning_rate": 0.00012045454545454546,
+ "loss": 0.8886,
"step": 560
},
{
- "epoch": 11.35,
- "learning_rate": 0.0001284438775510204,
- "loss": 1.3466,
+ "epoch": 6.34,
+ "learning_rate": 0.0001203125,
+ "loss": 0.8988,
"step": 561
},
{
- "epoch": 11.37,
- "learning_rate": 0.00012831632653061226,
- "loss": 1.3449,
+ "epoch": 6.35,
+ "learning_rate": 0.00012017045454545455,
+ "loss": 0.8852,
"step": 562
},
{
- "epoch": 11.39,
- "learning_rate": 0.0001281887755102041,
- "loss": 1.3866,
+ "epoch": 6.36,
+ "learning_rate": 0.0001200284090909091,
+ "loss": 0.8818,
"step": 563
},
{
- "epoch": 11.41,
- "learning_rate": 0.00012806122448979593,
- "loss": 1.3106,
+ "epoch": 6.37,
+ "learning_rate": 0.00011988636363636365,
+ "loss": 0.8881,
"step": 564
},
{
- "epoch": 11.43,
- "learning_rate": 0.00012793367346938776,
- "loss": 1.4414,
+ "epoch": 6.38,
+ "learning_rate": 0.0001197443181818182,
+ "loss": 0.9226,
"step": 565
},
{
- "epoch": 11.45,
- "learning_rate": 0.00012780612244897962,
- "loss": 1.3737,
+ "epoch": 6.39,
+ "learning_rate": 0.00011960227272727273,
+ "loss": 0.8849,
"step": 566
},
{
- "epoch": 11.47,
- "learning_rate": 0.00012767857142857142,
- "loss": 1.4053,
+ "epoch": 6.41,
+ "learning_rate": 0.00011946022727272727,
+ "loss": 0.8894,
"step": 567
},
{
- "epoch": 11.49,
- "learning_rate": 0.00012755102040816328,
- "loss": 1.4561,
+ "epoch": 6.42,
+ "learning_rate": 0.00011931818181818182,
+ "loss": 0.9207,
"step": 568
},
{
- "epoch": 11.51,
- "learning_rate": 0.0001274234693877551,
- "loss": 1.3684,
+ "epoch": 6.43,
+ "learning_rate": 0.00011917613636363636,
+ "loss": 0.9105,
"step": 569
},
{
- "epoch": 11.53,
- "learning_rate": 0.00012729591836734697,
- "loss": 1.3117,
+ "epoch": 6.44,
+ "learning_rate": 0.00011903409090909092,
+ "loss": 0.8762,
"step": 570
},
{
- "epoch": 11.55,
- "learning_rate": 0.00012716836734693877,
- "loss": 1.3474,
+ "epoch": 6.45,
+ "learning_rate": 0.00011889204545454547,
+ "loss": 0.8926,
"step": 571
},
{
- "epoch": 11.57,
- "learning_rate": 0.00012704081632653063,
- "loss": 1.3804,
+ "epoch": 6.46,
+ "learning_rate": 0.00011875,
+ "loss": 0.8719,
"step": 572
},
{
- "epoch": 11.59,
- "learning_rate": 0.00012691326530612246,
- "loss": 1.3656,
+ "epoch": 6.47,
+ "learning_rate": 0.00011860795454545454,
+ "loss": 0.9198,
"step": 573
},
{
- "epoch": 11.61,
- "learning_rate": 0.0001267857142857143,
- "loss": 1.3133,
+ "epoch": 6.48,
+ "learning_rate": 0.00011846590909090909,
+ "loss": 0.8846,
"step": 574
},
{
- "epoch": 11.63,
- "learning_rate": 0.00012665816326530612,
- "loss": 1.4077,
+ "epoch": 6.5,
+ "learning_rate": 0.00011832386363636365,
+ "loss": 0.8495,
"step": 575
},
{
- "epoch": 11.65,
- "learning_rate": 0.00012653061224489798,
- "loss": 1.4087,
+ "epoch": 6.51,
+ "learning_rate": 0.0001181818181818182,
+ "loss": 0.8953,
"step": 576
},
{
- "epoch": 11.67,
- "learning_rate": 0.00012640306122448978,
- "loss": 1.3524,
+ "epoch": 6.52,
+ "learning_rate": 0.00011803977272727274,
+ "loss": 0.8686,
"step": 577
},
{
- "epoch": 11.7,
- "learning_rate": 0.00012627551020408164,
- "loss": 1.3481,
+ "epoch": 6.53,
+ "learning_rate": 0.00011789772727272727,
+ "loss": 0.8841,
"step": 578
},
{
- "epoch": 11.72,
- "learning_rate": 0.00012614795918367347,
- "loss": 1.4497,
+ "epoch": 6.54,
+ "learning_rate": 0.00011775568181818182,
+ "loss": 0.8681,
"step": 579
},
{
- "epoch": 11.74,
- "learning_rate": 0.0001260204081632653,
- "loss": 1.3866,
+ "epoch": 6.55,
+ "learning_rate": 0.00011761363636363636,
+ "loss": 0.8732,
"step": 580
},
{
- "epoch": 11.76,
- "learning_rate": 0.00012589285714285713,
- "loss": 1.42,
+ "epoch": 6.56,
+ "learning_rate": 0.00011747159090909092,
+ "loss": 0.8582,
"step": 581
},
{
- "epoch": 11.78,
- "learning_rate": 0.000125765306122449,
- "loss": 1.3562,
+ "epoch": 6.58,
+ "learning_rate": 0.00011732954545454546,
+ "loss": 0.8744,
"step": 582
},
{
- "epoch": 11.8,
- "learning_rate": 0.00012563775510204082,
- "loss": 1.3249,
+ "epoch": 6.59,
+ "learning_rate": 0.00011718750000000001,
+ "loss": 0.8694,
"step": 583
},
{
- "epoch": 11.82,
- "learning_rate": 0.00012551020408163265,
- "loss": 1.4277,
+ "epoch": 6.6,
+ "learning_rate": 0.00011704545454545454,
+ "loss": 0.8565,
"step": 584
},
{
- "epoch": 11.84,
- "learning_rate": 0.0001253826530612245,
- "loss": 1.3734,
+ "epoch": 6.61,
+ "learning_rate": 0.00011690340909090909,
+ "loss": 0.8584,
"step": 585
},
{
- "epoch": 11.86,
- "learning_rate": 0.00012525510204081634,
- "loss": 1.3765,
+ "epoch": 6.62,
+ "learning_rate": 0.00011676136363636366,
+ "loss": 0.8859,
"step": 586
},
{
- "epoch": 11.88,
- "learning_rate": 0.00012512755102040817,
- "loss": 1.4153,
+ "epoch": 6.63,
+ "learning_rate": 0.00011661931818181819,
+ "loss": 0.8452,
"step": 587
},
{
- "epoch": 11.9,
- "learning_rate": 0.000125,
- "loss": 1.3847,
+ "epoch": 6.64,
+ "learning_rate": 0.00011647727272727273,
+ "loss": 0.8323,
"step": 588
},
{
- "epoch": 11.92,
- "learning_rate": 0.00012487244897959186,
- "loss": 1.3824,
+ "epoch": 6.65,
+ "learning_rate": 0.00011633522727272728,
+ "loss": 0.8548,
"step": 589
},
{
- "epoch": 11.94,
- "learning_rate": 0.00012474489795918366,
- "loss": 1.3938,
+ "epoch": 6.67,
+ "learning_rate": 0.00011619318181818181,
+ "loss": 0.8506,
"step": 590
},
{
- "epoch": 11.96,
- "learning_rate": 0.00012461734693877552,
- "loss": 1.4143,
+ "epoch": 6.68,
+ "learning_rate": 0.00011605113636363636,
+ "loss": 0.8556,
"step": 591
},
{
- "epoch": 11.98,
- "learning_rate": 0.00012448979591836735,
- "loss": 1.3794,
+ "epoch": 6.69,
+ "learning_rate": 0.00011590909090909093,
+ "loss": 0.8459,
"step": 592
},
{
- "epoch": 12.0,
- "learning_rate": 0.00012436224489795918,
- "loss": 1.3755,
+ "epoch": 6.7,
+ "learning_rate": 0.00011576704545454546,
+ "loss": 0.8432,
"step": 593
},
{
- "epoch": 12.02,
- "learning_rate": 0.00012423469387755101,
- "loss": 1.3736,
+ "epoch": 6.71,
+ "learning_rate": 0.000115625,
+ "loss": 0.8645,
"step": 594
},
{
- "epoch": 12.04,
- "learning_rate": 0.00012410714285714287,
- "loss": 1.2957,
+ "epoch": 6.72,
+ "learning_rate": 0.00011548295454545455,
+ "loss": 0.86,
"step": 595
},
{
- "epoch": 12.06,
- "learning_rate": 0.0001239795918367347,
- "loss": 1.2996,
+ "epoch": 6.73,
+ "learning_rate": 0.00011534090909090908,
+ "loss": 0.8161,
"step": 596
},
{
- "epoch": 12.08,
- "learning_rate": 0.00012385204081632653,
- "loss": 1.3648,
+ "epoch": 6.74,
+ "learning_rate": 0.00011519886363636365,
+ "loss": 0.8133,
"step": 597
},
{
- "epoch": 12.1,
- "learning_rate": 0.00012372448979591837,
- "loss": 1.3031,
+ "epoch": 6.76,
+ "learning_rate": 0.0001150568181818182,
+ "loss": 0.8372,
"step": 598
},
{
- "epoch": 12.12,
- "learning_rate": 0.00012359693877551022,
- "loss": 1.2933,
+ "epoch": 6.77,
+ "learning_rate": 0.00011491477272727273,
+ "loss": 0.8222,
"step": 599
},
{
- "epoch": 12.14,
- "learning_rate": 0.00012346938775510203,
- "loss": 1.322,
+ "epoch": 6.78,
+ "learning_rate": 0.00011477272727272728,
+ "loss": 0.8372,
"step": 600
},
{
- "epoch": 12.16,
- "learning_rate": 0.00012334183673469389,
- "loss": 1.3123,
+ "epoch": 6.79,
+ "learning_rate": 0.00011463068181818182,
+ "loss": 0.837,
"step": 601
},
{
- "epoch": 12.18,
- "learning_rate": 0.00012321428571428572,
- "loss": 1.3187,
+ "epoch": 6.8,
+ "learning_rate": 0.00011448863636363637,
+ "loss": 0.8406,
"step": 602
},
{
- "epoch": 12.2,
- "learning_rate": 0.00012308673469387755,
- "loss": 1.3353,
+ "epoch": 6.81,
+ "learning_rate": 0.00011434659090909092,
+ "loss": 0.836,
"step": 603
},
{
- "epoch": 12.22,
- "learning_rate": 0.0001229591836734694,
- "loss": 1.3221,
+ "epoch": 6.82,
+ "learning_rate": 0.00011420454545454547,
+ "loss": 0.8476,
"step": 604
},
{
- "epoch": 12.24,
- "learning_rate": 0.00012283163265306124,
- "loss": 1.3458,
+ "epoch": 6.83,
+ "learning_rate": 0.0001140625,
+ "loss": 0.8368,
"step": 605
},
{
- "epoch": 12.26,
- "learning_rate": 0.00012270408163265307,
- "loss": 1.275,
+ "epoch": 6.85,
+ "learning_rate": 0.00011392045454545455,
+ "loss": 0.822,
"step": 606
},
{
- "epoch": 12.28,
- "learning_rate": 0.0001225765306122449,
- "loss": 1.3455,
+ "epoch": 6.86,
+ "learning_rate": 0.00011377840909090909,
+ "loss": 0.8107,
"step": 607
},
{
- "epoch": 12.3,
- "learning_rate": 0.00012244897959183676,
- "loss": 1.2769,
+ "epoch": 6.87,
+ "learning_rate": 0.00011363636363636365,
+ "loss": 0.8395,
"step": 608
},
{
- "epoch": 12.32,
- "learning_rate": 0.00012232142857142859,
- "loss": 1.3201,
+ "epoch": 6.88,
+ "learning_rate": 0.0001134943181818182,
+ "loss": 0.8083,
"step": 609
},
{
- "epoch": 12.34,
- "learning_rate": 0.00012219387755102042,
- "loss": 1.3073,
+ "epoch": 6.89,
+ "learning_rate": 0.00011335227272727274,
+ "loss": 0.828,
"step": 610
},
{
- "epoch": 12.36,
- "learning_rate": 0.00012206632653061225,
- "loss": 1.3103,
+ "epoch": 6.9,
+ "learning_rate": 0.00011321022727272727,
+ "loss": 0.8494,
"step": 611
},
{
- "epoch": 12.38,
- "learning_rate": 0.00012193877551020409,
- "loss": 1.4437,
+ "epoch": 6.91,
+ "learning_rate": 0.00011306818181818182,
+ "loss": 0.8169,
"step": 612
},
{
- "epoch": 12.4,
- "learning_rate": 0.00012181122448979591,
- "loss": 1.3086,
+ "epoch": 6.93,
+ "learning_rate": 0.00011292613636363636,
+ "loss": 0.8224,
"step": 613
},
{
- "epoch": 12.42,
- "learning_rate": 0.00012168367346938775,
- "loss": 1.3867,
+ "epoch": 6.94,
+ "learning_rate": 0.00011278409090909092,
+ "loss": 0.8173,
"step": 614
},
{
- "epoch": 12.44,
- "learning_rate": 0.0001215561224489796,
- "loss": 1.2565,
+ "epoch": 6.95,
+ "learning_rate": 0.00011264204545454547,
+ "loss": 0.7961,
"step": 615
},
{
- "epoch": 12.46,
- "learning_rate": 0.00012142857142857143,
- "loss": 1.335,
+ "epoch": 6.96,
+ "learning_rate": 0.00011250000000000001,
+ "loss": 0.7948,
"step": 616
},
{
- "epoch": 12.48,
- "learning_rate": 0.00012130102040816327,
- "loss": 1.3423,
+ "epoch": 6.97,
+ "learning_rate": 0.00011235795454545454,
+ "loss": 0.7746,
"step": 617
},
{
- "epoch": 12.5,
- "learning_rate": 0.00012117346938775512,
- "loss": 1.3433,
+ "epoch": 6.98,
+ "learning_rate": 0.00011221590909090909,
+ "loss": 0.8325,
"step": 618
},
{
- "epoch": 12.52,
- "learning_rate": 0.00012104591836734695,
- "loss": 1.3387,
+ "epoch": 6.99,
+ "learning_rate": 0.00011207386363636365,
+ "loss": 0.8149,
"step": 619
},
{
- "epoch": 12.55,
- "learning_rate": 0.00012091836734693878,
- "loss": 1.3923,
+ "epoch": 7.0,
+ "learning_rate": 0.00011193181818181819,
+ "loss": 0.7516,
"step": 620
},
{
- "epoch": 12.57,
- "learning_rate": 0.00012079081632653062,
- "loss": 1.3774,
+ "epoch": 7.02,
+ "learning_rate": 0.00011178977272727274,
+ "loss": 0.7571,
"step": 621
},
{
- "epoch": 12.59,
- "learning_rate": 0.00012066326530612247,
- "loss": 1.3203,
+ "epoch": 7.03,
+ "learning_rate": 0.00011164772727272728,
+ "loss": 0.7397,
"step": 622
},
{
- "epoch": 12.61,
- "learning_rate": 0.00012053571428571429,
- "loss": 1.2924,
+ "epoch": 7.04,
+ "learning_rate": 0.00011150568181818181,
+ "loss": 0.761,
"step": 623
},
{
- "epoch": 12.63,
- "learning_rate": 0.00012040816326530613,
- "loss": 1.3292,
+ "epoch": 7.05,
+ "learning_rate": 0.00011136363636363636,
+ "loss": 0.7783,
"step": 624
},
{
- "epoch": 12.65,
- "learning_rate": 0.00012028061224489798,
- "loss": 1.3161,
+ "epoch": 7.06,
+ "learning_rate": 0.00011122159090909092,
+ "loss": 0.7571,
"step": 625
},
{
- "epoch": 12.67,
- "learning_rate": 0.00012015306122448979,
- "loss": 1.352,
+ "epoch": 7.07,
+ "learning_rate": 0.00011107954545454546,
+ "loss": 0.7628,
"step": 626
},
{
- "epoch": 12.69,
- "learning_rate": 0.00012002551020408164,
- "loss": 1.3577,
+ "epoch": 7.08,
+ "learning_rate": 0.0001109375,
+ "loss": 0.7561,
"step": 627
},
{
- "epoch": 12.71,
- "learning_rate": 0.00011989795918367348,
- "loss": 1.3575,
+ "epoch": 7.09,
+ "learning_rate": 0.00011079545454545455,
+ "loss": 0.7432,
"step": 628
},
{
- "epoch": 12.73,
- "learning_rate": 0.0001197704081632653,
- "loss": 1.3727,
+ "epoch": 7.11,
+ "learning_rate": 0.00011065340909090908,
+ "loss": 0.7245,
"step": 629
},
{
- "epoch": 12.75,
- "learning_rate": 0.00011964285714285714,
- "loss": 1.3312,
+ "epoch": 7.12,
+ "learning_rate": 0.00011051136363636366,
+ "loss": 0.7279,
"step": 630
},
{
- "epoch": 12.77,
- "learning_rate": 0.00011951530612244899,
- "loss": 1.3378,
+ "epoch": 7.13,
+ "learning_rate": 0.00011036931818181819,
+ "loss": 0.7347,
"step": 631
},
{
- "epoch": 12.79,
- "learning_rate": 0.00011938775510204083,
- "loss": 1.295,
+ "epoch": 7.14,
+ "learning_rate": 0.00011022727272727273,
+ "loss": 0.7427,
"step": 632
},
{
- "epoch": 12.81,
- "learning_rate": 0.00011926020408163265,
- "loss": 1.3447,
+ "epoch": 7.15,
+ "learning_rate": 0.00011008522727272728,
+ "loss": 0.7339,
"step": 633
},
{
- "epoch": 12.83,
- "learning_rate": 0.0001191326530612245,
- "loss": 1.3835,
+ "epoch": 7.16,
+ "learning_rate": 0.00010994318181818182,
+ "loss": 0.7375,
"step": 634
},
{
- "epoch": 12.85,
- "learning_rate": 0.00011900510204081634,
- "loss": 1.3222,
+ "epoch": 7.17,
+ "learning_rate": 0.00010980113636363635,
+ "loss": 0.7182,
"step": 635
},
{
- "epoch": 12.87,
- "learning_rate": 0.00011887755102040817,
- "loss": 1.2851,
+ "epoch": 7.19,
+ "learning_rate": 0.00010965909090909093,
+ "loss": 0.7452,
"step": 636
},
{
- "epoch": 12.89,
- "learning_rate": 0.00011875,
- "loss": 1.2723,
+ "epoch": 7.2,
+ "learning_rate": 0.00010951704545454546,
+ "loss": 0.7565,
"step": 637
},
{
- "epoch": 12.91,
- "learning_rate": 0.00011862244897959184,
- "loss": 1.3924,
+ "epoch": 7.21,
+ "learning_rate": 0.000109375,
+ "loss": 0.7296,
"step": 638
},
{
- "epoch": 12.93,
- "learning_rate": 0.00011849489795918368,
- "loss": 1.4625,
+ "epoch": 7.22,
+ "learning_rate": 0.00010923295454545455,
+ "loss": 0.7484,
"step": 639
},
{
- "epoch": 12.95,
- "learning_rate": 0.00011836734693877552,
- "loss": 1.3245,
+ "epoch": 7.23,
+ "learning_rate": 0.00010909090909090909,
+ "loss": 0.732,
"step": 640
},
{
- "epoch": 12.97,
- "learning_rate": 0.00011823979591836736,
- "loss": 1.4042,
+ "epoch": 7.24,
+ "learning_rate": 0.00010894886363636365,
+ "loss": 0.7415,
"step": 641
},
{
- "epoch": 12.99,
- "learning_rate": 0.00011811224489795918,
- "loss": 1.3761,
+ "epoch": 7.25,
+ "learning_rate": 0.0001088068181818182,
+ "loss": 0.7344,
"step": 642
},
{
- "epoch": 13.01,
- "learning_rate": 0.00011798469387755103,
- "loss": 1.3376,
+ "epoch": 7.26,
+ "learning_rate": 0.00010866477272727274,
+ "loss": 0.7267,
"step": 643
},
{
- "epoch": 13.03,
- "learning_rate": 0.00011785714285714287,
- "loss": 1.2174,
+ "epoch": 7.28,
+ "learning_rate": 0.00010852272727272727,
+ "loss": 0.7543,
"step": 644
},
{
- "epoch": 13.05,
- "learning_rate": 0.00011772959183673471,
- "loss": 1.3602,
+ "epoch": 7.29,
+ "learning_rate": 0.00010838068181818182,
+ "loss": 0.7266,
"step": 645
},
{
- "epoch": 13.07,
- "learning_rate": 0.00011760204081632653,
- "loss": 1.3002,
+ "epoch": 7.3,
+ "learning_rate": 0.00010823863636363636,
+ "loss": 0.7449,
"step": 646
},
{
- "epoch": 13.09,
- "learning_rate": 0.00011747448979591838,
- "loss": 1.2262,
+ "epoch": 7.31,
+ "learning_rate": 0.00010809659090909092,
+ "loss": 0.7324,
"step": 647
},
{
- "epoch": 13.11,
- "learning_rate": 0.00011734693877551022,
- "loss": 1.3048,
+ "epoch": 7.32,
+ "learning_rate": 0.00010795454545454547,
+ "loss": 0.7268,
"step": 648
},
{
- "epoch": 13.13,
- "learning_rate": 0.00011721938775510204,
- "loss": 1.2231,
+ "epoch": 7.33,
+ "learning_rate": 0.00010781250000000001,
+ "loss": 0.7172,
"step": 649
},
{
- "epoch": 13.15,
- "learning_rate": 0.00011709183673469388,
- "loss": 1.2996,
+ "epoch": 7.34,
+ "learning_rate": 0.00010767045454545454,
+ "loss": 0.7169,
"step": 650
},
{
- "epoch": 13.17,
- "learning_rate": 0.00011696428571428573,
- "loss": 1.2708,
+ "epoch": 7.35,
+ "learning_rate": 0.00010752840909090909,
+ "loss": 0.7194,
"step": 651
},
{
- "epoch": 13.19,
- "learning_rate": 0.00011683673469387754,
- "loss": 1.2776,
+ "epoch": 7.37,
+ "learning_rate": 0.00010738636363636365,
+ "loss": 0.7223,
"step": 652
},
{
- "epoch": 13.21,
- "learning_rate": 0.00011670918367346939,
- "loss": 1.248,
+ "epoch": 7.38,
+ "learning_rate": 0.00010724431818181819,
+ "loss": 0.7158,
"step": 653
},
{
- "epoch": 13.23,
- "learning_rate": 0.00011658163265306123,
- "loss": 1.2582,
+ "epoch": 7.39,
+ "learning_rate": 0.00010710227272727274,
+ "loss": 0.7122,
"step": 654
},
{
- "epoch": 13.25,
- "learning_rate": 0.00011645408163265305,
- "loss": 1.3011,
+ "epoch": 7.4,
+ "learning_rate": 0.00010696022727272728,
+ "loss": 0.7225,
"step": 655
},
{
- "epoch": 13.27,
- "learning_rate": 0.0001163265306122449,
- "loss": 1.2969,
+ "epoch": 7.41,
+ "learning_rate": 0.00010681818181818181,
+ "loss": 0.7102,
"step": 656
},
{
- "epoch": 13.29,
- "learning_rate": 0.00011619897959183674,
- "loss": 1.2454,
+ "epoch": 7.42,
+ "learning_rate": 0.00010667613636363636,
+ "loss": 0.7251,
"step": 657
},
{
- "epoch": 13.31,
- "learning_rate": 0.00011607142857142858,
- "loss": 1.1914,
+ "epoch": 7.43,
+ "learning_rate": 0.00010653409090909092,
+ "loss": 0.7191,
"step": 658
},
{
- "epoch": 13.33,
- "learning_rate": 0.00011594387755102041,
- "loss": 1.34,
+ "epoch": 7.45,
+ "learning_rate": 0.00010639204545454546,
+ "loss": 0.7015,
"step": 659
},
{
- "epoch": 13.35,
- "learning_rate": 0.00011581632653061225,
- "loss": 1.2828,
+ "epoch": 7.46,
+ "learning_rate": 0.00010625000000000001,
+ "loss": 0.693,
"step": 660
},
{
- "epoch": 13.37,
- "learning_rate": 0.00011568877551020409,
- "loss": 1.2962,
+ "epoch": 7.47,
+ "learning_rate": 0.00010610795454545455,
+ "loss": 0.7039,
"step": 661
},
{
- "epoch": 13.39,
- "learning_rate": 0.00011556122448979592,
- "loss": 1.3334,
+ "epoch": 7.48,
+ "learning_rate": 0.00010596590909090908,
+ "loss": 0.7305,
"step": 662
},
{
- "epoch": 13.42,
- "learning_rate": 0.00011543367346938776,
- "loss": 1.2832,
+ "epoch": 7.49,
+ "learning_rate": 0.00010582386363636366,
+ "loss": 0.6978,
"step": 663
},
{
- "epoch": 13.44,
- "learning_rate": 0.00011530612244897961,
- "loss": 1.3012,
+ "epoch": 7.5,
+ "learning_rate": 0.00010568181818181819,
+ "loss": 0.7219,
"step": 664
},
{
- "epoch": 13.46,
- "learning_rate": 0.00011517857142857143,
- "loss": 1.2857,
+ "epoch": 7.51,
+ "learning_rate": 0.00010553977272727273,
+ "loss": 0.7199,
"step": 665
},
{
- "epoch": 13.48,
- "learning_rate": 0.00011505102040816327,
- "loss": 1.2855,
+ "epoch": 7.52,
+ "learning_rate": 0.00010539772727272728,
+ "loss": 0.6979,
"step": 666
},
{
- "epoch": 13.5,
- "learning_rate": 0.00011492346938775512,
- "loss": 1.3077,
+ "epoch": 7.54,
+ "learning_rate": 0.00010525568181818182,
+ "loss": 0.7058,
"step": 667
},
{
- "epoch": 13.52,
- "learning_rate": 0.00011479591836734696,
- "loss": 1.3139,
+ "epoch": 7.55,
+ "learning_rate": 0.00010511363636363635,
+ "loss": 0.6994,
"step": 668
},
{
- "epoch": 13.54,
- "learning_rate": 0.00011466836734693878,
- "loss": 1.3138,
+ "epoch": 7.56,
+ "learning_rate": 0.00010497159090909093,
+ "loss": 0.7141,
"step": 669
},
{
- "epoch": 13.56,
- "learning_rate": 0.00011454081632653062,
- "loss": 1.2808,
+ "epoch": 7.57,
+ "learning_rate": 0.00010482954545454546,
+ "loss": 0.7092,
"step": 670
},
{
- "epoch": 13.58,
- "learning_rate": 0.00011441326530612247,
- "loss": 1.2492,
+ "epoch": 7.58,
+ "learning_rate": 0.0001046875,
+ "loss": 0.7059,
"step": 671
},
{
- "epoch": 13.6,
- "learning_rate": 0.00011428571428571428,
- "loss": 1.2027,
+ "epoch": 7.59,
+ "learning_rate": 0.00010454545454545455,
+ "loss": 0.6904,
"step": 672
},
{
- "epoch": 13.62,
- "learning_rate": 0.00011415816326530613,
- "loss": 1.33,
+ "epoch": 7.6,
+ "learning_rate": 0.0001044034090909091,
+ "loss": 0.7115,
"step": 673
},
{
- "epoch": 13.64,
- "learning_rate": 0.00011403061224489797,
- "loss": 1.3112,
+ "epoch": 7.61,
+ "learning_rate": 0.00010426136363636365,
+ "loss": 0.7254,
"step": 674
},
{
- "epoch": 13.66,
- "learning_rate": 0.00011390306122448979,
- "loss": 1.2772,
+ "epoch": 7.63,
+ "learning_rate": 0.0001041193181818182,
+ "loss": 0.7181,
"step": 675
},
{
- "epoch": 13.68,
- "learning_rate": 0.00011377551020408163,
- "loss": 1.2701,
+ "epoch": 7.64,
+ "learning_rate": 0.00010397727272727273,
+ "loss": 0.6867,
"step": 676
},
{
- "epoch": 13.7,
- "learning_rate": 0.00011364795918367348,
- "loss": 1.1973,
+ "epoch": 7.65,
+ "learning_rate": 0.00010383522727272727,
+ "loss": 0.6917,
"step": 677
},
{
- "epoch": 13.72,
- "learning_rate": 0.0001135204081632653,
- "loss": 1.3124,
+ "epoch": 7.66,
+ "learning_rate": 0.00010369318181818182,
+ "loss": 0.6908,
"step": 678
},
{
- "epoch": 13.74,
- "learning_rate": 0.00011339285714285714,
- "loss": 1.3085,
+ "epoch": 7.67,
+ "learning_rate": 0.00010355113636363636,
+ "loss": 0.6871,
"step": 679
},
{
- "epoch": 13.76,
- "learning_rate": 0.00011326530612244898,
- "loss": 1.3457,
+ "epoch": 7.68,
+ "learning_rate": 0.00010340909090909092,
+ "loss": 0.682,
"step": 680
},
{
- "epoch": 13.78,
- "learning_rate": 0.00011313775510204083,
- "loss": 1.3338,
+ "epoch": 7.69,
+ "learning_rate": 0.00010326704545454547,
+ "loss": 0.6737,
"step": 681
},
{
- "epoch": 13.8,
- "learning_rate": 0.00011301020408163266,
- "loss": 1.2753,
+ "epoch": 7.7,
+ "learning_rate": 0.000103125,
+ "loss": 0.7023,
"step": 682
},
{
- "epoch": 13.82,
- "learning_rate": 0.00011288265306122449,
- "loss": 1.2786,
+ "epoch": 7.72,
+ "learning_rate": 0.00010298295454545454,
+ "loss": 0.7079,
"step": 683
},
{
- "epoch": 13.84,
- "learning_rate": 0.00011275510204081634,
- "loss": 1.2584,
+ "epoch": 7.73,
+ "learning_rate": 0.00010284090909090909,
+ "loss": 0.6954,
"step": 684
},
{
- "epoch": 13.86,
- "learning_rate": 0.00011262755102040817,
- "loss": 1.2779,
+ "epoch": 7.74,
+ "learning_rate": 0.00010269886363636365,
+ "loss": 0.6834,
"step": 685
},
{
- "epoch": 13.88,
- "learning_rate": 0.00011250000000000001,
- "loss": 1.3502,
+ "epoch": 7.75,
+ "learning_rate": 0.0001025568181818182,
+ "loss": 0.6706,
"step": 686
},
{
- "epoch": 13.9,
- "learning_rate": 0.00011237244897959185,
- "loss": 1.3251,
+ "epoch": 7.76,
+ "learning_rate": 0.00010241477272727274,
+ "loss": 0.6706,
"step": 687
},
{
- "epoch": 13.92,
- "learning_rate": 0.00011224489795918367,
- "loss": 1.273,
+ "epoch": 7.77,
+ "learning_rate": 0.00010227272727272727,
+ "loss": 0.681,
"step": 688
},
{
- "epoch": 13.94,
- "learning_rate": 0.00011211734693877552,
- "loss": 1.3341,
+ "epoch": 7.78,
+ "learning_rate": 0.00010213068181818182,
+ "loss": 0.6853,
"step": 689
},
{
- "epoch": 13.96,
- "learning_rate": 0.00011198979591836736,
- "loss": 1.2654,
+ "epoch": 7.8,
+ "learning_rate": 0.00010198863636363636,
+ "loss": 0.6772,
"step": 690
},
{
- "epoch": 13.98,
- "learning_rate": 0.00011186224489795918,
- "loss": 1.3333,
+ "epoch": 7.81,
+ "learning_rate": 0.00010184659090909092,
+ "loss": 0.6635,
"step": 691
},
{
- "epoch": 14.0,
- "learning_rate": 0.00011173469387755102,
- "loss": 1.3246,
+ "epoch": 7.82,
+ "learning_rate": 0.00010170454545454546,
+ "loss": 0.6712,
"step": 692
},
{
- "epoch": 14.02,
- "learning_rate": 0.00011160714285714287,
- "loss": 1.2547,
+ "epoch": 7.83,
+ "learning_rate": 0.00010156250000000001,
+ "loss": 0.6884,
"step": 693
},
{
- "epoch": 14.04,
- "learning_rate": 0.00011147959183673471,
- "loss": 1.208,
+ "epoch": 7.84,
+ "learning_rate": 0.00010142045454545454,
+ "loss": 0.6641,
"step": 694
},
{
- "epoch": 14.06,
- "learning_rate": 0.00011135204081632653,
- "loss": 1.223,
+ "epoch": 7.85,
+ "learning_rate": 0.00010127840909090909,
+ "loss": 0.6838,
"step": 695
},
{
- "epoch": 14.08,
- "learning_rate": 0.00011122448979591837,
- "loss": 1.2483,
+ "epoch": 7.86,
+ "learning_rate": 0.00010113636363636366,
+ "loss": 0.675,
"step": 696
},
{
- "epoch": 14.1,
- "learning_rate": 0.00011109693877551022,
- "loss": 1.2823,
+ "epoch": 7.87,
+ "learning_rate": 0.00010099431818181819,
+ "loss": 0.6626,
"step": 697
},
{
- "epoch": 14.12,
- "learning_rate": 0.00011096938775510204,
- "loss": 1.2013,
+ "epoch": 7.89,
+ "learning_rate": 0.00010085227272727273,
+ "loss": 0.6605,
"step": 698
},
{
- "epoch": 14.14,
- "learning_rate": 0.00011084183673469388,
- "loss": 1.1883,
+ "epoch": 7.9,
+ "learning_rate": 0.00010071022727272728,
+ "loss": 0.6777,
"step": 699
},
{
- "epoch": 14.16,
- "learning_rate": 0.00011071428571428572,
- "loss": 1.2364,
+ "epoch": 7.91,
+ "learning_rate": 0.00010056818181818181,
+ "loss": 0.6347,
"step": 700
},
{
- "epoch": 14.18,
- "learning_rate": 0.00011058673469387754,
- "loss": 1.2069,
+ "epoch": 7.92,
+ "learning_rate": 0.00010042613636363636,
+ "loss": 0.6857,
"step": 701
},
{
- "epoch": 14.2,
- "learning_rate": 0.00011045918367346939,
- "loss": 1.1968,
+ "epoch": 7.93,
+ "learning_rate": 0.00010028409090909093,
+ "loss": 0.6677,
"step": 702
},
{
- "epoch": 14.22,
- "learning_rate": 0.00011033163265306123,
- "loss": 1.2236,
+ "epoch": 7.94,
+ "learning_rate": 0.00010014204545454546,
+ "loss": 0.6697,
"step": 703
},
{
- "epoch": 14.24,
- "learning_rate": 0.00011020408163265306,
- "loss": 1.1942,
+ "epoch": 7.95,
+ "learning_rate": 0.0001,
+ "loss": 0.6375,
"step": 704
},
{
- "epoch": 14.26,
- "learning_rate": 0.0001100765306122449,
- "loss": 1.2561,
+ "epoch": 7.96,
+ "learning_rate": 9.985795454545455e-05,
+ "loss": 0.6572,
"step": 705
},
{
- "epoch": 14.29,
- "learning_rate": 0.00010994897959183674,
- "loss": 1.1839,
+ "epoch": 7.98,
+ "learning_rate": 9.97159090909091e-05,
+ "loss": 0.668,
"step": 706
},
{
- "epoch": 14.31,
- "learning_rate": 0.00010982142857142858,
- "loss": 1.2128,
+ "epoch": 7.99,
+ "learning_rate": 9.957386363636364e-05,
+ "loss": 0.6797,
"step": 707
},
{
- "epoch": 14.33,
- "learning_rate": 0.00010969387755102041,
- "loss": 1.3086,
+ "epoch": 8.0,
+ "learning_rate": 9.943181818181819e-05,
+ "loss": 0.6784,
"step": 708
},
{
- "epoch": 14.35,
- "learning_rate": 0.00010956632653061226,
- "loss": 1.2379,
+ "epoch": 8.01,
+ "learning_rate": 9.928977272727273e-05,
+ "loss": 0.6192,
"step": 709
},
{
- "epoch": 14.37,
- "learning_rate": 0.0001094387755102041,
- "loss": 1.176,
+ "epoch": 8.02,
+ "learning_rate": 9.914772727272728e-05,
+ "loss": 0.6287,
"step": 710
},
{
- "epoch": 14.39,
- "learning_rate": 0.00010931122448979592,
- "loss": 1.2105,
+ "epoch": 8.03,
+ "learning_rate": 9.900568181818183e-05,
+ "loss": 0.6034,
"step": 711
},
{
- "epoch": 14.41,
- "learning_rate": 0.00010918367346938776,
- "loss": 1.2149,
+ "epoch": 8.04,
+ "learning_rate": 9.886363636363637e-05,
+ "loss": 0.6167,
"step": 712
},
{
- "epoch": 14.43,
- "learning_rate": 0.0001090561224489796,
- "loss": 1.2392,
+ "epoch": 8.06,
+ "learning_rate": 9.872159090909091e-05,
+ "loss": 0.6353,
"step": 713
},
{
- "epoch": 14.45,
- "learning_rate": 0.00010892857142857142,
- "loss": 1.2471,
+ "epoch": 8.07,
+ "learning_rate": 9.857954545454547e-05,
+ "loss": 0.6222,
"step": 714
},
{
- "epoch": 14.47,
- "learning_rate": 0.00010880102040816327,
- "loss": 1.2561,
+ "epoch": 8.08,
+ "learning_rate": 9.84375e-05,
+ "loss": 0.5963,
"step": 715
},
{
- "epoch": 14.49,
- "learning_rate": 0.00010867346938775511,
- "loss": 1.2179,
+ "epoch": 8.09,
+ "learning_rate": 9.829545454545455e-05,
+ "loss": 0.6042,
"step": 716
},
{
- "epoch": 14.51,
- "learning_rate": 0.00010854591836734696,
- "loss": 1.2459,
+ "epoch": 8.1,
+ "learning_rate": 9.81534090909091e-05,
+ "loss": 0.612,
"step": 717
},
{
- "epoch": 14.53,
- "learning_rate": 0.00010841836734693877,
- "loss": 1.2933,
+ "epoch": 8.11,
+ "learning_rate": 9.801136363636364e-05,
+ "loss": 0.6069,
"step": 718
},
{
- "epoch": 14.55,
- "learning_rate": 0.00010829081632653062,
- "loss": 1.2862,
+ "epoch": 8.12,
+ "learning_rate": 9.786931818181818e-05,
+ "loss": 0.6001,
"step": 719
},
{
- "epoch": 14.57,
- "learning_rate": 0.00010816326530612246,
- "loss": 1.2976,
+ "epoch": 8.13,
+ "learning_rate": 9.772727272727274e-05,
+ "loss": 0.6007,
"step": 720
},
{
- "epoch": 14.59,
- "learning_rate": 0.00010803571428571428,
- "loss": 1.231,
+ "epoch": 8.15,
+ "learning_rate": 9.758522727272727e-05,
+ "loss": 0.6079,
"step": 721
},
{
- "epoch": 14.61,
- "learning_rate": 0.00010790816326530613,
- "loss": 1.2464,
+ "epoch": 8.16,
+ "learning_rate": 9.744318181818183e-05,
+ "loss": 0.6216,
"step": 722
},
{
- "epoch": 14.63,
- "learning_rate": 0.00010778061224489797,
- "loss": 1.2181,
+ "epoch": 8.17,
+ "learning_rate": 9.730113636363637e-05,
+ "loss": 0.6321,
"step": 723
},
{
- "epoch": 14.65,
- "learning_rate": 0.00010765306122448979,
- "loss": 1.3307,
+ "epoch": 8.18,
+ "learning_rate": 9.71590909090909e-05,
+ "loss": 0.6044,
"step": 724
},
{
- "epoch": 14.67,
- "learning_rate": 0.00010752551020408163,
- "loss": 1.1723,
+ "epoch": 8.19,
+ "learning_rate": 9.701704545454547e-05,
+ "loss": 0.6028,
"step": 725
},
{
- "epoch": 14.69,
- "learning_rate": 0.00010739795918367348,
- "loss": 1.1528,
+ "epoch": 8.2,
+ "learning_rate": 9.687500000000001e-05,
+ "loss": 0.6098,
"step": 726
},
{
- "epoch": 14.71,
- "learning_rate": 0.0001072704081632653,
- "loss": 1.215,
+ "epoch": 8.21,
+ "learning_rate": 9.673295454545454e-05,
+ "loss": 0.6032,
"step": 727
},
{
- "epoch": 14.73,
- "learning_rate": 0.00010714285714285715,
- "loss": 1.2624,
+ "epoch": 8.22,
+ "learning_rate": 9.65909090909091e-05,
+ "loss": 0.6298,
"step": 728
},
{
- "epoch": 14.75,
- "learning_rate": 0.00010701530612244898,
- "loss": 1.3117,
+ "epoch": 8.24,
+ "learning_rate": 9.644886363636365e-05,
+ "loss": 0.6115,
"step": 729
},
{
- "epoch": 14.77,
- "learning_rate": 0.00010688775510204083,
- "loss": 1.2572,
+ "epoch": 8.25,
+ "learning_rate": 9.630681818181818e-05,
+ "loss": 0.6052,
"step": 730
},
{
- "epoch": 14.79,
- "learning_rate": 0.00010676020408163266,
- "loss": 1.222,
+ "epoch": 8.26,
+ "learning_rate": 9.616477272727274e-05,
+ "loss": 0.6097,
"step": 731
},
{
- "epoch": 14.81,
- "learning_rate": 0.0001066326530612245,
- "loss": 1.2881,
+ "epoch": 8.27,
+ "learning_rate": 9.602272727272728e-05,
+ "loss": 0.6062,
"step": 732
},
{
- "epoch": 14.83,
- "learning_rate": 0.00010650510204081635,
- "loss": 1.2676,
+ "epoch": 8.28,
+ "learning_rate": 9.588068181818183e-05,
+ "loss": 0.5984,
"step": 733
},
{
- "epoch": 14.85,
- "learning_rate": 0.00010637755102040816,
- "loss": 1.2734,
+ "epoch": 8.29,
+ "learning_rate": 9.573863636363637e-05,
+ "loss": 0.6432,
"step": 734
},
{
- "epoch": 14.87,
- "learning_rate": 0.00010625000000000001,
- "loss": 1.2885,
+ "epoch": 8.3,
+ "learning_rate": 9.559659090909092e-05,
+ "loss": 0.5814,
"step": 735
},
{
- "epoch": 14.89,
- "learning_rate": 0.00010612244897959185,
- "loss": 1.2764,
+ "epoch": 8.31,
+ "learning_rate": 9.545454545454546e-05,
+ "loss": 0.5965,
"step": 736
},
{
- "epoch": 14.91,
- "learning_rate": 0.00010599489795918367,
- "loss": 1.3267,
+ "epoch": 8.33,
+ "learning_rate": 9.53125e-05,
+ "loss": 0.6102,
"step": 737
},
{
- "epoch": 14.93,
- "learning_rate": 0.00010586734693877551,
- "loss": 1.2445,
+ "epoch": 8.34,
+ "learning_rate": 9.517045454545455e-05,
+ "loss": 0.5849,
"step": 738
},
{
- "epoch": 14.95,
- "learning_rate": 0.00010573979591836736,
- "loss": 1.3359,
+ "epoch": 8.35,
+ "learning_rate": 9.50284090909091e-05,
+ "loss": 0.6062,
"step": 739
},
{
- "epoch": 14.97,
- "learning_rate": 0.00010561224489795918,
- "loss": 1.2508,
+ "epoch": 8.36,
+ "learning_rate": 9.488636363636364e-05,
+ "loss": 0.6031,
"step": 740
},
{
- "epoch": 14.99,
- "learning_rate": 0.00010548469387755102,
- "loss": 1.2227,
+ "epoch": 8.37,
+ "learning_rate": 9.474431818181819e-05,
+ "loss": 0.5932,
"step": 741
},
{
- "epoch": 15.01,
- "learning_rate": 0.00010535714285714286,
- "loss": 1.1889,
+ "epoch": 8.38,
+ "learning_rate": 9.460227272727273e-05,
+ "loss": 0.589,
"step": 742
},
{
- "epoch": 15.03,
- "learning_rate": 0.00010522959183673471,
- "loss": 1.1919,
+ "epoch": 8.39,
+ "learning_rate": 9.446022727272728e-05,
+ "loss": 0.6096,
"step": 743
},
{
- "epoch": 15.05,
- "learning_rate": 0.00010510204081632653,
- "loss": 1.2383,
+ "epoch": 8.41,
+ "learning_rate": 9.431818181818182e-05,
+ "loss": 0.601,
"step": 744
},
{
- "epoch": 15.07,
- "learning_rate": 0.00010497448979591837,
- "loss": 1.2401,
+ "epoch": 8.42,
+ "learning_rate": 9.417613636363637e-05,
+ "loss": 0.5798,
"step": 745
},
{
- "epoch": 15.09,
- "learning_rate": 0.00010484693877551021,
- "loss": 1.2015,
+ "epoch": 8.43,
+ "learning_rate": 9.403409090909091e-05,
+ "loss": 0.59,
"step": 746
},
{
- "epoch": 15.11,
- "learning_rate": 0.00010471938775510203,
- "loss": 1.1509,
+ "epoch": 8.44,
+ "learning_rate": 9.389204545454546e-05,
+ "loss": 0.5988,
"step": 747
},
{
- "epoch": 15.13,
- "learning_rate": 0.00010459183673469388,
- "loss": 1.1878,
+ "epoch": 8.45,
+ "learning_rate": 9.375e-05,
+ "loss": 0.5591,
"step": 748
},
{
- "epoch": 15.16,
- "learning_rate": 0.00010446428571428572,
- "loss": 1.1706,
+ "epoch": 8.46,
+ "learning_rate": 9.360795454545455e-05,
+ "loss": 0.5939,
"step": 749
},
{
- "epoch": 15.18,
- "learning_rate": 0.00010433673469387755,
- "loss": 1.1285,
+ "epoch": 8.47,
+ "learning_rate": 9.346590909090909e-05,
+ "loss": 0.5886,
"step": 750
},
{
- "epoch": 15.2,
- "learning_rate": 0.0001042091836734694,
- "loss": 1.1608,
+ "epoch": 8.48,
+ "learning_rate": 9.332386363636364e-05,
+ "loss": 0.5994,
"step": 751
},
{
- "epoch": 15.22,
- "learning_rate": 0.00010408163265306123,
- "loss": 1.1178,
+ "epoch": 8.5,
+ "learning_rate": 9.318181818181818e-05,
+ "loss": 0.5821,
"step": 752
},
{
- "epoch": 15.24,
- "learning_rate": 0.00010395408163265306,
- "loss": 1.1293,
+ "epoch": 8.51,
+ "learning_rate": 9.303977272727273e-05,
+ "loss": 0.602,
"step": 753
},
{
- "epoch": 15.26,
- "learning_rate": 0.0001038265306122449,
- "loss": 1.2306,
+ "epoch": 8.52,
+ "learning_rate": 9.289772727272727e-05,
+ "loss": 0.5708,
"step": 754
},
{
- "epoch": 15.28,
- "learning_rate": 0.00010369897959183675,
- "loss": 1.1541,
+ "epoch": 8.53,
+ "learning_rate": 9.275568181818183e-05,
+ "loss": 0.5902,
"step": 755
},
{
- "epoch": 15.3,
- "learning_rate": 0.00010357142857142859,
- "loss": 1.1702,
+ "epoch": 8.54,
+ "learning_rate": 9.261363636363636e-05,
+ "loss": 0.6053,
"step": 756
},
{
- "epoch": 15.32,
- "learning_rate": 0.00010344387755102041,
- "loss": 1.2119,
+ "epoch": 8.55,
+ "learning_rate": 9.247159090909091e-05,
+ "loss": 0.5797,
"step": 757
},
{
- "epoch": 15.34,
- "learning_rate": 0.00010331632653061225,
- "loss": 1.2239,
+ "epoch": 8.56,
+ "learning_rate": 9.232954545454547e-05,
+ "loss": 0.5965,
"step": 758
},
{
- "epoch": 15.36,
- "learning_rate": 0.0001031887755102041,
- "loss": 1.2019,
+ "epoch": 8.57,
+ "learning_rate": 9.21875e-05,
+ "loss": 0.5738,
"step": 759
},
{
- "epoch": 15.38,
- "learning_rate": 0.00010306122448979591,
- "loss": 1.2197,
+ "epoch": 8.59,
+ "learning_rate": 9.204545454545454e-05,
+ "loss": 0.5819,
"step": 760
},
{
- "epoch": 15.4,
- "learning_rate": 0.00010293367346938776,
- "loss": 1.1769,
+ "epoch": 8.6,
+ "learning_rate": 9.19034090909091e-05,
+ "loss": 0.5994,
"step": 761
},
{
- "epoch": 15.42,
- "learning_rate": 0.0001028061224489796,
- "loss": 1.1907,
+ "epoch": 8.61,
+ "learning_rate": 9.176136363636363e-05,
+ "loss": 0.5738,
"step": 762
},
{
- "epoch": 15.44,
- "learning_rate": 0.00010267857142857142,
- "loss": 1.2089,
+ "epoch": 8.62,
+ "learning_rate": 9.161931818181818e-05,
+ "loss": 0.5663,
"step": 763
},
{
- "epoch": 15.46,
- "learning_rate": 0.00010255102040816327,
- "loss": 1.1335,
+ "epoch": 8.63,
+ "learning_rate": 9.147727272727274e-05,
+ "loss": 0.5798,
"step": 764
},
{
- "epoch": 15.48,
- "learning_rate": 0.00010242346938775511,
- "loss": 1.1633,
+ "epoch": 8.64,
+ "learning_rate": 9.133522727272727e-05,
+ "loss": 0.5705,
"step": 765
},
{
- "epoch": 15.5,
- "learning_rate": 0.00010229591836734695,
- "loss": 1.1578,
+ "epoch": 8.65,
+ "learning_rate": 9.119318181818183e-05,
+ "loss": 0.5943,
"step": 766
},
{
- "epoch": 15.52,
- "learning_rate": 0.00010216836734693877,
- "loss": 1.2236,
+ "epoch": 8.67,
+ "learning_rate": 9.105113636363637e-05,
+ "loss": 0.6019,
"step": 767
},
{
- "epoch": 15.54,
- "learning_rate": 0.00010204081632653062,
- "loss": 1.1941,
+ "epoch": 8.68,
+ "learning_rate": 9.090909090909092e-05,
+ "loss": 0.5733,
"step": 768
},
{
- "epoch": 15.56,
- "learning_rate": 0.00010191326530612246,
- "loss": 1.2666,
+ "epoch": 8.69,
+ "learning_rate": 9.076704545454546e-05,
+ "loss": 0.575,
"step": 769
},
{
- "epoch": 15.58,
- "learning_rate": 0.00010178571428571428,
- "loss": 1.1232,
+ "epoch": 8.7,
+ "learning_rate": 9.062500000000001e-05,
+ "loss": 0.5675,
"step": 770
},
{
- "epoch": 15.6,
- "learning_rate": 0.00010165816326530612,
- "loss": 1.2242,
+ "epoch": 8.71,
+ "learning_rate": 9.048295454545455e-05,
+ "loss": 0.566,
"step": 771
},
{
- "epoch": 15.62,
- "learning_rate": 0.00010153061224489797,
- "loss": 1.1852,
+ "epoch": 8.72,
+ "learning_rate": 9.03409090909091e-05,
+ "loss": 0.5513,
"step": 772
},
{
- "epoch": 15.64,
- "learning_rate": 0.0001014030612244898,
- "loss": 1.2626,
+ "epoch": 8.73,
+ "learning_rate": 9.019886363636364e-05,
+ "loss": 0.5682,
"step": 773
},
{
- "epoch": 15.66,
- "learning_rate": 0.00010127551020408164,
- "loss": 1.1873,
+ "epoch": 8.74,
+ "learning_rate": 9.005681818181819e-05,
+ "loss": 0.5508,
"step": 774
},
{
- "epoch": 15.68,
- "learning_rate": 0.00010114795918367349,
- "loss": 1.3005,
+ "epoch": 8.76,
+ "learning_rate": 8.991477272727273e-05,
+ "loss": 0.5668,
"step": 775
},
{
- "epoch": 15.7,
- "learning_rate": 0.0001010204081632653,
- "loss": 1.1904,
+ "epoch": 8.77,
+ "learning_rate": 8.977272727272728e-05,
+ "loss": 0.569,
"step": 776
},
{
- "epoch": 15.72,
- "learning_rate": 0.00010089285714285715,
- "loss": 1.2927,
+ "epoch": 8.78,
+ "learning_rate": 8.963068181818182e-05,
+ "loss": 0.5897,
"step": 777
},
{
- "epoch": 15.74,
- "learning_rate": 0.00010076530612244899,
- "loss": 1.179,
+ "epoch": 8.79,
+ "learning_rate": 8.948863636363637e-05,
+ "loss": 0.5738,
"step": 778
},
{
- "epoch": 15.76,
- "learning_rate": 0.00010063775510204084,
- "loss": 1.2027,
+ "epoch": 8.8,
+ "learning_rate": 8.934659090909091e-05,
+ "loss": 0.5511,
"step": 779
},
{
- "epoch": 15.78,
- "learning_rate": 0.00010051020408163265,
- "loss": 1.2428,
+ "epoch": 8.81,
+ "learning_rate": 8.920454545454546e-05,
+ "loss": 0.5659,
"step": 780
},
{
- "epoch": 15.8,
- "learning_rate": 0.0001003826530612245,
- "loss": 1.2324,
+ "epoch": 8.82,
+ "learning_rate": 8.90625e-05,
+ "loss": 0.5649,
"step": 781
},
{
- "epoch": 15.82,
- "learning_rate": 0.00010025510204081634,
- "loss": 1.1251,
+ "epoch": 8.83,
+ "learning_rate": 8.892045454545455e-05,
+ "loss": 0.5618,
"step": 782
},
{
- "epoch": 15.84,
- "learning_rate": 0.00010012755102040816,
- "loss": 1.2405,
+ "epoch": 8.85,
+ "learning_rate": 8.87784090909091e-05,
+ "loss": 0.5602,
"step": 783
},
{
- "epoch": 15.86,
- "learning_rate": 0.0001,
- "loss": 1.2005,
+ "epoch": 8.86,
+ "learning_rate": 8.863636363636364e-05,
+ "loss": 0.5723,
"step": 784
},
{
- "epoch": 15.88,
- "learning_rate": 9.987244897959184e-05,
- "loss": 1.2259,
+ "epoch": 8.87,
+ "learning_rate": 8.849431818181818e-05,
+ "loss": 0.5816,
"step": 785
},
{
- "epoch": 15.9,
- "learning_rate": 9.974489795918368e-05,
- "loss": 1.1576,
+ "epoch": 8.88,
+ "learning_rate": 8.835227272727273e-05,
+ "loss": 0.555,
"step": 786
},
{
- "epoch": 15.92,
- "learning_rate": 9.961734693877551e-05,
- "loss": 1.1834,
+ "epoch": 8.89,
+ "learning_rate": 8.821022727272727e-05,
+ "loss": 0.5563,
"step": 787
},
{
- "epoch": 15.94,
- "learning_rate": 9.948979591836736e-05,
- "loss": 1.2396,
+ "epoch": 8.9,
+ "learning_rate": 8.806818181818183e-05,
+ "loss": 0.554,
"step": 788
},
{
- "epoch": 15.96,
- "learning_rate": 9.936224489795919e-05,
- "loss": 1.1865,
+ "epoch": 8.91,
+ "learning_rate": 8.792613636363636e-05,
+ "loss": 0.5671,
"step": 789
},
{
- "epoch": 15.98,
- "learning_rate": 9.923469387755102e-05,
- "loss": 1.2356,
+ "epoch": 8.92,
+ "learning_rate": 8.778409090909091e-05,
+ "loss": 0.5485,
"step": 790
},
{
- "epoch": 16.01,
- "learning_rate": 9.910714285714286e-05,
- "loss": 1.2639,
+ "epoch": 8.94,
+ "learning_rate": 8.764204545454547e-05,
+ "loss": 0.5712,
"step": 791
},
{
- "epoch": 16.03,
- "learning_rate": 9.897959183673469e-05,
- "loss": 1.1216,
+ "epoch": 8.95,
+ "learning_rate": 8.75e-05,
+ "loss": 0.5507,
"step": 792
},
{
- "epoch": 16.05,
- "learning_rate": 9.885204081632652e-05,
- "loss": 1.1051,
+ "epoch": 8.96,
+ "learning_rate": 8.735795454545454e-05,
+ "loss": 0.5718,
"step": 793
},
{
- "epoch": 16.07,
- "learning_rate": 9.872448979591837e-05,
- "loss": 1.0864,
+ "epoch": 8.97,
+ "learning_rate": 8.72159090909091e-05,
+ "loss": 0.5585,
"step": 794
},
{
- "epoch": 16.09,
- "learning_rate": 9.859693877551021e-05,
- "loss": 1.182,
+ "epoch": 8.98,
+ "learning_rate": 8.707386363636363e-05,
+ "loss": 0.5563,
"step": 795
},
{
- "epoch": 16.11,
- "learning_rate": 9.846938775510204e-05,
- "loss": 1.1272,
+ "epoch": 8.99,
+ "learning_rate": 8.693181818181818e-05,
+ "loss": 0.581,
"step": 796
},
{
- "epoch": 16.13,
- "learning_rate": 9.834183673469389e-05,
- "loss": 1.1946,
+ "epoch": 9.0,
+ "learning_rate": 8.678977272727274e-05,
+ "loss": 0.5511,
"step": 797
},
{
- "epoch": 16.15,
- "learning_rate": 9.821428571428572e-05,
- "loss": 1.0875,
+ "epoch": 9.02,
+ "learning_rate": 8.664772727272727e-05,
+ "loss": 0.5103,
"step": 798
},
{
- "epoch": 16.17,
- "learning_rate": 9.808673469387756e-05,
- "loss": 1.1671,
+ "epoch": 9.03,
+ "learning_rate": 8.650568181818183e-05,
+ "loss": 0.5323,
"step": 799
},
{
- "epoch": 16.19,
- "learning_rate": 9.79591836734694e-05,
- "loss": 1.1502,
+ "epoch": 9.04,
+ "learning_rate": 8.636363636363637e-05,
+ "loss": 0.5092,
"step": 800
},
{
- "epoch": 16.21,
- "learning_rate": 9.783163265306124e-05,
- "loss": 1.19,
+ "epoch": 9.05,
+ "learning_rate": 8.62215909090909e-05,
+ "loss": 0.5247,
"step": 801
},
{
- "epoch": 16.23,
- "learning_rate": 9.770408163265307e-05,
- "loss": 1.1258,
+ "epoch": 9.06,
+ "learning_rate": 8.607954545454546e-05,
+ "loss": 0.5403,
"step": 802
},
{
- "epoch": 16.25,
- "learning_rate": 9.75765306122449e-05,
- "loss": 1.1765,
+ "epoch": 9.07,
+ "learning_rate": 8.593750000000001e-05,
+ "loss": 0.5252,
"step": 803
},
{
- "epoch": 16.27,
- "learning_rate": 9.744897959183674e-05,
- "loss": 1.1217,
+ "epoch": 9.08,
+ "learning_rate": 8.579545454545454e-05,
+ "loss": 0.5296,
"step": 804
},
{
- "epoch": 16.29,
- "learning_rate": 9.732142857142858e-05,
- "loss": 1.1293,
+ "epoch": 9.09,
+ "learning_rate": 8.56534090909091e-05,
+ "loss": 0.5223,
"step": 805
},
{
- "epoch": 16.31,
- "learning_rate": 9.719387755102042e-05,
- "loss": 1.17,
+ "epoch": 9.11,
+ "learning_rate": 8.551136363636364e-05,
+ "loss": 0.4972,
"step": 806
},
{
- "epoch": 16.33,
- "learning_rate": 9.706632653061225e-05,
- "loss": 1.17,
+ "epoch": 9.12,
+ "learning_rate": 8.536931818181818e-05,
+ "loss": 0.5005,
"step": 807
},
{
- "epoch": 16.35,
- "learning_rate": 9.693877551020408e-05,
- "loss": 1.2004,
+ "epoch": 9.13,
+ "learning_rate": 8.522727272727273e-05,
+ "loss": 0.5249,
"step": 808
},
{
- "epoch": 16.37,
- "learning_rate": 9.681122448979593e-05,
- "loss": 1.1648,
+ "epoch": 9.14,
+ "learning_rate": 8.508522727272728e-05,
+ "loss": 0.5135,
"step": 809
},
{
- "epoch": 16.39,
- "learning_rate": 9.668367346938776e-05,
- "loss": 1.0688,
+ "epoch": 9.15,
+ "learning_rate": 8.494318181818182e-05,
+ "loss": 0.5053,
"step": 810
},
{
- "epoch": 16.41,
- "learning_rate": 9.655612244897959e-05,
- "loss": 1.1607,
+ "epoch": 9.16,
+ "learning_rate": 8.480113636363637e-05,
+ "loss": 0.5158,
"step": 811
},
{
- "epoch": 16.43,
- "learning_rate": 9.642857142857143e-05,
- "loss": 1.1298,
+ "epoch": 9.17,
+ "learning_rate": 8.465909090909091e-05,
+ "loss": 0.5061,
"step": 812
},
{
- "epoch": 16.45,
- "learning_rate": 9.630102040816326e-05,
- "loss": 1.1064,
+ "epoch": 9.18,
+ "learning_rate": 8.451704545454546e-05,
+ "loss": 0.4988,
"step": 813
},
{
- "epoch": 16.47,
- "learning_rate": 9.617346938775511e-05,
- "loss": 1.1472,
+ "epoch": 9.2,
+ "learning_rate": 8.4375e-05,
+ "loss": 0.5273,
"step": 814
},
{
- "epoch": 16.49,
- "learning_rate": 9.604591836734694e-05,
- "loss": 1.1577,
+ "epoch": 9.21,
+ "learning_rate": 8.423295454545455e-05,
+ "loss": 0.5332,
"step": 815
},
{
- "epoch": 16.51,
- "learning_rate": 9.591836734693878e-05,
- "loss": 1.1436,
+ "epoch": 9.22,
+ "learning_rate": 8.40909090909091e-05,
+ "loss": 0.5181,
"step": 816
},
{
- "epoch": 16.53,
- "learning_rate": 9.579081632653061e-05,
- "loss": 1.1657,
+ "epoch": 9.23,
+ "learning_rate": 8.394886363636364e-05,
+ "loss": 0.5085,
"step": 817
},
{
- "epoch": 16.55,
- "learning_rate": 9.566326530612246e-05,
- "loss": 1.1147,
+ "epoch": 9.24,
+ "learning_rate": 8.380681818181818e-05,
+ "loss": 0.5137,
"step": 818
},
{
- "epoch": 16.57,
- "learning_rate": 9.553571428571429e-05,
- "loss": 1.1839,
+ "epoch": 9.25,
+ "learning_rate": 8.366477272727273e-05,
+ "loss": 0.5195,
"step": 819
},
{
- "epoch": 16.59,
- "learning_rate": 9.540816326530613e-05,
- "loss": 1.1298,
+ "epoch": 9.26,
+ "learning_rate": 8.352272727272727e-05,
+ "loss": 0.5077,
"step": 820
},
{
- "epoch": 16.61,
- "learning_rate": 9.528061224489796e-05,
- "loss": 1.2141,
+ "epoch": 9.28,
+ "learning_rate": 8.338068181818183e-05,
+ "loss": 0.5074,
"step": 821
},
{
- "epoch": 16.63,
- "learning_rate": 9.515306122448981e-05,
- "loss": 1.2045,
+ "epoch": 9.29,
+ "learning_rate": 8.323863636363637e-05,
+ "loss": 0.5142,
"step": 822
},
{
- "epoch": 16.65,
- "learning_rate": 9.502551020408164e-05,
- "loss": 1.1791,
+ "epoch": 9.3,
+ "learning_rate": 8.309659090909091e-05,
+ "loss": 0.5116,
"step": 823
},
{
- "epoch": 16.67,
- "learning_rate": 9.489795918367348e-05,
- "loss": 1.1137,
+ "epoch": 9.31,
+ "learning_rate": 8.295454545454547e-05,
+ "loss": 0.4974,
"step": 824
},
{
- "epoch": 16.69,
- "learning_rate": 9.477040816326531e-05,
- "loss": 1.1312,
+ "epoch": 9.32,
+ "learning_rate": 8.28125e-05,
+ "loss": 0.5117,
"step": 825
},
{
- "epoch": 16.71,
- "learning_rate": 9.464285714285715e-05,
- "loss": 1.1102,
+ "epoch": 9.33,
+ "learning_rate": 8.267045454545455e-05,
+ "loss": 0.5114,
"step": 826
},
{
- "epoch": 16.73,
- "learning_rate": 9.451530612244899e-05,
- "loss": 1.1865,
+ "epoch": 9.34,
+ "learning_rate": 8.25284090909091e-05,
+ "loss": 0.5039,
"step": 827
},
{
- "epoch": 16.75,
- "learning_rate": 9.438775510204082e-05,
- "loss": 1.1232,
+ "epoch": 9.35,
+ "learning_rate": 8.238636363636364e-05,
+ "loss": 0.498,
"step": 828
},
{
- "epoch": 16.77,
- "learning_rate": 9.426020408163265e-05,
- "loss": 1.2068,
+ "epoch": 9.37,
+ "learning_rate": 8.224431818181818e-05,
+ "loss": 0.5042,
"step": 829
},
{
- "epoch": 16.79,
- "learning_rate": 9.41326530612245e-05,
- "loss": 1.1864,
+ "epoch": 9.38,
+ "learning_rate": 8.210227272727274e-05,
+ "loss": 0.5049,
"step": 830
},
{
- "epoch": 16.81,
- "learning_rate": 9.400510204081633e-05,
- "loss": 1.2195,
+ "epoch": 9.39,
+ "learning_rate": 8.196022727272727e-05,
+ "loss": 0.5123,
"step": 831
},
{
- "epoch": 16.83,
- "learning_rate": 9.387755102040817e-05,
- "loss": 1.2063,
+ "epoch": 9.4,
+ "learning_rate": 8.181818181818183e-05,
+ "loss": 0.4907,
"step": 832
},
{
- "epoch": 16.85,
- "learning_rate": 9.375e-05,
- "loss": 1.1455,
+ "epoch": 9.41,
+ "learning_rate": 8.167613636363637e-05,
+ "loss": 0.5267,
"step": 833
},
{
- "epoch": 16.88,
- "learning_rate": 9.362244897959183e-05,
- "loss": 1.1819,
+ "epoch": 9.42,
+ "learning_rate": 8.15340909090909e-05,
+ "loss": 0.5314,
"step": 834
},
{
- "epoch": 16.9,
- "learning_rate": 9.349489795918368e-05,
- "loss": 1.1887,
+ "epoch": 9.43,
+ "learning_rate": 8.139204545454546e-05,
+ "loss": 0.4952,
"step": 835
},
{
- "epoch": 16.92,
- "learning_rate": 9.336734693877551e-05,
- "loss": 1.1557,
+ "epoch": 9.44,
+ "learning_rate": 8.125000000000001e-05,
+ "loss": 0.5014,
"step": 836
},
{
- "epoch": 16.94,
- "learning_rate": 9.323979591836735e-05,
- "loss": 1.2094,
+ "epoch": 9.46,
+ "learning_rate": 8.110795454545454e-05,
+ "loss": 0.4967,
"step": 837
},
{
- "epoch": 16.96,
- "learning_rate": 9.311224489795918e-05,
- "loss": 1.1512,
+ "epoch": 9.47,
+ "learning_rate": 8.09659090909091e-05,
+ "loss": 0.5116,
"step": 838
},
{
- "epoch": 16.98,
- "learning_rate": 9.298469387755103e-05,
- "loss": 1.1463,
+ "epoch": 9.48,
+ "learning_rate": 8.082386363636365e-05,
+ "loss": 0.5119,
"step": 839
},
{
- "epoch": 17.0,
- "learning_rate": 9.285714285714286e-05,
- "loss": 1.155,
+ "epoch": 9.49,
+ "learning_rate": 8.068181818181818e-05,
+ "loss": 0.4987,
"step": 840
},
{
- "epoch": 17.02,
- "learning_rate": 9.27295918367347e-05,
- "loss": 1.1292,
+ "epoch": 9.5,
+ "learning_rate": 8.053977272727274e-05,
+ "loss": 0.5063,
"step": 841
},
{
- "epoch": 17.04,
- "learning_rate": 9.260204081632653e-05,
- "loss": 1.0996,
+ "epoch": 9.51,
+ "learning_rate": 8.039772727272728e-05,
+ "loss": 0.5019,
"step": 842
},
{
- "epoch": 17.06,
- "learning_rate": 9.247448979591838e-05,
- "loss": 1.0662,
+ "epoch": 9.52,
+ "learning_rate": 8.025568181818183e-05,
+ "loss": 0.5272,
"step": 843
},
{
- "epoch": 17.08,
- "learning_rate": 9.234693877551021e-05,
- "loss": 1.0931,
+ "epoch": 9.54,
+ "learning_rate": 8.011363636363637e-05,
+ "loss": 0.4969,
"step": 844
},
{
- "epoch": 17.1,
- "learning_rate": 9.221938775510205e-05,
- "loss": 1.0727,
+ "epoch": 9.55,
+ "learning_rate": 7.997159090909092e-05,
+ "loss": 0.5222,
"step": 845
},
{
- "epoch": 17.12,
- "learning_rate": 9.209183673469388e-05,
- "loss": 1.1043,
+ "epoch": 9.56,
+ "learning_rate": 7.982954545454546e-05,
+ "loss": 0.4729,
"step": 846
},
{
- "epoch": 17.14,
- "learning_rate": 9.196428571428572e-05,
- "loss": 1.0594,
+ "epoch": 9.57,
+ "learning_rate": 7.96875e-05,
+ "loss": 0.4976,
"step": 847
},
{
- "epoch": 17.16,
- "learning_rate": 9.183673469387756e-05,
- "loss": 1.0952,
+ "epoch": 9.58,
+ "learning_rate": 7.954545454545455e-05,
+ "loss": 0.4974,
"step": 848
},
{
- "epoch": 17.18,
- "learning_rate": 9.170918367346939e-05,
- "loss": 1.0639,
+ "epoch": 9.59,
+ "learning_rate": 7.94034090909091e-05,
+ "loss": 0.4849,
"step": 849
},
{
- "epoch": 17.2,
- "learning_rate": 9.158163265306124e-05,
- "loss": 1.132,
+ "epoch": 9.6,
+ "learning_rate": 7.926136363636364e-05,
+ "loss": 0.4897,
"step": 850
},
{
- "epoch": 17.22,
- "learning_rate": 9.145408163265307e-05,
- "loss": 1.1083,
+ "epoch": 9.61,
+ "learning_rate": 7.911931818181819e-05,
+ "loss": 0.4962,
"step": 851
},
{
- "epoch": 17.24,
- "learning_rate": 9.13265306122449e-05,
- "loss": 1.1282,
+ "epoch": 9.63,
+ "learning_rate": 7.897727272727273e-05,
+ "loss": 0.4877,
"step": 852
},
{
- "epoch": 17.26,
- "learning_rate": 9.119897959183674e-05,
- "loss": 1.0474,
+ "epoch": 9.64,
+ "learning_rate": 7.883522727272728e-05,
+ "loss": 0.4921,
"step": 853
},
{
- "epoch": 17.28,
- "learning_rate": 9.107142857142857e-05,
- "loss": 1.1138,
+ "epoch": 9.65,
+ "learning_rate": 7.869318181818182e-05,
+ "loss": 0.4969,
"step": 854
},
{
- "epoch": 17.3,
- "learning_rate": 9.094387755102042e-05,
- "loss": 1.1025,
+ "epoch": 9.66,
+ "learning_rate": 7.855113636363637e-05,
+ "loss": 0.5045,
"step": 855
},
{
- "epoch": 17.32,
- "learning_rate": 9.081632653061225e-05,
- "loss": 1.0968,
+ "epoch": 9.67,
+ "learning_rate": 7.840909090909091e-05,
+ "loss": 0.5207,
"step": 856
},
{
- "epoch": 17.34,
- "learning_rate": 9.068877551020408e-05,
- "loss": 1.1683,
+ "epoch": 9.68,
+ "learning_rate": 7.826704545454546e-05,
+ "loss": 0.5098,
"step": 857
},
{
- "epoch": 17.36,
- "learning_rate": 9.056122448979592e-05,
- "loss": 1.0975,
+ "epoch": 9.69,
+ "learning_rate": 7.8125e-05,
+ "loss": 0.5005,
"step": 858
},
{
- "epoch": 17.38,
- "learning_rate": 9.043367346938775e-05,
- "loss": 1.1274,
+ "epoch": 9.7,
+ "learning_rate": 7.798295454545455e-05,
+ "loss": 0.5028,
"step": 859
},
{
- "epoch": 17.4,
- "learning_rate": 9.030612244897958e-05,
- "loss": 1.0916,
+ "epoch": 9.72,
+ "learning_rate": 7.784090909090909e-05,
+ "loss": 0.5067,
"step": 860
},
{
- "epoch": 17.42,
- "learning_rate": 9.017857142857143e-05,
- "loss": 1.0912,
+ "epoch": 9.73,
+ "learning_rate": 7.769886363636364e-05,
+ "loss": 0.484,
"step": 861
},
{
- "epoch": 17.44,
- "learning_rate": 9.005102040816327e-05,
- "loss": 1.0875,
+ "epoch": 9.74,
+ "learning_rate": 7.755681818181818e-05,
+ "loss": 0.5029,
"step": 862
},
{
- "epoch": 17.46,
- "learning_rate": 8.99234693877551e-05,
- "loss": 1.05,
+ "epoch": 9.75,
+ "learning_rate": 7.741477272727273e-05,
+ "loss": 0.5077,
"step": 863
},
{
- "epoch": 17.48,
- "learning_rate": 8.979591836734695e-05,
- "loss": 1.1418,
+ "epoch": 9.76,
+ "learning_rate": 7.727272727272727e-05,
+ "loss": 0.5091,
"step": 864
},
{
- "epoch": 17.5,
- "learning_rate": 8.966836734693878e-05,
- "loss": 1.0609,
+ "epoch": 9.77,
+ "learning_rate": 7.713068181818183e-05,
+ "loss": 0.4781,
"step": 865
},
{
- "epoch": 17.52,
- "learning_rate": 8.954081632653062e-05,
- "loss": 1.1611,
+ "epoch": 9.78,
+ "learning_rate": 7.698863636363636e-05,
+ "loss": 0.5124,
"step": 866
},
{
- "epoch": 17.54,
- "learning_rate": 8.941326530612245e-05,
- "loss": 1.1065,
+ "epoch": 9.79,
+ "learning_rate": 7.684659090909091e-05,
+ "loss": 0.4859,
"step": 867
},
{
- "epoch": 17.56,
- "learning_rate": 8.92857142857143e-05,
- "loss": 1.1611,
+ "epoch": 9.81,
+ "learning_rate": 7.670454545454547e-05,
+ "loss": 0.4872,
"step": 868
},
{
- "epoch": 17.58,
- "learning_rate": 8.915816326530613e-05,
- "loss": 1.1398,
+ "epoch": 9.82,
+ "learning_rate": 7.65625e-05,
+ "loss": 0.4675,
"step": 869
},
{
- "epoch": 17.6,
- "learning_rate": 8.903061224489796e-05,
- "loss": 1.1055,
+ "epoch": 9.83,
+ "learning_rate": 7.642045454545454e-05,
+ "loss": 0.5056,
"step": 870
},
{
- "epoch": 17.62,
- "learning_rate": 8.89030612244898e-05,
- "loss": 1.1314,
+ "epoch": 9.84,
+ "learning_rate": 7.62784090909091e-05,
+ "loss": 0.4868,
"step": 871
},
{
- "epoch": 17.64,
- "learning_rate": 8.877551020408164e-05,
- "loss": 1.1084,
+ "epoch": 9.85,
+ "learning_rate": 7.613636363636363e-05,
+ "loss": 0.4907,
"step": 872
},
{
- "epoch": 17.66,
- "learning_rate": 8.864795918367348e-05,
- "loss": 1.1254,
+ "epoch": 9.86,
+ "learning_rate": 7.599431818181818e-05,
+ "loss": 0.474,
"step": 873
},
{
- "epoch": 17.68,
- "learning_rate": 8.852040816326531e-05,
- "loss": 1.142,
+ "epoch": 9.87,
+ "learning_rate": 7.585227272727274e-05,
+ "loss": 0.4813,
"step": 874
},
{
- "epoch": 17.7,
- "learning_rate": 8.839285714285714e-05,
- "loss": 1.1371,
+ "epoch": 9.89,
+ "learning_rate": 7.571022727272727e-05,
+ "loss": 0.4838,
"step": 875
},
{
- "epoch": 17.72,
- "learning_rate": 8.826530612244899e-05,
- "loss": 1.1092,
+ "epoch": 9.9,
+ "learning_rate": 7.556818181818183e-05,
+ "loss": 0.4935,
"step": 876
},
{
- "epoch": 17.75,
- "learning_rate": 8.813775510204082e-05,
- "loss": 1.161,
+ "epoch": 9.91,
+ "learning_rate": 7.542613636363637e-05,
+ "loss": 0.4884,
"step": 877
},
{
- "epoch": 17.77,
- "learning_rate": 8.801020408163265e-05,
- "loss": 1.1044,
+ "epoch": 9.92,
+ "learning_rate": 7.52840909090909e-05,
+ "loss": 0.4797,
"step": 878
},
{
- "epoch": 17.79,
- "learning_rate": 8.788265306122449e-05,
- "loss": 1.117,
+ "epoch": 9.93,
+ "learning_rate": 7.514204545454546e-05,
+ "loss": 0.479,
"step": 879
},
{
- "epoch": 17.81,
- "learning_rate": 8.775510204081632e-05,
- "loss": 1.1262,
+ "epoch": 9.94,
+ "learning_rate": 7.500000000000001e-05,
+ "loss": 0.4727,
"step": 880
},
{
- "epoch": 17.83,
- "learning_rate": 8.762755102040817e-05,
- "loss": 1.0829,
+ "epoch": 9.95,
+ "learning_rate": 7.485795454545454e-05,
+ "loss": 0.4758,
"step": 881
},
{
- "epoch": 17.85,
- "learning_rate": 8.75e-05,
- "loss": 1.1393,
+ "epoch": 9.96,
+ "learning_rate": 7.47159090909091e-05,
+ "loss": 0.482,
"step": 882
},
{
- "epoch": 17.87,
- "learning_rate": 8.737244897959183e-05,
- "loss": 1.1781,
+ "epoch": 9.98,
+ "learning_rate": 7.457386363636364e-05,
+ "loss": 0.4951,
"step": 883
},
{
- "epoch": 17.89,
- "learning_rate": 8.724489795918367e-05,
- "loss": 1.1582,
+ "epoch": 9.99,
+ "learning_rate": 7.443181818181817e-05,
+ "loss": 0.4823,
"step": 884
},
{
- "epoch": 17.91,
- "learning_rate": 8.711734693877552e-05,
- "loss": 1.1469,
+ "epoch": 10.0,
+ "learning_rate": 7.428977272727273e-05,
+ "loss": 0.4638,
"step": 885
},
{
- "epoch": 17.93,
- "learning_rate": 8.698979591836735e-05,
- "loss": 1.1494,
+ "epoch": 10.01,
+ "learning_rate": 7.414772727272728e-05,
+ "loss": 0.4715,
"step": 886
},
{
- "epoch": 17.95,
- "learning_rate": 8.68622448979592e-05,
- "loss": 1.1251,
+ "epoch": 10.02,
+ "learning_rate": 7.400568181818182e-05,
+ "loss": 0.461,
"step": 887
},
{
- "epoch": 17.97,
- "learning_rate": 8.673469387755102e-05,
- "loss": 1.1624,
+ "epoch": 10.03,
+ "learning_rate": 7.386363636363637e-05,
+ "loss": 0.4429,
"step": 888
},
{
- "epoch": 17.99,
- "learning_rate": 8.660714285714287e-05,
- "loss": 1.0842,
+ "epoch": 10.04,
+ "learning_rate": 7.372159090909091e-05,
+ "loss": 0.4403,
"step": 889
},
{
- "epoch": 18.01,
- "learning_rate": 8.64795918367347e-05,
- "loss": 1.1944,
+ "epoch": 10.05,
+ "learning_rate": 7.357954545454546e-05,
+ "loss": 0.4519,
"step": 890
},
{
- "epoch": 18.03,
- "learning_rate": 8.635204081632653e-05,
- "loss": 1.0642,
+ "epoch": 10.07,
+ "learning_rate": 7.34375e-05,
+ "loss": 0.4611,
"step": 891
},
{
- "epoch": 18.05,
- "learning_rate": 8.622448979591838e-05,
- "loss": 1.0459,
+ "epoch": 10.08,
+ "learning_rate": 7.329545454545455e-05,
+ "loss": 0.4543,
"step": 892
},
{
- "epoch": 18.07,
- "learning_rate": 8.60969387755102e-05,
- "loss": 1.0941,
+ "epoch": 10.09,
+ "learning_rate": 7.315340909090909e-05,
+ "loss": 0.4528,
"step": 893
},
{
- "epoch": 18.09,
- "learning_rate": 8.596938775510205e-05,
- "loss": 1.0457,
+ "epoch": 10.1,
+ "learning_rate": 7.301136363636364e-05,
+ "loss": 0.4586,
"step": 894
},
{
- "epoch": 18.11,
- "learning_rate": 8.584183673469388e-05,
- "loss": 1.1033,
+ "epoch": 10.11,
+ "learning_rate": 7.286931818181818e-05,
+ "loss": 0.4418,
"step": 895
},
{
- "epoch": 18.13,
- "learning_rate": 8.571428571428571e-05,
- "loss": 1.0756,
+ "epoch": 10.12,
+ "learning_rate": 7.272727272727273e-05,
+ "loss": 0.4435,
"step": 896
},
{
- "epoch": 18.15,
- "learning_rate": 8.558673469387756e-05,
- "loss": 1.0615,
+ "epoch": 10.13,
+ "learning_rate": 7.258522727272727e-05,
+ "loss": 0.44,
"step": 897
},
{
- "epoch": 18.17,
- "learning_rate": 8.545918367346939e-05,
- "loss": 1.0828,
+ "epoch": 10.15,
+ "learning_rate": 7.244318181818183e-05,
+ "loss": 0.4589,
"step": 898
},
{
- "epoch": 18.19,
- "learning_rate": 8.533163265306123e-05,
- "loss": 1.1158,
+ "epoch": 10.16,
+ "learning_rate": 7.230113636363636e-05,
+ "loss": 0.4597,
"step": 899
},
{
- "epoch": 18.21,
- "learning_rate": 8.520408163265306e-05,
- "loss": 1.0133,
+ "epoch": 10.17,
+ "learning_rate": 7.215909090909091e-05,
+ "loss": 0.4479,
"step": 900
},
{
- "epoch": 18.23,
- "learning_rate": 8.50765306122449e-05,
- "loss": 1.0437,
+ "epoch": 10.18,
+ "learning_rate": 7.201704545454547e-05,
+ "loss": 0.4477,
"step": 901
},
{
- "epoch": 18.25,
- "learning_rate": 8.494897959183674e-05,
- "loss": 1.0372,
+ "epoch": 10.19,
+ "learning_rate": 7.1875e-05,
+ "loss": 0.446,
"step": 902
},
{
- "epoch": 18.27,
- "learning_rate": 8.482142857142857e-05,
- "loss": 1.1012,
+ "epoch": 10.2,
+ "learning_rate": 7.173295454545454e-05,
+ "loss": 0.4546,
"step": 903
},
{
- "epoch": 18.29,
- "learning_rate": 8.469387755102041e-05,
- "loss": 1.0777,
+ "epoch": 10.21,
+ "learning_rate": 7.15909090909091e-05,
+ "loss": 0.4347,
"step": 904
},
{
- "epoch": 18.31,
- "learning_rate": 8.456632653061224e-05,
- "loss": 1.0799,
+ "epoch": 10.22,
+ "learning_rate": 7.144886363636363e-05,
+ "loss": 0.452,
"step": 905
},
{
- "epoch": 18.33,
- "learning_rate": 8.443877551020409e-05,
- "loss": 0.9846,
+ "epoch": 10.24,
+ "learning_rate": 7.130681818181818e-05,
+ "loss": 0.4536,
"step": 906
},
{
- "epoch": 18.35,
- "learning_rate": 8.431122448979592e-05,
- "loss": 1.1,
+ "epoch": 10.25,
+ "learning_rate": 7.116477272727274e-05,
+ "loss": 0.4492,
"step": 907
},
{
- "epoch": 18.37,
- "learning_rate": 8.418367346938776e-05,
- "loss": 1.0787,
+ "epoch": 10.26,
+ "learning_rate": 7.102272727272727e-05,
+ "loss": 0.4401,
"step": 908
},
{
- "epoch": 18.39,
- "learning_rate": 8.40561224489796e-05,
- "loss": 1.0647,
+ "epoch": 10.27,
+ "learning_rate": 7.088068181818183e-05,
+ "loss": 0.4609,
"step": 909
},
{
- "epoch": 18.41,
- "learning_rate": 8.392857142857144e-05,
- "loss": 1.056,
+ "epoch": 10.28,
+ "learning_rate": 7.073863636363637e-05,
+ "loss": 0.4544,
"step": 910
},
{
- "epoch": 18.43,
- "learning_rate": 8.380102040816327e-05,
- "loss": 1.1131,
+ "epoch": 10.29,
+ "learning_rate": 7.05965909090909e-05,
+ "loss": 0.4477,
"step": 911
},
{
- "epoch": 18.45,
- "learning_rate": 8.367346938775511e-05,
- "loss": 1.0825,
+ "epoch": 10.3,
+ "learning_rate": 7.045454545454546e-05,
+ "loss": 0.4445,
"step": 912
},
{
- "epoch": 18.47,
- "learning_rate": 8.354591836734695e-05,
- "loss": 1.0681,
+ "epoch": 10.31,
+ "learning_rate": 7.031250000000001e-05,
+ "loss": 0.4544,
"step": 913
},
{
- "epoch": 18.49,
- "learning_rate": 8.341836734693878e-05,
- "loss": 1.0479,
+ "epoch": 10.33,
+ "learning_rate": 7.017045454545454e-05,
+ "loss": 0.4634,
"step": 914
},
{
- "epoch": 18.51,
- "learning_rate": 8.329081632653062e-05,
- "loss": 1.0921,
+ "epoch": 10.34,
+ "learning_rate": 7.00284090909091e-05,
+ "loss": 0.4499,
"step": 915
},
{
- "epoch": 18.53,
- "learning_rate": 8.316326530612245e-05,
- "loss": 1.0626,
+ "epoch": 10.35,
+ "learning_rate": 6.988636363636364e-05,
+ "loss": 0.4354,
"step": 916
},
{
- "epoch": 18.55,
- "learning_rate": 8.30357142857143e-05,
- "loss": 1.0518,
+ "epoch": 10.36,
+ "learning_rate": 6.974431818181818e-05,
+ "loss": 0.454,
"step": 917
},
{
- "epoch": 18.57,
- "learning_rate": 8.290816326530613e-05,
- "loss": 1.0557,
+ "epoch": 10.37,
+ "learning_rate": 6.960227272727273e-05,
+ "loss": 0.4473,
"step": 918
},
{
- "epoch": 18.6,
- "learning_rate": 8.278061224489796e-05,
- "loss": 1.0831,
+ "epoch": 10.38,
+ "learning_rate": 6.946022727272728e-05,
+ "loss": 0.4347,
"step": 919
},
{
- "epoch": 18.62,
- "learning_rate": 8.26530612244898e-05,
- "loss": 1.0307,
+ "epoch": 10.39,
+ "learning_rate": 6.931818181818182e-05,
+ "loss": 0.441,
"step": 920
},
{
- "epoch": 18.64,
- "learning_rate": 8.252551020408163e-05,
- "loss": 1.0455,
+ "epoch": 10.4,
+ "learning_rate": 6.917613636363637e-05,
+ "loss": 0.4545,
"step": 921
},
{
- "epoch": 18.66,
- "learning_rate": 8.239795918367348e-05,
- "loss": 1.0667,
+ "epoch": 10.42,
+ "learning_rate": 6.903409090909091e-05,
+ "loss": 0.458,
"step": 922
},
{
- "epoch": 18.68,
- "learning_rate": 8.227040816326531e-05,
- "loss": 1.0736,
+ "epoch": 10.43,
+ "learning_rate": 6.889204545454546e-05,
+ "loss": 0.4381,
"step": 923
},
{
- "epoch": 18.7,
- "learning_rate": 8.214285714285714e-05,
- "loss": 1.0108,
+ "epoch": 10.44,
+ "learning_rate": 6.875e-05,
+ "loss": 0.441,
"step": 924
},
{
- "epoch": 18.72,
- "learning_rate": 8.201530612244898e-05,
- "loss": 1.0458,
+ "epoch": 10.45,
+ "learning_rate": 6.860795454545455e-05,
+ "loss": 0.4446,
"step": 925
},
{
- "epoch": 18.74,
- "learning_rate": 8.188775510204081e-05,
- "loss": 1.0852,
+ "epoch": 10.46,
+ "learning_rate": 6.84659090909091e-05,
+ "loss": 0.4548,
"step": 926
},
{
- "epoch": 18.76,
- "learning_rate": 8.176020408163265e-05,
- "loss": 1.1207,
+ "epoch": 10.47,
+ "learning_rate": 6.832386363636364e-05,
+ "loss": 0.4404,
"step": 927
},
{
- "epoch": 18.78,
- "learning_rate": 8.163265306122449e-05,
- "loss": 1.0914,
+ "epoch": 10.48,
+ "learning_rate": 6.818181818181818e-05,
+ "loss": 0.4446,
"step": 928
},
{
- "epoch": 18.8,
- "learning_rate": 8.150510204081633e-05,
- "loss": 1.1108,
+ "epoch": 10.5,
+ "learning_rate": 6.803977272727273e-05,
+ "loss": 0.4434,
"step": 929
},
{
- "epoch": 18.82,
- "learning_rate": 8.137755102040817e-05,
- "loss": 1.1394,
+ "epoch": 10.51,
+ "learning_rate": 6.789772727272727e-05,
+ "loss": 0.4778,
"step": 930
},
{
- "epoch": 18.84,
- "learning_rate": 8.125000000000001e-05,
- "loss": 1.029,
+ "epoch": 10.52,
+ "learning_rate": 6.775568181818182e-05,
+ "loss": 0.4356,
"step": 931
},
{
- "epoch": 18.86,
- "learning_rate": 8.112244897959184e-05,
- "loss": 1.0661,
+ "epoch": 10.53,
+ "learning_rate": 6.761363636363636e-05,
+ "loss": 0.4464,
"step": 932
},
{
- "epoch": 18.88,
- "learning_rate": 8.099489795918369e-05,
- "loss": 1.0303,
+ "epoch": 10.54,
+ "learning_rate": 6.747159090909091e-05,
+ "loss": 0.4387,
"step": 933
},
{
- "epoch": 18.9,
- "learning_rate": 8.086734693877552e-05,
- "loss": 1.1144,
+ "epoch": 10.55,
+ "learning_rate": 6.732954545454547e-05,
+ "loss": 0.456,
"step": 934
},
{
- "epoch": 18.92,
- "learning_rate": 8.073979591836736e-05,
- "loss": 1.1096,
+ "epoch": 10.56,
+ "learning_rate": 6.71875e-05,
+ "loss": 0.453,
"step": 935
},
{
- "epoch": 18.94,
- "learning_rate": 8.061224489795919e-05,
- "loss": 1.123,
+ "epoch": 10.57,
+ "learning_rate": 6.704545454545455e-05,
+ "loss": 0.4611,
"step": 936
},
{
- "epoch": 18.96,
- "learning_rate": 8.048469387755102e-05,
- "loss": 1.1002,
+ "epoch": 10.59,
+ "learning_rate": 6.69034090909091e-05,
+ "loss": 0.4354,
"step": 937
},
{
- "epoch": 18.98,
- "learning_rate": 8.035714285714287e-05,
- "loss": 1.1016,
+ "epoch": 10.6,
+ "learning_rate": 6.676136363636364e-05,
+ "loss": 0.4519,
"step": 938
},
{
- "epoch": 19.0,
- "learning_rate": 8.02295918367347e-05,
- "loss": 1.0847,
+ "epoch": 10.61,
+ "learning_rate": 6.661931818181818e-05,
+ "loss": 0.4435,
"step": 939
},
{
- "epoch": 19.02,
- "learning_rate": 8.010204081632653e-05,
- "loss": 1.1029,
+ "epoch": 10.62,
+ "learning_rate": 6.647727272727274e-05,
+ "loss": 0.4422,
"step": 940
},
{
- "epoch": 19.04,
- "learning_rate": 7.997448979591837e-05,
- "loss": 1.041,
+ "epoch": 10.63,
+ "learning_rate": 6.633522727272727e-05,
+ "loss": 0.4344,
"step": 941
},
{
- "epoch": 19.06,
- "learning_rate": 7.98469387755102e-05,
- "loss": 1.01,
+ "epoch": 10.64,
+ "learning_rate": 6.619318181818183e-05,
+ "loss": 0.4419,
"step": 942
},
{
- "epoch": 19.08,
- "learning_rate": 7.971938775510205e-05,
- "loss": 1.0197,
+ "epoch": 10.65,
+ "learning_rate": 6.605113636363637e-05,
+ "loss": 0.4308,
"step": 943
},
{
- "epoch": 19.1,
- "learning_rate": 7.959183673469388e-05,
- "loss": 1.0543,
+ "epoch": 10.66,
+ "learning_rate": 6.59090909090909e-05,
+ "loss": 0.4043,
"step": 944
},
{
- "epoch": 19.12,
- "learning_rate": 7.946428571428571e-05,
- "loss": 1.0369,
+ "epoch": 10.68,
+ "learning_rate": 6.576704545454546e-05,
+ "loss": 0.4626,
"step": 945
},
{
- "epoch": 19.14,
- "learning_rate": 7.933673469387755e-05,
- "loss": 1.0154,
+ "epoch": 10.69,
+ "learning_rate": 6.562500000000001e-05,
+ "loss": 0.4365,
"step": 946
},
{
- "epoch": 19.16,
- "learning_rate": 7.920918367346939e-05,
- "loss": 0.9546,
+ "epoch": 10.7,
+ "learning_rate": 6.548295454545454e-05,
+ "loss": 0.4397,
"step": 947
},
{
- "epoch": 19.18,
- "learning_rate": 7.908163265306123e-05,
- "loss": 0.9982,
+ "epoch": 10.71,
+ "learning_rate": 6.53409090909091e-05,
+ "loss": 0.4463,
"step": 948
},
{
- "epoch": 19.2,
- "learning_rate": 7.895408163265306e-05,
- "loss": 1.0748,
+ "epoch": 10.72,
+ "learning_rate": 6.519886363636364e-05,
+ "loss": 0.4394,
"step": 949
},
{
- "epoch": 19.22,
- "learning_rate": 7.882653061224489e-05,
- "loss": 1.0562,
+ "epoch": 10.73,
+ "learning_rate": 6.505681818181818e-05,
+ "loss": 0.45,
"step": 950
},
{
- "epoch": 19.24,
- "learning_rate": 7.869897959183674e-05,
- "loss": 1.0352,
+ "epoch": 10.74,
+ "learning_rate": 6.491477272727273e-05,
+ "loss": 0.4363,
"step": 951
},
{
- "epoch": 19.26,
- "learning_rate": 7.857142857142858e-05,
- "loss": 0.9976,
+ "epoch": 10.76,
+ "learning_rate": 6.477272727272728e-05,
+ "loss": 0.4566,
"step": 952
},
{
- "epoch": 19.28,
- "learning_rate": 7.844387755102041e-05,
- "loss": 1.0221,
+ "epoch": 10.77,
+ "learning_rate": 6.463068181818183e-05,
+ "loss": 0.4235,
"step": 953
},
{
- "epoch": 19.3,
- "learning_rate": 7.831632653061226e-05,
- "loss": 1.0119,
+ "epoch": 10.78,
+ "learning_rate": 6.448863636363637e-05,
+ "loss": 0.4458,
"step": 954
},
{
- "epoch": 19.32,
- "learning_rate": 7.818877551020409e-05,
- "loss": 1.0657,
+ "epoch": 10.79,
+ "learning_rate": 6.434659090909092e-05,
+ "loss": 0.423,
"step": 955
},
{
- "epoch": 19.34,
- "learning_rate": 7.806122448979593e-05,
- "loss": 0.9591,
+ "epoch": 10.8,
+ "learning_rate": 6.420454545454546e-05,
+ "loss": 0.445,
"step": 956
},
{
- "epoch": 19.36,
- "learning_rate": 7.793367346938776e-05,
- "loss": 1.0101,
+ "epoch": 10.81,
+ "learning_rate": 6.40625e-05,
+ "loss": 0.424,
"step": 957
},
{
- "epoch": 19.38,
- "learning_rate": 7.780612244897959e-05,
- "loss": 1.0453,
+ "epoch": 10.82,
+ "learning_rate": 6.392045454545455e-05,
+ "loss": 0.4224,
"step": 958
},
{
- "epoch": 19.4,
- "learning_rate": 7.767857142857144e-05,
- "loss": 1.0461,
+ "epoch": 10.83,
+ "learning_rate": 6.37784090909091e-05,
+ "loss": 0.4223,
"step": 959
},
{
- "epoch": 19.42,
- "learning_rate": 7.755102040816327e-05,
- "loss": 1.0959,
+ "epoch": 10.85,
+ "learning_rate": 6.363636363636364e-05,
+ "loss": 0.4314,
"step": 960
},
{
- "epoch": 19.44,
- "learning_rate": 7.742346938775511e-05,
- "loss": 1.0608,
+ "epoch": 10.86,
+ "learning_rate": 6.349431818181819e-05,
+ "loss": 0.4488,
"step": 961
},
{
- "epoch": 19.47,
- "learning_rate": 7.729591836734694e-05,
- "loss": 1.1177,
+ "epoch": 10.87,
+ "learning_rate": 6.335227272727273e-05,
+ "loss": 0.423,
"step": 962
},
{
- "epoch": 19.49,
- "learning_rate": 7.716836734693877e-05,
- "loss": 1.0354,
+ "epoch": 10.88,
+ "learning_rate": 6.321022727272728e-05,
+ "loss": 0.4416,
"step": 963
},
{
- "epoch": 19.51,
- "learning_rate": 7.704081632653062e-05,
- "loss": 1.0507,
+ "epoch": 10.89,
+ "learning_rate": 6.306818181818182e-05,
+ "loss": 0.423,
"step": 964
},
{
- "epoch": 19.53,
- "learning_rate": 7.691326530612245e-05,
- "loss": 1.0313,
+ "epoch": 10.9,
+ "learning_rate": 6.292613636363637e-05,
+ "loss": 0.4502,
"step": 965
},
{
- "epoch": 19.55,
- "learning_rate": 7.67857142857143e-05,
- "loss": 1.0569,
+ "epoch": 10.91,
+ "learning_rate": 6.278409090909091e-05,
+ "loss": 0.4266,
"step": 966
},
{
- "epoch": 19.57,
- "learning_rate": 7.665816326530612e-05,
- "loss": 1.0862,
+ "epoch": 10.92,
+ "learning_rate": 6.264204545454546e-05,
+ "loss": 0.4344,
"step": 967
},
{
- "epoch": 19.59,
- "learning_rate": 7.653061224489796e-05,
- "loss": 1.0593,
+ "epoch": 10.94,
+ "learning_rate": 6.25e-05,
+ "loss": 0.434,
"step": 968
},
{
- "epoch": 19.61,
- "learning_rate": 7.64030612244898e-05,
- "loss": 1.0602,
+ "epoch": 10.95,
+ "learning_rate": 6.235795454545455e-05,
+ "loss": 0.4269,
"step": 969
},
{
- "epoch": 19.63,
- "learning_rate": 7.627551020408163e-05,
- "loss": 1.0048,
+ "epoch": 10.96,
+ "learning_rate": 6.221590909090909e-05,
+ "loss": 0.4158,
"step": 970
},
{
- "epoch": 19.65,
- "learning_rate": 7.614795918367347e-05,
- "loss": 1.0346,
+ "epoch": 10.97,
+ "learning_rate": 6.207386363636364e-05,
+ "loss": 0.4231,
"step": 971
},
{
- "epoch": 19.67,
- "learning_rate": 7.60204081632653e-05,
- "loss": 1.0172,
+ "epoch": 10.98,
+ "learning_rate": 6.193181818181818e-05,
+ "loss": 0.4235,
"step": 972
},
{
- "epoch": 19.69,
- "learning_rate": 7.589285714285714e-05,
- "loss": 1.02,
+ "epoch": 10.99,
+ "learning_rate": 6.178977272727273e-05,
+ "loss": 0.4504,
"step": 973
},
{
- "epoch": 19.71,
- "learning_rate": 7.576530612244898e-05,
- "loss": 1.0028,
+ "epoch": 11.0,
+ "learning_rate": 6.164772727272727e-05,
+ "loss": 0.4394,
"step": 974
},
{
- "epoch": 19.73,
- "learning_rate": 7.563775510204083e-05,
- "loss": 1.08,
+ "epoch": 11.02,
+ "learning_rate": 6.150568181818183e-05,
+ "loss": 0.4333,
"step": 975
},
{
- "epoch": 19.75,
- "learning_rate": 7.551020408163266e-05,
- "loss": 1.0402,
+ "epoch": 11.03,
+ "learning_rate": 6.136363636363636e-05,
+ "loss": 0.3936,
"step": 976
},
{
- "epoch": 19.77,
- "learning_rate": 7.53826530612245e-05,
- "loss": 1.0567,
+ "epoch": 11.04,
+ "learning_rate": 6.122159090909091e-05,
+ "loss": 0.3933,
"step": 977
},
{
- "epoch": 19.79,
- "learning_rate": 7.525510204081633e-05,
- "loss": 1.0169,
+ "epoch": 11.05,
+ "learning_rate": 6.107954545454547e-05,
+ "loss": 0.4161,
"step": 978
},
{
- "epoch": 19.81,
- "learning_rate": 7.512755102040818e-05,
- "loss": 0.9881,
+ "epoch": 11.06,
+ "learning_rate": 6.0937500000000004e-05,
+ "loss": 0.4097,
"step": 979
},
{
- "epoch": 19.83,
- "learning_rate": 7.500000000000001e-05,
- "loss": 1.0677,
+ "epoch": 11.07,
+ "learning_rate": 6.079545454545454e-05,
+ "loss": 0.412,
"step": 980
},
{
- "epoch": 19.85,
- "learning_rate": 7.487244897959184e-05,
- "loss": 1.1026,
+ "epoch": 11.08,
+ "learning_rate": 6.0653409090909094e-05,
+ "loss": 0.4104,
"step": 981
},
{
- "epoch": 19.87,
- "learning_rate": 7.474489795918368e-05,
- "loss": 1.0101,
+ "epoch": 11.09,
+ "learning_rate": 6.051136363636364e-05,
+ "loss": 0.4152,
"step": 982
},
{
- "epoch": 19.89,
- "learning_rate": 7.461734693877551e-05,
- "loss": 1.069,
+ "epoch": 11.11,
+ "learning_rate": 6.036931818181818e-05,
+ "loss": 0.4037,
"step": 983
},
{
- "epoch": 19.91,
- "learning_rate": 7.448979591836736e-05,
- "loss": 1.0493,
+ "epoch": 11.12,
+ "learning_rate": 6.022727272727273e-05,
+ "loss": 0.413,
"step": 984
},
{
- "epoch": 19.93,
- "learning_rate": 7.436224489795919e-05,
- "loss": 1.0858,
+ "epoch": 11.13,
+ "learning_rate": 6.0085227272727274e-05,
+ "loss": 0.4413,
"step": 985
},
{
- "epoch": 19.95,
- "learning_rate": 7.423469387755102e-05,
- "loss": 1.0734,
+ "epoch": 11.14,
+ "learning_rate": 5.9943181818181826e-05,
+ "loss": 0.3908,
"step": 986
},
{
- "epoch": 19.97,
- "learning_rate": 7.410714285714286e-05,
- "loss": 1.0203,
+ "epoch": 11.15,
+ "learning_rate": 5.9801136363636365e-05,
+ "loss": 0.3982,
"step": 987
},
{
- "epoch": 19.99,
- "learning_rate": 7.39795918367347e-05,
- "loss": 1.0285,
+ "epoch": 11.16,
+ "learning_rate": 5.965909090909091e-05,
+ "loss": 0.4109,
"step": 988
},
{
- "epoch": 20.01,
- "learning_rate": 7.385204081632653e-05,
- "loss": 0.9446,
+ "epoch": 11.17,
+ "learning_rate": 5.951704545454546e-05,
+ "loss": 0.3923,
"step": 989
},
{
- "epoch": 20.03,
- "learning_rate": 7.372448979591837e-05,
- "loss": 0.9915,
+ "epoch": 11.18,
+ "learning_rate": 5.9375e-05,
+ "loss": 0.4107,
"step": 990
},
{
- "epoch": 20.05,
- "learning_rate": 7.35969387755102e-05,
- "loss": 0.9882,
+ "epoch": 11.2,
+ "learning_rate": 5.9232954545454545e-05,
+ "loss": 0.4099,
"step": 991
},
{
- "epoch": 20.07,
- "learning_rate": 7.346938775510205e-05,
- "loss": 0.9338,
+ "epoch": 11.21,
+ "learning_rate": 5.90909090909091e-05,
+ "loss": 0.4163,
"step": 992
},
{
- "epoch": 20.09,
- "learning_rate": 7.334183673469388e-05,
- "loss": 0.942,
+ "epoch": 11.22,
+ "learning_rate": 5.8948863636363635e-05,
+ "loss": 0.4189,
"step": 993
},
{
- "epoch": 20.11,
- "learning_rate": 7.321428571428571e-05,
- "loss": 0.9725,
+ "epoch": 11.23,
+ "learning_rate": 5.880681818181818e-05,
+ "loss": 0.3889,
"step": 994
},
{
- "epoch": 20.13,
- "learning_rate": 7.308673469387755e-05,
- "loss": 1.027,
+ "epoch": 11.24,
+ "learning_rate": 5.866477272727273e-05,
+ "loss": 0.3988,
"step": 995
},
{
- "epoch": 20.15,
- "learning_rate": 7.29591836734694e-05,
- "loss": 1.0081,
+ "epoch": 11.25,
+ "learning_rate": 5.852272727272727e-05,
+ "loss": 0.4215,
"step": 996
},
{
- "epoch": 20.17,
- "learning_rate": 7.283163265306123e-05,
- "loss": 1.0117,
+ "epoch": 11.26,
+ "learning_rate": 5.838068181818183e-05,
+ "loss": 0.4207,
"step": 997
},
{
- "epoch": 20.19,
- "learning_rate": 7.270408163265307e-05,
- "loss": 0.969,
+ "epoch": 11.27,
+ "learning_rate": 5.823863636363637e-05,
+ "loss": 0.413,
"step": 998
},
{
- "epoch": 20.21,
- "learning_rate": 7.25765306122449e-05,
- "loss": 1.0024,
+ "epoch": 11.29,
+ "learning_rate": 5.8096590909090906e-05,
+ "loss": 0.4057,
"step": 999
},
{
- "epoch": 20.23,
- "learning_rate": 7.244897959183675e-05,
- "loss": 0.994,
+ "epoch": 11.3,
+ "learning_rate": 5.7954545454545464e-05,
+ "loss": 0.3939,
"step": 1000
},
{
- "epoch": 20.25,
- "learning_rate": 7.232142857142858e-05,
- "loss": 1.0248,
+ "epoch": 11.31,
+ "learning_rate": 5.78125e-05,
+ "loss": 0.4199,
"step": 1001
},
{
- "epoch": 20.27,
- "learning_rate": 7.219387755102042e-05,
- "loss": 1.0493,
+ "epoch": 11.32,
+ "learning_rate": 5.767045454545454e-05,
+ "loss": 0.4076,
"step": 1002
},
{
- "epoch": 20.29,
- "learning_rate": 7.206632653061225e-05,
- "loss": 1.0011,
+ "epoch": 11.33,
+ "learning_rate": 5.75284090909091e-05,
+ "loss": 0.4079,
"step": 1003
},
{
- "epoch": 20.31,
- "learning_rate": 7.193877551020408e-05,
- "loss": 0.9874,
+ "epoch": 11.34,
+ "learning_rate": 5.738636363636364e-05,
+ "loss": 0.4002,
"step": 1004
},
{
- "epoch": 20.34,
- "learning_rate": 7.181122448979593e-05,
- "loss": 1.0049,
+ "epoch": 11.35,
+ "learning_rate": 5.724431818181818e-05,
+ "loss": 0.3801,
"step": 1005
},
{
- "epoch": 20.36,
- "learning_rate": 7.168367346938776e-05,
- "loss": 1.0314,
+ "epoch": 11.37,
+ "learning_rate": 5.7102272727272735e-05,
+ "loss": 0.3939,
"step": 1006
},
{
- "epoch": 20.38,
- "learning_rate": 7.155612244897959e-05,
- "loss": 0.9742,
+ "epoch": 11.38,
+ "learning_rate": 5.696022727272727e-05,
+ "loss": 0.3904,
"step": 1007
},
{
- "epoch": 20.4,
- "learning_rate": 7.142857142857143e-05,
- "loss": 1.0621,
+ "epoch": 11.39,
+ "learning_rate": 5.6818181818181825e-05,
+ "loss": 0.406,
"step": 1008
},
{
- "epoch": 20.42,
- "learning_rate": 7.130102040816326e-05,
- "loss": 0.9672,
+ "epoch": 11.4,
+ "learning_rate": 5.667613636363637e-05,
+ "loss": 0.4185,
"step": 1009
},
{
- "epoch": 20.44,
- "learning_rate": 7.117346938775511e-05,
- "loss": 1.0018,
+ "epoch": 11.41,
+ "learning_rate": 5.653409090909091e-05,
+ "loss": 0.3976,
"step": 1010
},
{
- "epoch": 20.46,
- "learning_rate": 7.104591836734694e-05,
- "loss": 1.0045,
+ "epoch": 11.42,
+ "learning_rate": 5.639204545454546e-05,
+ "loss": 0.3907,
"step": 1011
},
{
- "epoch": 20.48,
- "learning_rate": 7.091836734693877e-05,
- "loss": 0.9675,
+ "epoch": 11.43,
+ "learning_rate": 5.6250000000000005e-05,
+ "loss": 0.4065,
"step": 1012
},
{
- "epoch": 20.5,
- "learning_rate": 7.079081632653062e-05,
- "loss": 0.976,
+ "epoch": 11.44,
+ "learning_rate": 5.6107954545454544e-05,
+ "loss": 0.4069,
"step": 1013
},
{
- "epoch": 20.52,
- "learning_rate": 7.066326530612245e-05,
- "loss": 1.0523,
+ "epoch": 11.46,
+ "learning_rate": 5.5965909090909095e-05,
+ "loss": 0.3964,
"step": 1014
},
{
- "epoch": 20.54,
- "learning_rate": 7.053571428571429e-05,
- "loss": 1.052,
+ "epoch": 11.47,
+ "learning_rate": 5.582386363636364e-05,
+ "loss": 0.3912,
"step": 1015
},
{
- "epoch": 20.56,
- "learning_rate": 7.040816326530612e-05,
- "loss": 0.9903,
+ "epoch": 11.48,
+ "learning_rate": 5.568181818181818e-05,
+ "loss": 0.3944,
"step": 1016
},
{
- "epoch": 20.58,
- "learning_rate": 7.028061224489795e-05,
- "loss": 1.0337,
+ "epoch": 11.49,
+ "learning_rate": 5.553977272727273e-05,
+ "loss": 0.4197,
"step": 1017
},
{
- "epoch": 20.6,
- "learning_rate": 7.01530612244898e-05,
- "loss": 1.1122,
+ "epoch": 11.5,
+ "learning_rate": 5.5397727272727276e-05,
+ "loss": 0.4064,
"step": 1018
},
{
- "epoch": 20.62,
- "learning_rate": 7.002551020408164e-05,
- "loss": 1.0133,
+ "epoch": 11.51,
+ "learning_rate": 5.525568181818183e-05,
+ "loss": 0.4054,
"step": 1019
},
{
- "epoch": 20.64,
- "learning_rate": 6.989795918367347e-05,
- "loss": 0.9588,
+ "epoch": 11.52,
+ "learning_rate": 5.5113636363636366e-05,
+ "loss": 0.4128,
"step": 1020
},
{
- "epoch": 20.66,
- "learning_rate": 6.977040816326532e-05,
- "loss": 0.9892,
+ "epoch": 11.53,
+ "learning_rate": 5.497159090909091e-05,
+ "loss": 0.3976,
"step": 1021
},
{
- "epoch": 20.68,
- "learning_rate": 6.964285714285715e-05,
- "loss": 1.025,
+ "epoch": 11.55,
+ "learning_rate": 5.482954545454546e-05,
+ "loss": 0.3863,
"step": 1022
},
{
- "epoch": 20.7,
- "learning_rate": 6.951530612244899e-05,
- "loss": 1.0196,
+ "epoch": 11.56,
+ "learning_rate": 5.46875e-05,
+ "loss": 0.3994,
"step": 1023
},
{
- "epoch": 20.72,
- "learning_rate": 6.938775510204082e-05,
- "loss": 1.0146,
+ "epoch": 11.57,
+ "learning_rate": 5.4545454545454546e-05,
+ "loss": 0.401,
"step": 1024
},
{
- "epoch": 20.74,
- "learning_rate": 6.926020408163265e-05,
- "loss": 1.0656,
+ "epoch": 11.58,
+ "learning_rate": 5.44034090909091e-05,
+ "loss": 0.3948,
"step": 1025
},
{
- "epoch": 20.76,
- "learning_rate": 6.91326530612245e-05,
- "loss": 0.9584,
+ "epoch": 11.59,
+ "learning_rate": 5.4261363636363636e-05,
+ "loss": 0.3967,
"step": 1026
},
{
- "epoch": 20.78,
- "learning_rate": 6.900510204081633e-05,
- "loss": 0.9877,
+ "epoch": 11.6,
+ "learning_rate": 5.411931818181818e-05,
+ "loss": 0.413,
"step": 1027
},
{
- "epoch": 20.8,
- "learning_rate": 6.887755102040817e-05,
- "loss": 1.0607,
+ "epoch": 11.61,
+ "learning_rate": 5.397727272727273e-05,
+ "loss": 0.4032,
"step": 1028
},
{
- "epoch": 20.82,
- "learning_rate": 6.875e-05,
- "loss": 0.9969,
+ "epoch": 11.63,
+ "learning_rate": 5.383522727272727e-05,
+ "loss": 0.3905,
"step": 1029
},
{
- "epoch": 20.84,
- "learning_rate": 6.862244897959184e-05,
- "loss": 0.9506,
+ "epoch": 11.64,
+ "learning_rate": 5.3693181818181823e-05,
+ "loss": 0.4041,
"step": 1030
},
{
- "epoch": 20.86,
- "learning_rate": 6.849489795918368e-05,
- "loss": 1.0576,
+ "epoch": 11.65,
+ "learning_rate": 5.355113636363637e-05,
+ "loss": 0.392,
"step": 1031
},
{
- "epoch": 20.88,
- "learning_rate": 6.836734693877551e-05,
- "loss": 1.0094,
+ "epoch": 11.66,
+ "learning_rate": 5.340909090909091e-05,
+ "loss": 0.3942,
"step": 1032
},
{
- "epoch": 20.9,
- "learning_rate": 6.823979591836735e-05,
- "loss": 0.9872,
+ "epoch": 11.67,
+ "learning_rate": 5.326704545454546e-05,
+ "loss": 0.3946,
"step": 1033
},
{
- "epoch": 20.92,
- "learning_rate": 6.811224489795919e-05,
- "loss": 1.0544,
+ "epoch": 11.68,
+ "learning_rate": 5.3125000000000004e-05,
+ "loss": 0.3989,
"step": 1034
},
{
- "epoch": 20.94,
- "learning_rate": 6.798469387755102e-05,
- "loss": 1.0194,
+ "epoch": 11.69,
+ "learning_rate": 5.298295454545454e-05,
+ "loss": 0.4101,
"step": 1035
},
{
- "epoch": 20.96,
- "learning_rate": 6.785714285714286e-05,
- "loss": 1.0009,
+ "epoch": 11.7,
+ "learning_rate": 5.2840909090909094e-05,
+ "loss": 0.4033,
"step": 1036
},
{
- "epoch": 20.98,
- "learning_rate": 6.772959183673469e-05,
- "loss": 0.9727,
+ "epoch": 11.72,
+ "learning_rate": 5.269886363636364e-05,
+ "loss": 0.3937,
"step": 1037
},
{
- "epoch": 21.0,
- "learning_rate": 6.760204081632652e-05,
- "loss": 0.9754,
+ "epoch": 11.73,
+ "learning_rate": 5.255681818181818e-05,
+ "loss": 0.3873,
"step": 1038
},
{
- "epoch": 21.02,
- "learning_rate": 6.747448979591837e-05,
- "loss": 0.9953,
+ "epoch": 11.74,
+ "learning_rate": 5.241477272727273e-05,
+ "loss": 0.3922,
"step": 1039
},
{
- "epoch": 21.04,
- "learning_rate": 6.73469387755102e-05,
- "loss": 0.9307,
+ "epoch": 11.75,
+ "learning_rate": 5.2272727272727274e-05,
+ "loss": 0.4016,
"step": 1040
},
{
- "epoch": 21.06,
- "learning_rate": 6.721938775510204e-05,
- "loss": 0.9151,
+ "epoch": 11.76,
+ "learning_rate": 5.2130681818181826e-05,
+ "loss": 0.3892,
"step": 1041
},
{
- "epoch": 21.08,
- "learning_rate": 6.709183673469389e-05,
- "loss": 0.9474,
+ "epoch": 11.77,
+ "learning_rate": 5.1988636363636364e-05,
+ "loss": 0.3974,
"step": 1042
},
{
- "epoch": 21.1,
- "learning_rate": 6.696428571428572e-05,
- "loss": 0.9697,
+ "epoch": 11.78,
+ "learning_rate": 5.184659090909091e-05,
+ "loss": 0.4024,
"step": 1043
},
{
- "epoch": 21.12,
- "learning_rate": 6.683673469387756e-05,
- "loss": 0.9423,
+ "epoch": 11.79,
+ "learning_rate": 5.170454545454546e-05,
+ "loss": 0.3889,
"step": 1044
},
{
- "epoch": 21.14,
- "learning_rate": 6.670918367346939e-05,
- "loss": 0.9797,
+ "epoch": 11.81,
+ "learning_rate": 5.15625e-05,
+ "loss": 0.4097,
"step": 1045
},
{
- "epoch": 21.16,
- "learning_rate": 6.658163265306124e-05,
- "loss": 0.919,
+ "epoch": 11.82,
+ "learning_rate": 5.1420454545454545e-05,
+ "loss": 0.4047,
"step": 1046
},
{
- "epoch": 21.18,
- "learning_rate": 6.645408163265307e-05,
- "loss": 0.9743,
+ "epoch": 11.83,
+ "learning_rate": 5.12784090909091e-05,
+ "loss": 0.4033,
"step": 1047
},
{
- "epoch": 21.21,
- "learning_rate": 6.63265306122449e-05,
- "loss": 0.9575,
+ "epoch": 11.84,
+ "learning_rate": 5.1136363636363635e-05,
+ "loss": 0.3774,
"step": 1048
},
{
- "epoch": 21.23,
- "learning_rate": 6.619897959183674e-05,
- "loss": 0.9861,
+ "epoch": 11.85,
+ "learning_rate": 5.099431818181818e-05,
+ "loss": 0.405,
"step": 1049
},
{
- "epoch": 21.25,
- "learning_rate": 6.607142857142857e-05,
- "loss": 0.9103,
+ "epoch": 11.86,
+ "learning_rate": 5.085227272727273e-05,
+ "loss": 0.3996,
"step": 1050
},
{
- "epoch": 21.27,
- "learning_rate": 6.594387755102042e-05,
- "loss": 0.993,
+ "epoch": 11.87,
+ "learning_rate": 5.071022727272727e-05,
+ "loss": 0.3885,
"step": 1051
},
{
- "epoch": 21.29,
- "learning_rate": 6.581632653061225e-05,
- "loss": 0.9668,
+ "epoch": 11.88,
+ "learning_rate": 5.056818181818183e-05,
+ "loss": 0.3914,
"step": 1052
},
{
- "epoch": 21.31,
- "learning_rate": 6.568877551020408e-05,
- "loss": 1.0008,
+ "epoch": 11.9,
+ "learning_rate": 5.042613636363637e-05,
+ "loss": 0.3908,
"step": 1053
},
{
- "epoch": 21.33,
- "learning_rate": 6.556122448979592e-05,
- "loss": 0.9825,
+ "epoch": 11.91,
+ "learning_rate": 5.0284090909090905e-05,
+ "loss": 0.3921,
"step": 1054
},
{
- "epoch": 21.35,
- "learning_rate": 6.543367346938776e-05,
- "loss": 1.0174,
+ "epoch": 11.92,
+ "learning_rate": 5.0142045454545464e-05,
+ "loss": 0.4077,
"step": 1055
},
{
- "epoch": 21.37,
- "learning_rate": 6.530612244897959e-05,
- "loss": 0.9685,
+ "epoch": 11.93,
+ "learning_rate": 5e-05,
+ "loss": 0.3973,
"step": 1056
},
{
- "epoch": 21.39,
- "learning_rate": 6.517857142857143e-05,
- "loss": 0.9265,
+ "epoch": 11.94,
+ "learning_rate": 4.985795454545455e-05,
+ "loss": 0.3986,
"step": 1057
},
{
- "epoch": 21.41,
- "learning_rate": 6.505102040816326e-05,
- "loss": 0.9495,
+ "epoch": 11.95,
+ "learning_rate": 4.971590909090909e-05,
+ "loss": 0.3938,
"step": 1058
},
{
- "epoch": 21.43,
- "learning_rate": 6.49234693877551e-05,
- "loss": 0.9541,
+ "epoch": 11.96,
+ "learning_rate": 4.957386363636364e-05,
+ "loss": 0.3897,
"step": 1059
},
{
- "epoch": 21.45,
- "learning_rate": 6.479591836734694e-05,
- "loss": 0.9299,
+ "epoch": 11.98,
+ "learning_rate": 4.943181818181818e-05,
+ "loss": 0.3965,
"step": 1060
},
{
- "epoch": 21.47,
- "learning_rate": 6.466836734693877e-05,
- "loss": 0.9625,
+ "epoch": 11.99,
+ "learning_rate": 4.9289772727272735e-05,
+ "loss": 0.3999,
"step": 1061
},
{
- "epoch": 21.49,
- "learning_rate": 6.454081632653061e-05,
- "loss": 1.0054,
+ "epoch": 12.0,
+ "learning_rate": 4.914772727272727e-05,
+ "loss": 0.3814,
"step": 1062
},
{
- "epoch": 21.51,
- "learning_rate": 6.441326530612244e-05,
- "loss": 0.9893,
+ "epoch": 12.01,
+ "learning_rate": 4.900568181818182e-05,
+ "loss": 0.3879,
"step": 1063
},
{
- "epoch": 21.53,
- "learning_rate": 6.428571428571429e-05,
- "loss": 0.9906,
+ "epoch": 12.02,
+ "learning_rate": 4.886363636363637e-05,
+ "loss": 0.3768,
"step": 1064
},
{
- "epoch": 21.55,
- "learning_rate": 6.415816326530613e-05,
- "loss": 0.9487,
+ "epoch": 12.03,
+ "learning_rate": 4.8721590909090915e-05,
+ "loss": 0.3813,
"step": 1065
},
{
- "epoch": 21.57,
- "learning_rate": 6.403061224489796e-05,
- "loss": 0.9728,
+ "epoch": 12.04,
+ "learning_rate": 4.857954545454545e-05,
+ "loss": 0.3759,
"step": 1066
},
{
- "epoch": 21.59,
- "learning_rate": 6.390306122448981e-05,
- "loss": 0.9883,
+ "epoch": 12.05,
+ "learning_rate": 4.8437500000000005e-05,
+ "loss": 0.3817,
"step": 1067
},
{
- "epoch": 21.61,
- "learning_rate": 6.377551020408164e-05,
- "loss": 1.053,
+ "epoch": 12.07,
+ "learning_rate": 4.829545454545455e-05,
+ "loss": 0.3773,
"step": 1068
},
{
- "epoch": 21.63,
- "learning_rate": 6.364795918367348e-05,
- "loss": 1.012,
+ "epoch": 12.08,
+ "learning_rate": 4.815340909090909e-05,
+ "loss": 0.3807,
"step": 1069
},
{
- "epoch": 21.65,
- "learning_rate": 6.352040816326531e-05,
- "loss": 0.962,
+ "epoch": 12.09,
+ "learning_rate": 4.801136363636364e-05,
+ "loss": 0.3757,
"step": 1070
},
{
- "epoch": 21.67,
- "learning_rate": 6.339285714285714e-05,
- "loss": 0.9955,
+ "epoch": 12.1,
+ "learning_rate": 4.7869318181818185e-05,
+ "loss": 0.3819,
"step": 1071
},
{
- "epoch": 21.69,
- "learning_rate": 6.326530612244899e-05,
- "loss": 0.9908,
+ "epoch": 12.11,
+ "learning_rate": 4.772727272727273e-05,
+ "loss": 0.3731,
"step": 1072
},
{
- "epoch": 21.71,
- "learning_rate": 6.313775510204082e-05,
- "loss": 1.0327,
+ "epoch": 12.12,
+ "learning_rate": 4.7585227272727276e-05,
+ "loss": 0.3706,
"step": 1073
},
{
- "epoch": 21.73,
- "learning_rate": 6.301020408163265e-05,
- "loss": 0.9255,
+ "epoch": 12.13,
+ "learning_rate": 4.744318181818182e-05,
+ "loss": 0.3762,
"step": 1074
},
{
- "epoch": 21.75,
- "learning_rate": 6.28826530612245e-05,
- "loss": 0.9268,
+ "epoch": 12.14,
+ "learning_rate": 4.7301136363636366e-05,
+ "loss": 0.3749,
"step": 1075
},
{
- "epoch": 21.77,
- "learning_rate": 6.275510204081633e-05,
- "loss": 0.9204,
+ "epoch": 12.16,
+ "learning_rate": 4.715909090909091e-05,
+ "loss": 0.3884,
"step": 1076
},
{
- "epoch": 21.79,
- "learning_rate": 6.262755102040817e-05,
- "loss": 0.9838,
+ "epoch": 12.17,
+ "learning_rate": 4.7017045454545456e-05,
+ "loss": 0.373,
"step": 1077
},
{
- "epoch": 21.81,
- "learning_rate": 6.25e-05,
- "loss": 0.954,
+ "epoch": 12.18,
+ "learning_rate": 4.6875e-05,
+ "loss": 0.374,
"step": 1078
},
{
- "epoch": 21.83,
- "learning_rate": 6.237244897959183e-05,
- "loss": 1.0102,
+ "epoch": 12.19,
+ "learning_rate": 4.6732954545454546e-05,
+ "loss": 0.3813,
"step": 1079
},
{
- "epoch": 21.85,
- "learning_rate": 6.224489795918368e-05,
- "loss": 0.916,
+ "epoch": 12.2,
+ "learning_rate": 4.659090909090909e-05,
+ "loss": 0.3745,
"step": 1080
},
{
- "epoch": 21.87,
- "learning_rate": 6.211734693877551e-05,
- "loss": 0.9939,
+ "epoch": 12.21,
+ "learning_rate": 4.6448863636363636e-05,
+ "loss": 0.3646,
"step": 1081
},
{
- "epoch": 21.89,
- "learning_rate": 6.198979591836735e-05,
- "loss": 0.9675,
+ "epoch": 12.22,
+ "learning_rate": 4.630681818181818e-05,
+ "loss": 0.3729,
"step": 1082
},
{
- "epoch": 21.91,
- "learning_rate": 6.186224489795918e-05,
- "loss": 0.9666,
+ "epoch": 12.24,
+ "learning_rate": 4.616477272727273e-05,
+ "loss": 0.3701,
"step": 1083
},
{
- "epoch": 21.93,
- "learning_rate": 6.173469387755101e-05,
- "loss": 0.9919,
+ "epoch": 12.25,
+ "learning_rate": 4.602272727272727e-05,
+ "loss": 0.3655,
"step": 1084
},
{
- "epoch": 21.95,
- "learning_rate": 6.160714285714286e-05,
- "loss": 1.0106,
+ "epoch": 12.26,
+ "learning_rate": 4.5880681818181817e-05,
+ "loss": 0.3758,
"step": 1085
},
{
- "epoch": 21.97,
- "learning_rate": 6.14795918367347e-05,
- "loss": 0.9982,
+ "epoch": 12.27,
+ "learning_rate": 4.573863636363637e-05,
+ "loss": 0.3682,
"step": 1086
},
{
- "epoch": 21.99,
- "learning_rate": 6.135204081632653e-05,
- "loss": 1.0137,
+ "epoch": 12.28,
+ "learning_rate": 4.5596590909090913e-05,
+ "loss": 0.3865,
"step": 1087
},
{
- "epoch": 22.01,
- "learning_rate": 6.122448979591838e-05,
- "loss": 0.9331,
+ "epoch": 12.29,
+ "learning_rate": 4.545454545454546e-05,
+ "loss": 0.363,
"step": 1088
},
{
- "epoch": 22.03,
- "learning_rate": 6.109693877551021e-05,
- "loss": 0.8834,
+ "epoch": 12.3,
+ "learning_rate": 4.5312500000000004e-05,
+ "loss": 0.3727,
"step": 1089
},
{
- "epoch": 22.06,
- "learning_rate": 6.0969387755102046e-05,
- "loss": 0.9757,
+ "epoch": 12.31,
+ "learning_rate": 4.517045454545455e-05,
+ "loss": 0.3827,
"step": 1090
},
{
- "epoch": 22.08,
- "learning_rate": 6.084183673469388e-05,
- "loss": 0.9038,
+ "epoch": 12.33,
+ "learning_rate": 4.5028409090909094e-05,
+ "loss": 0.3658,
"step": 1091
},
{
- "epoch": 22.1,
- "learning_rate": 6.0714285714285715e-05,
- "loss": 0.9097,
+ "epoch": 12.34,
+ "learning_rate": 4.488636363636364e-05,
+ "loss": 0.3844,
"step": 1092
},
{
- "epoch": 22.12,
- "learning_rate": 6.058673469387756e-05,
- "loss": 0.8972,
+ "epoch": 12.35,
+ "learning_rate": 4.4744318181818184e-05,
+ "loss": 0.3731,
"step": 1093
},
{
- "epoch": 22.14,
- "learning_rate": 6.045918367346939e-05,
- "loss": 0.8825,
+ "epoch": 12.36,
+ "learning_rate": 4.460227272727273e-05,
+ "loss": 0.3767,
"step": 1094
},
{
- "epoch": 22.16,
- "learning_rate": 6.0331632653061234e-05,
- "loss": 0.9814,
+ "epoch": 12.37,
+ "learning_rate": 4.4460227272727274e-05,
+ "loss": 0.3751,
"step": 1095
},
{
- "epoch": 22.18,
- "learning_rate": 6.0204081632653065e-05,
- "loss": 0.9874,
+ "epoch": 12.38,
+ "learning_rate": 4.431818181818182e-05,
+ "loss": 0.3718,
"step": 1096
},
{
- "epoch": 22.2,
- "learning_rate": 6.0076530612244896e-05,
- "loss": 0.912,
+ "epoch": 12.39,
+ "learning_rate": 4.4176136363636364e-05,
+ "loss": 0.3833,
"step": 1097
},
{
- "epoch": 22.22,
- "learning_rate": 5.994897959183674e-05,
- "loss": 0.9206,
+ "epoch": 12.4,
+ "learning_rate": 4.4034090909090916e-05,
+ "loss": 0.3673,
"step": 1098
},
{
- "epoch": 22.24,
- "learning_rate": 5.982142857142857e-05,
- "loss": 0.9497,
+ "epoch": 12.42,
+ "learning_rate": 4.3892045454545454e-05,
+ "loss": 0.3799,
"step": 1099
},
{
- "epoch": 22.26,
- "learning_rate": 5.9693877551020416e-05,
- "loss": 0.9269,
+ "epoch": 12.43,
+ "learning_rate": 4.375e-05,
+ "loss": 0.3661,
"step": 1100
},
{
- "epoch": 22.28,
- "learning_rate": 5.956632653061225e-05,
- "loss": 0.9452,
+ "epoch": 12.44,
+ "learning_rate": 4.360795454545455e-05,
+ "loss": 0.3554,
"step": 1101
},
{
- "epoch": 22.3,
- "learning_rate": 5.9438775510204084e-05,
- "loss": 0.9548,
+ "epoch": 12.45,
+ "learning_rate": 4.346590909090909e-05,
+ "loss": 0.3787,
"step": 1102
},
{
- "epoch": 22.32,
- "learning_rate": 5.931122448979592e-05,
- "loss": 0.9689,
+ "epoch": 12.46,
+ "learning_rate": 4.3323863636363635e-05,
+ "loss": 0.3695,
"step": 1103
},
{
- "epoch": 22.34,
- "learning_rate": 5.918367346938776e-05,
- "loss": 0.9455,
+ "epoch": 12.47,
+ "learning_rate": 4.318181818181819e-05,
+ "loss": 0.3777,
"step": 1104
},
{
- "epoch": 22.36,
- "learning_rate": 5.905612244897959e-05,
- "loss": 0.9409,
+ "epoch": 12.48,
+ "learning_rate": 4.303977272727273e-05,
+ "loss": 0.3693,
"step": 1105
},
{
- "epoch": 22.38,
- "learning_rate": 5.8928571428571435e-05,
- "loss": 0.9093,
+ "epoch": 12.49,
+ "learning_rate": 4.289772727272727e-05,
+ "loss": 0.3731,
"step": 1106
},
{
- "epoch": 22.4,
- "learning_rate": 5.8801020408163266e-05,
- "loss": 0.921,
+ "epoch": 12.51,
+ "learning_rate": 4.275568181818182e-05,
+ "loss": 0.3659,
"step": 1107
},
{
- "epoch": 22.42,
- "learning_rate": 5.867346938775511e-05,
- "loss": 0.9368,
+ "epoch": 12.52,
+ "learning_rate": 4.261363636363637e-05,
+ "loss": 0.3689,
"step": 1108
},
{
- "epoch": 22.44,
- "learning_rate": 5.854591836734694e-05,
- "loss": 0.907,
+ "epoch": 12.53,
+ "learning_rate": 4.247159090909091e-05,
+ "loss": 0.3625,
"step": 1109
},
{
- "epoch": 22.46,
- "learning_rate": 5.841836734693877e-05,
- "loss": 0.9126,
+ "epoch": 12.54,
+ "learning_rate": 4.232954545454546e-05,
+ "loss": 0.3874,
"step": 1110
},
{
- "epoch": 22.48,
- "learning_rate": 5.8290816326530616e-05,
- "loss": 0.9161,
+ "epoch": 12.55,
+ "learning_rate": 4.21875e-05,
+ "loss": 0.3651,
"step": 1111
},
{
- "epoch": 22.5,
- "learning_rate": 5.816326530612245e-05,
- "loss": 0.9542,
+ "epoch": 12.56,
+ "learning_rate": 4.204545454545455e-05,
+ "loss": 0.3639,
"step": 1112
},
{
- "epoch": 22.52,
- "learning_rate": 5.803571428571429e-05,
- "loss": 0.9775,
+ "epoch": 12.57,
+ "learning_rate": 4.190340909090909e-05,
+ "loss": 0.378,
"step": 1113
},
{
- "epoch": 22.54,
- "learning_rate": 5.790816326530612e-05,
- "loss": 1.0006,
+ "epoch": 12.59,
+ "learning_rate": 4.176136363636364e-05,
+ "loss": 0.3726,
"step": 1114
},
{
- "epoch": 22.56,
- "learning_rate": 5.778061224489796e-05,
- "loss": 0.8965,
+ "epoch": 12.6,
+ "learning_rate": 4.161931818181818e-05,
+ "loss": 0.3732,
"step": 1115
},
{
- "epoch": 22.58,
- "learning_rate": 5.7653061224489805e-05,
- "loss": 0.944,
+ "epoch": 12.61,
+ "learning_rate": 4.1477272727272734e-05,
+ "loss": 0.3673,
"step": 1116
},
{
- "epoch": 22.6,
- "learning_rate": 5.7525510204081636e-05,
- "loss": 0.9162,
+ "epoch": 12.62,
+ "learning_rate": 4.133522727272727e-05,
+ "loss": 0.3566,
"step": 1117
},
{
- "epoch": 22.62,
- "learning_rate": 5.739795918367348e-05,
- "loss": 0.9325,
+ "epoch": 12.63,
+ "learning_rate": 4.119318181818182e-05,
+ "loss": 0.3757,
"step": 1118
},
{
- "epoch": 22.64,
- "learning_rate": 5.727040816326531e-05,
- "loss": 0.8998,
+ "epoch": 12.64,
+ "learning_rate": 4.105113636363637e-05,
+ "loss": 0.3739,
"step": 1119
},
{
- "epoch": 22.66,
- "learning_rate": 5.714285714285714e-05,
- "loss": 0.9362,
+ "epoch": 12.65,
+ "learning_rate": 4.0909090909090915e-05,
+ "loss": 0.3768,
"step": 1120
},
{
- "epoch": 22.68,
- "learning_rate": 5.7015306122448986e-05,
- "loss": 0.9969,
+ "epoch": 12.66,
+ "learning_rate": 4.076704545454545e-05,
+ "loss": 0.3758,
"step": 1121
},
{
- "epoch": 22.7,
- "learning_rate": 5.688775510204082e-05,
- "loss": 0.9104,
+ "epoch": 12.68,
+ "learning_rate": 4.0625000000000005e-05,
+ "loss": 0.3655,
"step": 1122
},
{
- "epoch": 22.72,
- "learning_rate": 5.676020408163265e-05,
- "loss": 0.9746,
+ "epoch": 12.69,
+ "learning_rate": 4.048295454545455e-05,
+ "loss": 0.3673,
"step": 1123
},
{
- "epoch": 22.74,
- "learning_rate": 5.663265306122449e-05,
- "loss": 0.9821,
+ "epoch": 12.7,
+ "learning_rate": 4.034090909090909e-05,
+ "loss": 0.3683,
"step": 1124
},
{
- "epoch": 22.76,
- "learning_rate": 5.650510204081633e-05,
- "loss": 0.9526,
+ "epoch": 12.71,
+ "learning_rate": 4.019886363636364e-05,
+ "loss": 0.3569,
"step": 1125
},
{
- "epoch": 22.78,
- "learning_rate": 5.637755102040817e-05,
- "loss": 0.871,
+ "epoch": 12.72,
+ "learning_rate": 4.0056818181818185e-05,
+ "loss": 0.3741,
"step": 1126
},
{
- "epoch": 22.8,
- "learning_rate": 5.6250000000000005e-05,
- "loss": 0.9534,
+ "epoch": 12.73,
+ "learning_rate": 3.991477272727273e-05,
+ "loss": 0.3817,
"step": 1127
},
{
- "epoch": 22.82,
- "learning_rate": 5.6122448979591836e-05,
- "loss": 0.9616,
+ "epoch": 12.74,
+ "learning_rate": 3.9772727272727275e-05,
+ "loss": 0.3748,
"step": 1128
},
{
- "epoch": 22.84,
- "learning_rate": 5.599489795918368e-05,
- "loss": 0.9627,
+ "epoch": 12.75,
+ "learning_rate": 3.963068181818182e-05,
+ "loss": 0.3625,
"step": 1129
},
{
- "epoch": 22.86,
- "learning_rate": 5.586734693877551e-05,
- "loss": 0.9704,
+ "epoch": 12.77,
+ "learning_rate": 3.9488636363636366e-05,
+ "loss": 0.3656,
"step": 1130
},
{
- "epoch": 22.88,
- "learning_rate": 5.5739795918367356e-05,
- "loss": 0.9506,
+ "epoch": 12.78,
+ "learning_rate": 3.934659090909091e-05,
+ "loss": 0.3564,
"step": 1131
},
{
- "epoch": 22.9,
- "learning_rate": 5.561224489795919e-05,
- "loss": 0.9553,
+ "epoch": 12.79,
+ "learning_rate": 3.9204545454545456e-05,
+ "loss": 0.3737,
"step": 1132
},
{
- "epoch": 22.93,
- "learning_rate": 5.548469387755102e-05,
- "loss": 0.9294,
+ "epoch": 12.8,
+ "learning_rate": 3.90625e-05,
+ "loss": 0.3649,
"step": 1133
},
{
- "epoch": 22.95,
- "learning_rate": 5.535714285714286e-05,
- "loss": 0.8979,
+ "epoch": 12.81,
+ "learning_rate": 3.8920454545454546e-05,
+ "loss": 0.3728,
"step": 1134
},
{
- "epoch": 22.97,
- "learning_rate": 5.522959183673469e-05,
- "loss": 1.0004,
+ "epoch": 12.82,
+ "learning_rate": 3.877840909090909e-05,
+ "loss": 0.3865,
"step": 1135
},
{
- "epoch": 22.99,
- "learning_rate": 5.510204081632653e-05,
- "loss": 0.9821,
+ "epoch": 12.83,
+ "learning_rate": 3.8636363636363636e-05,
+ "loss": 0.3866,
"step": 1136
},
{
- "epoch": 23.01,
- "learning_rate": 5.497448979591837e-05,
- "loss": 0.9607,
+ "epoch": 12.85,
+ "learning_rate": 3.849431818181818e-05,
+ "loss": 0.3725,
"step": 1137
},
{
- "epoch": 23.03,
- "learning_rate": 5.4846938775510206e-05,
- "loss": 0.9757,
+ "epoch": 12.86,
+ "learning_rate": 3.835227272727273e-05,
+ "loss": 0.3662,
"step": 1138
},
{
- "epoch": 23.05,
- "learning_rate": 5.471938775510205e-05,
- "loss": 0.9096,
+ "epoch": 12.87,
+ "learning_rate": 3.821022727272727e-05,
+ "loss": 0.3742,
"step": 1139
},
{
- "epoch": 23.07,
- "learning_rate": 5.459183673469388e-05,
- "loss": 0.9144,
+ "epoch": 12.88,
+ "learning_rate": 3.8068181818181816e-05,
+ "loss": 0.3727,
"step": 1140
},
{
- "epoch": 23.09,
- "learning_rate": 5.446428571428571e-05,
- "loss": 0.8667,
+ "epoch": 12.89,
+ "learning_rate": 3.792613636363637e-05,
+ "loss": 0.3653,
"step": 1141
},
{
- "epoch": 23.11,
- "learning_rate": 5.4336734693877556e-05,
- "loss": 0.8993,
+ "epoch": 12.9,
+ "learning_rate": 3.778409090909091e-05,
+ "loss": 0.3631,
"step": 1142
},
{
- "epoch": 23.13,
- "learning_rate": 5.420918367346939e-05,
- "loss": 0.8964,
+ "epoch": 12.91,
+ "learning_rate": 3.764204545454545e-05,
+ "loss": 0.3674,
"step": 1143
},
{
- "epoch": 23.15,
- "learning_rate": 5.408163265306123e-05,
- "loss": 0.9173,
+ "epoch": 12.92,
+ "learning_rate": 3.7500000000000003e-05,
+ "loss": 0.3598,
"step": 1144
},
{
- "epoch": 23.17,
- "learning_rate": 5.395408163265306e-05,
- "loss": 0.9019,
+ "epoch": 12.94,
+ "learning_rate": 3.735795454545455e-05,
+ "loss": 0.3697,
"step": 1145
},
{
- "epoch": 23.19,
- "learning_rate": 5.382653061224489e-05,
- "loss": 0.9303,
+ "epoch": 12.95,
+ "learning_rate": 3.721590909090909e-05,
+ "loss": 0.3639,
"step": 1146
},
{
- "epoch": 23.21,
- "learning_rate": 5.369897959183674e-05,
- "loss": 0.9268,
+ "epoch": 12.96,
+ "learning_rate": 3.707386363636364e-05,
+ "loss": 0.3597,
"step": 1147
},
{
- "epoch": 23.23,
- "learning_rate": 5.3571428571428575e-05,
- "loss": 0.8803,
+ "epoch": 12.97,
+ "learning_rate": 3.6931818181818184e-05,
+ "loss": 0.3815,
"step": 1148
},
{
- "epoch": 23.25,
- "learning_rate": 5.344387755102041e-05,
- "loss": 0.9197,
+ "epoch": 12.98,
+ "learning_rate": 3.678977272727273e-05,
+ "loss": 0.3477,
"step": 1149
},
{
- "epoch": 23.27,
- "learning_rate": 5.331632653061225e-05,
- "loss": 0.9204,
+ "epoch": 12.99,
+ "learning_rate": 3.6647727272727274e-05,
+ "loss": 0.3631,
"step": 1150
},
{
- "epoch": 23.29,
- "learning_rate": 5.318877551020408e-05,
- "loss": 0.8802,
+ "epoch": 13.0,
+ "learning_rate": 3.650568181818182e-05,
+ "loss": 0.3569,
"step": 1151
},
{
- "epoch": 23.31,
- "learning_rate": 5.3061224489795926e-05,
- "loss": 0.9044,
+ "epoch": 13.01,
+ "learning_rate": 3.6363636363636364e-05,
+ "loss": 0.3435,
"step": 1152
},
{
- "epoch": 23.33,
- "learning_rate": 5.293367346938776e-05,
- "loss": 0.8893,
+ "epoch": 13.03,
+ "learning_rate": 3.6221590909090916e-05,
+ "loss": 0.3504,
"step": 1153
},
{
- "epoch": 23.35,
- "learning_rate": 5.280612244897959e-05,
- "loss": 0.8928,
+ "epoch": 13.04,
+ "learning_rate": 3.6079545454545454e-05,
+ "loss": 0.3582,
"step": 1154
},
{
- "epoch": 23.37,
- "learning_rate": 5.267857142857143e-05,
- "loss": 0.9353,
+ "epoch": 13.05,
+ "learning_rate": 3.59375e-05,
+ "loss": 0.356,
"step": 1155
},
{
- "epoch": 23.39,
- "learning_rate": 5.255102040816326e-05,
- "loss": 0.9345,
+ "epoch": 13.06,
+ "learning_rate": 3.579545454545455e-05,
+ "loss": 0.3506,
"step": 1156
},
{
- "epoch": 23.41,
- "learning_rate": 5.242346938775511e-05,
- "loss": 0.9372,
+ "epoch": 13.07,
+ "learning_rate": 3.565340909090909e-05,
+ "loss": 0.3628,
"step": 1157
},
{
- "epoch": 23.43,
- "learning_rate": 5.229591836734694e-05,
- "loss": 0.9234,
+ "epoch": 13.08,
+ "learning_rate": 3.5511363636363635e-05,
+ "loss": 0.3494,
"step": 1158
},
{
- "epoch": 23.45,
- "learning_rate": 5.2168367346938776e-05,
- "loss": 0.9177,
+ "epoch": 13.09,
+ "learning_rate": 3.5369318181818186e-05,
+ "loss": 0.3653,
"step": 1159
},
{
- "epoch": 23.47,
- "learning_rate": 5.2040816326530614e-05,
- "loss": 0.8757,
+ "epoch": 13.11,
+ "learning_rate": 3.522727272727273e-05,
+ "loss": 0.3515,
"step": 1160
},
{
- "epoch": 23.49,
- "learning_rate": 5.191326530612245e-05,
- "loss": 0.9048,
+ "epoch": 13.12,
+ "learning_rate": 3.508522727272727e-05,
+ "loss": 0.3474,
"step": 1161
},
{
- "epoch": 23.51,
- "learning_rate": 5.1785714285714296e-05,
- "loss": 0.9248,
+ "epoch": 13.13,
+ "learning_rate": 3.494318181818182e-05,
+ "loss": 0.3469,
"step": 1162
},
{
- "epoch": 23.53,
- "learning_rate": 5.1658163265306127e-05,
- "loss": 0.9379,
+ "epoch": 13.14,
+ "learning_rate": 3.480113636363637e-05,
+ "loss": 0.3471,
"step": 1163
},
{
- "epoch": 23.55,
- "learning_rate": 5.153061224489796e-05,
- "loss": 0.8596,
+ "epoch": 13.15,
+ "learning_rate": 3.465909090909091e-05,
+ "loss": 0.355,
"step": 1164
},
{
- "epoch": 23.57,
- "learning_rate": 5.14030612244898e-05,
- "loss": 0.9751,
+ "epoch": 13.16,
+ "learning_rate": 3.451704545454546e-05,
+ "loss": 0.3532,
"step": 1165
},
{
- "epoch": 23.59,
- "learning_rate": 5.127551020408163e-05,
- "loss": 0.8842,
+ "epoch": 13.17,
+ "learning_rate": 3.4375e-05,
+ "loss": 0.3533,
"step": 1166
},
{
- "epoch": 23.61,
- "learning_rate": 5.114795918367348e-05,
- "loss": 0.8765,
+ "epoch": 13.18,
+ "learning_rate": 3.423295454545455e-05,
+ "loss": 0.3571,
"step": 1167
},
{
- "epoch": 23.63,
- "learning_rate": 5.102040816326531e-05,
- "loss": 0.8942,
+ "epoch": 13.2,
+ "learning_rate": 3.409090909090909e-05,
+ "loss": 0.3435,
"step": 1168
},
{
- "epoch": 23.65,
- "learning_rate": 5.089285714285714e-05,
- "loss": 0.938,
+ "epoch": 13.21,
+ "learning_rate": 3.394886363636364e-05,
+ "loss": 0.348,
"step": 1169
},
{
- "epoch": 23.67,
- "learning_rate": 5.076530612244898e-05,
- "loss": 0.8993,
+ "epoch": 13.22,
+ "learning_rate": 3.380681818181818e-05,
+ "loss": 0.3505,
"step": 1170
},
{
- "epoch": 23.69,
- "learning_rate": 5.063775510204082e-05,
- "loss": 0.9362,
+ "epoch": 13.23,
+ "learning_rate": 3.3664772727272734e-05,
+ "loss": 0.346,
"step": 1171
},
{
- "epoch": 23.71,
- "learning_rate": 5.051020408163265e-05,
- "loss": 0.9249,
+ "epoch": 13.24,
+ "learning_rate": 3.352272727272727e-05,
+ "loss": 0.3568,
"step": 1172
},
{
- "epoch": 23.73,
- "learning_rate": 5.0382653061224496e-05,
- "loss": 0.9055,
+ "epoch": 13.25,
+ "learning_rate": 3.338068181818182e-05,
+ "loss": 0.3548,
"step": 1173
},
{
- "epoch": 23.75,
- "learning_rate": 5.025510204081633e-05,
- "loss": 0.8967,
+ "epoch": 13.26,
+ "learning_rate": 3.323863636363637e-05,
+ "loss": 0.352,
"step": 1174
},
{
- "epoch": 23.77,
- "learning_rate": 5.012755102040817e-05,
- "loss": 0.8795,
+ "epoch": 13.27,
+ "learning_rate": 3.3096590909090915e-05,
+ "loss": 0.3561,
"step": 1175
},
{
- "epoch": 23.8,
- "learning_rate": 5e-05,
- "loss": 0.9452,
+ "epoch": 13.29,
+ "learning_rate": 3.295454545454545e-05,
+ "loss": 0.3424,
"step": 1176
},
{
- "epoch": 23.82,
- "learning_rate": 4.987244897959184e-05,
- "loss": 0.926,
+ "epoch": 13.3,
+ "learning_rate": 3.2812500000000005e-05,
+ "loss": 0.3453,
"step": 1177
},
{
- "epoch": 23.84,
- "learning_rate": 4.974489795918368e-05,
- "loss": 0.8948,
+ "epoch": 13.31,
+ "learning_rate": 3.267045454545455e-05,
+ "loss": 0.347,
"step": 1178
},
{
- "epoch": 23.86,
- "learning_rate": 4.961734693877551e-05,
- "loss": 0.8926,
+ "epoch": 13.32,
+ "learning_rate": 3.252840909090909e-05,
+ "loss": 0.3526,
"step": 1179
},
{
- "epoch": 23.88,
- "learning_rate": 4.9489795918367346e-05,
- "loss": 0.8949,
+ "epoch": 13.33,
+ "learning_rate": 3.238636363636364e-05,
+ "loss": 0.3634,
"step": 1180
},
{
- "epoch": 23.9,
- "learning_rate": 4.9362244897959184e-05,
- "loss": 0.9648,
+ "epoch": 13.34,
+ "learning_rate": 3.2244318181818185e-05,
+ "loss": 0.3591,
"step": 1181
},
{
- "epoch": 23.92,
- "learning_rate": 4.923469387755102e-05,
- "loss": 0.9599,
+ "epoch": 13.35,
+ "learning_rate": 3.210227272727273e-05,
+ "loss": 0.3449,
"step": 1182
},
{
- "epoch": 23.94,
- "learning_rate": 4.910714285714286e-05,
- "loss": 0.9603,
+ "epoch": 13.36,
+ "learning_rate": 3.1960227272727275e-05,
+ "loss": 0.3362,
"step": 1183
},
{
- "epoch": 23.96,
- "learning_rate": 4.89795918367347e-05,
- "loss": 0.9302,
+ "epoch": 13.38,
+ "learning_rate": 3.181818181818182e-05,
+ "loss": 0.3613,
"step": 1184
},
{
- "epoch": 23.98,
- "learning_rate": 4.8852040816326534e-05,
- "loss": 0.9261,
+ "epoch": 13.39,
+ "learning_rate": 3.1676136363636365e-05,
+ "loss": 0.3509,
"step": 1185
},
{
- "epoch": 24.0,
- "learning_rate": 4.872448979591837e-05,
- "loss": 0.9257,
+ "epoch": 13.4,
+ "learning_rate": 3.153409090909091e-05,
+ "loss": 0.3534,
"step": 1186
},
{
- "epoch": 24.02,
- "learning_rate": 4.859693877551021e-05,
- "loss": 0.8725,
+ "epoch": 13.41,
+ "learning_rate": 3.1392045454545456e-05,
+ "loss": 0.3452,
"step": 1187
},
{
- "epoch": 24.04,
- "learning_rate": 4.846938775510204e-05,
- "loss": 0.8486,
+ "epoch": 13.42,
+ "learning_rate": 3.125e-05,
+ "loss": 0.3659,
"step": 1188
},
{
- "epoch": 24.06,
- "learning_rate": 4.834183673469388e-05,
- "loss": 0.8457,
+ "epoch": 13.43,
+ "learning_rate": 3.1107954545454546e-05,
+ "loss": 0.3445,
"step": 1189
},
{
- "epoch": 24.08,
- "learning_rate": 4.8214285714285716e-05,
- "loss": 0.7848,
+ "epoch": 13.44,
+ "learning_rate": 3.096590909090909e-05,
+ "loss": 0.3536,
"step": 1190
},
{
- "epoch": 24.1,
- "learning_rate": 4.8086734693877554e-05,
- "loss": 0.8885,
+ "epoch": 13.46,
+ "learning_rate": 3.0823863636363636e-05,
+ "loss": 0.3588,
"step": 1191
},
{
- "epoch": 24.12,
- "learning_rate": 4.795918367346939e-05,
- "loss": 0.9099,
+ "epoch": 13.47,
+ "learning_rate": 3.068181818181818e-05,
+ "loss": 0.347,
"step": 1192
},
{
- "epoch": 24.14,
- "learning_rate": 4.783163265306123e-05,
- "loss": 0.9147,
+ "epoch": 13.48,
+ "learning_rate": 3.053977272727273e-05,
+ "loss": 0.3537,
"step": 1193
},
{
- "epoch": 24.16,
- "learning_rate": 4.7704081632653066e-05,
- "loss": 0.8781,
+ "epoch": 13.49,
+ "learning_rate": 3.039772727272727e-05,
+ "loss": 0.3516,
"step": 1194
},
{
- "epoch": 24.18,
- "learning_rate": 4.7576530612244904e-05,
- "loss": 0.8847,
+ "epoch": 13.5,
+ "learning_rate": 3.025568181818182e-05,
+ "loss": 0.3587,
"step": 1195
},
{
- "epoch": 24.2,
- "learning_rate": 4.744897959183674e-05,
- "loss": 0.9041,
+ "epoch": 13.51,
+ "learning_rate": 3.0113636363636365e-05,
+ "loss": 0.3494,
"step": 1196
},
{
- "epoch": 24.22,
- "learning_rate": 4.732142857142857e-05,
- "loss": 0.8639,
+ "epoch": 13.52,
+ "learning_rate": 2.9971590909090913e-05,
+ "loss": 0.3341,
"step": 1197
},
{
- "epoch": 24.24,
- "learning_rate": 4.719387755102041e-05,
- "loss": 0.8831,
+ "epoch": 13.53,
+ "learning_rate": 2.9829545454545455e-05,
+ "loss": 0.3563,
"step": 1198
},
{
- "epoch": 24.26,
- "learning_rate": 4.706632653061225e-05,
- "loss": 0.9063,
+ "epoch": 13.55,
+ "learning_rate": 2.96875e-05,
+ "loss": 0.3534,
"step": 1199
},
{
- "epoch": 24.28,
- "learning_rate": 4.6938775510204086e-05,
- "loss": 0.8753,
+ "epoch": 13.56,
+ "learning_rate": 2.954545454545455e-05,
+ "loss": 0.3632,
"step": 1200
}
],
"logging_steps": 1,
- "max_steps": 1568,
- "num_train_epochs": 32,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
"save_steps": 100,
- "total_flos": 1.7762072708554138e+18,
+ "total_flos": 1.6376151934208102e+18,
"trial_name": null,
"trial_params": null
}
diff --git a/checkpoint-1200/training_args.bin b/checkpoint-1200/training_args.bin
index db23e07d097c18532e52f58a70eb72d22e39c8c1..ee7ddb867f05d9a969f71467a8eb88994865cf51 100644
--- a/checkpoint-1200/training_args.bin
+++ b/checkpoint-1200/training_args.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
size 4155
diff --git a/checkpoint-1300/adapter_model.bin b/checkpoint-1300/adapter_model.bin
index 2a46567e8a873934c32b5f6716c212c0583d11c5..4add2ddf3a60dfcddc63dc962185fc8c6748fc9c 100644
--- a/checkpoint-1300/adapter_model.bin
+++ b/checkpoint-1300/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:557e20c98ce81a1b2174b31161d704a79e1057d7cba9a8a3a044698f748e1a96
+oid sha256:fd38544a3f483f339db731e48dedd495f34e33524ab8ebb4dcaf56ed451e74e2
size 39409357
diff --git a/checkpoint-1300/optimizer.pt b/checkpoint-1300/optimizer.pt
index dc193c111e311e6c8b784c0d8a731044dca46428..51ce5db0fc1ad7ec09ad7d2d197ad5efee8c0a7e 100644
--- a/checkpoint-1300/optimizer.pt
+++ b/checkpoint-1300/optimizer.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:d2311ed46f1164ff3772d9c69e8f7347964538333edd4438abef82e7683876dc
+oid sha256:3050127d2eb3d707b91667223062e0f617e707678ffe8035de6051275306728f
size 78844421
diff --git a/checkpoint-1300/rng_state.pth b/checkpoint-1300/rng_state.pth
index c16fb5959f3252446d7952ca7b642c0f6b79609e..c1c4c79fcb2148e5de373db02c3ee2987200a3a9 100644
--- a/checkpoint-1300/rng_state.pth
+++ b/checkpoint-1300/rng_state.pth
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:e2233b71d28d82b8331de6224e1abb884bd9108ce746c680fd1c4d641c935668
+oid sha256:3e46ce4eb16240da9f3a8b3066acb6f59a234249ee2a3052f3323786da479838
size 14575
diff --git a/checkpoint-1300/scheduler.pt b/checkpoint-1300/scheduler.pt
index 6d80e9e6b9dff077ceec581106fad9de9f7ae96c..9e88dcb049f0353ddd8d1df6c49c0ea83286fa4e 100644
--- a/checkpoint-1300/scheduler.pt
+++ b/checkpoint-1300/scheduler.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:af8fb4309008de879e60055efbf110ed70c676d2270a50eb4a6b5b40910d4878
+oid sha256:d75bc5140c934078e850991a6d79c9d5e5d870823a1e52dc1b01bf1b267613ec
size 627
diff --git a/checkpoint-1300/trainer_state.json b/checkpoint-1300/trainer_state.json
index b03ed0161efaed231027c7690ba0e05c13ddb02c..e7fd57393f6115dc085faf1acc1b5c47dc2fe54a 100644
--- a/checkpoint-1300/trainer_state.json
+++ b/checkpoint-1300/trainer_state.json
@@ -1,7 +1,7 @@
{
"best_metric": null,
"best_model_checkpoint": null,
- "epoch": 26.304141637685742,
+ "epoch": 14.68667255075022,
"eval_steps": 500,
"global_step": 1300,
"is_hyper_param_search": false,
@@ -9,7811 +9,7811 @@
"is_world_process_zero": true,
"log_history": [
{
- "epoch": 0.02,
- "learning_rate": 0.00019987244897959184,
- "loss": 3.2215,
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
"step": 1
},
{
- "epoch": 0.04,
- "learning_rate": 0.00019974489795918367,
- "loss": 2.8365,
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
"step": 2
},
{
- "epoch": 0.06,
- "learning_rate": 0.00019961734693877553,
- "loss": 2.602,
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
"step": 3
},
{
- "epoch": 0.08,
- "learning_rate": 0.00019948979591836736,
- "loss": 2.4196,
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
"step": 4
},
{
- "epoch": 0.1,
- "learning_rate": 0.0001993622448979592,
- "loss": 2.2574,
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
"step": 5
},
{
- "epoch": 0.12,
- "learning_rate": 0.00019923469387755102,
- "loss": 2.2239,
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
"step": 6
},
{
- "epoch": 0.14,
- "learning_rate": 0.00019910714285714288,
- "loss": 2.1661,
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
"step": 7
},
{
- "epoch": 0.16,
- "learning_rate": 0.0001989795918367347,
- "loss": 2.0987,
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
"step": 8
},
{
- "epoch": 0.18,
- "learning_rate": 0.00019885204081632654,
- "loss": 2.015,
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
"step": 9
},
{
- "epoch": 0.2,
- "learning_rate": 0.00019872448979591837,
- "loss": 1.9771,
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
"step": 10
},
{
- "epoch": 0.22,
- "learning_rate": 0.00019859693877551023,
- "loss": 2.0271,
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
"step": 11
},
{
- "epoch": 0.24,
- "learning_rate": 0.00019846938775510203,
- "loss": 1.9812,
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
"step": 12
},
{
- "epoch": 0.26,
- "learning_rate": 0.0001983418367346939,
- "loss": 2.0834,
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
"step": 13
},
{
- "epoch": 0.28,
- "learning_rate": 0.00019821428571428572,
- "loss": 1.9174,
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
"step": 14
},
{
- "epoch": 0.3,
- "learning_rate": 0.00019808673469387755,
- "loss": 1.8409,
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
"step": 15
},
{
- "epoch": 0.32,
- "learning_rate": 0.00019795918367346938,
- "loss": 1.929,
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
"step": 16
},
{
- "epoch": 0.34,
- "learning_rate": 0.00019783163265306124,
- "loss": 2.0041,
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
"step": 17
},
{
- "epoch": 0.36,
- "learning_rate": 0.00019770408163265305,
- "loss": 1.9385,
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
"step": 18
},
{
- "epoch": 0.38,
- "learning_rate": 0.0001975765306122449,
- "loss": 1.9592,
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
"step": 19
},
{
- "epoch": 0.4,
- "learning_rate": 0.00019744897959183674,
- "loss": 1.9701,
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
"step": 20
},
{
- "epoch": 0.42,
- "learning_rate": 0.0001973214285714286,
- "loss": 1.9277,
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
"step": 21
},
{
- "epoch": 0.45,
- "learning_rate": 0.00019719387755102042,
- "loss": 1.8394,
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
"step": 22
},
{
- "epoch": 0.47,
- "learning_rate": 0.00019706632653061226,
- "loss": 1.8666,
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
"step": 23
},
{
- "epoch": 0.49,
- "learning_rate": 0.00019693877551020409,
- "loss": 1.8997,
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
"step": 24
},
{
- "epoch": 0.51,
- "learning_rate": 0.00019681122448979592,
- "loss": 1.9432,
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
"step": 25
},
{
- "epoch": 0.53,
- "learning_rate": 0.00019668367346938777,
- "loss": 1.9137,
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
"step": 26
},
{
- "epoch": 0.55,
- "learning_rate": 0.0001965561224489796,
- "loss": 1.905,
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
"step": 27
},
{
- "epoch": 0.57,
- "learning_rate": 0.00019642857142857144,
- "loss": 1.8708,
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
"step": 28
},
{
- "epoch": 0.59,
- "learning_rate": 0.00019630102040816327,
- "loss": 1.9097,
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
"step": 29
},
{
- "epoch": 0.61,
- "learning_rate": 0.00019617346938775513,
- "loss": 1.896,
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
"step": 30
},
{
- "epoch": 0.63,
- "learning_rate": 0.00019604591836734696,
- "loss": 1.8834,
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
"step": 31
},
{
- "epoch": 0.65,
- "learning_rate": 0.0001959183673469388,
- "loss": 1.8323,
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
"step": 32
},
{
- "epoch": 0.67,
- "learning_rate": 0.00019579081632653062,
- "loss": 1.804,
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
"step": 33
},
{
- "epoch": 0.69,
- "learning_rate": 0.00019566326530612248,
- "loss": 1.8906,
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
"step": 34
},
{
- "epoch": 0.71,
- "learning_rate": 0.00019553571428571428,
- "loss": 1.8693,
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
"step": 35
},
{
- "epoch": 0.73,
- "learning_rate": 0.00019540816326530614,
- "loss": 1.9308,
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
"step": 36
},
{
- "epoch": 0.75,
- "learning_rate": 0.00019528061224489797,
- "loss": 1.8082,
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
"step": 37
},
{
- "epoch": 0.77,
- "learning_rate": 0.0001951530612244898,
- "loss": 1.848,
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
"step": 38
},
{
- "epoch": 0.79,
- "learning_rate": 0.00019502551020408163,
- "loss": 1.8866,
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
"step": 39
},
{
- "epoch": 0.81,
- "learning_rate": 0.0001948979591836735,
- "loss": 1.7844,
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
"step": 40
},
{
- "epoch": 0.83,
- "learning_rate": 0.0001947704081632653,
- "loss": 1.8485,
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
"step": 41
},
{
- "epoch": 0.85,
- "learning_rate": 0.00019464285714285715,
- "loss": 1.7917,
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
"step": 42
},
{
- "epoch": 0.87,
- "learning_rate": 0.00019451530612244898,
- "loss": 1.7342,
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
"step": 43
},
{
- "epoch": 0.89,
- "learning_rate": 0.00019438775510204084,
- "loss": 1.8479,
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
"step": 44
},
{
- "epoch": 0.91,
- "learning_rate": 0.00019426020408163267,
- "loss": 1.8639,
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
"step": 45
},
{
- "epoch": 0.93,
- "learning_rate": 0.0001941326530612245,
- "loss": 1.8166,
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
"step": 46
},
{
- "epoch": 0.95,
- "learning_rate": 0.00019400510204081633,
- "loss": 1.7566,
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
"step": 47
},
{
- "epoch": 0.97,
- "learning_rate": 0.00019387755102040816,
- "loss": 1.8071,
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
"step": 48
},
{
- "epoch": 0.99,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.8612,
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
"step": 49
},
{
- "epoch": 1.01,
- "learning_rate": 0.00019362244897959185,
- "loss": 1.7819,
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
"step": 50
},
{
- "epoch": 1.03,
- "learning_rate": 0.00019349489795918368,
- "loss": 1.8647,
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
"step": 51
},
{
- "epoch": 1.05,
- "learning_rate": 0.0001933673469387755,
- "loss": 1.8196,
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
"step": 52
},
{
- "epoch": 1.07,
- "learning_rate": 0.00019323979591836737,
- "loss": 1.8027,
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
"step": 53
},
{
- "epoch": 1.09,
- "learning_rate": 0.00019311224489795917,
- "loss": 1.8927,
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
"step": 54
},
{
- "epoch": 1.11,
- "learning_rate": 0.00019298469387755103,
- "loss": 1.8481,
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
"step": 55
},
{
- "epoch": 1.13,
- "learning_rate": 0.00019285714285714286,
- "loss": 1.7781,
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
"step": 56
},
{
- "epoch": 1.15,
- "learning_rate": 0.00019272959183673472,
- "loss": 1.8101,
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
"step": 57
},
{
- "epoch": 1.17,
- "learning_rate": 0.00019260204081632653,
- "loss": 1.7257,
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
"step": 58
},
{
- "epoch": 1.19,
- "learning_rate": 0.00019247448979591838,
- "loss": 1.8185,
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
"step": 59
},
{
- "epoch": 1.21,
- "learning_rate": 0.00019234693877551021,
- "loss": 1.8557,
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
"step": 60
},
{
- "epoch": 1.23,
- "learning_rate": 0.00019221938775510204,
- "loss": 1.7418,
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
"step": 61
},
{
- "epoch": 1.25,
- "learning_rate": 0.00019209183673469388,
- "loss": 1.6879,
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
"step": 62
},
{
- "epoch": 1.27,
- "learning_rate": 0.00019196428571428573,
- "loss": 1.7651,
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
"step": 63
},
{
- "epoch": 1.29,
- "learning_rate": 0.00019183673469387756,
- "loss": 1.7759,
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
"step": 64
},
{
- "epoch": 1.32,
- "learning_rate": 0.0001917091836734694,
- "loss": 1.7691,
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
"step": 65
},
{
- "epoch": 1.34,
- "learning_rate": 0.00019158163265306123,
- "loss": 1.7794,
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
"step": 66
},
{
- "epoch": 1.36,
- "learning_rate": 0.00019145408163265306,
- "loss": 1.8152,
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
"step": 67
},
{
- "epoch": 1.38,
- "learning_rate": 0.00019132653061224492,
- "loss": 1.8052,
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
"step": 68
},
{
- "epoch": 1.4,
- "learning_rate": 0.00019119897959183675,
- "loss": 1.8054,
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
"step": 69
},
{
- "epoch": 1.42,
- "learning_rate": 0.00019107142857142858,
- "loss": 1.8114,
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
"step": 70
},
{
- "epoch": 1.44,
- "learning_rate": 0.0001909438775510204,
- "loss": 1.7749,
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
"step": 71
},
{
- "epoch": 1.46,
- "learning_rate": 0.00019081632653061227,
- "loss": 1.777,
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
"step": 72
},
{
- "epoch": 1.48,
- "learning_rate": 0.0001906887755102041,
- "loss": 1.7896,
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
"step": 73
},
{
- "epoch": 1.5,
- "learning_rate": 0.00019056122448979593,
- "loss": 1.8335,
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
"step": 74
},
{
- "epoch": 1.52,
- "learning_rate": 0.00019043367346938776,
- "loss": 1.8155,
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
"step": 75
},
{
- "epoch": 1.54,
- "learning_rate": 0.00019030612244897962,
- "loss": 1.8224,
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
"step": 76
},
{
- "epoch": 1.56,
- "learning_rate": 0.00019017857142857142,
- "loss": 1.7889,
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
"step": 77
},
{
- "epoch": 1.58,
- "learning_rate": 0.00019005102040816328,
- "loss": 1.8866,
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
"step": 78
},
{
- "epoch": 1.6,
- "learning_rate": 0.0001899234693877551,
- "loss": 1.8439,
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
"step": 79
},
{
- "epoch": 1.62,
- "learning_rate": 0.00018979591836734697,
- "loss": 1.7906,
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
"step": 80
},
{
- "epoch": 1.64,
- "learning_rate": 0.00018966836734693877,
- "loss": 1.8627,
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
"step": 81
},
{
- "epoch": 1.66,
- "learning_rate": 0.00018954081632653063,
- "loss": 1.7497,
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
"step": 82
},
{
- "epoch": 1.68,
- "learning_rate": 0.00018941326530612246,
- "loss": 1.7936,
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
"step": 83
},
{
- "epoch": 1.7,
- "learning_rate": 0.0001892857142857143,
- "loss": 1.8341,
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
"step": 84
},
{
- "epoch": 1.72,
- "learning_rate": 0.00018915816326530612,
- "loss": 1.7868,
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
"step": 85
},
{
- "epoch": 1.74,
- "learning_rate": 0.00018903061224489798,
- "loss": 1.7493,
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
"step": 86
},
{
- "epoch": 1.76,
- "learning_rate": 0.0001889030612244898,
- "loss": 1.7926,
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
"step": 87
},
{
- "epoch": 1.78,
- "learning_rate": 0.00018877551020408164,
- "loss": 1.8278,
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
"step": 88
},
{
- "epoch": 1.8,
- "learning_rate": 0.00018864795918367347,
- "loss": 1.7387,
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
"step": 89
},
{
- "epoch": 1.82,
- "learning_rate": 0.0001885204081632653,
- "loss": 1.7669,
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
"step": 90
},
{
- "epoch": 1.84,
- "learning_rate": 0.00018839285714285716,
- "loss": 1.7686,
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
"step": 91
},
{
- "epoch": 1.86,
- "learning_rate": 0.000188265306122449,
- "loss": 1.7759,
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
"step": 92
},
{
- "epoch": 1.88,
- "learning_rate": 0.00018813775510204082,
- "loss": 1.7016,
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
"step": 93
},
{
- "epoch": 1.9,
- "learning_rate": 0.00018801020408163265,
- "loss": 1.8123,
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
"step": 94
},
{
- "epoch": 1.92,
- "learning_rate": 0.0001878826530612245,
- "loss": 1.8315,
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
"step": 95
},
{
- "epoch": 1.94,
- "learning_rate": 0.00018775510204081634,
- "loss": 1.7679,
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
"step": 96
},
{
- "epoch": 1.96,
- "learning_rate": 0.00018762755102040817,
- "loss": 1.7874,
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
"step": 97
},
{
- "epoch": 1.98,
- "learning_rate": 0.0001875,
- "loss": 1.8008,
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
"step": 98
},
{
- "epoch": 2.0,
- "learning_rate": 0.00018737244897959186,
- "loss": 1.7177,
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
"step": 99
},
{
- "epoch": 2.02,
- "learning_rate": 0.00018724489795918367,
- "loss": 1.7272,
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
"step": 100
},
{
- "epoch": 2.04,
- "learning_rate": 0.00018711734693877552,
- "loss": 1.7848,
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
"step": 101
},
{
- "epoch": 2.06,
- "learning_rate": 0.00018698979591836735,
- "loss": 1.744,
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
"step": 102
},
{
- "epoch": 2.08,
- "learning_rate": 0.00018686224489795919,
- "loss": 1.7005,
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
"step": 103
},
{
- "epoch": 2.1,
- "learning_rate": 0.00018673469387755102,
- "loss": 1.8247,
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
"step": 104
},
{
- "epoch": 2.12,
- "learning_rate": 0.00018660714285714287,
- "loss": 1.6855,
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
"step": 105
},
{
- "epoch": 2.14,
- "learning_rate": 0.0001864795918367347,
- "loss": 1.7627,
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
"step": 106
},
{
- "epoch": 2.17,
- "learning_rate": 0.00018635204081632654,
- "loss": 1.7564,
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
"step": 107
},
{
- "epoch": 2.19,
- "learning_rate": 0.00018622448979591837,
- "loss": 1.8237,
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
"step": 108
},
{
- "epoch": 2.21,
- "learning_rate": 0.00018609693877551022,
- "loss": 1.7421,
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
"step": 109
},
{
- "epoch": 2.23,
- "learning_rate": 0.00018596938775510206,
- "loss": 1.7517,
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
"step": 110
},
{
- "epoch": 2.25,
- "learning_rate": 0.0001858418367346939,
- "loss": 1.7515,
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
"step": 111
},
{
- "epoch": 2.27,
- "learning_rate": 0.00018571428571428572,
- "loss": 1.7842,
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
"step": 112
},
{
- "epoch": 2.29,
- "learning_rate": 0.00018558673469387755,
- "loss": 1.8001,
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
"step": 113
},
{
- "epoch": 2.31,
- "learning_rate": 0.0001854591836734694,
- "loss": 1.7653,
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
"step": 114
},
{
- "epoch": 2.33,
- "learning_rate": 0.00018533163265306124,
- "loss": 1.694,
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
"step": 115
},
{
- "epoch": 2.35,
- "learning_rate": 0.00018520408163265307,
- "loss": 1.7457,
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
"step": 116
},
{
- "epoch": 2.37,
- "learning_rate": 0.0001850765306122449,
- "loss": 1.7899,
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
"step": 117
},
{
- "epoch": 2.39,
- "learning_rate": 0.00018494897959183676,
- "loss": 1.7473,
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
"step": 118
},
{
- "epoch": 2.41,
- "learning_rate": 0.0001848214285714286,
- "loss": 1.6639,
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
"step": 119
},
{
- "epoch": 2.43,
- "learning_rate": 0.00018469387755102042,
- "loss": 1.762,
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
"step": 120
},
{
- "epoch": 2.45,
- "learning_rate": 0.00018456632653061225,
- "loss": 1.7378,
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
"step": 121
},
{
- "epoch": 2.47,
- "learning_rate": 0.0001844387755102041,
- "loss": 1.672,
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
"step": 122
},
{
- "epoch": 2.49,
- "learning_rate": 0.0001843112244897959,
- "loss": 1.7267,
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
"step": 123
},
{
- "epoch": 2.51,
- "learning_rate": 0.00018418367346938777,
- "loss": 1.7825,
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
"step": 124
},
{
- "epoch": 2.53,
- "learning_rate": 0.0001840561224489796,
- "loss": 1.7566,
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
"step": 125
},
{
- "epoch": 2.55,
- "learning_rate": 0.00018392857142857143,
- "loss": 1.8169,
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
"step": 126
},
{
- "epoch": 2.57,
- "learning_rate": 0.00018380102040816326,
- "loss": 1.6801,
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
"step": 127
},
{
- "epoch": 2.59,
- "learning_rate": 0.00018367346938775512,
- "loss": 1.7292,
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
"step": 128
},
{
- "epoch": 2.61,
- "learning_rate": 0.00018354591836734695,
- "loss": 1.737,
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
"step": 129
},
{
- "epoch": 2.63,
- "learning_rate": 0.00018341836734693878,
- "loss": 1.7696,
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
"step": 130
},
{
- "epoch": 2.65,
- "learning_rate": 0.0001832908163265306,
- "loss": 1.7239,
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
"step": 131
},
{
- "epoch": 2.67,
- "learning_rate": 0.00018316326530612247,
- "loss": 1.7441,
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
"step": 132
},
{
- "epoch": 2.69,
- "learning_rate": 0.0001830357142857143,
- "loss": 1.7825,
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
"step": 133
},
{
- "epoch": 2.71,
- "learning_rate": 0.00018290816326530613,
- "loss": 1.7411,
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
"step": 134
},
{
- "epoch": 2.73,
- "learning_rate": 0.00018278061224489796,
- "loss": 1.7119,
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
"step": 135
},
{
- "epoch": 2.75,
- "learning_rate": 0.0001826530612244898,
- "loss": 1.7443,
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
"step": 136
},
{
- "epoch": 2.77,
- "learning_rate": 0.00018252551020408165,
- "loss": 1.7197,
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
"step": 137
},
{
- "epoch": 2.79,
- "learning_rate": 0.00018239795918367348,
- "loss": 1.7273,
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
"step": 138
},
{
- "epoch": 2.81,
- "learning_rate": 0.0001822704081632653,
- "loss": 1.7681,
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
"step": 139
},
{
- "epoch": 2.83,
- "learning_rate": 0.00018214285714285714,
- "loss": 1.8088,
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
"step": 140
},
{
- "epoch": 2.85,
- "learning_rate": 0.000182015306122449,
- "loss": 1.7301,
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
"step": 141
},
{
- "epoch": 2.87,
- "learning_rate": 0.00018188775510204083,
- "loss": 1.6853,
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
"step": 142
},
{
- "epoch": 2.89,
- "learning_rate": 0.00018176020408163266,
- "loss": 1.6966,
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
"step": 143
},
{
- "epoch": 2.91,
- "learning_rate": 0.0001816326530612245,
- "loss": 1.7938,
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
"step": 144
},
{
- "epoch": 2.93,
- "learning_rate": 0.00018150510204081635,
- "loss": 1.7639,
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
"step": 145
},
{
- "epoch": 2.95,
- "learning_rate": 0.00018137755102040816,
- "loss": 1.7527,
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
"step": 146
},
{
- "epoch": 2.97,
- "learning_rate": 0.00018125000000000001,
- "loss": 1.7386,
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
"step": 147
},
{
- "epoch": 2.99,
- "learning_rate": 0.00018112244897959185,
- "loss": 1.7223,
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
"step": 148
},
{
- "epoch": 3.01,
- "learning_rate": 0.00018099489795918368,
- "loss": 1.7571,
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
"step": 149
},
{
- "epoch": 3.04,
- "learning_rate": 0.0001808673469387755,
- "loss": 1.7054,
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
"step": 150
},
{
- "epoch": 3.06,
- "learning_rate": 0.00018073979591836737,
- "loss": 1.6581,
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
"step": 151
},
{
- "epoch": 3.08,
- "learning_rate": 0.00018061224489795917,
- "loss": 1.681,
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
"step": 152
},
{
- "epoch": 3.1,
- "learning_rate": 0.00018048469387755103,
- "loss": 1.7425,
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
"step": 153
},
{
- "epoch": 3.12,
- "learning_rate": 0.00018035714285714286,
- "loss": 1.7108,
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
"step": 154
},
{
- "epoch": 3.14,
- "learning_rate": 0.00018022959183673472,
- "loss": 1.7194,
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
"step": 155
},
{
- "epoch": 3.16,
- "learning_rate": 0.00018010204081632655,
- "loss": 1.6953,
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
"step": 156
},
{
- "epoch": 3.18,
- "learning_rate": 0.00017997448979591838,
- "loss": 1.669,
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
"step": 157
},
{
- "epoch": 3.2,
- "learning_rate": 0.0001798469387755102,
- "loss": 1.744,
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
"step": 158
},
{
- "epoch": 3.22,
- "learning_rate": 0.00017971938775510204,
- "loss": 1.6467,
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
"step": 159
},
{
- "epoch": 3.24,
- "learning_rate": 0.0001795918367346939,
- "loss": 1.7103,
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
"step": 160
},
{
- "epoch": 3.26,
- "learning_rate": 0.00017946428571428573,
- "loss": 1.6662,
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
"step": 161
},
{
- "epoch": 3.28,
- "learning_rate": 0.00017933673469387756,
- "loss": 1.6657,
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
"step": 162
},
{
- "epoch": 3.3,
- "learning_rate": 0.0001792091836734694,
- "loss": 1.791,
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
"step": 163
},
{
- "epoch": 3.32,
- "learning_rate": 0.00017908163265306125,
- "loss": 1.7704,
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
"step": 164
},
{
- "epoch": 3.34,
- "learning_rate": 0.00017895408163265305,
- "loss": 1.7229,
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
"step": 165
},
{
- "epoch": 3.36,
- "learning_rate": 0.0001788265306122449,
- "loss": 1.76,
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
"step": 166
},
{
- "epoch": 3.38,
- "learning_rate": 0.00017869897959183674,
- "loss": 1.6482,
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
"step": 167
},
{
- "epoch": 3.4,
- "learning_rate": 0.0001785714285714286,
- "loss": 1.8076,
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
"step": 168
},
{
- "epoch": 3.42,
- "learning_rate": 0.0001784438775510204,
- "loss": 1.7368,
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
"step": 169
},
{
- "epoch": 3.44,
- "learning_rate": 0.00017831632653061226,
- "loss": 1.6264,
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
"step": 170
},
{
- "epoch": 3.46,
- "learning_rate": 0.0001781887755102041,
- "loss": 1.6289,
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
"step": 171
},
{
- "epoch": 3.48,
- "learning_rate": 0.00017806122448979592,
- "loss": 1.7913,
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
"step": 172
},
{
- "epoch": 3.5,
- "learning_rate": 0.00017793367346938775,
- "loss": 1.6985,
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
"step": 173
},
{
- "epoch": 3.52,
- "learning_rate": 0.0001778061224489796,
- "loss": 1.6936,
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
"step": 174
},
{
- "epoch": 3.54,
- "learning_rate": 0.00017767857142857141,
- "loss": 1.8068,
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
"step": 175
},
{
- "epoch": 3.56,
- "learning_rate": 0.00017755102040816327,
- "loss": 1.7243,
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
"step": 176
},
{
- "epoch": 3.58,
- "learning_rate": 0.0001774234693877551,
- "loss": 1.6893,
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
"step": 177
},
{
- "epoch": 3.6,
- "learning_rate": 0.00017729591836734696,
- "loss": 1.8122,
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
"step": 178
},
{
- "epoch": 3.62,
- "learning_rate": 0.0001771683673469388,
- "loss": 1.6562,
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
"step": 179
},
{
- "epoch": 3.64,
- "learning_rate": 0.00017704081632653062,
- "loss": 1.6999,
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
"step": 180
},
{
- "epoch": 3.66,
- "learning_rate": 0.00017691326530612245,
- "loss": 1.7229,
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
"step": 181
},
{
- "epoch": 3.68,
- "learning_rate": 0.00017678571428571428,
- "loss": 1.6764,
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
"step": 182
},
{
- "epoch": 3.7,
- "learning_rate": 0.00017665816326530614,
- "loss": 1.6982,
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
"step": 183
},
{
- "epoch": 3.72,
- "learning_rate": 0.00017653061224489797,
- "loss": 1.696,
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
"step": 184
},
{
- "epoch": 3.74,
- "learning_rate": 0.0001764030612244898,
- "loss": 1.6797,
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
"step": 185
},
{
- "epoch": 3.76,
- "learning_rate": 0.00017627551020408164,
- "loss": 1.637,
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
"step": 186
},
{
- "epoch": 3.78,
- "learning_rate": 0.0001761479591836735,
- "loss": 1.7074,
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
"step": 187
},
{
- "epoch": 3.8,
- "learning_rate": 0.0001760204081632653,
- "loss": 1.705,
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
"step": 188
},
{
- "epoch": 3.82,
- "learning_rate": 0.00017589285714285716,
- "loss": 1.6153,
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
"step": 189
},
{
- "epoch": 3.84,
- "learning_rate": 0.00017576530612244899,
- "loss": 1.7354,
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
"step": 190
},
{
- "epoch": 3.86,
- "learning_rate": 0.00017563775510204084,
- "loss": 1.6941,
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
"step": 191
},
{
- "epoch": 3.88,
- "learning_rate": 0.00017551020408163265,
- "loss": 1.7231,
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
"step": 192
},
{
- "epoch": 3.91,
- "learning_rate": 0.0001753826530612245,
- "loss": 1.7663,
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
"step": 193
},
{
- "epoch": 3.93,
- "learning_rate": 0.00017525510204081634,
- "loss": 1.6532,
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
"step": 194
},
{
- "epoch": 3.95,
- "learning_rate": 0.00017512755102040817,
- "loss": 1.7115,
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
"step": 195
},
{
- "epoch": 3.97,
- "learning_rate": 0.000175,
- "loss": 1.6955,
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
"step": 196
},
{
- "epoch": 3.99,
- "learning_rate": 0.00017487244897959186,
- "loss": 1.6863,
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
"step": 197
},
{
- "epoch": 4.01,
- "learning_rate": 0.00017474489795918366,
- "loss": 1.7012,
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
"step": 198
},
{
- "epoch": 4.03,
- "learning_rate": 0.00017461734693877552,
- "loss": 1.5927,
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
"step": 199
},
{
- "epoch": 4.05,
- "learning_rate": 0.00017448979591836735,
- "loss": 1.6272,
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
"step": 200
},
{
- "epoch": 4.07,
- "learning_rate": 0.00017436224489795918,
- "loss": 1.5994,
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
"step": 201
},
{
- "epoch": 4.09,
- "learning_rate": 0.00017423469387755104,
- "loss": 1.7141,
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
"step": 202
},
{
- "epoch": 4.11,
- "learning_rate": 0.00017410714285714287,
- "loss": 1.7547,
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
"step": 203
},
{
- "epoch": 4.13,
- "learning_rate": 0.0001739795918367347,
- "loss": 1.6254,
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
"step": 204
},
{
- "epoch": 4.15,
- "learning_rate": 0.00017385204081632653,
- "loss": 1.6686,
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
"step": 205
},
{
- "epoch": 4.17,
- "learning_rate": 0.0001737244897959184,
- "loss": 1.6684,
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
"step": 206
},
{
- "epoch": 4.19,
- "learning_rate": 0.00017359693877551022,
- "loss": 1.6724,
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
"step": 207
},
{
- "epoch": 4.21,
- "learning_rate": 0.00017346938775510205,
- "loss": 1.7361,
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
"step": 208
},
{
- "epoch": 4.23,
- "learning_rate": 0.00017334183673469388,
- "loss": 1.7167,
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
"step": 209
},
{
- "epoch": 4.25,
- "learning_rate": 0.00017321428571428574,
- "loss": 1.7226,
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
"step": 210
},
{
- "epoch": 4.27,
- "learning_rate": 0.00017308673469387754,
- "loss": 1.7133,
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
"step": 211
},
{
- "epoch": 4.29,
- "learning_rate": 0.0001729591836734694,
- "loss": 1.649,
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
"step": 212
},
{
- "epoch": 4.31,
- "learning_rate": 0.00017283163265306123,
- "loss": 1.7104,
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
"step": 213
},
{
- "epoch": 4.33,
- "learning_rate": 0.00017270408163265306,
- "loss": 1.6861,
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
"step": 214
},
{
- "epoch": 4.35,
- "learning_rate": 0.0001725765306122449,
- "loss": 1.648,
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
"step": 215
},
{
- "epoch": 4.37,
- "learning_rate": 0.00017244897959183675,
- "loss": 1.6215,
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
"step": 216
},
{
- "epoch": 4.39,
- "learning_rate": 0.00017232142857142858,
- "loss": 1.6334,
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
"step": 217
},
{
- "epoch": 4.41,
- "learning_rate": 0.0001721938775510204,
- "loss": 1.6283,
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
"step": 218
},
{
- "epoch": 4.43,
- "learning_rate": 0.00017206632653061224,
- "loss": 1.6462,
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
"step": 219
},
{
- "epoch": 4.45,
- "learning_rate": 0.0001719387755102041,
- "loss": 1.7233,
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
"step": 220
},
{
- "epoch": 4.47,
- "learning_rate": 0.0001718112244897959,
- "loss": 1.7839,
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
"step": 221
},
{
- "epoch": 4.49,
- "learning_rate": 0.00017168367346938776,
- "loss": 1.7204,
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
"step": 222
},
{
- "epoch": 4.51,
- "learning_rate": 0.0001715561224489796,
- "loss": 1.7671,
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
"step": 223
},
{
- "epoch": 4.53,
- "learning_rate": 0.00017142857142857143,
- "loss": 1.6824,
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
"step": 224
},
{
- "epoch": 4.55,
- "learning_rate": 0.00017130102040816328,
- "loss": 1.7068,
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
"step": 225
},
{
- "epoch": 4.57,
- "learning_rate": 0.00017117346938775511,
- "loss": 1.6515,
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
"step": 226
},
{
- "epoch": 4.59,
- "learning_rate": 0.00017104591836734694,
- "loss": 1.6586,
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
"step": 227
},
{
- "epoch": 4.61,
- "learning_rate": 0.00017091836734693878,
- "loss": 1.6355,
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
"step": 228
},
{
- "epoch": 4.63,
- "learning_rate": 0.00017079081632653063,
- "loss": 1.7173,
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
"step": 229
},
{
- "epoch": 4.65,
- "learning_rate": 0.00017066326530612246,
- "loss": 1.6585,
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
"step": 230
},
{
- "epoch": 4.67,
- "learning_rate": 0.0001705357142857143,
- "loss": 1.5856,
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
"step": 231
},
{
- "epoch": 4.69,
- "learning_rate": 0.00017040816326530613,
- "loss": 1.5923,
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
"step": 232
},
{
- "epoch": 4.71,
- "learning_rate": 0.00017028061224489798,
- "loss": 1.7128,
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
"step": 233
},
{
- "epoch": 4.73,
- "learning_rate": 0.0001701530612244898,
- "loss": 1.6971,
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
"step": 234
},
{
- "epoch": 4.75,
- "learning_rate": 0.00017002551020408165,
- "loss": 1.6416,
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
"step": 235
},
{
- "epoch": 4.78,
- "learning_rate": 0.00016989795918367348,
- "loss": 1.645,
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
"step": 236
},
{
- "epoch": 4.8,
- "learning_rate": 0.0001697704081632653,
- "loss": 1.6792,
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
"step": 237
},
{
- "epoch": 4.82,
- "learning_rate": 0.00016964285714285714,
- "loss": 1.6522,
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
"step": 238
},
{
- "epoch": 4.84,
- "learning_rate": 0.000169515306122449,
- "loss": 1.6315,
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
"step": 239
},
{
- "epoch": 4.86,
- "learning_rate": 0.00016938775510204083,
- "loss": 1.6622,
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
"step": 240
},
{
- "epoch": 4.88,
- "learning_rate": 0.00016926020408163266,
- "loss": 1.6566,
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
"step": 241
},
{
- "epoch": 4.9,
- "learning_rate": 0.0001691326530612245,
- "loss": 1.7141,
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
"step": 242
},
{
- "epoch": 4.92,
- "learning_rate": 0.00016900510204081635,
- "loss": 1.5873,
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
"step": 243
},
{
- "epoch": 4.94,
- "learning_rate": 0.00016887755102040818,
- "loss": 1.6571,
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
"step": 244
},
{
- "epoch": 4.96,
- "learning_rate": 0.00016875,
- "loss": 1.6829,
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
"step": 245
},
{
- "epoch": 4.98,
- "learning_rate": 0.00016862244897959184,
- "loss": 1.6935,
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
"step": 246
},
{
- "epoch": 5.0,
- "learning_rate": 0.00016849489795918367,
- "loss": 1.6782,
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
"step": 247
},
{
- "epoch": 5.02,
- "learning_rate": 0.00016836734693877553,
- "loss": 1.622,
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
"step": 248
},
{
- "epoch": 5.04,
- "learning_rate": 0.00016823979591836736,
- "loss": 1.6596,
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
"step": 249
},
{
- "epoch": 5.06,
- "learning_rate": 0.0001681122448979592,
- "loss": 1.5821,
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
"step": 250
},
{
- "epoch": 5.08,
- "learning_rate": 0.00016798469387755102,
- "loss": 1.7292,
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
"step": 251
},
{
- "epoch": 5.1,
- "learning_rate": 0.00016785714285714288,
- "loss": 1.646,
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
"step": 252
},
{
- "epoch": 5.12,
- "learning_rate": 0.0001677295918367347,
- "loss": 1.6969,
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
"step": 253
},
{
- "epoch": 5.14,
- "learning_rate": 0.00016760204081632654,
- "loss": 1.6082,
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
"step": 254
},
{
- "epoch": 5.16,
- "learning_rate": 0.00016747448979591837,
- "loss": 1.5843,
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
"step": 255
},
{
- "epoch": 5.18,
- "learning_rate": 0.00016734693877551023,
- "loss": 1.6827,
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
"step": 256
},
{
- "epoch": 5.2,
- "learning_rate": 0.00016721938775510203,
- "loss": 1.5824,
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
"step": 257
},
{
- "epoch": 5.22,
- "learning_rate": 0.0001670918367346939,
- "loss": 1.6795,
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
"step": 258
},
{
- "epoch": 5.24,
- "learning_rate": 0.00016696428571428572,
- "loss": 1.5639,
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
"step": 259
},
{
- "epoch": 5.26,
- "learning_rate": 0.00016683673469387755,
- "loss": 1.592,
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
"step": 260
},
{
- "epoch": 5.28,
- "learning_rate": 0.00016670918367346938,
- "loss": 1.65,
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
"step": 261
},
{
- "epoch": 5.3,
- "learning_rate": 0.00016658163265306124,
- "loss": 1.5592,
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
"step": 262
},
{
- "epoch": 5.32,
- "learning_rate": 0.00016645408163265305,
- "loss": 1.5091,
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
"step": 263
},
{
- "epoch": 5.34,
- "learning_rate": 0.0001663265306122449,
- "loss": 1.6138,
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
"step": 264
},
{
- "epoch": 5.36,
- "learning_rate": 0.00016619897959183673,
- "loss": 1.625,
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
"step": 265
},
{
- "epoch": 5.38,
- "learning_rate": 0.0001660714285714286,
- "loss": 1.5757,
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
"step": 266
},
{
- "epoch": 5.4,
- "learning_rate": 0.00016594387755102042,
- "loss": 1.6372,
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
"step": 267
},
{
- "epoch": 5.42,
- "learning_rate": 0.00016581632653061225,
- "loss": 1.5891,
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
"step": 268
},
{
- "epoch": 5.44,
- "learning_rate": 0.00016568877551020409,
- "loss": 1.6893,
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
"step": 269
},
{
- "epoch": 5.46,
- "learning_rate": 0.00016556122448979592,
- "loss": 1.6662,
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
"step": 270
},
{
- "epoch": 5.48,
- "learning_rate": 0.00016543367346938777,
- "loss": 1.7132,
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
"step": 271
},
{
- "epoch": 5.5,
- "learning_rate": 0.0001653061224489796,
- "loss": 1.5835,
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
"step": 272
},
{
- "epoch": 5.52,
- "learning_rate": 0.00016517857142857144,
- "loss": 1.6342,
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
"step": 273
},
{
- "epoch": 5.54,
- "learning_rate": 0.00016505102040816327,
- "loss": 1.6717,
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
"step": 274
},
{
- "epoch": 5.56,
- "learning_rate": 0.00016492346938775512,
- "loss": 1.6248,
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
"step": 275
},
{
- "epoch": 5.58,
- "learning_rate": 0.00016479591836734696,
- "loss": 1.6117,
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
"step": 276
},
{
- "epoch": 5.6,
- "learning_rate": 0.0001646683673469388,
- "loss": 1.6798,
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
"step": 277
},
{
- "epoch": 5.63,
- "learning_rate": 0.00016454081632653062,
- "loss": 1.6406,
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
"step": 278
},
{
- "epoch": 5.65,
- "learning_rate": 0.00016441326530612248,
- "loss": 1.6512,
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
"step": 279
},
{
- "epoch": 5.67,
- "learning_rate": 0.00016428571428571428,
- "loss": 1.6102,
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
"step": 280
},
{
- "epoch": 5.69,
- "learning_rate": 0.00016415816326530614,
- "loss": 1.6113,
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
"step": 281
},
{
- "epoch": 5.71,
- "learning_rate": 0.00016403061224489797,
- "loss": 1.7116,
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
"step": 282
},
{
- "epoch": 5.73,
- "learning_rate": 0.0001639030612244898,
- "loss": 1.6846,
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
"step": 283
},
{
- "epoch": 5.75,
- "learning_rate": 0.00016377551020408163,
- "loss": 1.6911,
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
"step": 284
},
{
- "epoch": 5.77,
- "learning_rate": 0.0001636479591836735,
- "loss": 1.6202,
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
"step": 285
},
{
- "epoch": 5.79,
- "learning_rate": 0.0001635204081632653,
- "loss": 1.5715,
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
"step": 286
},
{
- "epoch": 5.81,
- "learning_rate": 0.00016339285714285715,
- "loss": 1.6461,
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
"step": 287
},
{
- "epoch": 5.83,
- "learning_rate": 0.00016326530612244898,
- "loss": 1.6624,
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
"step": 288
},
{
- "epoch": 5.85,
- "learning_rate": 0.00016313775510204084,
- "loss": 1.6535,
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
"step": 289
},
{
- "epoch": 5.87,
- "learning_rate": 0.00016301020408163267,
- "loss": 1.6275,
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
"step": 290
},
{
- "epoch": 5.89,
- "learning_rate": 0.0001628826530612245,
- "loss": 1.6636,
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
"step": 291
},
{
- "epoch": 5.91,
- "learning_rate": 0.00016275510204081633,
- "loss": 1.6546,
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
"step": 292
},
{
- "epoch": 5.93,
- "learning_rate": 0.00016262755102040816,
- "loss": 1.7274,
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
"step": 293
},
{
- "epoch": 5.95,
- "learning_rate": 0.00016250000000000002,
- "loss": 1.5901,
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
"step": 294
},
{
- "epoch": 5.97,
- "learning_rate": 0.00016237244897959185,
- "loss": 1.6046,
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
"step": 295
},
{
- "epoch": 5.99,
- "learning_rate": 0.00016224489795918368,
- "loss": 1.5828,
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
"step": 296
},
{
- "epoch": 6.01,
- "learning_rate": 0.0001621173469387755,
- "loss": 1.6435,
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
"step": 297
},
{
- "epoch": 6.03,
- "learning_rate": 0.00016198979591836737,
- "loss": 1.6263,
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
"step": 298
},
{
- "epoch": 6.05,
- "learning_rate": 0.00016186224489795917,
- "loss": 1.4944,
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
"step": 299
},
{
- "epoch": 6.07,
- "learning_rate": 0.00016173469387755103,
- "loss": 1.6286,
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
"step": 300
},
{
- "epoch": 6.09,
- "learning_rate": 0.00016160714285714286,
- "loss": 1.694,
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
"step": 301
},
{
- "epoch": 6.11,
- "learning_rate": 0.00016147959183673472,
- "loss": 1.6197,
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
"step": 302
},
{
- "epoch": 6.13,
- "learning_rate": 0.00016135204081632652,
- "loss": 1.5597,
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
"step": 303
},
{
- "epoch": 6.15,
- "learning_rate": 0.00016122448979591838,
- "loss": 1.5487,
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
"step": 304
},
{
- "epoch": 6.17,
- "learning_rate": 0.0001610969387755102,
- "loss": 1.5769,
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
"step": 305
},
{
- "epoch": 6.19,
- "learning_rate": 0.00016096938775510204,
- "loss": 1.6367,
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
"step": 306
},
{
- "epoch": 6.21,
- "learning_rate": 0.00016084183673469388,
- "loss": 1.583,
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
"step": 307
},
{
- "epoch": 6.23,
- "learning_rate": 0.00016071428571428573,
- "loss": 1.6201,
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
"step": 308
},
{
- "epoch": 6.25,
- "learning_rate": 0.00016058673469387754,
- "loss": 1.6586,
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
"step": 309
},
{
- "epoch": 6.27,
- "learning_rate": 0.0001604591836734694,
- "loss": 1.6711,
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
"step": 310
},
{
- "epoch": 6.29,
- "learning_rate": 0.00016033163265306123,
- "loss": 1.6402,
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
"step": 311
},
{
- "epoch": 6.31,
- "learning_rate": 0.00016020408163265306,
- "loss": 1.5247,
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
"step": 312
},
{
- "epoch": 6.33,
- "learning_rate": 0.00016007653061224491,
- "loss": 1.5356,
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
"step": 313
},
{
- "epoch": 6.35,
- "learning_rate": 0.00015994897959183675,
- "loss": 1.564,
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
"step": 314
},
{
- "epoch": 6.37,
- "learning_rate": 0.00015982142857142858,
- "loss": 1.563,
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
"step": 315
},
{
- "epoch": 6.39,
- "learning_rate": 0.0001596938775510204,
- "loss": 1.5198,
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
"step": 316
},
{
- "epoch": 6.41,
- "learning_rate": 0.00015956632653061227,
- "loss": 1.6558,
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
"step": 317
},
{
- "epoch": 6.43,
- "learning_rate": 0.0001594387755102041,
- "loss": 1.5534,
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
"step": 318
},
{
- "epoch": 6.45,
- "learning_rate": 0.00015931122448979593,
- "loss": 1.6239,
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
"step": 319
},
{
- "epoch": 6.47,
- "learning_rate": 0.00015918367346938776,
- "loss": 1.5645,
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
"step": 320
},
{
- "epoch": 6.5,
- "learning_rate": 0.00015905612244897962,
- "loss": 1.5713,
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
"step": 321
},
{
- "epoch": 6.52,
- "learning_rate": 0.00015892857142857142,
- "loss": 1.6176,
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
"step": 322
},
{
- "epoch": 6.54,
- "learning_rate": 0.00015880102040816328,
- "loss": 1.502,
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
"step": 323
},
{
- "epoch": 6.56,
- "learning_rate": 0.0001586734693877551,
- "loss": 1.645,
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
"step": 324
},
{
- "epoch": 6.58,
- "learning_rate": 0.00015854591836734697,
- "loss": 1.5904,
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
"step": 325
},
{
- "epoch": 6.6,
- "learning_rate": 0.00015841836734693877,
- "loss": 1.6149,
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
"step": 326
},
{
- "epoch": 6.62,
- "learning_rate": 0.00015829081632653063,
- "loss": 1.6757,
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
"step": 327
},
{
- "epoch": 6.64,
- "learning_rate": 0.00015816326530612246,
- "loss": 1.541,
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
"step": 328
},
{
- "epoch": 6.66,
- "learning_rate": 0.0001580357142857143,
- "loss": 1.5898,
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
"step": 329
},
{
- "epoch": 6.68,
- "learning_rate": 0.00015790816326530612,
- "loss": 1.5441,
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
"step": 330
},
{
- "epoch": 6.7,
- "learning_rate": 0.00015778061224489798,
- "loss": 1.61,
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
"step": 331
},
{
- "epoch": 6.72,
- "learning_rate": 0.00015765306122448978,
- "loss": 1.615,
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
"step": 332
},
{
- "epoch": 6.74,
- "learning_rate": 0.00015752551020408164,
- "loss": 1.6575,
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
"step": 333
},
{
- "epoch": 6.76,
- "learning_rate": 0.00015739795918367347,
- "loss": 1.6702,
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
"step": 334
},
{
- "epoch": 6.78,
- "learning_rate": 0.0001572704081632653,
- "loss": 1.6009,
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
"step": 335
},
{
- "epoch": 6.8,
- "learning_rate": 0.00015714285714285716,
- "loss": 1.5568,
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
"step": 336
},
{
- "epoch": 6.82,
- "learning_rate": 0.000157015306122449,
- "loss": 1.619,
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
"step": 337
},
{
- "epoch": 6.84,
- "learning_rate": 0.00015688775510204082,
- "loss": 1.5563,
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
"step": 338
},
{
- "epoch": 6.86,
- "learning_rate": 0.00015676020408163265,
- "loss": 1.6328,
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
"step": 339
},
{
- "epoch": 6.88,
- "learning_rate": 0.0001566326530612245,
- "loss": 1.5726,
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
"step": 340
},
{
- "epoch": 6.9,
- "learning_rate": 0.00015650510204081634,
- "loss": 1.6199,
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
"step": 341
},
{
- "epoch": 6.92,
- "learning_rate": 0.00015637755102040817,
- "loss": 1.5722,
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
"step": 342
},
{
- "epoch": 6.94,
- "learning_rate": 0.00015625,
- "loss": 1.5685,
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
"step": 343
},
{
- "epoch": 6.96,
- "learning_rate": 0.00015612244897959186,
- "loss": 1.5615,
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
"step": 344
},
{
- "epoch": 6.98,
- "learning_rate": 0.00015599489795918366,
- "loss": 1.5994,
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
"step": 345
},
{
- "epoch": 7.0,
- "learning_rate": 0.00015586734693877552,
- "loss": 1.5579,
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
"step": 346
},
{
- "epoch": 7.02,
- "learning_rate": 0.00015573979591836735,
- "loss": 1.547,
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
"step": 347
},
{
- "epoch": 7.04,
- "learning_rate": 0.00015561224489795918,
- "loss": 1.5292,
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
"step": 348
},
{
- "epoch": 7.06,
- "learning_rate": 0.00015548469387755102,
- "loss": 1.6032,
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
"step": 349
},
{
- "epoch": 7.08,
- "learning_rate": 0.00015535714285714287,
- "loss": 1.5149,
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
"step": 350
},
{
- "epoch": 7.1,
- "learning_rate": 0.0001552295918367347,
- "loss": 1.6093,
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
"step": 351
},
{
- "epoch": 7.12,
- "learning_rate": 0.00015510204081632654,
- "loss": 1.5421,
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
"step": 352
},
{
- "epoch": 7.14,
- "learning_rate": 0.00015497448979591837,
- "loss": 1.5733,
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
"step": 353
},
{
- "epoch": 7.16,
- "learning_rate": 0.00015484693877551022,
- "loss": 1.5703,
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
"step": 354
},
{
- "epoch": 7.18,
- "learning_rate": 0.00015471938775510203,
- "loss": 1.6141,
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
"step": 355
},
{
- "epoch": 7.2,
- "learning_rate": 0.00015459183673469389,
- "loss": 1.5526,
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
"step": 356
},
{
- "epoch": 7.22,
- "learning_rate": 0.00015446428571428572,
- "loss": 1.5347,
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
"step": 357
},
{
- "epoch": 7.24,
- "learning_rate": 0.00015433673469387755,
- "loss": 1.5682,
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
"step": 358
},
{
- "epoch": 7.26,
- "learning_rate": 0.0001542091836734694,
- "loss": 1.5292,
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
"step": 359
},
{
- "epoch": 7.28,
- "learning_rate": 0.00015408163265306124,
- "loss": 1.499,
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
"step": 360
},
{
- "epoch": 7.3,
- "learning_rate": 0.00015395408163265307,
- "loss": 1.5624,
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
"step": 361
},
{
- "epoch": 7.32,
- "learning_rate": 0.0001538265306122449,
- "loss": 1.627,
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
"step": 362
},
{
- "epoch": 7.34,
- "learning_rate": 0.00015369897959183676,
- "loss": 1.5327,
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
"step": 363
},
{
- "epoch": 7.37,
- "learning_rate": 0.0001535714285714286,
- "loss": 1.5622,
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
"step": 364
},
{
- "epoch": 7.39,
- "learning_rate": 0.00015344387755102042,
- "loss": 1.5659,
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
"step": 365
},
{
- "epoch": 7.41,
- "learning_rate": 0.00015331632653061225,
- "loss": 1.5019,
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
"step": 366
},
{
- "epoch": 7.43,
- "learning_rate": 0.0001531887755102041,
- "loss": 1.5921,
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
"step": 367
},
{
- "epoch": 7.45,
- "learning_rate": 0.0001530612244897959,
- "loss": 1.5914,
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
"step": 368
},
{
- "epoch": 7.47,
- "learning_rate": 0.00015293367346938777,
- "loss": 1.5045,
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
"step": 369
},
{
- "epoch": 7.49,
- "learning_rate": 0.0001528061224489796,
- "loss": 1.6209,
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
"step": 370
},
{
- "epoch": 7.51,
- "learning_rate": 0.00015267857142857143,
- "loss": 1.5198,
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
"step": 371
},
{
- "epoch": 7.53,
- "learning_rate": 0.00015255102040816326,
- "loss": 1.5363,
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
"step": 372
},
{
- "epoch": 7.55,
- "learning_rate": 0.00015242346938775512,
- "loss": 1.5391,
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
"step": 373
},
{
- "epoch": 7.57,
- "learning_rate": 0.00015229591836734695,
- "loss": 1.4546,
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
"step": 374
},
{
- "epoch": 7.59,
- "learning_rate": 0.00015216836734693878,
- "loss": 1.5546,
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
"step": 375
},
{
- "epoch": 7.61,
- "learning_rate": 0.0001520408163265306,
- "loss": 1.5629,
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
"step": 376
},
{
- "epoch": 7.63,
- "learning_rate": 0.00015191326530612247,
- "loss": 1.6002,
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
"step": 377
},
{
- "epoch": 7.65,
- "learning_rate": 0.00015178571428571427,
- "loss": 1.5543,
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
"step": 378
},
{
- "epoch": 7.67,
- "learning_rate": 0.00015165816326530613,
- "loss": 1.5925,
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
"step": 379
},
{
- "epoch": 7.69,
- "learning_rate": 0.00015153061224489796,
- "loss": 1.5631,
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
"step": 380
},
{
- "epoch": 7.71,
- "learning_rate": 0.0001514030612244898,
- "loss": 1.5677,
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
"step": 381
},
{
- "epoch": 7.73,
- "learning_rate": 0.00015127551020408165,
- "loss": 1.5828,
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
"step": 382
},
{
- "epoch": 7.75,
- "learning_rate": 0.00015114795918367348,
- "loss": 1.6494,
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
"step": 383
},
{
- "epoch": 7.77,
- "learning_rate": 0.0001510204081632653,
- "loss": 1.553,
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
"step": 384
},
{
- "epoch": 7.79,
- "learning_rate": 0.00015089285714285714,
- "loss": 1.6156,
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
"step": 385
},
{
- "epoch": 7.81,
- "learning_rate": 0.000150765306122449,
- "loss": 1.5001,
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
"step": 386
},
{
- "epoch": 7.83,
- "learning_rate": 0.00015063775510204083,
- "loss": 1.5321,
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
"step": 387
},
{
- "epoch": 7.85,
- "learning_rate": 0.00015051020408163266,
- "loss": 1.5307,
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
"step": 388
},
{
- "epoch": 7.87,
- "learning_rate": 0.0001503826530612245,
- "loss": 1.5639,
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
"step": 389
},
{
- "epoch": 7.89,
- "learning_rate": 0.00015025510204081635,
- "loss": 1.517,
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
"step": 390
},
{
- "epoch": 7.91,
- "learning_rate": 0.00015012755102040816,
- "loss": 1.4776,
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
"step": 391
},
{
- "epoch": 7.93,
- "learning_rate": 0.00015000000000000001,
- "loss": 1.5368,
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
"step": 392
},
{
- "epoch": 7.95,
- "learning_rate": 0.00014987244897959184,
- "loss": 1.5636,
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
"step": 393
},
{
- "epoch": 7.97,
- "learning_rate": 0.00014974489795918368,
- "loss": 1.6004,
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
"step": 394
},
{
- "epoch": 7.99,
- "learning_rate": 0.0001496173469387755,
- "loss": 1.5524,
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
"step": 395
},
{
- "epoch": 8.01,
- "learning_rate": 0.00014948979591836736,
- "loss": 1.5307,
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
"step": 396
},
{
- "epoch": 8.03,
- "learning_rate": 0.00014936224489795917,
- "loss": 1.5123,
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
"step": 397
},
{
- "epoch": 8.05,
- "learning_rate": 0.00014923469387755103,
- "loss": 1.5132,
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
"step": 398
},
{
- "epoch": 8.07,
- "learning_rate": 0.00014910714285714286,
- "loss": 1.5109,
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
"step": 399
},
{
- "epoch": 8.09,
- "learning_rate": 0.00014897959183673472,
- "loss": 1.5302,
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
"step": 400
},
{
- "epoch": 8.11,
- "learning_rate": 0.00014885204081632652,
- "loss": 1.5238,
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
"step": 401
},
{
- "epoch": 8.13,
- "learning_rate": 0.00014872448979591838,
- "loss": 1.4781,
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
"step": 402
},
{
- "epoch": 8.15,
- "learning_rate": 0.0001485969387755102,
- "loss": 1.5446,
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
"step": 403
},
{
- "epoch": 8.17,
- "learning_rate": 0.00014846938775510204,
- "loss": 1.5,
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
"step": 404
},
{
- "epoch": 8.19,
- "learning_rate": 0.0001483418367346939,
- "loss": 1.5458,
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
"step": 405
},
{
- "epoch": 8.21,
- "learning_rate": 0.00014821428571428573,
- "loss": 1.5257,
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
"step": 406
},
{
- "epoch": 8.24,
- "learning_rate": 0.00014808673469387756,
- "loss": 1.4607,
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
"step": 407
},
{
- "epoch": 8.26,
- "learning_rate": 0.0001479591836734694,
- "loss": 1.4282,
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
"step": 408
},
{
- "epoch": 8.28,
- "learning_rate": 0.00014783163265306125,
- "loss": 1.4519,
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
"step": 409
},
{
- "epoch": 8.3,
- "learning_rate": 0.00014770408163265305,
- "loss": 1.475,
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
"step": 410
},
{
- "epoch": 8.32,
- "learning_rate": 0.0001475765306122449,
- "loss": 1.5425,
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
"step": 411
},
{
- "epoch": 8.34,
- "learning_rate": 0.00014744897959183674,
- "loss": 1.5407,
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
"step": 412
},
{
- "epoch": 8.36,
- "learning_rate": 0.0001473214285714286,
- "loss": 1.5698,
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
"step": 413
},
{
- "epoch": 8.38,
- "learning_rate": 0.0001471938775510204,
- "loss": 1.4282,
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
"step": 414
},
{
- "epoch": 8.4,
- "learning_rate": 0.00014706632653061226,
- "loss": 1.5301,
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
"step": 415
},
{
- "epoch": 8.42,
- "learning_rate": 0.0001469387755102041,
- "loss": 1.5083,
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
"step": 416
},
{
- "epoch": 8.44,
- "learning_rate": 0.00014681122448979592,
- "loss": 1.5712,
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
"step": 417
},
{
- "epoch": 8.46,
- "learning_rate": 0.00014668367346938775,
- "loss": 1.4363,
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
"step": 418
},
{
- "epoch": 8.48,
- "learning_rate": 0.0001465561224489796,
- "loss": 1.4463,
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
"step": 419
},
{
- "epoch": 8.5,
- "learning_rate": 0.00014642857142857141,
- "loss": 1.4738,
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
"step": 420
},
{
- "epoch": 8.52,
- "learning_rate": 0.00014630102040816327,
- "loss": 1.5396,
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
"step": 421
},
{
- "epoch": 8.54,
- "learning_rate": 0.0001461734693877551,
- "loss": 1.4384,
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
"step": 422
},
{
- "epoch": 8.56,
- "learning_rate": 0.00014604591836734696,
- "loss": 1.5345,
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
"step": 423
},
{
- "epoch": 8.58,
- "learning_rate": 0.0001459183673469388,
- "loss": 1.5355,
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
"step": 424
},
{
- "epoch": 8.6,
- "learning_rate": 0.00014579081632653062,
- "loss": 1.5188,
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
"step": 425
},
{
- "epoch": 8.62,
- "learning_rate": 0.00014566326530612245,
- "loss": 1.5575,
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
"step": 426
},
{
- "epoch": 8.64,
- "learning_rate": 0.00014553571428571428,
- "loss": 1.5279,
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
"step": 427
},
{
- "epoch": 8.66,
- "learning_rate": 0.00014540816326530614,
- "loss": 1.5484,
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
"step": 428
},
{
- "epoch": 8.68,
- "learning_rate": 0.00014528061224489797,
- "loss": 1.4878,
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
"step": 429
},
{
- "epoch": 8.7,
- "learning_rate": 0.0001451530612244898,
- "loss": 1.503,
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
"step": 430
},
{
- "epoch": 8.72,
- "learning_rate": 0.00014502551020408163,
- "loss": 1.4723,
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
"step": 431
},
{
- "epoch": 8.74,
- "learning_rate": 0.0001448979591836735,
- "loss": 1.5579,
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
"step": 432
},
{
- "epoch": 8.76,
- "learning_rate": 0.0001447704081632653,
- "loss": 1.4789,
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
"step": 433
},
{
- "epoch": 8.78,
- "learning_rate": 0.00014464285714285715,
- "loss": 1.5501,
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
"step": 434
},
{
- "epoch": 8.8,
- "learning_rate": 0.00014451530612244899,
- "loss": 1.5204,
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
"step": 435
},
{
- "epoch": 8.82,
- "learning_rate": 0.00014438775510204084,
- "loss": 1.5489,
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
"step": 436
},
{
- "epoch": 8.84,
- "learning_rate": 0.00014426020408163265,
- "loss": 1.5464,
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
"step": 437
},
{
- "epoch": 8.86,
- "learning_rate": 0.0001441326530612245,
- "loss": 1.5896,
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
"step": 438
},
{
- "epoch": 8.88,
- "learning_rate": 0.00014400510204081634,
- "loss": 1.5465,
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
"step": 439
},
{
- "epoch": 8.9,
- "learning_rate": 0.00014387755102040817,
- "loss": 1.5094,
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
"step": 440
},
{
- "epoch": 8.92,
- "learning_rate": 0.00014375,
- "loss": 1.5144,
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
"step": 441
},
{
- "epoch": 8.94,
- "learning_rate": 0.00014362244897959186,
- "loss": 1.4919,
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
"step": 442
},
{
- "epoch": 8.96,
- "learning_rate": 0.00014349489795918366,
- "loss": 1.4702,
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
"step": 443
},
{
- "epoch": 8.98,
- "learning_rate": 0.00014336734693877552,
- "loss": 1.4996,
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
"step": 444
},
{
- "epoch": 9.0,
- "learning_rate": 0.00014323979591836735,
- "loss": 1.5503,
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
"step": 445
},
{
- "epoch": 9.02,
- "learning_rate": 0.00014311224489795918,
- "loss": 1.4125,
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
"step": 446
},
{
- "epoch": 9.04,
- "learning_rate": 0.00014298469387755104,
- "loss": 1.4722,
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
"step": 447
},
{
- "epoch": 9.06,
- "learning_rate": 0.00014285714285714287,
- "loss": 1.5199,
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
"step": 448
},
{
- "epoch": 9.09,
- "learning_rate": 0.0001427295918367347,
- "loss": 1.4571,
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
"step": 449
},
{
- "epoch": 9.11,
- "learning_rate": 0.00014260204081632653,
- "loss": 1.4996,
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
"step": 450
},
{
- "epoch": 9.13,
- "learning_rate": 0.0001424744897959184,
- "loss": 1.4092,
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
"step": 451
},
{
- "epoch": 9.15,
- "learning_rate": 0.00014234693877551022,
- "loss": 1.4198,
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
"step": 452
},
{
- "epoch": 9.17,
- "learning_rate": 0.00014221938775510205,
- "loss": 1.4916,
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
"step": 453
},
{
- "epoch": 9.19,
- "learning_rate": 0.00014209183673469388,
- "loss": 1.5051,
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
"step": 454
},
{
- "epoch": 9.21,
- "learning_rate": 0.00014196428571428574,
- "loss": 1.4321,
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
"step": 455
},
{
- "epoch": 9.23,
- "learning_rate": 0.00014183673469387754,
- "loss": 1.4097,
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
"step": 456
},
{
- "epoch": 9.25,
- "learning_rate": 0.0001417091836734694,
- "loss": 1.4853,
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
"step": 457
},
{
- "epoch": 9.27,
- "learning_rate": 0.00014158163265306123,
- "loss": 1.4593,
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
"step": 458
},
{
- "epoch": 9.29,
- "learning_rate": 0.00014145408163265306,
- "loss": 1.3729,
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
"step": 459
},
{
- "epoch": 9.31,
- "learning_rate": 0.0001413265306122449,
- "loss": 1.4467,
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
"step": 460
},
{
- "epoch": 9.33,
- "learning_rate": 0.00014119897959183675,
- "loss": 1.4467,
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
"step": 461
},
{
- "epoch": 9.35,
- "learning_rate": 0.00014107142857142858,
- "loss": 1.4785,
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
"step": 462
},
{
- "epoch": 9.37,
- "learning_rate": 0.0001409438775510204,
- "loss": 1.4089,
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
"step": 463
},
{
- "epoch": 9.39,
- "learning_rate": 0.00014081632653061224,
- "loss": 1.5026,
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
"step": 464
},
{
- "epoch": 9.41,
- "learning_rate": 0.0001406887755102041,
- "loss": 1.4857,
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
"step": 465
},
{
- "epoch": 9.43,
- "learning_rate": 0.0001405612244897959,
- "loss": 1.3745,
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
"step": 466
},
{
- "epoch": 9.45,
- "learning_rate": 0.00014043367346938776,
- "loss": 1.4733,
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
"step": 467
},
{
- "epoch": 9.47,
- "learning_rate": 0.0001403061224489796,
- "loss": 1.5212,
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
"step": 468
},
{
- "epoch": 9.49,
- "learning_rate": 0.00014017857142857142,
- "loss": 1.5398,
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
"step": 469
},
{
- "epoch": 9.51,
- "learning_rate": 0.00014005102040816328,
- "loss": 1.478,
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
"step": 470
},
{
- "epoch": 9.53,
- "learning_rate": 0.0001399234693877551,
- "loss": 1.496,
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
"step": 471
},
{
- "epoch": 9.55,
- "learning_rate": 0.00013979591836734694,
- "loss": 1.4837,
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
"step": 472
},
{
- "epoch": 9.57,
- "learning_rate": 0.00013966836734693878,
- "loss": 1.4724,
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
"step": 473
},
{
- "epoch": 9.59,
- "learning_rate": 0.00013954081632653063,
- "loss": 1.4828,
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
"step": 474
},
{
- "epoch": 9.61,
- "learning_rate": 0.00013941326530612246,
- "loss": 1.5012,
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
"step": 475
},
{
- "epoch": 9.63,
- "learning_rate": 0.0001392857142857143,
- "loss": 1.4879,
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
"step": 476
},
{
- "epoch": 9.65,
- "learning_rate": 0.00013915816326530613,
- "loss": 1.4196,
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
"step": 477
},
{
- "epoch": 9.67,
- "learning_rate": 0.00013903061224489798,
- "loss": 1.4915,
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
"step": 478
},
{
- "epoch": 9.69,
- "learning_rate": 0.0001389030612244898,
- "loss": 1.3878,
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
"step": 479
},
{
- "epoch": 9.71,
- "learning_rate": 0.00013877551020408165,
- "loss": 1.466,
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
"step": 480
},
{
- "epoch": 9.73,
- "learning_rate": 0.00013864795918367348,
- "loss": 1.4582,
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
"step": 481
},
{
- "epoch": 9.75,
- "learning_rate": 0.0001385204081632653,
- "loss": 1.533,
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
"step": 482
},
{
- "epoch": 9.77,
- "learning_rate": 0.00013839285714285714,
- "loss": 1.4697,
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
"step": 483
},
{
- "epoch": 9.79,
- "learning_rate": 0.000138265306122449,
- "loss": 1.3989,
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
"step": 484
},
{
- "epoch": 9.81,
- "learning_rate": 0.00013813775510204083,
- "loss": 1.4361,
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
"step": 485
},
{
- "epoch": 9.83,
- "learning_rate": 0.00013801020408163266,
- "loss": 1.5271,
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
"step": 486
},
{
- "epoch": 9.85,
- "learning_rate": 0.0001378826530612245,
- "loss": 1.4905,
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
"step": 487
},
{
- "epoch": 9.87,
- "learning_rate": 0.00013775510204081635,
- "loss": 1.4757,
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
"step": 488
},
{
- "epoch": 9.89,
- "learning_rate": 0.00013762755102040815,
- "loss": 1.5485,
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
"step": 489
},
{
- "epoch": 9.91,
- "learning_rate": 0.0001375,
- "loss": 1.4783,
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
"step": 490
},
{
- "epoch": 9.93,
- "learning_rate": 0.00013737244897959184,
- "loss": 1.4849,
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
"step": 491
},
{
- "epoch": 9.96,
- "learning_rate": 0.00013724489795918367,
- "loss": 1.5382,
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
"step": 492
},
{
- "epoch": 9.98,
- "learning_rate": 0.00013711734693877553,
- "loss": 1.4902,
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
"step": 493
},
{
- "epoch": 10.0,
- "learning_rate": 0.00013698979591836736,
- "loss": 1.4865,
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
"step": 494
},
{
- "epoch": 10.02,
- "learning_rate": 0.0001368622448979592,
- "loss": 1.4436,
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
"step": 495
},
{
- "epoch": 10.04,
- "learning_rate": 0.00013673469387755102,
- "loss": 1.408,
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
"step": 496
},
{
- "epoch": 10.06,
- "learning_rate": 0.00013660714285714288,
- "loss": 1.4764,
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
"step": 497
},
{
- "epoch": 10.08,
- "learning_rate": 0.0001364795918367347,
- "loss": 1.4646,
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
"step": 498
},
{
- "epoch": 10.1,
- "learning_rate": 0.00013635204081632654,
- "loss": 1.406,
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
"step": 499
},
{
- "epoch": 10.12,
- "learning_rate": 0.00013622448979591837,
- "loss": 1.4785,
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
"step": 500
},
{
- "epoch": 10.14,
- "learning_rate": 0.00013609693877551023,
- "loss": 1.4117,
+ "epoch": 5.66,
+ "learning_rate": 0.00012883522727272727,
+ "loss": 1.0755,
"step": 501
},
{
- "epoch": 10.16,
- "learning_rate": 0.00013596938775510203,
- "loss": 1.4108,
+ "epoch": 5.67,
+ "learning_rate": 0.00012869318181818183,
+ "loss": 1.0755,
"step": 502
},
{
- "epoch": 10.18,
- "learning_rate": 0.0001358418367346939,
- "loss": 1.4155,
+ "epoch": 5.68,
+ "learning_rate": 0.00012855113636363636,
+ "loss": 1.0869,
"step": 503
},
{
- "epoch": 10.2,
- "learning_rate": 0.00013571428571428572,
- "loss": 1.4021,
+ "epoch": 5.69,
+ "learning_rate": 0.00012840909090909092,
+ "loss": 1.0673,
"step": 504
},
{
- "epoch": 10.22,
- "learning_rate": 0.00013558673469387755,
- "loss": 1.411,
+ "epoch": 5.71,
+ "learning_rate": 0.00012826704545454545,
+ "loss": 1.0692,
"step": 505
},
{
- "epoch": 10.24,
- "learning_rate": 0.00013545918367346938,
- "loss": 1.3851,
+ "epoch": 5.72,
+ "learning_rate": 0.000128125,
+ "loss": 1.0474,
"step": 506
},
{
- "epoch": 10.26,
- "learning_rate": 0.00013533163265306124,
- "loss": 1.387,
+ "epoch": 5.73,
+ "learning_rate": 0.00012798295454545454,
+ "loss": 1.0749,
"step": 507
},
{
- "epoch": 10.28,
- "learning_rate": 0.00013520408163265305,
- "loss": 1.4163,
+ "epoch": 5.74,
+ "learning_rate": 0.0001278409090909091,
+ "loss": 1.0519,
"step": 508
},
{
- "epoch": 10.3,
- "learning_rate": 0.0001350765306122449,
- "loss": 1.3343,
+ "epoch": 5.75,
+ "learning_rate": 0.00012769886363636366,
+ "loss": 1.0566,
"step": 509
},
{
- "epoch": 10.32,
- "learning_rate": 0.00013494897959183673,
- "loss": 1.4811,
+ "epoch": 5.76,
+ "learning_rate": 0.0001275568181818182,
+ "loss": 1.06,
"step": 510
},
{
- "epoch": 10.34,
- "learning_rate": 0.0001348214285714286,
- "loss": 1.4086,
+ "epoch": 5.77,
+ "learning_rate": 0.00012741477272727272,
+ "loss": 1.0618,
"step": 511
},
{
- "epoch": 10.36,
- "learning_rate": 0.0001346938775510204,
- "loss": 1.3879,
+ "epoch": 5.78,
+ "learning_rate": 0.00012727272727272728,
+ "loss": 1.0643,
"step": 512
},
{
- "epoch": 10.38,
- "learning_rate": 0.00013456632653061225,
- "loss": 1.4204,
+ "epoch": 5.8,
+ "learning_rate": 0.0001271306818181818,
+ "loss": 1.026,
"step": 513
},
{
- "epoch": 10.4,
- "learning_rate": 0.00013443877551020408,
- "loss": 1.4158,
+ "epoch": 5.81,
+ "learning_rate": 0.00012698863636363637,
+ "loss": 1.0335,
"step": 514
},
{
- "epoch": 10.42,
- "learning_rate": 0.00013431122448979592,
- "loss": 1.4521,
+ "epoch": 5.82,
+ "learning_rate": 0.00012684659090909093,
+ "loss": 1.0205,
"step": 515
},
{
- "epoch": 10.44,
- "learning_rate": 0.00013418367346938777,
- "loss": 1.4196,
+ "epoch": 5.83,
+ "learning_rate": 0.00012670454545454546,
+ "loss": 1.0594,
"step": 516
},
{
- "epoch": 10.46,
- "learning_rate": 0.0001340561224489796,
- "loss": 1.4361,
+ "epoch": 5.84,
+ "learning_rate": 0.0001265625,
+ "loss": 1.0136,
"step": 517
},
{
- "epoch": 10.48,
- "learning_rate": 0.00013392857142857144,
- "loss": 1.4482,
+ "epoch": 5.85,
+ "learning_rate": 0.00012642045454545455,
+ "loss": 1.0244,
"step": 518
},
{
- "epoch": 10.5,
- "learning_rate": 0.00013380102040816327,
- "loss": 1.4801,
+ "epoch": 5.86,
+ "learning_rate": 0.00012627840909090908,
+ "loss": 1.0569,
"step": 519
},
{
- "epoch": 10.52,
- "learning_rate": 0.00013367346938775512,
- "loss": 1.4556,
+ "epoch": 5.87,
+ "learning_rate": 0.00012613636363636364,
+ "loss": 1.0416,
"step": 520
},
{
- "epoch": 10.54,
- "learning_rate": 0.00013354591836734695,
- "loss": 1.3902,
+ "epoch": 5.89,
+ "learning_rate": 0.0001259943181818182,
+ "loss": 0.9884,
"step": 521
},
{
- "epoch": 10.56,
- "learning_rate": 0.00013341836734693879,
- "loss": 1.4269,
+ "epoch": 5.9,
+ "learning_rate": 0.00012585227272727273,
+ "loss": 1.0351,
"step": 522
},
{
- "epoch": 10.58,
- "learning_rate": 0.00013329081632653062,
- "loss": 1.4899,
+ "epoch": 5.91,
+ "learning_rate": 0.00012571022727272726,
+ "loss": 1.0037,
"step": 523
},
{
- "epoch": 10.6,
- "learning_rate": 0.00013316326530612247,
- "loss": 1.3952,
+ "epoch": 5.92,
+ "learning_rate": 0.00012556818181818182,
+ "loss": 1.0219,
"step": 524
},
{
- "epoch": 10.62,
- "learning_rate": 0.00013303571428571428,
- "loss": 1.4116,
+ "epoch": 5.93,
+ "learning_rate": 0.00012542613636363635,
+ "loss": 1.0533,
"step": 525
},
{
- "epoch": 10.64,
- "learning_rate": 0.00013290816326530614,
- "loss": 1.4583,
+ "epoch": 5.94,
+ "learning_rate": 0.0001252840909090909,
+ "loss": 1.0031,
"step": 526
},
{
- "epoch": 10.66,
- "learning_rate": 0.00013278061224489797,
- "loss": 1.4466,
+ "epoch": 5.95,
+ "learning_rate": 0.00012514204545454547,
+ "loss": 1.0454,
"step": 527
},
{
- "epoch": 10.68,
- "learning_rate": 0.0001326530612244898,
- "loss": 1.4242,
+ "epoch": 5.97,
+ "learning_rate": 0.000125,
+ "loss": 1.0195,
"step": 528
},
{
- "epoch": 10.7,
- "learning_rate": 0.00013252551020408163,
- "loss": 1.3717,
+ "epoch": 5.98,
+ "learning_rate": 0.00012485795454545453,
+ "loss": 1.0076,
"step": 529
},
{
- "epoch": 10.72,
- "learning_rate": 0.0001323979591836735,
- "loss": 1.4583,
+ "epoch": 5.99,
+ "learning_rate": 0.0001247159090909091,
+ "loss": 1.0378,
"step": 530
},
{
- "epoch": 10.74,
- "learning_rate": 0.0001322704081632653,
- "loss": 1.4185,
+ "epoch": 6.0,
+ "learning_rate": 0.00012457386363636365,
+ "loss": 0.9795,
"step": 531
},
{
- "epoch": 10.76,
- "learning_rate": 0.00013214285714285715,
- "loss": 1.4287,
+ "epoch": 6.01,
+ "learning_rate": 0.00012443181818181818,
+ "loss": 0.9405,
"step": 532
},
{
- "epoch": 10.78,
- "learning_rate": 0.00013201530612244898,
- "loss": 1.4385,
+ "epoch": 6.02,
+ "learning_rate": 0.00012428977272727274,
+ "loss": 0.9503,
"step": 533
},
{
- "epoch": 10.8,
- "learning_rate": 0.00013188775510204084,
- "loss": 1.453,
+ "epoch": 6.03,
+ "learning_rate": 0.00012414772727272727,
+ "loss": 0.9456,
"step": 534
},
{
- "epoch": 10.83,
- "learning_rate": 0.00013176020408163264,
- "loss": 1.4161,
+ "epoch": 6.04,
+ "learning_rate": 0.0001240056818181818,
+ "loss": 0.9536,
"step": 535
},
{
- "epoch": 10.85,
- "learning_rate": 0.0001316326530612245,
- "loss": 1.457,
+ "epoch": 6.06,
+ "learning_rate": 0.00012386363636363636,
+ "loss": 0.9412,
"step": 536
},
{
- "epoch": 10.87,
- "learning_rate": 0.00013150510204081633,
- "loss": 1.4367,
+ "epoch": 6.07,
+ "learning_rate": 0.00012372159090909092,
+ "loss": 0.9315,
"step": 537
},
{
- "epoch": 10.89,
- "learning_rate": 0.00013137755102040816,
- "loss": 1.4256,
+ "epoch": 6.08,
+ "learning_rate": 0.00012357954545454545,
+ "loss": 0.9486,
"step": 538
},
{
- "epoch": 10.91,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.424,
+ "epoch": 6.09,
+ "learning_rate": 0.0001234375,
+ "loss": 0.9405,
"step": 539
},
{
- "epoch": 10.93,
- "learning_rate": 0.00013112244897959185,
- "loss": 1.3923,
+ "epoch": 6.1,
+ "learning_rate": 0.00012329545454545454,
+ "loss": 0.9269,
"step": 540
},
{
- "epoch": 10.95,
- "learning_rate": 0.00013099489795918368,
- "loss": 1.4225,
+ "epoch": 6.11,
+ "learning_rate": 0.0001231534090909091,
+ "loss": 0.9378,
"step": 541
},
{
- "epoch": 10.97,
- "learning_rate": 0.0001308673469387755,
- "loss": 1.3969,
+ "epoch": 6.12,
+ "learning_rate": 0.00012301136363636366,
+ "loss": 0.9431,
"step": 542
},
{
- "epoch": 10.99,
- "learning_rate": 0.00013073979591836737,
- "loss": 1.4446,
+ "epoch": 6.13,
+ "learning_rate": 0.0001228693181818182,
+ "loss": 0.9256,
"step": 543
},
{
- "epoch": 11.01,
- "learning_rate": 0.00013061224489795917,
- "loss": 1.4375,
+ "epoch": 6.15,
+ "learning_rate": 0.00012272727272727272,
+ "loss": 0.919,
"step": 544
},
{
- "epoch": 11.03,
- "learning_rate": 0.00013048469387755103,
- "loss": 1.4064,
+ "epoch": 6.16,
+ "learning_rate": 0.00012258522727272728,
+ "loss": 0.9188,
"step": 545
},
{
- "epoch": 11.05,
- "learning_rate": 0.00013035714285714286,
- "loss": 1.3454,
+ "epoch": 6.17,
+ "learning_rate": 0.00012244318181818181,
+ "loss": 0.9447,
"step": 546
},
{
- "epoch": 11.07,
- "learning_rate": 0.00013022959183673472,
- "loss": 1.3234,
+ "epoch": 6.18,
+ "learning_rate": 0.00012230113636363637,
+ "loss": 0.9261,
"step": 547
},
{
- "epoch": 11.09,
- "learning_rate": 0.00013010204081632652,
- "loss": 1.3759,
+ "epoch": 6.19,
+ "learning_rate": 0.00012215909090909093,
+ "loss": 0.9302,
"step": 548
},
{
- "epoch": 11.11,
- "learning_rate": 0.00012997448979591838,
- "loss": 1.4221,
+ "epoch": 6.2,
+ "learning_rate": 0.00012201704545454546,
+ "loss": 0.9161,
"step": 549
},
{
- "epoch": 11.13,
- "learning_rate": 0.0001298469387755102,
- "loss": 1.4261,
+ "epoch": 6.21,
+ "learning_rate": 0.00012187500000000001,
+ "loss": 0.9521,
"step": 550
},
{
- "epoch": 11.15,
- "learning_rate": 0.00012971938775510204,
- "loss": 1.3341,
+ "epoch": 6.22,
+ "learning_rate": 0.00012173295454545455,
+ "loss": 0.9026,
"step": 551
},
{
- "epoch": 11.17,
- "learning_rate": 0.00012959183673469387,
- "loss": 1.3994,
+ "epoch": 6.24,
+ "learning_rate": 0.00012159090909090908,
+ "loss": 0.9361,
"step": 552
},
{
- "epoch": 11.19,
- "learning_rate": 0.00012946428571428573,
- "loss": 1.3894,
+ "epoch": 6.25,
+ "learning_rate": 0.00012144886363636366,
+ "loss": 0.8944,
"step": 553
},
{
- "epoch": 11.21,
- "learning_rate": 0.00012933673469387754,
- "loss": 1.3585,
+ "epoch": 6.26,
+ "learning_rate": 0.00012130681818181819,
+ "loss": 0.895,
"step": 554
},
{
- "epoch": 11.23,
- "learning_rate": 0.0001292091836734694,
- "loss": 1.3763,
+ "epoch": 6.27,
+ "learning_rate": 0.00012116477272727273,
+ "loss": 0.8956,
"step": 555
},
{
- "epoch": 11.25,
- "learning_rate": 0.00012908163265306123,
- "loss": 1.3623,
+ "epoch": 6.28,
+ "learning_rate": 0.00012102272727272728,
+ "loss": 0.8998,
"step": 556
},
{
- "epoch": 11.27,
- "learning_rate": 0.00012895408163265306,
- "loss": 1.3907,
+ "epoch": 6.29,
+ "learning_rate": 0.00012088068181818182,
+ "loss": 0.915,
"step": 557
},
{
- "epoch": 11.29,
- "learning_rate": 0.0001288265306122449,
- "loss": 1.3807,
+ "epoch": 6.3,
+ "learning_rate": 0.00012073863636363636,
+ "loss": 0.9282,
"step": 558
},
{
- "epoch": 11.31,
- "learning_rate": 0.00012869897959183674,
- "loss": 1.4045,
+ "epoch": 6.32,
+ "learning_rate": 0.00012059659090909093,
+ "loss": 0.8938,
"step": 559
},
{
- "epoch": 11.33,
- "learning_rate": 0.00012857142857142858,
- "loss": 1.4038,
+ "epoch": 6.33,
+ "learning_rate": 0.00012045454545454546,
+ "loss": 0.8886,
"step": 560
},
{
- "epoch": 11.35,
- "learning_rate": 0.0001284438775510204,
- "loss": 1.3466,
+ "epoch": 6.34,
+ "learning_rate": 0.0001203125,
+ "loss": 0.8988,
"step": 561
},
{
- "epoch": 11.37,
- "learning_rate": 0.00012831632653061226,
- "loss": 1.3449,
+ "epoch": 6.35,
+ "learning_rate": 0.00012017045454545455,
+ "loss": 0.8852,
"step": 562
},
{
- "epoch": 11.39,
- "learning_rate": 0.0001281887755102041,
- "loss": 1.3866,
+ "epoch": 6.36,
+ "learning_rate": 0.0001200284090909091,
+ "loss": 0.8818,
"step": 563
},
{
- "epoch": 11.41,
- "learning_rate": 0.00012806122448979593,
- "loss": 1.3106,
+ "epoch": 6.37,
+ "learning_rate": 0.00011988636363636365,
+ "loss": 0.8881,
"step": 564
},
{
- "epoch": 11.43,
- "learning_rate": 0.00012793367346938776,
- "loss": 1.4414,
+ "epoch": 6.38,
+ "learning_rate": 0.0001197443181818182,
+ "loss": 0.9226,
"step": 565
},
{
- "epoch": 11.45,
- "learning_rate": 0.00012780612244897962,
- "loss": 1.3737,
+ "epoch": 6.39,
+ "learning_rate": 0.00011960227272727273,
+ "loss": 0.8849,
"step": 566
},
{
- "epoch": 11.47,
- "learning_rate": 0.00012767857142857142,
- "loss": 1.4053,
+ "epoch": 6.41,
+ "learning_rate": 0.00011946022727272727,
+ "loss": 0.8894,
"step": 567
},
{
- "epoch": 11.49,
- "learning_rate": 0.00012755102040816328,
- "loss": 1.4561,
+ "epoch": 6.42,
+ "learning_rate": 0.00011931818181818182,
+ "loss": 0.9207,
"step": 568
},
{
- "epoch": 11.51,
- "learning_rate": 0.0001274234693877551,
- "loss": 1.3684,
+ "epoch": 6.43,
+ "learning_rate": 0.00011917613636363636,
+ "loss": 0.9105,
"step": 569
},
{
- "epoch": 11.53,
- "learning_rate": 0.00012729591836734697,
- "loss": 1.3117,
+ "epoch": 6.44,
+ "learning_rate": 0.00011903409090909092,
+ "loss": 0.8762,
"step": 570
},
{
- "epoch": 11.55,
- "learning_rate": 0.00012716836734693877,
- "loss": 1.3474,
+ "epoch": 6.45,
+ "learning_rate": 0.00011889204545454547,
+ "loss": 0.8926,
"step": 571
},
{
- "epoch": 11.57,
- "learning_rate": 0.00012704081632653063,
- "loss": 1.3804,
+ "epoch": 6.46,
+ "learning_rate": 0.00011875,
+ "loss": 0.8719,
"step": 572
},
{
- "epoch": 11.59,
- "learning_rate": 0.00012691326530612246,
- "loss": 1.3656,
+ "epoch": 6.47,
+ "learning_rate": 0.00011860795454545454,
+ "loss": 0.9198,
"step": 573
},
{
- "epoch": 11.61,
- "learning_rate": 0.0001267857142857143,
- "loss": 1.3133,
+ "epoch": 6.48,
+ "learning_rate": 0.00011846590909090909,
+ "loss": 0.8846,
"step": 574
},
{
- "epoch": 11.63,
- "learning_rate": 0.00012665816326530612,
- "loss": 1.4077,
+ "epoch": 6.5,
+ "learning_rate": 0.00011832386363636365,
+ "loss": 0.8495,
"step": 575
},
{
- "epoch": 11.65,
- "learning_rate": 0.00012653061224489798,
- "loss": 1.4087,
+ "epoch": 6.51,
+ "learning_rate": 0.0001181818181818182,
+ "loss": 0.8953,
"step": 576
},
{
- "epoch": 11.67,
- "learning_rate": 0.00012640306122448978,
- "loss": 1.3524,
+ "epoch": 6.52,
+ "learning_rate": 0.00011803977272727274,
+ "loss": 0.8686,
"step": 577
},
{
- "epoch": 11.7,
- "learning_rate": 0.00012627551020408164,
- "loss": 1.3481,
+ "epoch": 6.53,
+ "learning_rate": 0.00011789772727272727,
+ "loss": 0.8841,
"step": 578
},
{
- "epoch": 11.72,
- "learning_rate": 0.00012614795918367347,
- "loss": 1.4497,
+ "epoch": 6.54,
+ "learning_rate": 0.00011775568181818182,
+ "loss": 0.8681,
"step": 579
},
{
- "epoch": 11.74,
- "learning_rate": 0.0001260204081632653,
- "loss": 1.3866,
+ "epoch": 6.55,
+ "learning_rate": 0.00011761363636363636,
+ "loss": 0.8732,
"step": 580
},
{
- "epoch": 11.76,
- "learning_rate": 0.00012589285714285713,
- "loss": 1.42,
+ "epoch": 6.56,
+ "learning_rate": 0.00011747159090909092,
+ "loss": 0.8582,
"step": 581
},
{
- "epoch": 11.78,
- "learning_rate": 0.000125765306122449,
- "loss": 1.3562,
+ "epoch": 6.58,
+ "learning_rate": 0.00011732954545454546,
+ "loss": 0.8744,
"step": 582
},
{
- "epoch": 11.8,
- "learning_rate": 0.00012563775510204082,
- "loss": 1.3249,
+ "epoch": 6.59,
+ "learning_rate": 0.00011718750000000001,
+ "loss": 0.8694,
"step": 583
},
{
- "epoch": 11.82,
- "learning_rate": 0.00012551020408163265,
- "loss": 1.4277,
+ "epoch": 6.6,
+ "learning_rate": 0.00011704545454545454,
+ "loss": 0.8565,
"step": 584
},
{
- "epoch": 11.84,
- "learning_rate": 0.0001253826530612245,
- "loss": 1.3734,
+ "epoch": 6.61,
+ "learning_rate": 0.00011690340909090909,
+ "loss": 0.8584,
"step": 585
},
{
- "epoch": 11.86,
- "learning_rate": 0.00012525510204081634,
- "loss": 1.3765,
+ "epoch": 6.62,
+ "learning_rate": 0.00011676136363636366,
+ "loss": 0.8859,
"step": 586
},
{
- "epoch": 11.88,
- "learning_rate": 0.00012512755102040817,
- "loss": 1.4153,
+ "epoch": 6.63,
+ "learning_rate": 0.00011661931818181819,
+ "loss": 0.8452,
"step": 587
},
{
- "epoch": 11.9,
- "learning_rate": 0.000125,
- "loss": 1.3847,
+ "epoch": 6.64,
+ "learning_rate": 0.00011647727272727273,
+ "loss": 0.8323,
"step": 588
},
{
- "epoch": 11.92,
- "learning_rate": 0.00012487244897959186,
- "loss": 1.3824,
+ "epoch": 6.65,
+ "learning_rate": 0.00011633522727272728,
+ "loss": 0.8548,
"step": 589
},
{
- "epoch": 11.94,
- "learning_rate": 0.00012474489795918366,
- "loss": 1.3938,
+ "epoch": 6.67,
+ "learning_rate": 0.00011619318181818181,
+ "loss": 0.8506,
"step": 590
},
{
- "epoch": 11.96,
- "learning_rate": 0.00012461734693877552,
- "loss": 1.4143,
+ "epoch": 6.68,
+ "learning_rate": 0.00011605113636363636,
+ "loss": 0.8556,
"step": 591
},
{
- "epoch": 11.98,
- "learning_rate": 0.00012448979591836735,
- "loss": 1.3794,
+ "epoch": 6.69,
+ "learning_rate": 0.00011590909090909093,
+ "loss": 0.8459,
"step": 592
},
{
- "epoch": 12.0,
- "learning_rate": 0.00012436224489795918,
- "loss": 1.3755,
+ "epoch": 6.7,
+ "learning_rate": 0.00011576704545454546,
+ "loss": 0.8432,
"step": 593
},
{
- "epoch": 12.02,
- "learning_rate": 0.00012423469387755101,
- "loss": 1.3736,
+ "epoch": 6.71,
+ "learning_rate": 0.000115625,
+ "loss": 0.8645,
"step": 594
},
{
- "epoch": 12.04,
- "learning_rate": 0.00012410714285714287,
- "loss": 1.2957,
+ "epoch": 6.72,
+ "learning_rate": 0.00011548295454545455,
+ "loss": 0.86,
"step": 595
},
{
- "epoch": 12.06,
- "learning_rate": 0.0001239795918367347,
- "loss": 1.2996,
+ "epoch": 6.73,
+ "learning_rate": 0.00011534090909090908,
+ "loss": 0.8161,
"step": 596
},
{
- "epoch": 12.08,
- "learning_rate": 0.00012385204081632653,
- "loss": 1.3648,
+ "epoch": 6.74,
+ "learning_rate": 0.00011519886363636365,
+ "loss": 0.8133,
"step": 597
},
{
- "epoch": 12.1,
- "learning_rate": 0.00012372448979591837,
- "loss": 1.3031,
+ "epoch": 6.76,
+ "learning_rate": 0.0001150568181818182,
+ "loss": 0.8372,
"step": 598
},
{
- "epoch": 12.12,
- "learning_rate": 0.00012359693877551022,
- "loss": 1.2933,
+ "epoch": 6.77,
+ "learning_rate": 0.00011491477272727273,
+ "loss": 0.8222,
"step": 599
},
{
- "epoch": 12.14,
- "learning_rate": 0.00012346938775510203,
- "loss": 1.322,
+ "epoch": 6.78,
+ "learning_rate": 0.00011477272727272728,
+ "loss": 0.8372,
"step": 600
},
{
- "epoch": 12.16,
- "learning_rate": 0.00012334183673469389,
- "loss": 1.3123,
+ "epoch": 6.79,
+ "learning_rate": 0.00011463068181818182,
+ "loss": 0.837,
"step": 601
},
{
- "epoch": 12.18,
- "learning_rate": 0.00012321428571428572,
- "loss": 1.3187,
+ "epoch": 6.8,
+ "learning_rate": 0.00011448863636363637,
+ "loss": 0.8406,
"step": 602
},
{
- "epoch": 12.2,
- "learning_rate": 0.00012308673469387755,
- "loss": 1.3353,
+ "epoch": 6.81,
+ "learning_rate": 0.00011434659090909092,
+ "loss": 0.836,
"step": 603
},
{
- "epoch": 12.22,
- "learning_rate": 0.0001229591836734694,
- "loss": 1.3221,
+ "epoch": 6.82,
+ "learning_rate": 0.00011420454545454547,
+ "loss": 0.8476,
"step": 604
},
{
- "epoch": 12.24,
- "learning_rate": 0.00012283163265306124,
- "loss": 1.3458,
+ "epoch": 6.83,
+ "learning_rate": 0.0001140625,
+ "loss": 0.8368,
"step": 605
},
{
- "epoch": 12.26,
- "learning_rate": 0.00012270408163265307,
- "loss": 1.275,
+ "epoch": 6.85,
+ "learning_rate": 0.00011392045454545455,
+ "loss": 0.822,
"step": 606
},
{
- "epoch": 12.28,
- "learning_rate": 0.0001225765306122449,
- "loss": 1.3455,
+ "epoch": 6.86,
+ "learning_rate": 0.00011377840909090909,
+ "loss": 0.8107,
"step": 607
},
{
- "epoch": 12.3,
- "learning_rate": 0.00012244897959183676,
- "loss": 1.2769,
+ "epoch": 6.87,
+ "learning_rate": 0.00011363636363636365,
+ "loss": 0.8395,
"step": 608
},
{
- "epoch": 12.32,
- "learning_rate": 0.00012232142857142859,
- "loss": 1.3201,
+ "epoch": 6.88,
+ "learning_rate": 0.0001134943181818182,
+ "loss": 0.8083,
"step": 609
},
{
- "epoch": 12.34,
- "learning_rate": 0.00012219387755102042,
- "loss": 1.3073,
+ "epoch": 6.89,
+ "learning_rate": 0.00011335227272727274,
+ "loss": 0.828,
"step": 610
},
{
- "epoch": 12.36,
- "learning_rate": 0.00012206632653061225,
- "loss": 1.3103,
+ "epoch": 6.9,
+ "learning_rate": 0.00011321022727272727,
+ "loss": 0.8494,
"step": 611
},
{
- "epoch": 12.38,
- "learning_rate": 0.00012193877551020409,
- "loss": 1.4437,
+ "epoch": 6.91,
+ "learning_rate": 0.00011306818181818182,
+ "loss": 0.8169,
"step": 612
},
{
- "epoch": 12.4,
- "learning_rate": 0.00012181122448979591,
- "loss": 1.3086,
+ "epoch": 6.93,
+ "learning_rate": 0.00011292613636363636,
+ "loss": 0.8224,
"step": 613
},
{
- "epoch": 12.42,
- "learning_rate": 0.00012168367346938775,
- "loss": 1.3867,
+ "epoch": 6.94,
+ "learning_rate": 0.00011278409090909092,
+ "loss": 0.8173,
"step": 614
},
{
- "epoch": 12.44,
- "learning_rate": 0.0001215561224489796,
- "loss": 1.2565,
+ "epoch": 6.95,
+ "learning_rate": 0.00011264204545454547,
+ "loss": 0.7961,
"step": 615
},
{
- "epoch": 12.46,
- "learning_rate": 0.00012142857142857143,
- "loss": 1.335,
+ "epoch": 6.96,
+ "learning_rate": 0.00011250000000000001,
+ "loss": 0.7948,
"step": 616
},
{
- "epoch": 12.48,
- "learning_rate": 0.00012130102040816327,
- "loss": 1.3423,
+ "epoch": 6.97,
+ "learning_rate": 0.00011235795454545454,
+ "loss": 0.7746,
"step": 617
},
{
- "epoch": 12.5,
- "learning_rate": 0.00012117346938775512,
- "loss": 1.3433,
+ "epoch": 6.98,
+ "learning_rate": 0.00011221590909090909,
+ "loss": 0.8325,
"step": 618
},
{
- "epoch": 12.52,
- "learning_rate": 0.00012104591836734695,
- "loss": 1.3387,
+ "epoch": 6.99,
+ "learning_rate": 0.00011207386363636365,
+ "loss": 0.8149,
"step": 619
},
{
- "epoch": 12.55,
- "learning_rate": 0.00012091836734693878,
- "loss": 1.3923,
+ "epoch": 7.0,
+ "learning_rate": 0.00011193181818181819,
+ "loss": 0.7516,
"step": 620
},
{
- "epoch": 12.57,
- "learning_rate": 0.00012079081632653062,
- "loss": 1.3774,
+ "epoch": 7.02,
+ "learning_rate": 0.00011178977272727274,
+ "loss": 0.7571,
"step": 621
},
{
- "epoch": 12.59,
- "learning_rate": 0.00012066326530612247,
- "loss": 1.3203,
+ "epoch": 7.03,
+ "learning_rate": 0.00011164772727272728,
+ "loss": 0.7397,
"step": 622
},
{
- "epoch": 12.61,
- "learning_rate": 0.00012053571428571429,
- "loss": 1.2924,
+ "epoch": 7.04,
+ "learning_rate": 0.00011150568181818181,
+ "loss": 0.761,
"step": 623
},
{
- "epoch": 12.63,
- "learning_rate": 0.00012040816326530613,
- "loss": 1.3292,
+ "epoch": 7.05,
+ "learning_rate": 0.00011136363636363636,
+ "loss": 0.7783,
"step": 624
},
{
- "epoch": 12.65,
- "learning_rate": 0.00012028061224489798,
- "loss": 1.3161,
+ "epoch": 7.06,
+ "learning_rate": 0.00011122159090909092,
+ "loss": 0.7571,
"step": 625
},
{
- "epoch": 12.67,
- "learning_rate": 0.00012015306122448979,
- "loss": 1.352,
+ "epoch": 7.07,
+ "learning_rate": 0.00011107954545454546,
+ "loss": 0.7628,
"step": 626
},
{
- "epoch": 12.69,
- "learning_rate": 0.00012002551020408164,
- "loss": 1.3577,
+ "epoch": 7.08,
+ "learning_rate": 0.0001109375,
+ "loss": 0.7561,
"step": 627
},
{
- "epoch": 12.71,
- "learning_rate": 0.00011989795918367348,
- "loss": 1.3575,
+ "epoch": 7.09,
+ "learning_rate": 0.00011079545454545455,
+ "loss": 0.7432,
"step": 628
},
{
- "epoch": 12.73,
- "learning_rate": 0.0001197704081632653,
- "loss": 1.3727,
+ "epoch": 7.11,
+ "learning_rate": 0.00011065340909090908,
+ "loss": 0.7245,
"step": 629
},
{
- "epoch": 12.75,
- "learning_rate": 0.00011964285714285714,
- "loss": 1.3312,
+ "epoch": 7.12,
+ "learning_rate": 0.00011051136363636366,
+ "loss": 0.7279,
"step": 630
},
{
- "epoch": 12.77,
- "learning_rate": 0.00011951530612244899,
- "loss": 1.3378,
+ "epoch": 7.13,
+ "learning_rate": 0.00011036931818181819,
+ "loss": 0.7347,
"step": 631
},
{
- "epoch": 12.79,
- "learning_rate": 0.00011938775510204083,
- "loss": 1.295,
+ "epoch": 7.14,
+ "learning_rate": 0.00011022727272727273,
+ "loss": 0.7427,
"step": 632
},
{
- "epoch": 12.81,
- "learning_rate": 0.00011926020408163265,
- "loss": 1.3447,
+ "epoch": 7.15,
+ "learning_rate": 0.00011008522727272728,
+ "loss": 0.7339,
"step": 633
},
{
- "epoch": 12.83,
- "learning_rate": 0.0001191326530612245,
- "loss": 1.3835,
+ "epoch": 7.16,
+ "learning_rate": 0.00010994318181818182,
+ "loss": 0.7375,
"step": 634
},
{
- "epoch": 12.85,
- "learning_rate": 0.00011900510204081634,
- "loss": 1.3222,
+ "epoch": 7.17,
+ "learning_rate": 0.00010980113636363635,
+ "loss": 0.7182,
"step": 635
},
{
- "epoch": 12.87,
- "learning_rate": 0.00011887755102040817,
- "loss": 1.2851,
+ "epoch": 7.19,
+ "learning_rate": 0.00010965909090909093,
+ "loss": 0.7452,
"step": 636
},
{
- "epoch": 12.89,
- "learning_rate": 0.00011875,
- "loss": 1.2723,
+ "epoch": 7.2,
+ "learning_rate": 0.00010951704545454546,
+ "loss": 0.7565,
"step": 637
},
{
- "epoch": 12.91,
- "learning_rate": 0.00011862244897959184,
- "loss": 1.3924,
+ "epoch": 7.21,
+ "learning_rate": 0.000109375,
+ "loss": 0.7296,
"step": 638
},
{
- "epoch": 12.93,
- "learning_rate": 0.00011849489795918368,
- "loss": 1.4625,
+ "epoch": 7.22,
+ "learning_rate": 0.00010923295454545455,
+ "loss": 0.7484,
"step": 639
},
{
- "epoch": 12.95,
- "learning_rate": 0.00011836734693877552,
- "loss": 1.3245,
+ "epoch": 7.23,
+ "learning_rate": 0.00010909090909090909,
+ "loss": 0.732,
"step": 640
},
{
- "epoch": 12.97,
- "learning_rate": 0.00011823979591836736,
- "loss": 1.4042,
+ "epoch": 7.24,
+ "learning_rate": 0.00010894886363636365,
+ "loss": 0.7415,
"step": 641
},
{
- "epoch": 12.99,
- "learning_rate": 0.00011811224489795918,
- "loss": 1.3761,
+ "epoch": 7.25,
+ "learning_rate": 0.0001088068181818182,
+ "loss": 0.7344,
"step": 642
},
{
- "epoch": 13.01,
- "learning_rate": 0.00011798469387755103,
- "loss": 1.3376,
+ "epoch": 7.26,
+ "learning_rate": 0.00010866477272727274,
+ "loss": 0.7267,
"step": 643
},
{
- "epoch": 13.03,
- "learning_rate": 0.00011785714285714287,
- "loss": 1.2174,
+ "epoch": 7.28,
+ "learning_rate": 0.00010852272727272727,
+ "loss": 0.7543,
"step": 644
},
{
- "epoch": 13.05,
- "learning_rate": 0.00011772959183673471,
- "loss": 1.3602,
+ "epoch": 7.29,
+ "learning_rate": 0.00010838068181818182,
+ "loss": 0.7266,
"step": 645
},
{
- "epoch": 13.07,
- "learning_rate": 0.00011760204081632653,
- "loss": 1.3002,
+ "epoch": 7.3,
+ "learning_rate": 0.00010823863636363636,
+ "loss": 0.7449,
"step": 646
},
{
- "epoch": 13.09,
- "learning_rate": 0.00011747448979591838,
- "loss": 1.2262,
+ "epoch": 7.31,
+ "learning_rate": 0.00010809659090909092,
+ "loss": 0.7324,
"step": 647
},
{
- "epoch": 13.11,
- "learning_rate": 0.00011734693877551022,
- "loss": 1.3048,
+ "epoch": 7.32,
+ "learning_rate": 0.00010795454545454547,
+ "loss": 0.7268,
"step": 648
},
{
- "epoch": 13.13,
- "learning_rate": 0.00011721938775510204,
- "loss": 1.2231,
+ "epoch": 7.33,
+ "learning_rate": 0.00010781250000000001,
+ "loss": 0.7172,
"step": 649
},
{
- "epoch": 13.15,
- "learning_rate": 0.00011709183673469388,
- "loss": 1.2996,
+ "epoch": 7.34,
+ "learning_rate": 0.00010767045454545454,
+ "loss": 0.7169,
"step": 650
},
{
- "epoch": 13.17,
- "learning_rate": 0.00011696428571428573,
- "loss": 1.2708,
+ "epoch": 7.35,
+ "learning_rate": 0.00010752840909090909,
+ "loss": 0.7194,
"step": 651
},
{
- "epoch": 13.19,
- "learning_rate": 0.00011683673469387754,
- "loss": 1.2776,
+ "epoch": 7.37,
+ "learning_rate": 0.00010738636363636365,
+ "loss": 0.7223,
"step": 652
},
{
- "epoch": 13.21,
- "learning_rate": 0.00011670918367346939,
- "loss": 1.248,
+ "epoch": 7.38,
+ "learning_rate": 0.00010724431818181819,
+ "loss": 0.7158,
"step": 653
},
{
- "epoch": 13.23,
- "learning_rate": 0.00011658163265306123,
- "loss": 1.2582,
+ "epoch": 7.39,
+ "learning_rate": 0.00010710227272727274,
+ "loss": 0.7122,
"step": 654
},
{
- "epoch": 13.25,
- "learning_rate": 0.00011645408163265305,
- "loss": 1.3011,
+ "epoch": 7.4,
+ "learning_rate": 0.00010696022727272728,
+ "loss": 0.7225,
"step": 655
},
{
- "epoch": 13.27,
- "learning_rate": 0.0001163265306122449,
- "loss": 1.2969,
+ "epoch": 7.41,
+ "learning_rate": 0.00010681818181818181,
+ "loss": 0.7102,
"step": 656
},
{
- "epoch": 13.29,
- "learning_rate": 0.00011619897959183674,
- "loss": 1.2454,
+ "epoch": 7.42,
+ "learning_rate": 0.00010667613636363636,
+ "loss": 0.7251,
"step": 657
},
{
- "epoch": 13.31,
- "learning_rate": 0.00011607142857142858,
- "loss": 1.1914,
+ "epoch": 7.43,
+ "learning_rate": 0.00010653409090909092,
+ "loss": 0.7191,
"step": 658
},
{
- "epoch": 13.33,
- "learning_rate": 0.00011594387755102041,
- "loss": 1.34,
+ "epoch": 7.45,
+ "learning_rate": 0.00010639204545454546,
+ "loss": 0.7015,
"step": 659
},
{
- "epoch": 13.35,
- "learning_rate": 0.00011581632653061225,
- "loss": 1.2828,
+ "epoch": 7.46,
+ "learning_rate": 0.00010625000000000001,
+ "loss": 0.693,
"step": 660
},
{
- "epoch": 13.37,
- "learning_rate": 0.00011568877551020409,
- "loss": 1.2962,
+ "epoch": 7.47,
+ "learning_rate": 0.00010610795454545455,
+ "loss": 0.7039,
"step": 661
},
{
- "epoch": 13.39,
- "learning_rate": 0.00011556122448979592,
- "loss": 1.3334,
+ "epoch": 7.48,
+ "learning_rate": 0.00010596590909090908,
+ "loss": 0.7305,
"step": 662
},
{
- "epoch": 13.42,
- "learning_rate": 0.00011543367346938776,
- "loss": 1.2832,
+ "epoch": 7.49,
+ "learning_rate": 0.00010582386363636366,
+ "loss": 0.6978,
"step": 663
},
{
- "epoch": 13.44,
- "learning_rate": 0.00011530612244897961,
- "loss": 1.3012,
+ "epoch": 7.5,
+ "learning_rate": 0.00010568181818181819,
+ "loss": 0.7219,
"step": 664
},
{
- "epoch": 13.46,
- "learning_rate": 0.00011517857142857143,
- "loss": 1.2857,
+ "epoch": 7.51,
+ "learning_rate": 0.00010553977272727273,
+ "loss": 0.7199,
"step": 665
},
{
- "epoch": 13.48,
- "learning_rate": 0.00011505102040816327,
- "loss": 1.2855,
+ "epoch": 7.52,
+ "learning_rate": 0.00010539772727272728,
+ "loss": 0.6979,
"step": 666
},
{
- "epoch": 13.5,
- "learning_rate": 0.00011492346938775512,
- "loss": 1.3077,
+ "epoch": 7.54,
+ "learning_rate": 0.00010525568181818182,
+ "loss": 0.7058,
"step": 667
},
{
- "epoch": 13.52,
- "learning_rate": 0.00011479591836734696,
- "loss": 1.3139,
+ "epoch": 7.55,
+ "learning_rate": 0.00010511363636363635,
+ "loss": 0.6994,
"step": 668
},
{
- "epoch": 13.54,
- "learning_rate": 0.00011466836734693878,
- "loss": 1.3138,
+ "epoch": 7.56,
+ "learning_rate": 0.00010497159090909093,
+ "loss": 0.7141,
"step": 669
},
{
- "epoch": 13.56,
- "learning_rate": 0.00011454081632653062,
- "loss": 1.2808,
+ "epoch": 7.57,
+ "learning_rate": 0.00010482954545454546,
+ "loss": 0.7092,
"step": 670
},
{
- "epoch": 13.58,
- "learning_rate": 0.00011441326530612247,
- "loss": 1.2492,
+ "epoch": 7.58,
+ "learning_rate": 0.0001046875,
+ "loss": 0.7059,
"step": 671
},
{
- "epoch": 13.6,
- "learning_rate": 0.00011428571428571428,
- "loss": 1.2027,
+ "epoch": 7.59,
+ "learning_rate": 0.00010454545454545455,
+ "loss": 0.6904,
"step": 672
},
{
- "epoch": 13.62,
- "learning_rate": 0.00011415816326530613,
- "loss": 1.33,
+ "epoch": 7.6,
+ "learning_rate": 0.0001044034090909091,
+ "loss": 0.7115,
"step": 673
},
{
- "epoch": 13.64,
- "learning_rate": 0.00011403061224489797,
- "loss": 1.3112,
+ "epoch": 7.61,
+ "learning_rate": 0.00010426136363636365,
+ "loss": 0.7254,
"step": 674
},
{
- "epoch": 13.66,
- "learning_rate": 0.00011390306122448979,
- "loss": 1.2772,
+ "epoch": 7.63,
+ "learning_rate": 0.0001041193181818182,
+ "loss": 0.7181,
"step": 675
},
{
- "epoch": 13.68,
- "learning_rate": 0.00011377551020408163,
- "loss": 1.2701,
+ "epoch": 7.64,
+ "learning_rate": 0.00010397727272727273,
+ "loss": 0.6867,
"step": 676
},
{
- "epoch": 13.7,
- "learning_rate": 0.00011364795918367348,
- "loss": 1.1973,
+ "epoch": 7.65,
+ "learning_rate": 0.00010383522727272727,
+ "loss": 0.6917,
"step": 677
},
{
- "epoch": 13.72,
- "learning_rate": 0.0001135204081632653,
- "loss": 1.3124,
+ "epoch": 7.66,
+ "learning_rate": 0.00010369318181818182,
+ "loss": 0.6908,
"step": 678
},
{
- "epoch": 13.74,
- "learning_rate": 0.00011339285714285714,
- "loss": 1.3085,
+ "epoch": 7.67,
+ "learning_rate": 0.00010355113636363636,
+ "loss": 0.6871,
"step": 679
},
{
- "epoch": 13.76,
- "learning_rate": 0.00011326530612244898,
- "loss": 1.3457,
+ "epoch": 7.68,
+ "learning_rate": 0.00010340909090909092,
+ "loss": 0.682,
"step": 680
},
{
- "epoch": 13.78,
- "learning_rate": 0.00011313775510204083,
- "loss": 1.3338,
+ "epoch": 7.69,
+ "learning_rate": 0.00010326704545454547,
+ "loss": 0.6737,
"step": 681
},
{
- "epoch": 13.8,
- "learning_rate": 0.00011301020408163266,
- "loss": 1.2753,
+ "epoch": 7.7,
+ "learning_rate": 0.000103125,
+ "loss": 0.7023,
"step": 682
},
{
- "epoch": 13.82,
- "learning_rate": 0.00011288265306122449,
- "loss": 1.2786,
+ "epoch": 7.72,
+ "learning_rate": 0.00010298295454545454,
+ "loss": 0.7079,
"step": 683
},
{
- "epoch": 13.84,
- "learning_rate": 0.00011275510204081634,
- "loss": 1.2584,
+ "epoch": 7.73,
+ "learning_rate": 0.00010284090909090909,
+ "loss": 0.6954,
"step": 684
},
{
- "epoch": 13.86,
- "learning_rate": 0.00011262755102040817,
- "loss": 1.2779,
+ "epoch": 7.74,
+ "learning_rate": 0.00010269886363636365,
+ "loss": 0.6834,
"step": 685
},
{
- "epoch": 13.88,
- "learning_rate": 0.00011250000000000001,
- "loss": 1.3502,
+ "epoch": 7.75,
+ "learning_rate": 0.0001025568181818182,
+ "loss": 0.6706,
"step": 686
},
{
- "epoch": 13.9,
- "learning_rate": 0.00011237244897959185,
- "loss": 1.3251,
+ "epoch": 7.76,
+ "learning_rate": 0.00010241477272727274,
+ "loss": 0.6706,
"step": 687
},
{
- "epoch": 13.92,
- "learning_rate": 0.00011224489795918367,
- "loss": 1.273,
+ "epoch": 7.77,
+ "learning_rate": 0.00010227272727272727,
+ "loss": 0.681,
"step": 688
},
{
- "epoch": 13.94,
- "learning_rate": 0.00011211734693877552,
- "loss": 1.3341,
+ "epoch": 7.78,
+ "learning_rate": 0.00010213068181818182,
+ "loss": 0.6853,
"step": 689
},
{
- "epoch": 13.96,
- "learning_rate": 0.00011198979591836736,
- "loss": 1.2654,
+ "epoch": 7.8,
+ "learning_rate": 0.00010198863636363636,
+ "loss": 0.6772,
"step": 690
},
{
- "epoch": 13.98,
- "learning_rate": 0.00011186224489795918,
- "loss": 1.3333,
+ "epoch": 7.81,
+ "learning_rate": 0.00010184659090909092,
+ "loss": 0.6635,
"step": 691
},
{
- "epoch": 14.0,
- "learning_rate": 0.00011173469387755102,
- "loss": 1.3246,
+ "epoch": 7.82,
+ "learning_rate": 0.00010170454545454546,
+ "loss": 0.6712,
"step": 692
},
{
- "epoch": 14.02,
- "learning_rate": 0.00011160714285714287,
- "loss": 1.2547,
+ "epoch": 7.83,
+ "learning_rate": 0.00010156250000000001,
+ "loss": 0.6884,
"step": 693
},
{
- "epoch": 14.04,
- "learning_rate": 0.00011147959183673471,
- "loss": 1.208,
+ "epoch": 7.84,
+ "learning_rate": 0.00010142045454545454,
+ "loss": 0.6641,
"step": 694
},
{
- "epoch": 14.06,
- "learning_rate": 0.00011135204081632653,
- "loss": 1.223,
+ "epoch": 7.85,
+ "learning_rate": 0.00010127840909090909,
+ "loss": 0.6838,
"step": 695
},
{
- "epoch": 14.08,
- "learning_rate": 0.00011122448979591837,
- "loss": 1.2483,
+ "epoch": 7.86,
+ "learning_rate": 0.00010113636363636366,
+ "loss": 0.675,
"step": 696
},
{
- "epoch": 14.1,
- "learning_rate": 0.00011109693877551022,
- "loss": 1.2823,
+ "epoch": 7.87,
+ "learning_rate": 0.00010099431818181819,
+ "loss": 0.6626,
"step": 697
},
{
- "epoch": 14.12,
- "learning_rate": 0.00011096938775510204,
- "loss": 1.2013,
+ "epoch": 7.89,
+ "learning_rate": 0.00010085227272727273,
+ "loss": 0.6605,
"step": 698
},
{
- "epoch": 14.14,
- "learning_rate": 0.00011084183673469388,
- "loss": 1.1883,
+ "epoch": 7.9,
+ "learning_rate": 0.00010071022727272728,
+ "loss": 0.6777,
"step": 699
},
{
- "epoch": 14.16,
- "learning_rate": 0.00011071428571428572,
- "loss": 1.2364,
+ "epoch": 7.91,
+ "learning_rate": 0.00010056818181818181,
+ "loss": 0.6347,
"step": 700
},
{
- "epoch": 14.18,
- "learning_rate": 0.00011058673469387754,
- "loss": 1.2069,
+ "epoch": 7.92,
+ "learning_rate": 0.00010042613636363636,
+ "loss": 0.6857,
"step": 701
},
{
- "epoch": 14.2,
- "learning_rate": 0.00011045918367346939,
- "loss": 1.1968,
+ "epoch": 7.93,
+ "learning_rate": 0.00010028409090909093,
+ "loss": 0.6677,
"step": 702
},
{
- "epoch": 14.22,
- "learning_rate": 0.00011033163265306123,
- "loss": 1.2236,
+ "epoch": 7.94,
+ "learning_rate": 0.00010014204545454546,
+ "loss": 0.6697,
"step": 703
},
{
- "epoch": 14.24,
- "learning_rate": 0.00011020408163265306,
- "loss": 1.1942,
+ "epoch": 7.95,
+ "learning_rate": 0.0001,
+ "loss": 0.6375,
"step": 704
},
{
- "epoch": 14.26,
- "learning_rate": 0.0001100765306122449,
- "loss": 1.2561,
+ "epoch": 7.96,
+ "learning_rate": 9.985795454545455e-05,
+ "loss": 0.6572,
"step": 705
},
{
- "epoch": 14.29,
- "learning_rate": 0.00010994897959183674,
- "loss": 1.1839,
+ "epoch": 7.98,
+ "learning_rate": 9.97159090909091e-05,
+ "loss": 0.668,
"step": 706
},
{
- "epoch": 14.31,
- "learning_rate": 0.00010982142857142858,
- "loss": 1.2128,
+ "epoch": 7.99,
+ "learning_rate": 9.957386363636364e-05,
+ "loss": 0.6797,
"step": 707
},
{
- "epoch": 14.33,
- "learning_rate": 0.00010969387755102041,
- "loss": 1.3086,
+ "epoch": 8.0,
+ "learning_rate": 9.943181818181819e-05,
+ "loss": 0.6784,
"step": 708
},
{
- "epoch": 14.35,
- "learning_rate": 0.00010956632653061226,
- "loss": 1.2379,
+ "epoch": 8.01,
+ "learning_rate": 9.928977272727273e-05,
+ "loss": 0.6192,
"step": 709
},
{
- "epoch": 14.37,
- "learning_rate": 0.0001094387755102041,
- "loss": 1.176,
+ "epoch": 8.02,
+ "learning_rate": 9.914772727272728e-05,
+ "loss": 0.6287,
"step": 710
},
{
- "epoch": 14.39,
- "learning_rate": 0.00010931122448979592,
- "loss": 1.2105,
+ "epoch": 8.03,
+ "learning_rate": 9.900568181818183e-05,
+ "loss": 0.6034,
"step": 711
},
{
- "epoch": 14.41,
- "learning_rate": 0.00010918367346938776,
- "loss": 1.2149,
+ "epoch": 8.04,
+ "learning_rate": 9.886363636363637e-05,
+ "loss": 0.6167,
"step": 712
},
{
- "epoch": 14.43,
- "learning_rate": 0.0001090561224489796,
- "loss": 1.2392,
+ "epoch": 8.06,
+ "learning_rate": 9.872159090909091e-05,
+ "loss": 0.6353,
"step": 713
},
{
- "epoch": 14.45,
- "learning_rate": 0.00010892857142857142,
- "loss": 1.2471,
+ "epoch": 8.07,
+ "learning_rate": 9.857954545454547e-05,
+ "loss": 0.6222,
"step": 714
},
{
- "epoch": 14.47,
- "learning_rate": 0.00010880102040816327,
- "loss": 1.2561,
+ "epoch": 8.08,
+ "learning_rate": 9.84375e-05,
+ "loss": 0.5963,
"step": 715
},
{
- "epoch": 14.49,
- "learning_rate": 0.00010867346938775511,
- "loss": 1.2179,
+ "epoch": 8.09,
+ "learning_rate": 9.829545454545455e-05,
+ "loss": 0.6042,
"step": 716
},
{
- "epoch": 14.51,
- "learning_rate": 0.00010854591836734696,
- "loss": 1.2459,
+ "epoch": 8.1,
+ "learning_rate": 9.81534090909091e-05,
+ "loss": 0.612,
"step": 717
},
{
- "epoch": 14.53,
- "learning_rate": 0.00010841836734693877,
- "loss": 1.2933,
+ "epoch": 8.11,
+ "learning_rate": 9.801136363636364e-05,
+ "loss": 0.6069,
"step": 718
},
{
- "epoch": 14.55,
- "learning_rate": 0.00010829081632653062,
- "loss": 1.2862,
+ "epoch": 8.12,
+ "learning_rate": 9.786931818181818e-05,
+ "loss": 0.6001,
"step": 719
},
{
- "epoch": 14.57,
- "learning_rate": 0.00010816326530612246,
- "loss": 1.2976,
+ "epoch": 8.13,
+ "learning_rate": 9.772727272727274e-05,
+ "loss": 0.6007,
"step": 720
},
{
- "epoch": 14.59,
- "learning_rate": 0.00010803571428571428,
- "loss": 1.231,
+ "epoch": 8.15,
+ "learning_rate": 9.758522727272727e-05,
+ "loss": 0.6079,
"step": 721
},
{
- "epoch": 14.61,
- "learning_rate": 0.00010790816326530613,
- "loss": 1.2464,
+ "epoch": 8.16,
+ "learning_rate": 9.744318181818183e-05,
+ "loss": 0.6216,
"step": 722
},
{
- "epoch": 14.63,
- "learning_rate": 0.00010778061224489797,
- "loss": 1.2181,
+ "epoch": 8.17,
+ "learning_rate": 9.730113636363637e-05,
+ "loss": 0.6321,
"step": 723
},
{
- "epoch": 14.65,
- "learning_rate": 0.00010765306122448979,
- "loss": 1.3307,
+ "epoch": 8.18,
+ "learning_rate": 9.71590909090909e-05,
+ "loss": 0.6044,
"step": 724
},
{
- "epoch": 14.67,
- "learning_rate": 0.00010752551020408163,
- "loss": 1.1723,
+ "epoch": 8.19,
+ "learning_rate": 9.701704545454547e-05,
+ "loss": 0.6028,
"step": 725
},
{
- "epoch": 14.69,
- "learning_rate": 0.00010739795918367348,
- "loss": 1.1528,
+ "epoch": 8.2,
+ "learning_rate": 9.687500000000001e-05,
+ "loss": 0.6098,
"step": 726
},
{
- "epoch": 14.71,
- "learning_rate": 0.0001072704081632653,
- "loss": 1.215,
+ "epoch": 8.21,
+ "learning_rate": 9.673295454545454e-05,
+ "loss": 0.6032,
"step": 727
},
{
- "epoch": 14.73,
- "learning_rate": 0.00010714285714285715,
- "loss": 1.2624,
+ "epoch": 8.22,
+ "learning_rate": 9.65909090909091e-05,
+ "loss": 0.6298,
"step": 728
},
{
- "epoch": 14.75,
- "learning_rate": 0.00010701530612244898,
- "loss": 1.3117,
+ "epoch": 8.24,
+ "learning_rate": 9.644886363636365e-05,
+ "loss": 0.6115,
"step": 729
},
{
- "epoch": 14.77,
- "learning_rate": 0.00010688775510204083,
- "loss": 1.2572,
+ "epoch": 8.25,
+ "learning_rate": 9.630681818181818e-05,
+ "loss": 0.6052,
"step": 730
},
{
- "epoch": 14.79,
- "learning_rate": 0.00010676020408163266,
- "loss": 1.222,
+ "epoch": 8.26,
+ "learning_rate": 9.616477272727274e-05,
+ "loss": 0.6097,
"step": 731
},
{
- "epoch": 14.81,
- "learning_rate": 0.0001066326530612245,
- "loss": 1.2881,
+ "epoch": 8.27,
+ "learning_rate": 9.602272727272728e-05,
+ "loss": 0.6062,
"step": 732
},
{
- "epoch": 14.83,
- "learning_rate": 0.00010650510204081635,
- "loss": 1.2676,
+ "epoch": 8.28,
+ "learning_rate": 9.588068181818183e-05,
+ "loss": 0.5984,
"step": 733
},
{
- "epoch": 14.85,
- "learning_rate": 0.00010637755102040816,
- "loss": 1.2734,
+ "epoch": 8.29,
+ "learning_rate": 9.573863636363637e-05,
+ "loss": 0.6432,
"step": 734
},
{
- "epoch": 14.87,
- "learning_rate": 0.00010625000000000001,
- "loss": 1.2885,
+ "epoch": 8.3,
+ "learning_rate": 9.559659090909092e-05,
+ "loss": 0.5814,
"step": 735
},
{
- "epoch": 14.89,
- "learning_rate": 0.00010612244897959185,
- "loss": 1.2764,
+ "epoch": 8.31,
+ "learning_rate": 9.545454545454546e-05,
+ "loss": 0.5965,
"step": 736
},
{
- "epoch": 14.91,
- "learning_rate": 0.00010599489795918367,
- "loss": 1.3267,
+ "epoch": 8.33,
+ "learning_rate": 9.53125e-05,
+ "loss": 0.6102,
"step": 737
},
{
- "epoch": 14.93,
- "learning_rate": 0.00010586734693877551,
- "loss": 1.2445,
+ "epoch": 8.34,
+ "learning_rate": 9.517045454545455e-05,
+ "loss": 0.5849,
"step": 738
},
{
- "epoch": 14.95,
- "learning_rate": 0.00010573979591836736,
- "loss": 1.3359,
+ "epoch": 8.35,
+ "learning_rate": 9.50284090909091e-05,
+ "loss": 0.6062,
"step": 739
},
{
- "epoch": 14.97,
- "learning_rate": 0.00010561224489795918,
- "loss": 1.2508,
+ "epoch": 8.36,
+ "learning_rate": 9.488636363636364e-05,
+ "loss": 0.6031,
"step": 740
},
{
- "epoch": 14.99,
- "learning_rate": 0.00010548469387755102,
- "loss": 1.2227,
+ "epoch": 8.37,
+ "learning_rate": 9.474431818181819e-05,
+ "loss": 0.5932,
"step": 741
},
{
- "epoch": 15.01,
- "learning_rate": 0.00010535714285714286,
- "loss": 1.1889,
+ "epoch": 8.38,
+ "learning_rate": 9.460227272727273e-05,
+ "loss": 0.589,
"step": 742
},
{
- "epoch": 15.03,
- "learning_rate": 0.00010522959183673471,
- "loss": 1.1919,
+ "epoch": 8.39,
+ "learning_rate": 9.446022727272728e-05,
+ "loss": 0.6096,
"step": 743
},
{
- "epoch": 15.05,
- "learning_rate": 0.00010510204081632653,
- "loss": 1.2383,
+ "epoch": 8.41,
+ "learning_rate": 9.431818181818182e-05,
+ "loss": 0.601,
"step": 744
},
{
- "epoch": 15.07,
- "learning_rate": 0.00010497448979591837,
- "loss": 1.2401,
+ "epoch": 8.42,
+ "learning_rate": 9.417613636363637e-05,
+ "loss": 0.5798,
"step": 745
},
{
- "epoch": 15.09,
- "learning_rate": 0.00010484693877551021,
- "loss": 1.2015,
+ "epoch": 8.43,
+ "learning_rate": 9.403409090909091e-05,
+ "loss": 0.59,
"step": 746
},
{
- "epoch": 15.11,
- "learning_rate": 0.00010471938775510203,
- "loss": 1.1509,
+ "epoch": 8.44,
+ "learning_rate": 9.389204545454546e-05,
+ "loss": 0.5988,
"step": 747
},
{
- "epoch": 15.13,
- "learning_rate": 0.00010459183673469388,
- "loss": 1.1878,
+ "epoch": 8.45,
+ "learning_rate": 9.375e-05,
+ "loss": 0.5591,
"step": 748
},
{
- "epoch": 15.16,
- "learning_rate": 0.00010446428571428572,
- "loss": 1.1706,
+ "epoch": 8.46,
+ "learning_rate": 9.360795454545455e-05,
+ "loss": 0.5939,
"step": 749
},
{
- "epoch": 15.18,
- "learning_rate": 0.00010433673469387755,
- "loss": 1.1285,
+ "epoch": 8.47,
+ "learning_rate": 9.346590909090909e-05,
+ "loss": 0.5886,
"step": 750
},
{
- "epoch": 15.2,
- "learning_rate": 0.0001042091836734694,
- "loss": 1.1608,
+ "epoch": 8.48,
+ "learning_rate": 9.332386363636364e-05,
+ "loss": 0.5994,
"step": 751
},
{
- "epoch": 15.22,
- "learning_rate": 0.00010408163265306123,
- "loss": 1.1178,
+ "epoch": 8.5,
+ "learning_rate": 9.318181818181818e-05,
+ "loss": 0.5821,
"step": 752
},
{
- "epoch": 15.24,
- "learning_rate": 0.00010395408163265306,
- "loss": 1.1293,
+ "epoch": 8.51,
+ "learning_rate": 9.303977272727273e-05,
+ "loss": 0.602,
"step": 753
},
{
- "epoch": 15.26,
- "learning_rate": 0.0001038265306122449,
- "loss": 1.2306,
+ "epoch": 8.52,
+ "learning_rate": 9.289772727272727e-05,
+ "loss": 0.5708,
"step": 754
},
{
- "epoch": 15.28,
- "learning_rate": 0.00010369897959183675,
- "loss": 1.1541,
+ "epoch": 8.53,
+ "learning_rate": 9.275568181818183e-05,
+ "loss": 0.5902,
"step": 755
},
{
- "epoch": 15.3,
- "learning_rate": 0.00010357142857142859,
- "loss": 1.1702,
+ "epoch": 8.54,
+ "learning_rate": 9.261363636363636e-05,
+ "loss": 0.6053,
"step": 756
},
{
- "epoch": 15.32,
- "learning_rate": 0.00010344387755102041,
- "loss": 1.2119,
+ "epoch": 8.55,
+ "learning_rate": 9.247159090909091e-05,
+ "loss": 0.5797,
"step": 757
},
{
- "epoch": 15.34,
- "learning_rate": 0.00010331632653061225,
- "loss": 1.2239,
+ "epoch": 8.56,
+ "learning_rate": 9.232954545454547e-05,
+ "loss": 0.5965,
"step": 758
},
{
- "epoch": 15.36,
- "learning_rate": 0.0001031887755102041,
- "loss": 1.2019,
+ "epoch": 8.57,
+ "learning_rate": 9.21875e-05,
+ "loss": 0.5738,
"step": 759
},
{
- "epoch": 15.38,
- "learning_rate": 0.00010306122448979591,
- "loss": 1.2197,
+ "epoch": 8.59,
+ "learning_rate": 9.204545454545454e-05,
+ "loss": 0.5819,
"step": 760
},
{
- "epoch": 15.4,
- "learning_rate": 0.00010293367346938776,
- "loss": 1.1769,
+ "epoch": 8.6,
+ "learning_rate": 9.19034090909091e-05,
+ "loss": 0.5994,
"step": 761
},
{
- "epoch": 15.42,
- "learning_rate": 0.0001028061224489796,
- "loss": 1.1907,
+ "epoch": 8.61,
+ "learning_rate": 9.176136363636363e-05,
+ "loss": 0.5738,
"step": 762
},
{
- "epoch": 15.44,
- "learning_rate": 0.00010267857142857142,
- "loss": 1.2089,
+ "epoch": 8.62,
+ "learning_rate": 9.161931818181818e-05,
+ "loss": 0.5663,
"step": 763
},
{
- "epoch": 15.46,
- "learning_rate": 0.00010255102040816327,
- "loss": 1.1335,
+ "epoch": 8.63,
+ "learning_rate": 9.147727272727274e-05,
+ "loss": 0.5798,
"step": 764
},
{
- "epoch": 15.48,
- "learning_rate": 0.00010242346938775511,
- "loss": 1.1633,
+ "epoch": 8.64,
+ "learning_rate": 9.133522727272727e-05,
+ "loss": 0.5705,
"step": 765
},
{
- "epoch": 15.5,
- "learning_rate": 0.00010229591836734695,
- "loss": 1.1578,
+ "epoch": 8.65,
+ "learning_rate": 9.119318181818183e-05,
+ "loss": 0.5943,
"step": 766
},
{
- "epoch": 15.52,
- "learning_rate": 0.00010216836734693877,
- "loss": 1.2236,
+ "epoch": 8.67,
+ "learning_rate": 9.105113636363637e-05,
+ "loss": 0.6019,
"step": 767
},
{
- "epoch": 15.54,
- "learning_rate": 0.00010204081632653062,
- "loss": 1.1941,
+ "epoch": 8.68,
+ "learning_rate": 9.090909090909092e-05,
+ "loss": 0.5733,
"step": 768
},
{
- "epoch": 15.56,
- "learning_rate": 0.00010191326530612246,
- "loss": 1.2666,
+ "epoch": 8.69,
+ "learning_rate": 9.076704545454546e-05,
+ "loss": 0.575,
"step": 769
},
{
- "epoch": 15.58,
- "learning_rate": 0.00010178571428571428,
- "loss": 1.1232,
+ "epoch": 8.7,
+ "learning_rate": 9.062500000000001e-05,
+ "loss": 0.5675,
"step": 770
},
{
- "epoch": 15.6,
- "learning_rate": 0.00010165816326530612,
- "loss": 1.2242,
+ "epoch": 8.71,
+ "learning_rate": 9.048295454545455e-05,
+ "loss": 0.566,
"step": 771
},
{
- "epoch": 15.62,
- "learning_rate": 0.00010153061224489797,
- "loss": 1.1852,
+ "epoch": 8.72,
+ "learning_rate": 9.03409090909091e-05,
+ "loss": 0.5513,
"step": 772
},
{
- "epoch": 15.64,
- "learning_rate": 0.0001014030612244898,
- "loss": 1.2626,
+ "epoch": 8.73,
+ "learning_rate": 9.019886363636364e-05,
+ "loss": 0.5682,
"step": 773
},
{
- "epoch": 15.66,
- "learning_rate": 0.00010127551020408164,
- "loss": 1.1873,
+ "epoch": 8.74,
+ "learning_rate": 9.005681818181819e-05,
+ "loss": 0.5508,
"step": 774
},
{
- "epoch": 15.68,
- "learning_rate": 0.00010114795918367349,
- "loss": 1.3005,
+ "epoch": 8.76,
+ "learning_rate": 8.991477272727273e-05,
+ "loss": 0.5668,
"step": 775
},
{
- "epoch": 15.7,
- "learning_rate": 0.0001010204081632653,
- "loss": 1.1904,
+ "epoch": 8.77,
+ "learning_rate": 8.977272727272728e-05,
+ "loss": 0.569,
"step": 776
},
{
- "epoch": 15.72,
- "learning_rate": 0.00010089285714285715,
- "loss": 1.2927,
+ "epoch": 8.78,
+ "learning_rate": 8.963068181818182e-05,
+ "loss": 0.5897,
"step": 777
},
{
- "epoch": 15.74,
- "learning_rate": 0.00010076530612244899,
- "loss": 1.179,
+ "epoch": 8.79,
+ "learning_rate": 8.948863636363637e-05,
+ "loss": 0.5738,
"step": 778
},
{
- "epoch": 15.76,
- "learning_rate": 0.00010063775510204084,
- "loss": 1.2027,
+ "epoch": 8.8,
+ "learning_rate": 8.934659090909091e-05,
+ "loss": 0.5511,
"step": 779
},
{
- "epoch": 15.78,
- "learning_rate": 0.00010051020408163265,
- "loss": 1.2428,
+ "epoch": 8.81,
+ "learning_rate": 8.920454545454546e-05,
+ "loss": 0.5659,
"step": 780
},
{
- "epoch": 15.8,
- "learning_rate": 0.0001003826530612245,
- "loss": 1.2324,
+ "epoch": 8.82,
+ "learning_rate": 8.90625e-05,
+ "loss": 0.5649,
"step": 781
},
{
- "epoch": 15.82,
- "learning_rate": 0.00010025510204081634,
- "loss": 1.1251,
+ "epoch": 8.83,
+ "learning_rate": 8.892045454545455e-05,
+ "loss": 0.5618,
"step": 782
},
{
- "epoch": 15.84,
- "learning_rate": 0.00010012755102040816,
- "loss": 1.2405,
+ "epoch": 8.85,
+ "learning_rate": 8.87784090909091e-05,
+ "loss": 0.5602,
"step": 783
},
{
- "epoch": 15.86,
- "learning_rate": 0.0001,
- "loss": 1.2005,
+ "epoch": 8.86,
+ "learning_rate": 8.863636363636364e-05,
+ "loss": 0.5723,
"step": 784
},
{
- "epoch": 15.88,
- "learning_rate": 9.987244897959184e-05,
- "loss": 1.2259,
+ "epoch": 8.87,
+ "learning_rate": 8.849431818181818e-05,
+ "loss": 0.5816,
"step": 785
},
{
- "epoch": 15.9,
- "learning_rate": 9.974489795918368e-05,
- "loss": 1.1576,
+ "epoch": 8.88,
+ "learning_rate": 8.835227272727273e-05,
+ "loss": 0.555,
"step": 786
},
{
- "epoch": 15.92,
- "learning_rate": 9.961734693877551e-05,
- "loss": 1.1834,
+ "epoch": 8.89,
+ "learning_rate": 8.821022727272727e-05,
+ "loss": 0.5563,
"step": 787
},
{
- "epoch": 15.94,
- "learning_rate": 9.948979591836736e-05,
- "loss": 1.2396,
+ "epoch": 8.9,
+ "learning_rate": 8.806818181818183e-05,
+ "loss": 0.554,
"step": 788
},
{
- "epoch": 15.96,
- "learning_rate": 9.936224489795919e-05,
- "loss": 1.1865,
+ "epoch": 8.91,
+ "learning_rate": 8.792613636363636e-05,
+ "loss": 0.5671,
"step": 789
},
{
- "epoch": 15.98,
- "learning_rate": 9.923469387755102e-05,
- "loss": 1.2356,
+ "epoch": 8.92,
+ "learning_rate": 8.778409090909091e-05,
+ "loss": 0.5485,
"step": 790
},
{
- "epoch": 16.01,
- "learning_rate": 9.910714285714286e-05,
- "loss": 1.2639,
+ "epoch": 8.94,
+ "learning_rate": 8.764204545454547e-05,
+ "loss": 0.5712,
"step": 791
},
{
- "epoch": 16.03,
- "learning_rate": 9.897959183673469e-05,
- "loss": 1.1216,
+ "epoch": 8.95,
+ "learning_rate": 8.75e-05,
+ "loss": 0.5507,
"step": 792
},
{
- "epoch": 16.05,
- "learning_rate": 9.885204081632652e-05,
- "loss": 1.1051,
+ "epoch": 8.96,
+ "learning_rate": 8.735795454545454e-05,
+ "loss": 0.5718,
"step": 793
},
{
- "epoch": 16.07,
- "learning_rate": 9.872448979591837e-05,
- "loss": 1.0864,
+ "epoch": 8.97,
+ "learning_rate": 8.72159090909091e-05,
+ "loss": 0.5585,
"step": 794
},
{
- "epoch": 16.09,
- "learning_rate": 9.859693877551021e-05,
- "loss": 1.182,
+ "epoch": 8.98,
+ "learning_rate": 8.707386363636363e-05,
+ "loss": 0.5563,
"step": 795
},
{
- "epoch": 16.11,
- "learning_rate": 9.846938775510204e-05,
- "loss": 1.1272,
+ "epoch": 8.99,
+ "learning_rate": 8.693181818181818e-05,
+ "loss": 0.581,
"step": 796
},
{
- "epoch": 16.13,
- "learning_rate": 9.834183673469389e-05,
- "loss": 1.1946,
+ "epoch": 9.0,
+ "learning_rate": 8.678977272727274e-05,
+ "loss": 0.5511,
"step": 797
},
{
- "epoch": 16.15,
- "learning_rate": 9.821428571428572e-05,
- "loss": 1.0875,
+ "epoch": 9.02,
+ "learning_rate": 8.664772727272727e-05,
+ "loss": 0.5103,
"step": 798
},
{
- "epoch": 16.17,
- "learning_rate": 9.808673469387756e-05,
- "loss": 1.1671,
+ "epoch": 9.03,
+ "learning_rate": 8.650568181818183e-05,
+ "loss": 0.5323,
"step": 799
},
{
- "epoch": 16.19,
- "learning_rate": 9.79591836734694e-05,
- "loss": 1.1502,
+ "epoch": 9.04,
+ "learning_rate": 8.636363636363637e-05,
+ "loss": 0.5092,
"step": 800
},
{
- "epoch": 16.21,
- "learning_rate": 9.783163265306124e-05,
- "loss": 1.19,
+ "epoch": 9.05,
+ "learning_rate": 8.62215909090909e-05,
+ "loss": 0.5247,
"step": 801
},
{
- "epoch": 16.23,
- "learning_rate": 9.770408163265307e-05,
- "loss": 1.1258,
+ "epoch": 9.06,
+ "learning_rate": 8.607954545454546e-05,
+ "loss": 0.5403,
"step": 802
},
{
- "epoch": 16.25,
- "learning_rate": 9.75765306122449e-05,
- "loss": 1.1765,
+ "epoch": 9.07,
+ "learning_rate": 8.593750000000001e-05,
+ "loss": 0.5252,
"step": 803
},
{
- "epoch": 16.27,
- "learning_rate": 9.744897959183674e-05,
- "loss": 1.1217,
+ "epoch": 9.08,
+ "learning_rate": 8.579545454545454e-05,
+ "loss": 0.5296,
"step": 804
},
{
- "epoch": 16.29,
- "learning_rate": 9.732142857142858e-05,
- "loss": 1.1293,
+ "epoch": 9.09,
+ "learning_rate": 8.56534090909091e-05,
+ "loss": 0.5223,
"step": 805
},
{
- "epoch": 16.31,
- "learning_rate": 9.719387755102042e-05,
- "loss": 1.17,
+ "epoch": 9.11,
+ "learning_rate": 8.551136363636364e-05,
+ "loss": 0.4972,
"step": 806
},
{
- "epoch": 16.33,
- "learning_rate": 9.706632653061225e-05,
- "loss": 1.17,
+ "epoch": 9.12,
+ "learning_rate": 8.536931818181818e-05,
+ "loss": 0.5005,
"step": 807
},
{
- "epoch": 16.35,
- "learning_rate": 9.693877551020408e-05,
- "loss": 1.2004,
+ "epoch": 9.13,
+ "learning_rate": 8.522727272727273e-05,
+ "loss": 0.5249,
"step": 808
},
{
- "epoch": 16.37,
- "learning_rate": 9.681122448979593e-05,
- "loss": 1.1648,
+ "epoch": 9.14,
+ "learning_rate": 8.508522727272728e-05,
+ "loss": 0.5135,
"step": 809
},
{
- "epoch": 16.39,
- "learning_rate": 9.668367346938776e-05,
- "loss": 1.0688,
+ "epoch": 9.15,
+ "learning_rate": 8.494318181818182e-05,
+ "loss": 0.5053,
"step": 810
},
{
- "epoch": 16.41,
- "learning_rate": 9.655612244897959e-05,
- "loss": 1.1607,
+ "epoch": 9.16,
+ "learning_rate": 8.480113636363637e-05,
+ "loss": 0.5158,
"step": 811
},
{
- "epoch": 16.43,
- "learning_rate": 9.642857142857143e-05,
- "loss": 1.1298,
+ "epoch": 9.17,
+ "learning_rate": 8.465909090909091e-05,
+ "loss": 0.5061,
"step": 812
},
{
- "epoch": 16.45,
- "learning_rate": 9.630102040816326e-05,
- "loss": 1.1064,
+ "epoch": 9.18,
+ "learning_rate": 8.451704545454546e-05,
+ "loss": 0.4988,
"step": 813
},
{
- "epoch": 16.47,
- "learning_rate": 9.617346938775511e-05,
- "loss": 1.1472,
+ "epoch": 9.2,
+ "learning_rate": 8.4375e-05,
+ "loss": 0.5273,
"step": 814
},
{
- "epoch": 16.49,
- "learning_rate": 9.604591836734694e-05,
- "loss": 1.1577,
+ "epoch": 9.21,
+ "learning_rate": 8.423295454545455e-05,
+ "loss": 0.5332,
"step": 815
},
{
- "epoch": 16.51,
- "learning_rate": 9.591836734693878e-05,
- "loss": 1.1436,
+ "epoch": 9.22,
+ "learning_rate": 8.40909090909091e-05,
+ "loss": 0.5181,
"step": 816
},
{
- "epoch": 16.53,
- "learning_rate": 9.579081632653061e-05,
- "loss": 1.1657,
+ "epoch": 9.23,
+ "learning_rate": 8.394886363636364e-05,
+ "loss": 0.5085,
"step": 817
},
{
- "epoch": 16.55,
- "learning_rate": 9.566326530612246e-05,
- "loss": 1.1147,
+ "epoch": 9.24,
+ "learning_rate": 8.380681818181818e-05,
+ "loss": 0.5137,
"step": 818
},
{
- "epoch": 16.57,
- "learning_rate": 9.553571428571429e-05,
- "loss": 1.1839,
+ "epoch": 9.25,
+ "learning_rate": 8.366477272727273e-05,
+ "loss": 0.5195,
"step": 819
},
{
- "epoch": 16.59,
- "learning_rate": 9.540816326530613e-05,
- "loss": 1.1298,
+ "epoch": 9.26,
+ "learning_rate": 8.352272727272727e-05,
+ "loss": 0.5077,
"step": 820
},
{
- "epoch": 16.61,
- "learning_rate": 9.528061224489796e-05,
- "loss": 1.2141,
+ "epoch": 9.28,
+ "learning_rate": 8.338068181818183e-05,
+ "loss": 0.5074,
"step": 821
},
{
- "epoch": 16.63,
- "learning_rate": 9.515306122448981e-05,
- "loss": 1.2045,
+ "epoch": 9.29,
+ "learning_rate": 8.323863636363637e-05,
+ "loss": 0.5142,
"step": 822
},
{
- "epoch": 16.65,
- "learning_rate": 9.502551020408164e-05,
- "loss": 1.1791,
+ "epoch": 9.3,
+ "learning_rate": 8.309659090909091e-05,
+ "loss": 0.5116,
"step": 823
},
{
- "epoch": 16.67,
- "learning_rate": 9.489795918367348e-05,
- "loss": 1.1137,
+ "epoch": 9.31,
+ "learning_rate": 8.295454545454547e-05,
+ "loss": 0.4974,
"step": 824
},
{
- "epoch": 16.69,
- "learning_rate": 9.477040816326531e-05,
- "loss": 1.1312,
+ "epoch": 9.32,
+ "learning_rate": 8.28125e-05,
+ "loss": 0.5117,
"step": 825
},
{
- "epoch": 16.71,
- "learning_rate": 9.464285714285715e-05,
- "loss": 1.1102,
+ "epoch": 9.33,
+ "learning_rate": 8.267045454545455e-05,
+ "loss": 0.5114,
"step": 826
},
{
- "epoch": 16.73,
- "learning_rate": 9.451530612244899e-05,
- "loss": 1.1865,
+ "epoch": 9.34,
+ "learning_rate": 8.25284090909091e-05,
+ "loss": 0.5039,
"step": 827
},
{
- "epoch": 16.75,
- "learning_rate": 9.438775510204082e-05,
- "loss": 1.1232,
+ "epoch": 9.35,
+ "learning_rate": 8.238636363636364e-05,
+ "loss": 0.498,
"step": 828
},
{
- "epoch": 16.77,
- "learning_rate": 9.426020408163265e-05,
- "loss": 1.2068,
+ "epoch": 9.37,
+ "learning_rate": 8.224431818181818e-05,
+ "loss": 0.5042,
"step": 829
},
{
- "epoch": 16.79,
- "learning_rate": 9.41326530612245e-05,
- "loss": 1.1864,
+ "epoch": 9.38,
+ "learning_rate": 8.210227272727274e-05,
+ "loss": 0.5049,
"step": 830
},
{
- "epoch": 16.81,
- "learning_rate": 9.400510204081633e-05,
- "loss": 1.2195,
+ "epoch": 9.39,
+ "learning_rate": 8.196022727272727e-05,
+ "loss": 0.5123,
"step": 831
},
{
- "epoch": 16.83,
- "learning_rate": 9.387755102040817e-05,
- "loss": 1.2063,
+ "epoch": 9.4,
+ "learning_rate": 8.181818181818183e-05,
+ "loss": 0.4907,
"step": 832
},
{
- "epoch": 16.85,
- "learning_rate": 9.375e-05,
- "loss": 1.1455,
+ "epoch": 9.41,
+ "learning_rate": 8.167613636363637e-05,
+ "loss": 0.5267,
"step": 833
},
{
- "epoch": 16.88,
- "learning_rate": 9.362244897959183e-05,
- "loss": 1.1819,
+ "epoch": 9.42,
+ "learning_rate": 8.15340909090909e-05,
+ "loss": 0.5314,
"step": 834
},
{
- "epoch": 16.9,
- "learning_rate": 9.349489795918368e-05,
- "loss": 1.1887,
+ "epoch": 9.43,
+ "learning_rate": 8.139204545454546e-05,
+ "loss": 0.4952,
"step": 835
},
{
- "epoch": 16.92,
- "learning_rate": 9.336734693877551e-05,
- "loss": 1.1557,
+ "epoch": 9.44,
+ "learning_rate": 8.125000000000001e-05,
+ "loss": 0.5014,
"step": 836
},
{
- "epoch": 16.94,
- "learning_rate": 9.323979591836735e-05,
- "loss": 1.2094,
+ "epoch": 9.46,
+ "learning_rate": 8.110795454545454e-05,
+ "loss": 0.4967,
"step": 837
},
{
- "epoch": 16.96,
- "learning_rate": 9.311224489795918e-05,
- "loss": 1.1512,
+ "epoch": 9.47,
+ "learning_rate": 8.09659090909091e-05,
+ "loss": 0.5116,
"step": 838
},
{
- "epoch": 16.98,
- "learning_rate": 9.298469387755103e-05,
- "loss": 1.1463,
+ "epoch": 9.48,
+ "learning_rate": 8.082386363636365e-05,
+ "loss": 0.5119,
"step": 839
},
{
- "epoch": 17.0,
- "learning_rate": 9.285714285714286e-05,
- "loss": 1.155,
+ "epoch": 9.49,
+ "learning_rate": 8.068181818181818e-05,
+ "loss": 0.4987,
"step": 840
},
{
- "epoch": 17.02,
- "learning_rate": 9.27295918367347e-05,
- "loss": 1.1292,
+ "epoch": 9.5,
+ "learning_rate": 8.053977272727274e-05,
+ "loss": 0.5063,
"step": 841
},
{
- "epoch": 17.04,
- "learning_rate": 9.260204081632653e-05,
- "loss": 1.0996,
+ "epoch": 9.51,
+ "learning_rate": 8.039772727272728e-05,
+ "loss": 0.5019,
"step": 842
},
{
- "epoch": 17.06,
- "learning_rate": 9.247448979591838e-05,
- "loss": 1.0662,
+ "epoch": 9.52,
+ "learning_rate": 8.025568181818183e-05,
+ "loss": 0.5272,
"step": 843
},
{
- "epoch": 17.08,
- "learning_rate": 9.234693877551021e-05,
- "loss": 1.0931,
+ "epoch": 9.54,
+ "learning_rate": 8.011363636363637e-05,
+ "loss": 0.4969,
"step": 844
},
{
- "epoch": 17.1,
- "learning_rate": 9.221938775510205e-05,
- "loss": 1.0727,
+ "epoch": 9.55,
+ "learning_rate": 7.997159090909092e-05,
+ "loss": 0.5222,
"step": 845
},
{
- "epoch": 17.12,
- "learning_rate": 9.209183673469388e-05,
- "loss": 1.1043,
+ "epoch": 9.56,
+ "learning_rate": 7.982954545454546e-05,
+ "loss": 0.4729,
"step": 846
},
{
- "epoch": 17.14,
- "learning_rate": 9.196428571428572e-05,
- "loss": 1.0594,
+ "epoch": 9.57,
+ "learning_rate": 7.96875e-05,
+ "loss": 0.4976,
"step": 847
},
{
- "epoch": 17.16,
- "learning_rate": 9.183673469387756e-05,
- "loss": 1.0952,
+ "epoch": 9.58,
+ "learning_rate": 7.954545454545455e-05,
+ "loss": 0.4974,
"step": 848
},
{
- "epoch": 17.18,
- "learning_rate": 9.170918367346939e-05,
- "loss": 1.0639,
+ "epoch": 9.59,
+ "learning_rate": 7.94034090909091e-05,
+ "loss": 0.4849,
"step": 849
},
{
- "epoch": 17.2,
- "learning_rate": 9.158163265306124e-05,
- "loss": 1.132,
+ "epoch": 9.6,
+ "learning_rate": 7.926136363636364e-05,
+ "loss": 0.4897,
"step": 850
},
{
- "epoch": 17.22,
- "learning_rate": 9.145408163265307e-05,
- "loss": 1.1083,
+ "epoch": 9.61,
+ "learning_rate": 7.911931818181819e-05,
+ "loss": 0.4962,
"step": 851
},
{
- "epoch": 17.24,
- "learning_rate": 9.13265306122449e-05,
- "loss": 1.1282,
+ "epoch": 9.63,
+ "learning_rate": 7.897727272727273e-05,
+ "loss": 0.4877,
"step": 852
},
{
- "epoch": 17.26,
- "learning_rate": 9.119897959183674e-05,
- "loss": 1.0474,
+ "epoch": 9.64,
+ "learning_rate": 7.883522727272728e-05,
+ "loss": 0.4921,
"step": 853
},
{
- "epoch": 17.28,
- "learning_rate": 9.107142857142857e-05,
- "loss": 1.1138,
+ "epoch": 9.65,
+ "learning_rate": 7.869318181818182e-05,
+ "loss": 0.4969,
"step": 854
},
{
- "epoch": 17.3,
- "learning_rate": 9.094387755102042e-05,
- "loss": 1.1025,
+ "epoch": 9.66,
+ "learning_rate": 7.855113636363637e-05,
+ "loss": 0.5045,
"step": 855
},
{
- "epoch": 17.32,
- "learning_rate": 9.081632653061225e-05,
- "loss": 1.0968,
+ "epoch": 9.67,
+ "learning_rate": 7.840909090909091e-05,
+ "loss": 0.5207,
"step": 856
},
{
- "epoch": 17.34,
- "learning_rate": 9.068877551020408e-05,
- "loss": 1.1683,
+ "epoch": 9.68,
+ "learning_rate": 7.826704545454546e-05,
+ "loss": 0.5098,
"step": 857
},
{
- "epoch": 17.36,
- "learning_rate": 9.056122448979592e-05,
- "loss": 1.0975,
+ "epoch": 9.69,
+ "learning_rate": 7.8125e-05,
+ "loss": 0.5005,
"step": 858
},
{
- "epoch": 17.38,
- "learning_rate": 9.043367346938775e-05,
- "loss": 1.1274,
+ "epoch": 9.7,
+ "learning_rate": 7.798295454545455e-05,
+ "loss": 0.5028,
"step": 859
},
{
- "epoch": 17.4,
- "learning_rate": 9.030612244897958e-05,
- "loss": 1.0916,
+ "epoch": 9.72,
+ "learning_rate": 7.784090909090909e-05,
+ "loss": 0.5067,
"step": 860
},
{
- "epoch": 17.42,
- "learning_rate": 9.017857142857143e-05,
- "loss": 1.0912,
+ "epoch": 9.73,
+ "learning_rate": 7.769886363636364e-05,
+ "loss": 0.484,
"step": 861
},
{
- "epoch": 17.44,
- "learning_rate": 9.005102040816327e-05,
- "loss": 1.0875,
+ "epoch": 9.74,
+ "learning_rate": 7.755681818181818e-05,
+ "loss": 0.5029,
"step": 862
},
{
- "epoch": 17.46,
- "learning_rate": 8.99234693877551e-05,
- "loss": 1.05,
+ "epoch": 9.75,
+ "learning_rate": 7.741477272727273e-05,
+ "loss": 0.5077,
"step": 863
},
{
- "epoch": 17.48,
- "learning_rate": 8.979591836734695e-05,
- "loss": 1.1418,
+ "epoch": 9.76,
+ "learning_rate": 7.727272727272727e-05,
+ "loss": 0.5091,
"step": 864
},
{
- "epoch": 17.5,
- "learning_rate": 8.966836734693878e-05,
- "loss": 1.0609,
+ "epoch": 9.77,
+ "learning_rate": 7.713068181818183e-05,
+ "loss": 0.4781,
"step": 865
},
{
- "epoch": 17.52,
- "learning_rate": 8.954081632653062e-05,
- "loss": 1.1611,
+ "epoch": 9.78,
+ "learning_rate": 7.698863636363636e-05,
+ "loss": 0.5124,
"step": 866
},
{
- "epoch": 17.54,
- "learning_rate": 8.941326530612245e-05,
- "loss": 1.1065,
+ "epoch": 9.79,
+ "learning_rate": 7.684659090909091e-05,
+ "loss": 0.4859,
"step": 867
},
{
- "epoch": 17.56,
- "learning_rate": 8.92857142857143e-05,
- "loss": 1.1611,
+ "epoch": 9.81,
+ "learning_rate": 7.670454545454547e-05,
+ "loss": 0.4872,
"step": 868
},
{
- "epoch": 17.58,
- "learning_rate": 8.915816326530613e-05,
- "loss": 1.1398,
+ "epoch": 9.82,
+ "learning_rate": 7.65625e-05,
+ "loss": 0.4675,
"step": 869
},
{
- "epoch": 17.6,
- "learning_rate": 8.903061224489796e-05,
- "loss": 1.1055,
+ "epoch": 9.83,
+ "learning_rate": 7.642045454545454e-05,
+ "loss": 0.5056,
"step": 870
},
{
- "epoch": 17.62,
- "learning_rate": 8.89030612244898e-05,
- "loss": 1.1314,
+ "epoch": 9.84,
+ "learning_rate": 7.62784090909091e-05,
+ "loss": 0.4868,
"step": 871
},
{
- "epoch": 17.64,
- "learning_rate": 8.877551020408164e-05,
- "loss": 1.1084,
+ "epoch": 9.85,
+ "learning_rate": 7.613636363636363e-05,
+ "loss": 0.4907,
"step": 872
},
{
- "epoch": 17.66,
- "learning_rate": 8.864795918367348e-05,
- "loss": 1.1254,
+ "epoch": 9.86,
+ "learning_rate": 7.599431818181818e-05,
+ "loss": 0.474,
"step": 873
},
{
- "epoch": 17.68,
- "learning_rate": 8.852040816326531e-05,
- "loss": 1.142,
+ "epoch": 9.87,
+ "learning_rate": 7.585227272727274e-05,
+ "loss": 0.4813,
"step": 874
},
{
- "epoch": 17.7,
- "learning_rate": 8.839285714285714e-05,
- "loss": 1.1371,
+ "epoch": 9.89,
+ "learning_rate": 7.571022727272727e-05,
+ "loss": 0.4838,
"step": 875
},
{
- "epoch": 17.72,
- "learning_rate": 8.826530612244899e-05,
- "loss": 1.1092,
+ "epoch": 9.9,
+ "learning_rate": 7.556818181818183e-05,
+ "loss": 0.4935,
"step": 876
},
{
- "epoch": 17.75,
- "learning_rate": 8.813775510204082e-05,
- "loss": 1.161,
+ "epoch": 9.91,
+ "learning_rate": 7.542613636363637e-05,
+ "loss": 0.4884,
"step": 877
},
{
- "epoch": 17.77,
- "learning_rate": 8.801020408163265e-05,
- "loss": 1.1044,
+ "epoch": 9.92,
+ "learning_rate": 7.52840909090909e-05,
+ "loss": 0.4797,
"step": 878
},
{
- "epoch": 17.79,
- "learning_rate": 8.788265306122449e-05,
- "loss": 1.117,
+ "epoch": 9.93,
+ "learning_rate": 7.514204545454546e-05,
+ "loss": 0.479,
"step": 879
},
{
- "epoch": 17.81,
- "learning_rate": 8.775510204081632e-05,
- "loss": 1.1262,
+ "epoch": 9.94,
+ "learning_rate": 7.500000000000001e-05,
+ "loss": 0.4727,
"step": 880
},
{
- "epoch": 17.83,
- "learning_rate": 8.762755102040817e-05,
- "loss": 1.0829,
+ "epoch": 9.95,
+ "learning_rate": 7.485795454545454e-05,
+ "loss": 0.4758,
"step": 881
},
{
- "epoch": 17.85,
- "learning_rate": 8.75e-05,
- "loss": 1.1393,
+ "epoch": 9.96,
+ "learning_rate": 7.47159090909091e-05,
+ "loss": 0.482,
"step": 882
},
{
- "epoch": 17.87,
- "learning_rate": 8.737244897959183e-05,
- "loss": 1.1781,
+ "epoch": 9.98,
+ "learning_rate": 7.457386363636364e-05,
+ "loss": 0.4951,
"step": 883
},
{
- "epoch": 17.89,
- "learning_rate": 8.724489795918367e-05,
- "loss": 1.1582,
+ "epoch": 9.99,
+ "learning_rate": 7.443181818181817e-05,
+ "loss": 0.4823,
"step": 884
},
{
- "epoch": 17.91,
- "learning_rate": 8.711734693877552e-05,
- "loss": 1.1469,
+ "epoch": 10.0,
+ "learning_rate": 7.428977272727273e-05,
+ "loss": 0.4638,
"step": 885
},
{
- "epoch": 17.93,
- "learning_rate": 8.698979591836735e-05,
- "loss": 1.1494,
+ "epoch": 10.01,
+ "learning_rate": 7.414772727272728e-05,
+ "loss": 0.4715,
"step": 886
},
{
- "epoch": 17.95,
- "learning_rate": 8.68622448979592e-05,
- "loss": 1.1251,
+ "epoch": 10.02,
+ "learning_rate": 7.400568181818182e-05,
+ "loss": 0.461,
"step": 887
},
{
- "epoch": 17.97,
- "learning_rate": 8.673469387755102e-05,
- "loss": 1.1624,
+ "epoch": 10.03,
+ "learning_rate": 7.386363636363637e-05,
+ "loss": 0.4429,
"step": 888
},
{
- "epoch": 17.99,
- "learning_rate": 8.660714285714287e-05,
- "loss": 1.0842,
+ "epoch": 10.04,
+ "learning_rate": 7.372159090909091e-05,
+ "loss": 0.4403,
"step": 889
},
{
- "epoch": 18.01,
- "learning_rate": 8.64795918367347e-05,
- "loss": 1.1944,
+ "epoch": 10.05,
+ "learning_rate": 7.357954545454546e-05,
+ "loss": 0.4519,
"step": 890
},
{
- "epoch": 18.03,
- "learning_rate": 8.635204081632653e-05,
- "loss": 1.0642,
+ "epoch": 10.07,
+ "learning_rate": 7.34375e-05,
+ "loss": 0.4611,
"step": 891
},
{
- "epoch": 18.05,
- "learning_rate": 8.622448979591838e-05,
- "loss": 1.0459,
+ "epoch": 10.08,
+ "learning_rate": 7.329545454545455e-05,
+ "loss": 0.4543,
"step": 892
},
{
- "epoch": 18.07,
- "learning_rate": 8.60969387755102e-05,
- "loss": 1.0941,
+ "epoch": 10.09,
+ "learning_rate": 7.315340909090909e-05,
+ "loss": 0.4528,
"step": 893
},
{
- "epoch": 18.09,
- "learning_rate": 8.596938775510205e-05,
- "loss": 1.0457,
+ "epoch": 10.1,
+ "learning_rate": 7.301136363636364e-05,
+ "loss": 0.4586,
"step": 894
},
{
- "epoch": 18.11,
- "learning_rate": 8.584183673469388e-05,
- "loss": 1.1033,
+ "epoch": 10.11,
+ "learning_rate": 7.286931818181818e-05,
+ "loss": 0.4418,
"step": 895
},
{
- "epoch": 18.13,
- "learning_rate": 8.571428571428571e-05,
- "loss": 1.0756,
+ "epoch": 10.12,
+ "learning_rate": 7.272727272727273e-05,
+ "loss": 0.4435,
"step": 896
},
{
- "epoch": 18.15,
- "learning_rate": 8.558673469387756e-05,
- "loss": 1.0615,
+ "epoch": 10.13,
+ "learning_rate": 7.258522727272727e-05,
+ "loss": 0.44,
"step": 897
},
{
- "epoch": 18.17,
- "learning_rate": 8.545918367346939e-05,
- "loss": 1.0828,
+ "epoch": 10.15,
+ "learning_rate": 7.244318181818183e-05,
+ "loss": 0.4589,
"step": 898
},
{
- "epoch": 18.19,
- "learning_rate": 8.533163265306123e-05,
- "loss": 1.1158,
+ "epoch": 10.16,
+ "learning_rate": 7.230113636363636e-05,
+ "loss": 0.4597,
"step": 899
},
{
- "epoch": 18.21,
- "learning_rate": 8.520408163265306e-05,
- "loss": 1.0133,
+ "epoch": 10.17,
+ "learning_rate": 7.215909090909091e-05,
+ "loss": 0.4479,
"step": 900
},
{
- "epoch": 18.23,
- "learning_rate": 8.50765306122449e-05,
- "loss": 1.0437,
+ "epoch": 10.18,
+ "learning_rate": 7.201704545454547e-05,
+ "loss": 0.4477,
"step": 901
},
{
- "epoch": 18.25,
- "learning_rate": 8.494897959183674e-05,
- "loss": 1.0372,
+ "epoch": 10.19,
+ "learning_rate": 7.1875e-05,
+ "loss": 0.446,
"step": 902
},
{
- "epoch": 18.27,
- "learning_rate": 8.482142857142857e-05,
- "loss": 1.1012,
+ "epoch": 10.2,
+ "learning_rate": 7.173295454545454e-05,
+ "loss": 0.4546,
"step": 903
},
{
- "epoch": 18.29,
- "learning_rate": 8.469387755102041e-05,
- "loss": 1.0777,
+ "epoch": 10.21,
+ "learning_rate": 7.15909090909091e-05,
+ "loss": 0.4347,
"step": 904
},
{
- "epoch": 18.31,
- "learning_rate": 8.456632653061224e-05,
- "loss": 1.0799,
+ "epoch": 10.22,
+ "learning_rate": 7.144886363636363e-05,
+ "loss": 0.452,
"step": 905
},
{
- "epoch": 18.33,
- "learning_rate": 8.443877551020409e-05,
- "loss": 0.9846,
+ "epoch": 10.24,
+ "learning_rate": 7.130681818181818e-05,
+ "loss": 0.4536,
"step": 906
},
{
- "epoch": 18.35,
- "learning_rate": 8.431122448979592e-05,
- "loss": 1.1,
+ "epoch": 10.25,
+ "learning_rate": 7.116477272727274e-05,
+ "loss": 0.4492,
"step": 907
},
{
- "epoch": 18.37,
- "learning_rate": 8.418367346938776e-05,
- "loss": 1.0787,
+ "epoch": 10.26,
+ "learning_rate": 7.102272727272727e-05,
+ "loss": 0.4401,
"step": 908
},
{
- "epoch": 18.39,
- "learning_rate": 8.40561224489796e-05,
- "loss": 1.0647,
+ "epoch": 10.27,
+ "learning_rate": 7.088068181818183e-05,
+ "loss": 0.4609,
"step": 909
},
{
- "epoch": 18.41,
- "learning_rate": 8.392857142857144e-05,
- "loss": 1.056,
+ "epoch": 10.28,
+ "learning_rate": 7.073863636363637e-05,
+ "loss": 0.4544,
"step": 910
},
{
- "epoch": 18.43,
- "learning_rate": 8.380102040816327e-05,
- "loss": 1.1131,
+ "epoch": 10.29,
+ "learning_rate": 7.05965909090909e-05,
+ "loss": 0.4477,
"step": 911
},
{
- "epoch": 18.45,
- "learning_rate": 8.367346938775511e-05,
- "loss": 1.0825,
+ "epoch": 10.3,
+ "learning_rate": 7.045454545454546e-05,
+ "loss": 0.4445,
"step": 912
},
{
- "epoch": 18.47,
- "learning_rate": 8.354591836734695e-05,
- "loss": 1.0681,
+ "epoch": 10.31,
+ "learning_rate": 7.031250000000001e-05,
+ "loss": 0.4544,
"step": 913
},
{
- "epoch": 18.49,
- "learning_rate": 8.341836734693878e-05,
- "loss": 1.0479,
+ "epoch": 10.33,
+ "learning_rate": 7.017045454545454e-05,
+ "loss": 0.4634,
"step": 914
},
{
- "epoch": 18.51,
- "learning_rate": 8.329081632653062e-05,
- "loss": 1.0921,
+ "epoch": 10.34,
+ "learning_rate": 7.00284090909091e-05,
+ "loss": 0.4499,
"step": 915
},
{
- "epoch": 18.53,
- "learning_rate": 8.316326530612245e-05,
- "loss": 1.0626,
+ "epoch": 10.35,
+ "learning_rate": 6.988636363636364e-05,
+ "loss": 0.4354,
"step": 916
},
{
- "epoch": 18.55,
- "learning_rate": 8.30357142857143e-05,
- "loss": 1.0518,
+ "epoch": 10.36,
+ "learning_rate": 6.974431818181818e-05,
+ "loss": 0.454,
"step": 917
},
{
- "epoch": 18.57,
- "learning_rate": 8.290816326530613e-05,
- "loss": 1.0557,
+ "epoch": 10.37,
+ "learning_rate": 6.960227272727273e-05,
+ "loss": 0.4473,
"step": 918
},
{
- "epoch": 18.6,
- "learning_rate": 8.278061224489796e-05,
- "loss": 1.0831,
+ "epoch": 10.38,
+ "learning_rate": 6.946022727272728e-05,
+ "loss": 0.4347,
"step": 919
},
{
- "epoch": 18.62,
- "learning_rate": 8.26530612244898e-05,
- "loss": 1.0307,
+ "epoch": 10.39,
+ "learning_rate": 6.931818181818182e-05,
+ "loss": 0.441,
"step": 920
},
{
- "epoch": 18.64,
- "learning_rate": 8.252551020408163e-05,
- "loss": 1.0455,
+ "epoch": 10.4,
+ "learning_rate": 6.917613636363637e-05,
+ "loss": 0.4545,
"step": 921
},
{
- "epoch": 18.66,
- "learning_rate": 8.239795918367348e-05,
- "loss": 1.0667,
+ "epoch": 10.42,
+ "learning_rate": 6.903409090909091e-05,
+ "loss": 0.458,
"step": 922
},
{
- "epoch": 18.68,
- "learning_rate": 8.227040816326531e-05,
- "loss": 1.0736,
+ "epoch": 10.43,
+ "learning_rate": 6.889204545454546e-05,
+ "loss": 0.4381,
"step": 923
},
{
- "epoch": 18.7,
- "learning_rate": 8.214285714285714e-05,
- "loss": 1.0108,
+ "epoch": 10.44,
+ "learning_rate": 6.875e-05,
+ "loss": 0.441,
"step": 924
},
{
- "epoch": 18.72,
- "learning_rate": 8.201530612244898e-05,
- "loss": 1.0458,
+ "epoch": 10.45,
+ "learning_rate": 6.860795454545455e-05,
+ "loss": 0.4446,
"step": 925
},
{
- "epoch": 18.74,
- "learning_rate": 8.188775510204081e-05,
- "loss": 1.0852,
+ "epoch": 10.46,
+ "learning_rate": 6.84659090909091e-05,
+ "loss": 0.4548,
"step": 926
},
{
- "epoch": 18.76,
- "learning_rate": 8.176020408163265e-05,
- "loss": 1.1207,
+ "epoch": 10.47,
+ "learning_rate": 6.832386363636364e-05,
+ "loss": 0.4404,
"step": 927
},
{
- "epoch": 18.78,
- "learning_rate": 8.163265306122449e-05,
- "loss": 1.0914,
+ "epoch": 10.48,
+ "learning_rate": 6.818181818181818e-05,
+ "loss": 0.4446,
"step": 928
},
{
- "epoch": 18.8,
- "learning_rate": 8.150510204081633e-05,
- "loss": 1.1108,
+ "epoch": 10.5,
+ "learning_rate": 6.803977272727273e-05,
+ "loss": 0.4434,
"step": 929
},
{
- "epoch": 18.82,
- "learning_rate": 8.137755102040817e-05,
- "loss": 1.1394,
+ "epoch": 10.51,
+ "learning_rate": 6.789772727272727e-05,
+ "loss": 0.4778,
"step": 930
},
{
- "epoch": 18.84,
- "learning_rate": 8.125000000000001e-05,
- "loss": 1.029,
+ "epoch": 10.52,
+ "learning_rate": 6.775568181818182e-05,
+ "loss": 0.4356,
"step": 931
},
{
- "epoch": 18.86,
- "learning_rate": 8.112244897959184e-05,
- "loss": 1.0661,
+ "epoch": 10.53,
+ "learning_rate": 6.761363636363636e-05,
+ "loss": 0.4464,
"step": 932
},
{
- "epoch": 18.88,
- "learning_rate": 8.099489795918369e-05,
- "loss": 1.0303,
+ "epoch": 10.54,
+ "learning_rate": 6.747159090909091e-05,
+ "loss": 0.4387,
"step": 933
},
{
- "epoch": 18.9,
- "learning_rate": 8.086734693877552e-05,
- "loss": 1.1144,
+ "epoch": 10.55,
+ "learning_rate": 6.732954545454547e-05,
+ "loss": 0.456,
"step": 934
},
{
- "epoch": 18.92,
- "learning_rate": 8.073979591836736e-05,
- "loss": 1.1096,
+ "epoch": 10.56,
+ "learning_rate": 6.71875e-05,
+ "loss": 0.453,
"step": 935
},
{
- "epoch": 18.94,
- "learning_rate": 8.061224489795919e-05,
- "loss": 1.123,
+ "epoch": 10.57,
+ "learning_rate": 6.704545454545455e-05,
+ "loss": 0.4611,
"step": 936
},
{
- "epoch": 18.96,
- "learning_rate": 8.048469387755102e-05,
- "loss": 1.1002,
+ "epoch": 10.59,
+ "learning_rate": 6.69034090909091e-05,
+ "loss": 0.4354,
"step": 937
},
{
- "epoch": 18.98,
- "learning_rate": 8.035714285714287e-05,
- "loss": 1.1016,
+ "epoch": 10.6,
+ "learning_rate": 6.676136363636364e-05,
+ "loss": 0.4519,
"step": 938
},
{
- "epoch": 19.0,
- "learning_rate": 8.02295918367347e-05,
- "loss": 1.0847,
+ "epoch": 10.61,
+ "learning_rate": 6.661931818181818e-05,
+ "loss": 0.4435,
"step": 939
},
{
- "epoch": 19.02,
- "learning_rate": 8.010204081632653e-05,
- "loss": 1.1029,
+ "epoch": 10.62,
+ "learning_rate": 6.647727272727274e-05,
+ "loss": 0.4422,
"step": 940
},
{
- "epoch": 19.04,
- "learning_rate": 7.997448979591837e-05,
- "loss": 1.041,
+ "epoch": 10.63,
+ "learning_rate": 6.633522727272727e-05,
+ "loss": 0.4344,
"step": 941
},
{
- "epoch": 19.06,
- "learning_rate": 7.98469387755102e-05,
- "loss": 1.01,
+ "epoch": 10.64,
+ "learning_rate": 6.619318181818183e-05,
+ "loss": 0.4419,
"step": 942
},
{
- "epoch": 19.08,
- "learning_rate": 7.971938775510205e-05,
- "loss": 1.0197,
+ "epoch": 10.65,
+ "learning_rate": 6.605113636363637e-05,
+ "loss": 0.4308,
"step": 943
},
{
- "epoch": 19.1,
- "learning_rate": 7.959183673469388e-05,
- "loss": 1.0543,
+ "epoch": 10.66,
+ "learning_rate": 6.59090909090909e-05,
+ "loss": 0.4043,
"step": 944
},
{
- "epoch": 19.12,
- "learning_rate": 7.946428571428571e-05,
- "loss": 1.0369,
+ "epoch": 10.68,
+ "learning_rate": 6.576704545454546e-05,
+ "loss": 0.4626,
"step": 945
},
{
- "epoch": 19.14,
- "learning_rate": 7.933673469387755e-05,
- "loss": 1.0154,
+ "epoch": 10.69,
+ "learning_rate": 6.562500000000001e-05,
+ "loss": 0.4365,
"step": 946
},
{
- "epoch": 19.16,
- "learning_rate": 7.920918367346939e-05,
- "loss": 0.9546,
+ "epoch": 10.7,
+ "learning_rate": 6.548295454545454e-05,
+ "loss": 0.4397,
"step": 947
},
{
- "epoch": 19.18,
- "learning_rate": 7.908163265306123e-05,
- "loss": 0.9982,
+ "epoch": 10.71,
+ "learning_rate": 6.53409090909091e-05,
+ "loss": 0.4463,
"step": 948
},
{
- "epoch": 19.2,
- "learning_rate": 7.895408163265306e-05,
- "loss": 1.0748,
+ "epoch": 10.72,
+ "learning_rate": 6.519886363636364e-05,
+ "loss": 0.4394,
"step": 949
},
{
- "epoch": 19.22,
- "learning_rate": 7.882653061224489e-05,
- "loss": 1.0562,
+ "epoch": 10.73,
+ "learning_rate": 6.505681818181818e-05,
+ "loss": 0.45,
"step": 950
},
{
- "epoch": 19.24,
- "learning_rate": 7.869897959183674e-05,
- "loss": 1.0352,
+ "epoch": 10.74,
+ "learning_rate": 6.491477272727273e-05,
+ "loss": 0.4363,
"step": 951
},
{
- "epoch": 19.26,
- "learning_rate": 7.857142857142858e-05,
- "loss": 0.9976,
+ "epoch": 10.76,
+ "learning_rate": 6.477272727272728e-05,
+ "loss": 0.4566,
"step": 952
},
{
- "epoch": 19.28,
- "learning_rate": 7.844387755102041e-05,
- "loss": 1.0221,
+ "epoch": 10.77,
+ "learning_rate": 6.463068181818183e-05,
+ "loss": 0.4235,
"step": 953
},
{
- "epoch": 19.3,
- "learning_rate": 7.831632653061226e-05,
- "loss": 1.0119,
+ "epoch": 10.78,
+ "learning_rate": 6.448863636363637e-05,
+ "loss": 0.4458,
"step": 954
},
{
- "epoch": 19.32,
- "learning_rate": 7.818877551020409e-05,
- "loss": 1.0657,
+ "epoch": 10.79,
+ "learning_rate": 6.434659090909092e-05,
+ "loss": 0.423,
"step": 955
},
{
- "epoch": 19.34,
- "learning_rate": 7.806122448979593e-05,
- "loss": 0.9591,
+ "epoch": 10.8,
+ "learning_rate": 6.420454545454546e-05,
+ "loss": 0.445,
"step": 956
},
{
- "epoch": 19.36,
- "learning_rate": 7.793367346938776e-05,
- "loss": 1.0101,
+ "epoch": 10.81,
+ "learning_rate": 6.40625e-05,
+ "loss": 0.424,
"step": 957
},
{
- "epoch": 19.38,
- "learning_rate": 7.780612244897959e-05,
- "loss": 1.0453,
+ "epoch": 10.82,
+ "learning_rate": 6.392045454545455e-05,
+ "loss": 0.4224,
"step": 958
},
{
- "epoch": 19.4,
- "learning_rate": 7.767857142857144e-05,
- "loss": 1.0461,
+ "epoch": 10.83,
+ "learning_rate": 6.37784090909091e-05,
+ "loss": 0.4223,
"step": 959
},
{
- "epoch": 19.42,
- "learning_rate": 7.755102040816327e-05,
- "loss": 1.0959,
+ "epoch": 10.85,
+ "learning_rate": 6.363636363636364e-05,
+ "loss": 0.4314,
"step": 960
},
{
- "epoch": 19.44,
- "learning_rate": 7.742346938775511e-05,
- "loss": 1.0608,
+ "epoch": 10.86,
+ "learning_rate": 6.349431818181819e-05,
+ "loss": 0.4488,
"step": 961
},
{
- "epoch": 19.47,
- "learning_rate": 7.729591836734694e-05,
- "loss": 1.1177,
+ "epoch": 10.87,
+ "learning_rate": 6.335227272727273e-05,
+ "loss": 0.423,
"step": 962
},
{
- "epoch": 19.49,
- "learning_rate": 7.716836734693877e-05,
- "loss": 1.0354,
+ "epoch": 10.88,
+ "learning_rate": 6.321022727272728e-05,
+ "loss": 0.4416,
"step": 963
},
{
- "epoch": 19.51,
- "learning_rate": 7.704081632653062e-05,
- "loss": 1.0507,
+ "epoch": 10.89,
+ "learning_rate": 6.306818181818182e-05,
+ "loss": 0.423,
"step": 964
},
{
- "epoch": 19.53,
- "learning_rate": 7.691326530612245e-05,
- "loss": 1.0313,
+ "epoch": 10.9,
+ "learning_rate": 6.292613636363637e-05,
+ "loss": 0.4502,
"step": 965
},
{
- "epoch": 19.55,
- "learning_rate": 7.67857142857143e-05,
- "loss": 1.0569,
+ "epoch": 10.91,
+ "learning_rate": 6.278409090909091e-05,
+ "loss": 0.4266,
"step": 966
},
{
- "epoch": 19.57,
- "learning_rate": 7.665816326530612e-05,
- "loss": 1.0862,
+ "epoch": 10.92,
+ "learning_rate": 6.264204545454546e-05,
+ "loss": 0.4344,
"step": 967
},
{
- "epoch": 19.59,
- "learning_rate": 7.653061224489796e-05,
- "loss": 1.0593,
+ "epoch": 10.94,
+ "learning_rate": 6.25e-05,
+ "loss": 0.434,
"step": 968
},
{
- "epoch": 19.61,
- "learning_rate": 7.64030612244898e-05,
- "loss": 1.0602,
+ "epoch": 10.95,
+ "learning_rate": 6.235795454545455e-05,
+ "loss": 0.4269,
"step": 969
},
{
- "epoch": 19.63,
- "learning_rate": 7.627551020408163e-05,
- "loss": 1.0048,
+ "epoch": 10.96,
+ "learning_rate": 6.221590909090909e-05,
+ "loss": 0.4158,
"step": 970
},
{
- "epoch": 19.65,
- "learning_rate": 7.614795918367347e-05,
- "loss": 1.0346,
+ "epoch": 10.97,
+ "learning_rate": 6.207386363636364e-05,
+ "loss": 0.4231,
"step": 971
},
{
- "epoch": 19.67,
- "learning_rate": 7.60204081632653e-05,
- "loss": 1.0172,
+ "epoch": 10.98,
+ "learning_rate": 6.193181818181818e-05,
+ "loss": 0.4235,
"step": 972
},
{
- "epoch": 19.69,
- "learning_rate": 7.589285714285714e-05,
- "loss": 1.02,
+ "epoch": 10.99,
+ "learning_rate": 6.178977272727273e-05,
+ "loss": 0.4504,
"step": 973
},
{
- "epoch": 19.71,
- "learning_rate": 7.576530612244898e-05,
- "loss": 1.0028,
+ "epoch": 11.0,
+ "learning_rate": 6.164772727272727e-05,
+ "loss": 0.4394,
"step": 974
},
{
- "epoch": 19.73,
- "learning_rate": 7.563775510204083e-05,
- "loss": 1.08,
+ "epoch": 11.02,
+ "learning_rate": 6.150568181818183e-05,
+ "loss": 0.4333,
"step": 975
},
{
- "epoch": 19.75,
- "learning_rate": 7.551020408163266e-05,
- "loss": 1.0402,
+ "epoch": 11.03,
+ "learning_rate": 6.136363636363636e-05,
+ "loss": 0.3936,
"step": 976
},
{
- "epoch": 19.77,
- "learning_rate": 7.53826530612245e-05,
- "loss": 1.0567,
+ "epoch": 11.04,
+ "learning_rate": 6.122159090909091e-05,
+ "loss": 0.3933,
"step": 977
},
{
- "epoch": 19.79,
- "learning_rate": 7.525510204081633e-05,
- "loss": 1.0169,
+ "epoch": 11.05,
+ "learning_rate": 6.107954545454547e-05,
+ "loss": 0.4161,
"step": 978
},
{
- "epoch": 19.81,
- "learning_rate": 7.512755102040818e-05,
- "loss": 0.9881,
+ "epoch": 11.06,
+ "learning_rate": 6.0937500000000004e-05,
+ "loss": 0.4097,
"step": 979
},
{
- "epoch": 19.83,
- "learning_rate": 7.500000000000001e-05,
- "loss": 1.0677,
+ "epoch": 11.07,
+ "learning_rate": 6.079545454545454e-05,
+ "loss": 0.412,
"step": 980
},
{
- "epoch": 19.85,
- "learning_rate": 7.487244897959184e-05,
- "loss": 1.1026,
+ "epoch": 11.08,
+ "learning_rate": 6.0653409090909094e-05,
+ "loss": 0.4104,
"step": 981
},
{
- "epoch": 19.87,
- "learning_rate": 7.474489795918368e-05,
- "loss": 1.0101,
+ "epoch": 11.09,
+ "learning_rate": 6.051136363636364e-05,
+ "loss": 0.4152,
"step": 982
},
{
- "epoch": 19.89,
- "learning_rate": 7.461734693877551e-05,
- "loss": 1.069,
+ "epoch": 11.11,
+ "learning_rate": 6.036931818181818e-05,
+ "loss": 0.4037,
"step": 983
},
{
- "epoch": 19.91,
- "learning_rate": 7.448979591836736e-05,
- "loss": 1.0493,
+ "epoch": 11.12,
+ "learning_rate": 6.022727272727273e-05,
+ "loss": 0.413,
"step": 984
},
{
- "epoch": 19.93,
- "learning_rate": 7.436224489795919e-05,
- "loss": 1.0858,
+ "epoch": 11.13,
+ "learning_rate": 6.0085227272727274e-05,
+ "loss": 0.4413,
"step": 985
},
{
- "epoch": 19.95,
- "learning_rate": 7.423469387755102e-05,
- "loss": 1.0734,
+ "epoch": 11.14,
+ "learning_rate": 5.9943181818181826e-05,
+ "loss": 0.3908,
"step": 986
},
{
- "epoch": 19.97,
- "learning_rate": 7.410714285714286e-05,
- "loss": 1.0203,
+ "epoch": 11.15,
+ "learning_rate": 5.9801136363636365e-05,
+ "loss": 0.3982,
"step": 987
},
{
- "epoch": 19.99,
- "learning_rate": 7.39795918367347e-05,
- "loss": 1.0285,
+ "epoch": 11.16,
+ "learning_rate": 5.965909090909091e-05,
+ "loss": 0.4109,
"step": 988
},
{
- "epoch": 20.01,
- "learning_rate": 7.385204081632653e-05,
- "loss": 0.9446,
+ "epoch": 11.17,
+ "learning_rate": 5.951704545454546e-05,
+ "loss": 0.3923,
"step": 989
},
{
- "epoch": 20.03,
- "learning_rate": 7.372448979591837e-05,
- "loss": 0.9915,
+ "epoch": 11.18,
+ "learning_rate": 5.9375e-05,
+ "loss": 0.4107,
"step": 990
},
{
- "epoch": 20.05,
- "learning_rate": 7.35969387755102e-05,
- "loss": 0.9882,
+ "epoch": 11.2,
+ "learning_rate": 5.9232954545454545e-05,
+ "loss": 0.4099,
"step": 991
},
{
- "epoch": 20.07,
- "learning_rate": 7.346938775510205e-05,
- "loss": 0.9338,
+ "epoch": 11.21,
+ "learning_rate": 5.90909090909091e-05,
+ "loss": 0.4163,
"step": 992
},
{
- "epoch": 20.09,
- "learning_rate": 7.334183673469388e-05,
- "loss": 0.942,
+ "epoch": 11.22,
+ "learning_rate": 5.8948863636363635e-05,
+ "loss": 0.4189,
"step": 993
},
{
- "epoch": 20.11,
- "learning_rate": 7.321428571428571e-05,
- "loss": 0.9725,
+ "epoch": 11.23,
+ "learning_rate": 5.880681818181818e-05,
+ "loss": 0.3889,
"step": 994
},
{
- "epoch": 20.13,
- "learning_rate": 7.308673469387755e-05,
- "loss": 1.027,
+ "epoch": 11.24,
+ "learning_rate": 5.866477272727273e-05,
+ "loss": 0.3988,
"step": 995
},
{
- "epoch": 20.15,
- "learning_rate": 7.29591836734694e-05,
- "loss": 1.0081,
+ "epoch": 11.25,
+ "learning_rate": 5.852272727272727e-05,
+ "loss": 0.4215,
"step": 996
},
{
- "epoch": 20.17,
- "learning_rate": 7.283163265306123e-05,
- "loss": 1.0117,
+ "epoch": 11.26,
+ "learning_rate": 5.838068181818183e-05,
+ "loss": 0.4207,
"step": 997
},
{
- "epoch": 20.19,
- "learning_rate": 7.270408163265307e-05,
- "loss": 0.969,
+ "epoch": 11.27,
+ "learning_rate": 5.823863636363637e-05,
+ "loss": 0.413,
"step": 998
},
{
- "epoch": 20.21,
- "learning_rate": 7.25765306122449e-05,
- "loss": 1.0024,
+ "epoch": 11.29,
+ "learning_rate": 5.8096590909090906e-05,
+ "loss": 0.4057,
"step": 999
},
{
- "epoch": 20.23,
- "learning_rate": 7.244897959183675e-05,
- "loss": 0.994,
+ "epoch": 11.3,
+ "learning_rate": 5.7954545454545464e-05,
+ "loss": 0.3939,
"step": 1000
},
{
- "epoch": 20.25,
- "learning_rate": 7.232142857142858e-05,
- "loss": 1.0248,
+ "epoch": 11.31,
+ "learning_rate": 5.78125e-05,
+ "loss": 0.4199,
"step": 1001
},
{
- "epoch": 20.27,
- "learning_rate": 7.219387755102042e-05,
- "loss": 1.0493,
+ "epoch": 11.32,
+ "learning_rate": 5.767045454545454e-05,
+ "loss": 0.4076,
"step": 1002
},
{
- "epoch": 20.29,
- "learning_rate": 7.206632653061225e-05,
- "loss": 1.0011,
+ "epoch": 11.33,
+ "learning_rate": 5.75284090909091e-05,
+ "loss": 0.4079,
"step": 1003
},
{
- "epoch": 20.31,
- "learning_rate": 7.193877551020408e-05,
- "loss": 0.9874,
+ "epoch": 11.34,
+ "learning_rate": 5.738636363636364e-05,
+ "loss": 0.4002,
"step": 1004
},
{
- "epoch": 20.34,
- "learning_rate": 7.181122448979593e-05,
- "loss": 1.0049,
+ "epoch": 11.35,
+ "learning_rate": 5.724431818181818e-05,
+ "loss": 0.3801,
"step": 1005
},
{
- "epoch": 20.36,
- "learning_rate": 7.168367346938776e-05,
- "loss": 1.0314,
+ "epoch": 11.37,
+ "learning_rate": 5.7102272727272735e-05,
+ "loss": 0.3939,
"step": 1006
},
{
- "epoch": 20.38,
- "learning_rate": 7.155612244897959e-05,
- "loss": 0.9742,
+ "epoch": 11.38,
+ "learning_rate": 5.696022727272727e-05,
+ "loss": 0.3904,
"step": 1007
},
{
- "epoch": 20.4,
- "learning_rate": 7.142857142857143e-05,
- "loss": 1.0621,
+ "epoch": 11.39,
+ "learning_rate": 5.6818181818181825e-05,
+ "loss": 0.406,
"step": 1008
},
{
- "epoch": 20.42,
- "learning_rate": 7.130102040816326e-05,
- "loss": 0.9672,
+ "epoch": 11.4,
+ "learning_rate": 5.667613636363637e-05,
+ "loss": 0.4185,
"step": 1009
},
{
- "epoch": 20.44,
- "learning_rate": 7.117346938775511e-05,
- "loss": 1.0018,
+ "epoch": 11.41,
+ "learning_rate": 5.653409090909091e-05,
+ "loss": 0.3976,
"step": 1010
},
{
- "epoch": 20.46,
- "learning_rate": 7.104591836734694e-05,
- "loss": 1.0045,
+ "epoch": 11.42,
+ "learning_rate": 5.639204545454546e-05,
+ "loss": 0.3907,
"step": 1011
},
{
- "epoch": 20.48,
- "learning_rate": 7.091836734693877e-05,
- "loss": 0.9675,
+ "epoch": 11.43,
+ "learning_rate": 5.6250000000000005e-05,
+ "loss": 0.4065,
"step": 1012
},
{
- "epoch": 20.5,
- "learning_rate": 7.079081632653062e-05,
- "loss": 0.976,
+ "epoch": 11.44,
+ "learning_rate": 5.6107954545454544e-05,
+ "loss": 0.4069,
"step": 1013
},
{
- "epoch": 20.52,
- "learning_rate": 7.066326530612245e-05,
- "loss": 1.0523,
+ "epoch": 11.46,
+ "learning_rate": 5.5965909090909095e-05,
+ "loss": 0.3964,
"step": 1014
},
{
- "epoch": 20.54,
- "learning_rate": 7.053571428571429e-05,
- "loss": 1.052,
+ "epoch": 11.47,
+ "learning_rate": 5.582386363636364e-05,
+ "loss": 0.3912,
"step": 1015
},
{
- "epoch": 20.56,
- "learning_rate": 7.040816326530612e-05,
- "loss": 0.9903,
+ "epoch": 11.48,
+ "learning_rate": 5.568181818181818e-05,
+ "loss": 0.3944,
"step": 1016
},
{
- "epoch": 20.58,
- "learning_rate": 7.028061224489795e-05,
- "loss": 1.0337,
+ "epoch": 11.49,
+ "learning_rate": 5.553977272727273e-05,
+ "loss": 0.4197,
"step": 1017
},
{
- "epoch": 20.6,
- "learning_rate": 7.01530612244898e-05,
- "loss": 1.1122,
+ "epoch": 11.5,
+ "learning_rate": 5.5397727272727276e-05,
+ "loss": 0.4064,
"step": 1018
},
{
- "epoch": 20.62,
- "learning_rate": 7.002551020408164e-05,
- "loss": 1.0133,
+ "epoch": 11.51,
+ "learning_rate": 5.525568181818183e-05,
+ "loss": 0.4054,
"step": 1019
},
{
- "epoch": 20.64,
- "learning_rate": 6.989795918367347e-05,
- "loss": 0.9588,
+ "epoch": 11.52,
+ "learning_rate": 5.5113636363636366e-05,
+ "loss": 0.4128,
"step": 1020
},
{
- "epoch": 20.66,
- "learning_rate": 6.977040816326532e-05,
- "loss": 0.9892,
+ "epoch": 11.53,
+ "learning_rate": 5.497159090909091e-05,
+ "loss": 0.3976,
"step": 1021
},
{
- "epoch": 20.68,
- "learning_rate": 6.964285714285715e-05,
- "loss": 1.025,
+ "epoch": 11.55,
+ "learning_rate": 5.482954545454546e-05,
+ "loss": 0.3863,
"step": 1022
},
{
- "epoch": 20.7,
- "learning_rate": 6.951530612244899e-05,
- "loss": 1.0196,
+ "epoch": 11.56,
+ "learning_rate": 5.46875e-05,
+ "loss": 0.3994,
"step": 1023
},
{
- "epoch": 20.72,
- "learning_rate": 6.938775510204082e-05,
- "loss": 1.0146,
+ "epoch": 11.57,
+ "learning_rate": 5.4545454545454546e-05,
+ "loss": 0.401,
"step": 1024
},
{
- "epoch": 20.74,
- "learning_rate": 6.926020408163265e-05,
- "loss": 1.0656,
+ "epoch": 11.58,
+ "learning_rate": 5.44034090909091e-05,
+ "loss": 0.3948,
"step": 1025
},
{
- "epoch": 20.76,
- "learning_rate": 6.91326530612245e-05,
- "loss": 0.9584,
+ "epoch": 11.59,
+ "learning_rate": 5.4261363636363636e-05,
+ "loss": 0.3967,
"step": 1026
},
{
- "epoch": 20.78,
- "learning_rate": 6.900510204081633e-05,
- "loss": 0.9877,
+ "epoch": 11.6,
+ "learning_rate": 5.411931818181818e-05,
+ "loss": 0.413,
"step": 1027
},
{
- "epoch": 20.8,
- "learning_rate": 6.887755102040817e-05,
- "loss": 1.0607,
+ "epoch": 11.61,
+ "learning_rate": 5.397727272727273e-05,
+ "loss": 0.4032,
"step": 1028
},
{
- "epoch": 20.82,
- "learning_rate": 6.875e-05,
- "loss": 0.9969,
+ "epoch": 11.63,
+ "learning_rate": 5.383522727272727e-05,
+ "loss": 0.3905,
"step": 1029
},
{
- "epoch": 20.84,
- "learning_rate": 6.862244897959184e-05,
- "loss": 0.9506,
+ "epoch": 11.64,
+ "learning_rate": 5.3693181818181823e-05,
+ "loss": 0.4041,
"step": 1030
},
{
- "epoch": 20.86,
- "learning_rate": 6.849489795918368e-05,
- "loss": 1.0576,
+ "epoch": 11.65,
+ "learning_rate": 5.355113636363637e-05,
+ "loss": 0.392,
"step": 1031
},
{
- "epoch": 20.88,
- "learning_rate": 6.836734693877551e-05,
- "loss": 1.0094,
+ "epoch": 11.66,
+ "learning_rate": 5.340909090909091e-05,
+ "loss": 0.3942,
"step": 1032
},
{
- "epoch": 20.9,
- "learning_rate": 6.823979591836735e-05,
- "loss": 0.9872,
+ "epoch": 11.67,
+ "learning_rate": 5.326704545454546e-05,
+ "loss": 0.3946,
"step": 1033
},
{
- "epoch": 20.92,
- "learning_rate": 6.811224489795919e-05,
- "loss": 1.0544,
+ "epoch": 11.68,
+ "learning_rate": 5.3125000000000004e-05,
+ "loss": 0.3989,
"step": 1034
},
{
- "epoch": 20.94,
- "learning_rate": 6.798469387755102e-05,
- "loss": 1.0194,
+ "epoch": 11.69,
+ "learning_rate": 5.298295454545454e-05,
+ "loss": 0.4101,
"step": 1035
},
{
- "epoch": 20.96,
- "learning_rate": 6.785714285714286e-05,
- "loss": 1.0009,
+ "epoch": 11.7,
+ "learning_rate": 5.2840909090909094e-05,
+ "loss": 0.4033,
"step": 1036
},
{
- "epoch": 20.98,
- "learning_rate": 6.772959183673469e-05,
- "loss": 0.9727,
+ "epoch": 11.72,
+ "learning_rate": 5.269886363636364e-05,
+ "loss": 0.3937,
"step": 1037
},
{
- "epoch": 21.0,
- "learning_rate": 6.760204081632652e-05,
- "loss": 0.9754,
+ "epoch": 11.73,
+ "learning_rate": 5.255681818181818e-05,
+ "loss": 0.3873,
"step": 1038
},
{
- "epoch": 21.02,
- "learning_rate": 6.747448979591837e-05,
- "loss": 0.9953,
+ "epoch": 11.74,
+ "learning_rate": 5.241477272727273e-05,
+ "loss": 0.3922,
"step": 1039
},
{
- "epoch": 21.04,
- "learning_rate": 6.73469387755102e-05,
- "loss": 0.9307,
+ "epoch": 11.75,
+ "learning_rate": 5.2272727272727274e-05,
+ "loss": 0.4016,
"step": 1040
},
{
- "epoch": 21.06,
- "learning_rate": 6.721938775510204e-05,
- "loss": 0.9151,
+ "epoch": 11.76,
+ "learning_rate": 5.2130681818181826e-05,
+ "loss": 0.3892,
"step": 1041
},
{
- "epoch": 21.08,
- "learning_rate": 6.709183673469389e-05,
- "loss": 0.9474,
+ "epoch": 11.77,
+ "learning_rate": 5.1988636363636364e-05,
+ "loss": 0.3974,
"step": 1042
},
{
- "epoch": 21.1,
- "learning_rate": 6.696428571428572e-05,
- "loss": 0.9697,
+ "epoch": 11.78,
+ "learning_rate": 5.184659090909091e-05,
+ "loss": 0.4024,
"step": 1043
},
{
- "epoch": 21.12,
- "learning_rate": 6.683673469387756e-05,
- "loss": 0.9423,
+ "epoch": 11.79,
+ "learning_rate": 5.170454545454546e-05,
+ "loss": 0.3889,
"step": 1044
},
{
- "epoch": 21.14,
- "learning_rate": 6.670918367346939e-05,
- "loss": 0.9797,
+ "epoch": 11.81,
+ "learning_rate": 5.15625e-05,
+ "loss": 0.4097,
"step": 1045
},
{
- "epoch": 21.16,
- "learning_rate": 6.658163265306124e-05,
- "loss": 0.919,
+ "epoch": 11.82,
+ "learning_rate": 5.1420454545454545e-05,
+ "loss": 0.4047,
"step": 1046
},
{
- "epoch": 21.18,
- "learning_rate": 6.645408163265307e-05,
- "loss": 0.9743,
+ "epoch": 11.83,
+ "learning_rate": 5.12784090909091e-05,
+ "loss": 0.4033,
"step": 1047
},
{
- "epoch": 21.21,
- "learning_rate": 6.63265306122449e-05,
- "loss": 0.9575,
+ "epoch": 11.84,
+ "learning_rate": 5.1136363636363635e-05,
+ "loss": 0.3774,
"step": 1048
},
{
- "epoch": 21.23,
- "learning_rate": 6.619897959183674e-05,
- "loss": 0.9861,
+ "epoch": 11.85,
+ "learning_rate": 5.099431818181818e-05,
+ "loss": 0.405,
"step": 1049
},
{
- "epoch": 21.25,
- "learning_rate": 6.607142857142857e-05,
- "loss": 0.9103,
+ "epoch": 11.86,
+ "learning_rate": 5.085227272727273e-05,
+ "loss": 0.3996,
"step": 1050
},
{
- "epoch": 21.27,
- "learning_rate": 6.594387755102042e-05,
- "loss": 0.993,
+ "epoch": 11.87,
+ "learning_rate": 5.071022727272727e-05,
+ "loss": 0.3885,
"step": 1051
},
{
- "epoch": 21.29,
- "learning_rate": 6.581632653061225e-05,
- "loss": 0.9668,
+ "epoch": 11.88,
+ "learning_rate": 5.056818181818183e-05,
+ "loss": 0.3914,
"step": 1052
},
{
- "epoch": 21.31,
- "learning_rate": 6.568877551020408e-05,
- "loss": 1.0008,
+ "epoch": 11.9,
+ "learning_rate": 5.042613636363637e-05,
+ "loss": 0.3908,
"step": 1053
},
{
- "epoch": 21.33,
- "learning_rate": 6.556122448979592e-05,
- "loss": 0.9825,
+ "epoch": 11.91,
+ "learning_rate": 5.0284090909090905e-05,
+ "loss": 0.3921,
"step": 1054
},
{
- "epoch": 21.35,
- "learning_rate": 6.543367346938776e-05,
- "loss": 1.0174,
+ "epoch": 11.92,
+ "learning_rate": 5.0142045454545464e-05,
+ "loss": 0.4077,
"step": 1055
},
{
- "epoch": 21.37,
- "learning_rate": 6.530612244897959e-05,
- "loss": 0.9685,
+ "epoch": 11.93,
+ "learning_rate": 5e-05,
+ "loss": 0.3973,
"step": 1056
},
{
- "epoch": 21.39,
- "learning_rate": 6.517857142857143e-05,
- "loss": 0.9265,
+ "epoch": 11.94,
+ "learning_rate": 4.985795454545455e-05,
+ "loss": 0.3986,
"step": 1057
},
{
- "epoch": 21.41,
- "learning_rate": 6.505102040816326e-05,
- "loss": 0.9495,
+ "epoch": 11.95,
+ "learning_rate": 4.971590909090909e-05,
+ "loss": 0.3938,
"step": 1058
},
{
- "epoch": 21.43,
- "learning_rate": 6.49234693877551e-05,
- "loss": 0.9541,
+ "epoch": 11.96,
+ "learning_rate": 4.957386363636364e-05,
+ "loss": 0.3897,
"step": 1059
},
{
- "epoch": 21.45,
- "learning_rate": 6.479591836734694e-05,
- "loss": 0.9299,
+ "epoch": 11.98,
+ "learning_rate": 4.943181818181818e-05,
+ "loss": 0.3965,
"step": 1060
},
{
- "epoch": 21.47,
- "learning_rate": 6.466836734693877e-05,
- "loss": 0.9625,
+ "epoch": 11.99,
+ "learning_rate": 4.9289772727272735e-05,
+ "loss": 0.3999,
"step": 1061
},
{
- "epoch": 21.49,
- "learning_rate": 6.454081632653061e-05,
- "loss": 1.0054,
+ "epoch": 12.0,
+ "learning_rate": 4.914772727272727e-05,
+ "loss": 0.3814,
"step": 1062
},
{
- "epoch": 21.51,
- "learning_rate": 6.441326530612244e-05,
- "loss": 0.9893,
+ "epoch": 12.01,
+ "learning_rate": 4.900568181818182e-05,
+ "loss": 0.3879,
"step": 1063
},
{
- "epoch": 21.53,
- "learning_rate": 6.428571428571429e-05,
- "loss": 0.9906,
+ "epoch": 12.02,
+ "learning_rate": 4.886363636363637e-05,
+ "loss": 0.3768,
"step": 1064
},
{
- "epoch": 21.55,
- "learning_rate": 6.415816326530613e-05,
- "loss": 0.9487,
+ "epoch": 12.03,
+ "learning_rate": 4.8721590909090915e-05,
+ "loss": 0.3813,
"step": 1065
},
{
- "epoch": 21.57,
- "learning_rate": 6.403061224489796e-05,
- "loss": 0.9728,
+ "epoch": 12.04,
+ "learning_rate": 4.857954545454545e-05,
+ "loss": 0.3759,
"step": 1066
},
{
- "epoch": 21.59,
- "learning_rate": 6.390306122448981e-05,
- "loss": 0.9883,
+ "epoch": 12.05,
+ "learning_rate": 4.8437500000000005e-05,
+ "loss": 0.3817,
"step": 1067
},
{
- "epoch": 21.61,
- "learning_rate": 6.377551020408164e-05,
- "loss": 1.053,
+ "epoch": 12.07,
+ "learning_rate": 4.829545454545455e-05,
+ "loss": 0.3773,
"step": 1068
},
{
- "epoch": 21.63,
- "learning_rate": 6.364795918367348e-05,
- "loss": 1.012,
+ "epoch": 12.08,
+ "learning_rate": 4.815340909090909e-05,
+ "loss": 0.3807,
"step": 1069
},
{
- "epoch": 21.65,
- "learning_rate": 6.352040816326531e-05,
- "loss": 0.962,
+ "epoch": 12.09,
+ "learning_rate": 4.801136363636364e-05,
+ "loss": 0.3757,
"step": 1070
},
{
- "epoch": 21.67,
- "learning_rate": 6.339285714285714e-05,
- "loss": 0.9955,
+ "epoch": 12.1,
+ "learning_rate": 4.7869318181818185e-05,
+ "loss": 0.3819,
"step": 1071
},
{
- "epoch": 21.69,
- "learning_rate": 6.326530612244899e-05,
- "loss": 0.9908,
+ "epoch": 12.11,
+ "learning_rate": 4.772727272727273e-05,
+ "loss": 0.3731,
"step": 1072
},
{
- "epoch": 21.71,
- "learning_rate": 6.313775510204082e-05,
- "loss": 1.0327,
+ "epoch": 12.12,
+ "learning_rate": 4.7585227272727276e-05,
+ "loss": 0.3706,
"step": 1073
},
{
- "epoch": 21.73,
- "learning_rate": 6.301020408163265e-05,
- "loss": 0.9255,
+ "epoch": 12.13,
+ "learning_rate": 4.744318181818182e-05,
+ "loss": 0.3762,
"step": 1074
},
{
- "epoch": 21.75,
- "learning_rate": 6.28826530612245e-05,
- "loss": 0.9268,
+ "epoch": 12.14,
+ "learning_rate": 4.7301136363636366e-05,
+ "loss": 0.3749,
"step": 1075
},
{
- "epoch": 21.77,
- "learning_rate": 6.275510204081633e-05,
- "loss": 0.9204,
+ "epoch": 12.16,
+ "learning_rate": 4.715909090909091e-05,
+ "loss": 0.3884,
"step": 1076
},
{
- "epoch": 21.79,
- "learning_rate": 6.262755102040817e-05,
- "loss": 0.9838,
+ "epoch": 12.17,
+ "learning_rate": 4.7017045454545456e-05,
+ "loss": 0.373,
"step": 1077
},
{
- "epoch": 21.81,
- "learning_rate": 6.25e-05,
- "loss": 0.954,
+ "epoch": 12.18,
+ "learning_rate": 4.6875e-05,
+ "loss": 0.374,
"step": 1078
},
{
- "epoch": 21.83,
- "learning_rate": 6.237244897959183e-05,
- "loss": 1.0102,
+ "epoch": 12.19,
+ "learning_rate": 4.6732954545454546e-05,
+ "loss": 0.3813,
"step": 1079
},
{
- "epoch": 21.85,
- "learning_rate": 6.224489795918368e-05,
- "loss": 0.916,
+ "epoch": 12.2,
+ "learning_rate": 4.659090909090909e-05,
+ "loss": 0.3745,
"step": 1080
},
{
- "epoch": 21.87,
- "learning_rate": 6.211734693877551e-05,
- "loss": 0.9939,
+ "epoch": 12.21,
+ "learning_rate": 4.6448863636363636e-05,
+ "loss": 0.3646,
"step": 1081
},
{
- "epoch": 21.89,
- "learning_rate": 6.198979591836735e-05,
- "loss": 0.9675,
+ "epoch": 12.22,
+ "learning_rate": 4.630681818181818e-05,
+ "loss": 0.3729,
"step": 1082
},
{
- "epoch": 21.91,
- "learning_rate": 6.186224489795918e-05,
- "loss": 0.9666,
+ "epoch": 12.24,
+ "learning_rate": 4.616477272727273e-05,
+ "loss": 0.3701,
"step": 1083
},
{
- "epoch": 21.93,
- "learning_rate": 6.173469387755101e-05,
- "loss": 0.9919,
+ "epoch": 12.25,
+ "learning_rate": 4.602272727272727e-05,
+ "loss": 0.3655,
"step": 1084
},
{
- "epoch": 21.95,
- "learning_rate": 6.160714285714286e-05,
- "loss": 1.0106,
+ "epoch": 12.26,
+ "learning_rate": 4.5880681818181817e-05,
+ "loss": 0.3758,
"step": 1085
},
{
- "epoch": 21.97,
- "learning_rate": 6.14795918367347e-05,
- "loss": 0.9982,
+ "epoch": 12.27,
+ "learning_rate": 4.573863636363637e-05,
+ "loss": 0.3682,
"step": 1086
},
{
- "epoch": 21.99,
- "learning_rate": 6.135204081632653e-05,
- "loss": 1.0137,
+ "epoch": 12.28,
+ "learning_rate": 4.5596590909090913e-05,
+ "loss": 0.3865,
"step": 1087
},
{
- "epoch": 22.01,
- "learning_rate": 6.122448979591838e-05,
- "loss": 0.9331,
+ "epoch": 12.29,
+ "learning_rate": 4.545454545454546e-05,
+ "loss": 0.363,
"step": 1088
},
{
- "epoch": 22.03,
- "learning_rate": 6.109693877551021e-05,
- "loss": 0.8834,
+ "epoch": 12.3,
+ "learning_rate": 4.5312500000000004e-05,
+ "loss": 0.3727,
"step": 1089
},
{
- "epoch": 22.06,
- "learning_rate": 6.0969387755102046e-05,
- "loss": 0.9757,
+ "epoch": 12.31,
+ "learning_rate": 4.517045454545455e-05,
+ "loss": 0.3827,
"step": 1090
},
{
- "epoch": 22.08,
- "learning_rate": 6.084183673469388e-05,
- "loss": 0.9038,
+ "epoch": 12.33,
+ "learning_rate": 4.5028409090909094e-05,
+ "loss": 0.3658,
"step": 1091
},
{
- "epoch": 22.1,
- "learning_rate": 6.0714285714285715e-05,
- "loss": 0.9097,
+ "epoch": 12.34,
+ "learning_rate": 4.488636363636364e-05,
+ "loss": 0.3844,
"step": 1092
},
{
- "epoch": 22.12,
- "learning_rate": 6.058673469387756e-05,
- "loss": 0.8972,
+ "epoch": 12.35,
+ "learning_rate": 4.4744318181818184e-05,
+ "loss": 0.3731,
"step": 1093
},
{
- "epoch": 22.14,
- "learning_rate": 6.045918367346939e-05,
- "loss": 0.8825,
+ "epoch": 12.36,
+ "learning_rate": 4.460227272727273e-05,
+ "loss": 0.3767,
"step": 1094
},
{
- "epoch": 22.16,
- "learning_rate": 6.0331632653061234e-05,
- "loss": 0.9814,
+ "epoch": 12.37,
+ "learning_rate": 4.4460227272727274e-05,
+ "loss": 0.3751,
"step": 1095
},
{
- "epoch": 22.18,
- "learning_rate": 6.0204081632653065e-05,
- "loss": 0.9874,
+ "epoch": 12.38,
+ "learning_rate": 4.431818181818182e-05,
+ "loss": 0.3718,
"step": 1096
},
{
- "epoch": 22.2,
- "learning_rate": 6.0076530612244896e-05,
- "loss": 0.912,
+ "epoch": 12.39,
+ "learning_rate": 4.4176136363636364e-05,
+ "loss": 0.3833,
"step": 1097
},
{
- "epoch": 22.22,
- "learning_rate": 5.994897959183674e-05,
- "loss": 0.9206,
+ "epoch": 12.4,
+ "learning_rate": 4.4034090909090916e-05,
+ "loss": 0.3673,
"step": 1098
},
{
- "epoch": 22.24,
- "learning_rate": 5.982142857142857e-05,
- "loss": 0.9497,
+ "epoch": 12.42,
+ "learning_rate": 4.3892045454545454e-05,
+ "loss": 0.3799,
"step": 1099
},
{
- "epoch": 22.26,
- "learning_rate": 5.9693877551020416e-05,
- "loss": 0.9269,
+ "epoch": 12.43,
+ "learning_rate": 4.375e-05,
+ "loss": 0.3661,
"step": 1100
},
{
- "epoch": 22.28,
- "learning_rate": 5.956632653061225e-05,
- "loss": 0.9452,
+ "epoch": 12.44,
+ "learning_rate": 4.360795454545455e-05,
+ "loss": 0.3554,
"step": 1101
},
{
- "epoch": 22.3,
- "learning_rate": 5.9438775510204084e-05,
- "loss": 0.9548,
+ "epoch": 12.45,
+ "learning_rate": 4.346590909090909e-05,
+ "loss": 0.3787,
"step": 1102
},
{
- "epoch": 22.32,
- "learning_rate": 5.931122448979592e-05,
- "loss": 0.9689,
+ "epoch": 12.46,
+ "learning_rate": 4.3323863636363635e-05,
+ "loss": 0.3695,
"step": 1103
},
{
- "epoch": 22.34,
- "learning_rate": 5.918367346938776e-05,
- "loss": 0.9455,
+ "epoch": 12.47,
+ "learning_rate": 4.318181818181819e-05,
+ "loss": 0.3777,
"step": 1104
},
{
- "epoch": 22.36,
- "learning_rate": 5.905612244897959e-05,
- "loss": 0.9409,
+ "epoch": 12.48,
+ "learning_rate": 4.303977272727273e-05,
+ "loss": 0.3693,
"step": 1105
},
{
- "epoch": 22.38,
- "learning_rate": 5.8928571428571435e-05,
- "loss": 0.9093,
+ "epoch": 12.49,
+ "learning_rate": 4.289772727272727e-05,
+ "loss": 0.3731,
"step": 1106
},
{
- "epoch": 22.4,
- "learning_rate": 5.8801020408163266e-05,
- "loss": 0.921,
+ "epoch": 12.51,
+ "learning_rate": 4.275568181818182e-05,
+ "loss": 0.3659,
"step": 1107
},
{
- "epoch": 22.42,
- "learning_rate": 5.867346938775511e-05,
- "loss": 0.9368,
+ "epoch": 12.52,
+ "learning_rate": 4.261363636363637e-05,
+ "loss": 0.3689,
"step": 1108
},
{
- "epoch": 22.44,
- "learning_rate": 5.854591836734694e-05,
- "loss": 0.907,
+ "epoch": 12.53,
+ "learning_rate": 4.247159090909091e-05,
+ "loss": 0.3625,
"step": 1109
},
{
- "epoch": 22.46,
- "learning_rate": 5.841836734693877e-05,
- "loss": 0.9126,
+ "epoch": 12.54,
+ "learning_rate": 4.232954545454546e-05,
+ "loss": 0.3874,
"step": 1110
},
{
- "epoch": 22.48,
- "learning_rate": 5.8290816326530616e-05,
- "loss": 0.9161,
+ "epoch": 12.55,
+ "learning_rate": 4.21875e-05,
+ "loss": 0.3651,
"step": 1111
},
{
- "epoch": 22.5,
- "learning_rate": 5.816326530612245e-05,
- "loss": 0.9542,
+ "epoch": 12.56,
+ "learning_rate": 4.204545454545455e-05,
+ "loss": 0.3639,
"step": 1112
},
{
- "epoch": 22.52,
- "learning_rate": 5.803571428571429e-05,
- "loss": 0.9775,
+ "epoch": 12.57,
+ "learning_rate": 4.190340909090909e-05,
+ "loss": 0.378,
"step": 1113
},
{
- "epoch": 22.54,
- "learning_rate": 5.790816326530612e-05,
- "loss": 1.0006,
+ "epoch": 12.59,
+ "learning_rate": 4.176136363636364e-05,
+ "loss": 0.3726,
"step": 1114
},
{
- "epoch": 22.56,
- "learning_rate": 5.778061224489796e-05,
- "loss": 0.8965,
+ "epoch": 12.6,
+ "learning_rate": 4.161931818181818e-05,
+ "loss": 0.3732,
"step": 1115
},
{
- "epoch": 22.58,
- "learning_rate": 5.7653061224489805e-05,
- "loss": 0.944,
+ "epoch": 12.61,
+ "learning_rate": 4.1477272727272734e-05,
+ "loss": 0.3673,
"step": 1116
},
{
- "epoch": 22.6,
- "learning_rate": 5.7525510204081636e-05,
- "loss": 0.9162,
+ "epoch": 12.62,
+ "learning_rate": 4.133522727272727e-05,
+ "loss": 0.3566,
"step": 1117
},
{
- "epoch": 22.62,
- "learning_rate": 5.739795918367348e-05,
- "loss": 0.9325,
+ "epoch": 12.63,
+ "learning_rate": 4.119318181818182e-05,
+ "loss": 0.3757,
"step": 1118
},
{
- "epoch": 22.64,
- "learning_rate": 5.727040816326531e-05,
- "loss": 0.8998,
+ "epoch": 12.64,
+ "learning_rate": 4.105113636363637e-05,
+ "loss": 0.3739,
"step": 1119
},
{
- "epoch": 22.66,
- "learning_rate": 5.714285714285714e-05,
- "loss": 0.9362,
+ "epoch": 12.65,
+ "learning_rate": 4.0909090909090915e-05,
+ "loss": 0.3768,
"step": 1120
},
{
- "epoch": 22.68,
- "learning_rate": 5.7015306122448986e-05,
- "loss": 0.9969,
+ "epoch": 12.66,
+ "learning_rate": 4.076704545454545e-05,
+ "loss": 0.3758,
"step": 1121
},
{
- "epoch": 22.7,
- "learning_rate": 5.688775510204082e-05,
- "loss": 0.9104,
+ "epoch": 12.68,
+ "learning_rate": 4.0625000000000005e-05,
+ "loss": 0.3655,
"step": 1122
},
{
- "epoch": 22.72,
- "learning_rate": 5.676020408163265e-05,
- "loss": 0.9746,
+ "epoch": 12.69,
+ "learning_rate": 4.048295454545455e-05,
+ "loss": 0.3673,
"step": 1123
},
{
- "epoch": 22.74,
- "learning_rate": 5.663265306122449e-05,
- "loss": 0.9821,
+ "epoch": 12.7,
+ "learning_rate": 4.034090909090909e-05,
+ "loss": 0.3683,
"step": 1124
},
{
- "epoch": 22.76,
- "learning_rate": 5.650510204081633e-05,
- "loss": 0.9526,
+ "epoch": 12.71,
+ "learning_rate": 4.019886363636364e-05,
+ "loss": 0.3569,
"step": 1125
},
{
- "epoch": 22.78,
- "learning_rate": 5.637755102040817e-05,
- "loss": 0.871,
+ "epoch": 12.72,
+ "learning_rate": 4.0056818181818185e-05,
+ "loss": 0.3741,
"step": 1126
},
{
- "epoch": 22.8,
- "learning_rate": 5.6250000000000005e-05,
- "loss": 0.9534,
+ "epoch": 12.73,
+ "learning_rate": 3.991477272727273e-05,
+ "loss": 0.3817,
"step": 1127
},
{
- "epoch": 22.82,
- "learning_rate": 5.6122448979591836e-05,
- "loss": 0.9616,
+ "epoch": 12.74,
+ "learning_rate": 3.9772727272727275e-05,
+ "loss": 0.3748,
"step": 1128
},
{
- "epoch": 22.84,
- "learning_rate": 5.599489795918368e-05,
- "loss": 0.9627,
+ "epoch": 12.75,
+ "learning_rate": 3.963068181818182e-05,
+ "loss": 0.3625,
"step": 1129
},
{
- "epoch": 22.86,
- "learning_rate": 5.586734693877551e-05,
- "loss": 0.9704,
+ "epoch": 12.77,
+ "learning_rate": 3.9488636363636366e-05,
+ "loss": 0.3656,
"step": 1130
},
{
- "epoch": 22.88,
- "learning_rate": 5.5739795918367356e-05,
- "loss": 0.9506,
+ "epoch": 12.78,
+ "learning_rate": 3.934659090909091e-05,
+ "loss": 0.3564,
"step": 1131
},
{
- "epoch": 22.9,
- "learning_rate": 5.561224489795919e-05,
- "loss": 0.9553,
+ "epoch": 12.79,
+ "learning_rate": 3.9204545454545456e-05,
+ "loss": 0.3737,
"step": 1132
},
{
- "epoch": 22.93,
- "learning_rate": 5.548469387755102e-05,
- "loss": 0.9294,
+ "epoch": 12.8,
+ "learning_rate": 3.90625e-05,
+ "loss": 0.3649,
"step": 1133
},
{
- "epoch": 22.95,
- "learning_rate": 5.535714285714286e-05,
- "loss": 0.8979,
+ "epoch": 12.81,
+ "learning_rate": 3.8920454545454546e-05,
+ "loss": 0.3728,
"step": 1134
},
{
- "epoch": 22.97,
- "learning_rate": 5.522959183673469e-05,
- "loss": 1.0004,
+ "epoch": 12.82,
+ "learning_rate": 3.877840909090909e-05,
+ "loss": 0.3865,
"step": 1135
},
{
- "epoch": 22.99,
- "learning_rate": 5.510204081632653e-05,
- "loss": 0.9821,
+ "epoch": 12.83,
+ "learning_rate": 3.8636363636363636e-05,
+ "loss": 0.3866,
"step": 1136
},
{
- "epoch": 23.01,
- "learning_rate": 5.497448979591837e-05,
- "loss": 0.9607,
+ "epoch": 12.85,
+ "learning_rate": 3.849431818181818e-05,
+ "loss": 0.3725,
"step": 1137
},
{
- "epoch": 23.03,
- "learning_rate": 5.4846938775510206e-05,
- "loss": 0.9757,
+ "epoch": 12.86,
+ "learning_rate": 3.835227272727273e-05,
+ "loss": 0.3662,
"step": 1138
},
{
- "epoch": 23.05,
- "learning_rate": 5.471938775510205e-05,
- "loss": 0.9096,
+ "epoch": 12.87,
+ "learning_rate": 3.821022727272727e-05,
+ "loss": 0.3742,
"step": 1139
},
{
- "epoch": 23.07,
- "learning_rate": 5.459183673469388e-05,
- "loss": 0.9144,
+ "epoch": 12.88,
+ "learning_rate": 3.8068181818181816e-05,
+ "loss": 0.3727,
"step": 1140
},
{
- "epoch": 23.09,
- "learning_rate": 5.446428571428571e-05,
- "loss": 0.8667,
+ "epoch": 12.89,
+ "learning_rate": 3.792613636363637e-05,
+ "loss": 0.3653,
"step": 1141
},
{
- "epoch": 23.11,
- "learning_rate": 5.4336734693877556e-05,
- "loss": 0.8993,
+ "epoch": 12.9,
+ "learning_rate": 3.778409090909091e-05,
+ "loss": 0.3631,
"step": 1142
},
{
- "epoch": 23.13,
- "learning_rate": 5.420918367346939e-05,
- "loss": 0.8964,
+ "epoch": 12.91,
+ "learning_rate": 3.764204545454545e-05,
+ "loss": 0.3674,
"step": 1143
},
{
- "epoch": 23.15,
- "learning_rate": 5.408163265306123e-05,
- "loss": 0.9173,
+ "epoch": 12.92,
+ "learning_rate": 3.7500000000000003e-05,
+ "loss": 0.3598,
"step": 1144
},
{
- "epoch": 23.17,
- "learning_rate": 5.395408163265306e-05,
- "loss": 0.9019,
+ "epoch": 12.94,
+ "learning_rate": 3.735795454545455e-05,
+ "loss": 0.3697,
"step": 1145
},
{
- "epoch": 23.19,
- "learning_rate": 5.382653061224489e-05,
- "loss": 0.9303,
+ "epoch": 12.95,
+ "learning_rate": 3.721590909090909e-05,
+ "loss": 0.3639,
"step": 1146
},
{
- "epoch": 23.21,
- "learning_rate": 5.369897959183674e-05,
- "loss": 0.9268,
+ "epoch": 12.96,
+ "learning_rate": 3.707386363636364e-05,
+ "loss": 0.3597,
"step": 1147
},
{
- "epoch": 23.23,
- "learning_rate": 5.3571428571428575e-05,
- "loss": 0.8803,
+ "epoch": 12.97,
+ "learning_rate": 3.6931818181818184e-05,
+ "loss": 0.3815,
"step": 1148
},
{
- "epoch": 23.25,
- "learning_rate": 5.344387755102041e-05,
- "loss": 0.9197,
+ "epoch": 12.98,
+ "learning_rate": 3.678977272727273e-05,
+ "loss": 0.3477,
"step": 1149
},
{
- "epoch": 23.27,
- "learning_rate": 5.331632653061225e-05,
- "loss": 0.9204,
+ "epoch": 12.99,
+ "learning_rate": 3.6647727272727274e-05,
+ "loss": 0.3631,
"step": 1150
},
{
- "epoch": 23.29,
- "learning_rate": 5.318877551020408e-05,
- "loss": 0.8802,
+ "epoch": 13.0,
+ "learning_rate": 3.650568181818182e-05,
+ "loss": 0.3569,
"step": 1151
},
{
- "epoch": 23.31,
- "learning_rate": 5.3061224489795926e-05,
- "loss": 0.9044,
+ "epoch": 13.01,
+ "learning_rate": 3.6363636363636364e-05,
+ "loss": 0.3435,
"step": 1152
},
{
- "epoch": 23.33,
- "learning_rate": 5.293367346938776e-05,
- "loss": 0.8893,
+ "epoch": 13.03,
+ "learning_rate": 3.6221590909090916e-05,
+ "loss": 0.3504,
"step": 1153
},
{
- "epoch": 23.35,
- "learning_rate": 5.280612244897959e-05,
- "loss": 0.8928,
+ "epoch": 13.04,
+ "learning_rate": 3.6079545454545454e-05,
+ "loss": 0.3582,
"step": 1154
},
{
- "epoch": 23.37,
- "learning_rate": 5.267857142857143e-05,
- "loss": 0.9353,
+ "epoch": 13.05,
+ "learning_rate": 3.59375e-05,
+ "loss": 0.356,
"step": 1155
},
{
- "epoch": 23.39,
- "learning_rate": 5.255102040816326e-05,
- "loss": 0.9345,
+ "epoch": 13.06,
+ "learning_rate": 3.579545454545455e-05,
+ "loss": 0.3506,
"step": 1156
},
{
- "epoch": 23.41,
- "learning_rate": 5.242346938775511e-05,
- "loss": 0.9372,
+ "epoch": 13.07,
+ "learning_rate": 3.565340909090909e-05,
+ "loss": 0.3628,
"step": 1157
},
{
- "epoch": 23.43,
- "learning_rate": 5.229591836734694e-05,
- "loss": 0.9234,
+ "epoch": 13.08,
+ "learning_rate": 3.5511363636363635e-05,
+ "loss": 0.3494,
"step": 1158
},
{
- "epoch": 23.45,
- "learning_rate": 5.2168367346938776e-05,
- "loss": 0.9177,
+ "epoch": 13.09,
+ "learning_rate": 3.5369318181818186e-05,
+ "loss": 0.3653,
"step": 1159
},
{
- "epoch": 23.47,
- "learning_rate": 5.2040816326530614e-05,
- "loss": 0.8757,
+ "epoch": 13.11,
+ "learning_rate": 3.522727272727273e-05,
+ "loss": 0.3515,
"step": 1160
},
{
- "epoch": 23.49,
- "learning_rate": 5.191326530612245e-05,
- "loss": 0.9048,
+ "epoch": 13.12,
+ "learning_rate": 3.508522727272727e-05,
+ "loss": 0.3474,
"step": 1161
},
{
- "epoch": 23.51,
- "learning_rate": 5.1785714285714296e-05,
- "loss": 0.9248,
+ "epoch": 13.13,
+ "learning_rate": 3.494318181818182e-05,
+ "loss": 0.3469,
"step": 1162
},
{
- "epoch": 23.53,
- "learning_rate": 5.1658163265306127e-05,
- "loss": 0.9379,
+ "epoch": 13.14,
+ "learning_rate": 3.480113636363637e-05,
+ "loss": 0.3471,
"step": 1163
},
{
- "epoch": 23.55,
- "learning_rate": 5.153061224489796e-05,
- "loss": 0.8596,
+ "epoch": 13.15,
+ "learning_rate": 3.465909090909091e-05,
+ "loss": 0.355,
"step": 1164
},
{
- "epoch": 23.57,
- "learning_rate": 5.14030612244898e-05,
- "loss": 0.9751,
+ "epoch": 13.16,
+ "learning_rate": 3.451704545454546e-05,
+ "loss": 0.3532,
"step": 1165
},
{
- "epoch": 23.59,
- "learning_rate": 5.127551020408163e-05,
- "loss": 0.8842,
+ "epoch": 13.17,
+ "learning_rate": 3.4375e-05,
+ "loss": 0.3533,
"step": 1166
},
{
- "epoch": 23.61,
- "learning_rate": 5.114795918367348e-05,
- "loss": 0.8765,
+ "epoch": 13.18,
+ "learning_rate": 3.423295454545455e-05,
+ "loss": 0.3571,
"step": 1167
},
{
- "epoch": 23.63,
- "learning_rate": 5.102040816326531e-05,
- "loss": 0.8942,
+ "epoch": 13.2,
+ "learning_rate": 3.409090909090909e-05,
+ "loss": 0.3435,
"step": 1168
},
{
- "epoch": 23.65,
- "learning_rate": 5.089285714285714e-05,
- "loss": 0.938,
+ "epoch": 13.21,
+ "learning_rate": 3.394886363636364e-05,
+ "loss": 0.348,
"step": 1169
},
{
- "epoch": 23.67,
- "learning_rate": 5.076530612244898e-05,
- "loss": 0.8993,
+ "epoch": 13.22,
+ "learning_rate": 3.380681818181818e-05,
+ "loss": 0.3505,
"step": 1170
},
{
- "epoch": 23.69,
- "learning_rate": 5.063775510204082e-05,
- "loss": 0.9362,
+ "epoch": 13.23,
+ "learning_rate": 3.3664772727272734e-05,
+ "loss": 0.346,
"step": 1171
},
{
- "epoch": 23.71,
- "learning_rate": 5.051020408163265e-05,
- "loss": 0.9249,
+ "epoch": 13.24,
+ "learning_rate": 3.352272727272727e-05,
+ "loss": 0.3568,
"step": 1172
},
{
- "epoch": 23.73,
- "learning_rate": 5.0382653061224496e-05,
- "loss": 0.9055,
+ "epoch": 13.25,
+ "learning_rate": 3.338068181818182e-05,
+ "loss": 0.3548,
"step": 1173
},
{
- "epoch": 23.75,
- "learning_rate": 5.025510204081633e-05,
- "loss": 0.8967,
+ "epoch": 13.26,
+ "learning_rate": 3.323863636363637e-05,
+ "loss": 0.352,
"step": 1174
},
{
- "epoch": 23.77,
- "learning_rate": 5.012755102040817e-05,
- "loss": 0.8795,
+ "epoch": 13.27,
+ "learning_rate": 3.3096590909090915e-05,
+ "loss": 0.3561,
"step": 1175
},
{
- "epoch": 23.8,
- "learning_rate": 5e-05,
- "loss": 0.9452,
+ "epoch": 13.29,
+ "learning_rate": 3.295454545454545e-05,
+ "loss": 0.3424,
"step": 1176
},
{
- "epoch": 23.82,
- "learning_rate": 4.987244897959184e-05,
- "loss": 0.926,
+ "epoch": 13.3,
+ "learning_rate": 3.2812500000000005e-05,
+ "loss": 0.3453,
"step": 1177
},
{
- "epoch": 23.84,
- "learning_rate": 4.974489795918368e-05,
- "loss": 0.8948,
+ "epoch": 13.31,
+ "learning_rate": 3.267045454545455e-05,
+ "loss": 0.347,
"step": 1178
},
{
- "epoch": 23.86,
- "learning_rate": 4.961734693877551e-05,
- "loss": 0.8926,
+ "epoch": 13.32,
+ "learning_rate": 3.252840909090909e-05,
+ "loss": 0.3526,
"step": 1179
},
{
- "epoch": 23.88,
- "learning_rate": 4.9489795918367346e-05,
- "loss": 0.8949,
+ "epoch": 13.33,
+ "learning_rate": 3.238636363636364e-05,
+ "loss": 0.3634,
"step": 1180
},
{
- "epoch": 23.9,
- "learning_rate": 4.9362244897959184e-05,
- "loss": 0.9648,
+ "epoch": 13.34,
+ "learning_rate": 3.2244318181818185e-05,
+ "loss": 0.3591,
"step": 1181
},
{
- "epoch": 23.92,
- "learning_rate": 4.923469387755102e-05,
- "loss": 0.9599,
+ "epoch": 13.35,
+ "learning_rate": 3.210227272727273e-05,
+ "loss": 0.3449,
"step": 1182
},
{
- "epoch": 23.94,
- "learning_rate": 4.910714285714286e-05,
- "loss": 0.9603,
+ "epoch": 13.36,
+ "learning_rate": 3.1960227272727275e-05,
+ "loss": 0.3362,
"step": 1183
},
{
- "epoch": 23.96,
- "learning_rate": 4.89795918367347e-05,
- "loss": 0.9302,
+ "epoch": 13.38,
+ "learning_rate": 3.181818181818182e-05,
+ "loss": 0.3613,
"step": 1184
},
{
- "epoch": 23.98,
- "learning_rate": 4.8852040816326534e-05,
- "loss": 0.9261,
+ "epoch": 13.39,
+ "learning_rate": 3.1676136363636365e-05,
+ "loss": 0.3509,
"step": 1185
},
{
- "epoch": 24.0,
- "learning_rate": 4.872448979591837e-05,
- "loss": 0.9257,
+ "epoch": 13.4,
+ "learning_rate": 3.153409090909091e-05,
+ "loss": 0.3534,
"step": 1186
},
{
- "epoch": 24.02,
- "learning_rate": 4.859693877551021e-05,
- "loss": 0.8725,
+ "epoch": 13.41,
+ "learning_rate": 3.1392045454545456e-05,
+ "loss": 0.3452,
"step": 1187
},
{
- "epoch": 24.04,
- "learning_rate": 4.846938775510204e-05,
- "loss": 0.8486,
+ "epoch": 13.42,
+ "learning_rate": 3.125e-05,
+ "loss": 0.3659,
"step": 1188
},
{
- "epoch": 24.06,
- "learning_rate": 4.834183673469388e-05,
- "loss": 0.8457,
+ "epoch": 13.43,
+ "learning_rate": 3.1107954545454546e-05,
+ "loss": 0.3445,
"step": 1189
},
{
- "epoch": 24.08,
- "learning_rate": 4.8214285714285716e-05,
- "loss": 0.7848,
+ "epoch": 13.44,
+ "learning_rate": 3.096590909090909e-05,
+ "loss": 0.3536,
"step": 1190
},
{
- "epoch": 24.1,
- "learning_rate": 4.8086734693877554e-05,
- "loss": 0.8885,
+ "epoch": 13.46,
+ "learning_rate": 3.0823863636363636e-05,
+ "loss": 0.3588,
"step": 1191
},
{
- "epoch": 24.12,
- "learning_rate": 4.795918367346939e-05,
- "loss": 0.9099,
+ "epoch": 13.47,
+ "learning_rate": 3.068181818181818e-05,
+ "loss": 0.347,
"step": 1192
},
{
- "epoch": 24.14,
- "learning_rate": 4.783163265306123e-05,
- "loss": 0.9147,
+ "epoch": 13.48,
+ "learning_rate": 3.053977272727273e-05,
+ "loss": 0.3537,
"step": 1193
},
{
- "epoch": 24.16,
- "learning_rate": 4.7704081632653066e-05,
- "loss": 0.8781,
+ "epoch": 13.49,
+ "learning_rate": 3.039772727272727e-05,
+ "loss": 0.3516,
"step": 1194
},
{
- "epoch": 24.18,
- "learning_rate": 4.7576530612244904e-05,
- "loss": 0.8847,
+ "epoch": 13.5,
+ "learning_rate": 3.025568181818182e-05,
+ "loss": 0.3587,
"step": 1195
},
{
- "epoch": 24.2,
- "learning_rate": 4.744897959183674e-05,
- "loss": 0.9041,
+ "epoch": 13.51,
+ "learning_rate": 3.0113636363636365e-05,
+ "loss": 0.3494,
"step": 1196
},
{
- "epoch": 24.22,
- "learning_rate": 4.732142857142857e-05,
- "loss": 0.8639,
+ "epoch": 13.52,
+ "learning_rate": 2.9971590909090913e-05,
+ "loss": 0.3341,
"step": 1197
},
{
- "epoch": 24.24,
- "learning_rate": 4.719387755102041e-05,
- "loss": 0.8831,
+ "epoch": 13.53,
+ "learning_rate": 2.9829545454545455e-05,
+ "loss": 0.3563,
"step": 1198
},
{
- "epoch": 24.26,
- "learning_rate": 4.706632653061225e-05,
- "loss": 0.9063,
+ "epoch": 13.55,
+ "learning_rate": 2.96875e-05,
+ "loss": 0.3534,
"step": 1199
},
{
- "epoch": 24.28,
- "learning_rate": 4.6938775510204086e-05,
- "loss": 0.8753,
+ "epoch": 13.56,
+ "learning_rate": 2.954545454545455e-05,
+ "loss": 0.3632,
"step": 1200
},
{
- "epoch": 24.3,
- "learning_rate": 4.6811224489795916e-05,
- "loss": 0.8977,
+ "epoch": 13.57,
+ "learning_rate": 2.940340909090909e-05,
+ "loss": 0.3523,
"step": 1201
},
{
- "epoch": 24.32,
- "learning_rate": 4.6683673469387754e-05,
- "loss": 0.8729,
+ "epoch": 13.58,
+ "learning_rate": 2.9261363636363635e-05,
+ "loss": 0.3587,
"step": 1202
},
{
- "epoch": 24.34,
- "learning_rate": 4.655612244897959e-05,
- "loss": 0.898,
+ "epoch": 13.59,
+ "learning_rate": 2.9119318181818184e-05,
+ "loss": 0.3523,
"step": 1203
},
{
- "epoch": 24.36,
- "learning_rate": 4.642857142857143e-05,
- "loss": 0.8521,
+ "epoch": 13.6,
+ "learning_rate": 2.8977272727272732e-05,
+ "loss": 0.3418,
"step": 1204
},
{
- "epoch": 24.38,
- "learning_rate": 4.630102040816327e-05,
- "loss": 0.8563,
+ "epoch": 13.61,
+ "learning_rate": 2.883522727272727e-05,
+ "loss": 0.3515,
"step": 1205
},
{
- "epoch": 24.4,
- "learning_rate": 4.6173469387755105e-05,
- "loss": 0.8462,
+ "epoch": 13.62,
+ "learning_rate": 2.869318181818182e-05,
+ "loss": 0.3362,
"step": 1206
},
{
- "epoch": 24.42,
- "learning_rate": 4.604591836734694e-05,
- "loss": 0.8929,
+ "epoch": 13.64,
+ "learning_rate": 2.8551136363636367e-05,
+ "loss": 0.3393,
"step": 1207
},
{
- "epoch": 24.44,
- "learning_rate": 4.591836734693878e-05,
- "loss": 0.9154,
+ "epoch": 13.65,
+ "learning_rate": 2.8409090909090912e-05,
+ "loss": 0.3395,
"step": 1208
},
{
- "epoch": 24.46,
- "learning_rate": 4.579081632653062e-05,
- "loss": 0.811,
+ "epoch": 13.66,
+ "learning_rate": 2.8267045454545454e-05,
+ "loss": 0.3434,
"step": 1209
},
{
- "epoch": 24.48,
- "learning_rate": 4.566326530612245e-05,
- "loss": 0.8667,
+ "epoch": 13.67,
+ "learning_rate": 2.8125000000000003e-05,
+ "loss": 0.3536,
"step": 1210
},
{
- "epoch": 24.5,
- "learning_rate": 4.5535714285714286e-05,
- "loss": 0.9179,
+ "epoch": 13.68,
+ "learning_rate": 2.7982954545454548e-05,
+ "loss": 0.3482,
"step": 1211
},
{
- "epoch": 24.52,
- "learning_rate": 4.5408163265306124e-05,
- "loss": 0.8757,
+ "epoch": 13.69,
+ "learning_rate": 2.784090909090909e-05,
+ "loss": 0.3383,
"step": 1212
},
{
- "epoch": 24.54,
- "learning_rate": 4.528061224489796e-05,
- "loss": 0.8519,
+ "epoch": 13.7,
+ "learning_rate": 2.7698863636363638e-05,
+ "loss": 0.3582,
"step": 1213
},
{
- "epoch": 24.56,
- "learning_rate": 4.515306122448979e-05,
- "loss": 0.9335,
+ "epoch": 13.72,
+ "learning_rate": 2.7556818181818183e-05,
+ "loss": 0.3469,
"step": 1214
},
{
- "epoch": 24.58,
- "learning_rate": 4.502551020408164e-05,
- "loss": 0.8785,
+ "epoch": 13.73,
+ "learning_rate": 2.741477272727273e-05,
+ "loss": 0.351,
"step": 1215
},
{
- "epoch": 24.6,
- "learning_rate": 4.4897959183673474e-05,
- "loss": 0.9022,
+ "epoch": 13.74,
+ "learning_rate": 2.7272727272727273e-05,
+ "loss": 0.3461,
"step": 1216
},
{
- "epoch": 24.62,
- "learning_rate": 4.477040816326531e-05,
- "loss": 0.9532,
+ "epoch": 13.75,
+ "learning_rate": 2.7130681818181818e-05,
+ "loss": 0.3497,
"step": 1217
},
{
- "epoch": 24.64,
- "learning_rate": 4.464285714285715e-05,
- "loss": 0.8956,
+ "epoch": 13.76,
+ "learning_rate": 2.6988636363636367e-05,
+ "loss": 0.3503,
"step": 1218
},
{
- "epoch": 24.67,
- "learning_rate": 4.451530612244898e-05,
- "loss": 0.8739,
+ "epoch": 13.77,
+ "learning_rate": 2.6846590909090912e-05,
+ "loss": 0.3499,
"step": 1219
},
{
- "epoch": 24.69,
- "learning_rate": 4.438775510204082e-05,
- "loss": 0.9312,
+ "epoch": 13.78,
+ "learning_rate": 2.6704545454545453e-05,
+ "loss": 0.3529,
"step": 1220
},
{
- "epoch": 24.71,
- "learning_rate": 4.4260204081632656e-05,
- "loss": 0.8536,
+ "epoch": 13.79,
+ "learning_rate": 2.6562500000000002e-05,
+ "loss": 0.3516,
"step": 1221
},
{
- "epoch": 24.73,
- "learning_rate": 4.4132653061224493e-05,
- "loss": 0.8984,
+ "epoch": 13.81,
+ "learning_rate": 2.6420454545454547e-05,
+ "loss": 0.3457,
"step": 1222
},
{
- "epoch": 24.75,
- "learning_rate": 4.4005102040816324e-05,
- "loss": 0.8949,
+ "epoch": 13.82,
+ "learning_rate": 2.627840909090909e-05,
+ "loss": 0.3482,
"step": 1223
},
{
- "epoch": 24.77,
- "learning_rate": 4.387755102040816e-05,
- "loss": 0.9389,
+ "epoch": 13.83,
+ "learning_rate": 2.6136363636363637e-05,
+ "loss": 0.3458,
"step": 1224
},
{
- "epoch": 24.79,
- "learning_rate": 4.375e-05,
- "loss": 0.8703,
+ "epoch": 13.84,
+ "learning_rate": 2.5994318181818182e-05,
+ "loss": 0.3442,
"step": 1225
},
{
- "epoch": 24.81,
- "learning_rate": 4.362244897959184e-05,
- "loss": 0.9407,
+ "epoch": 13.85,
+ "learning_rate": 2.585227272727273e-05,
+ "loss": 0.3717,
"step": 1226
},
{
- "epoch": 24.83,
- "learning_rate": 4.3494897959183675e-05,
- "loss": 0.9016,
+ "epoch": 13.86,
+ "learning_rate": 2.5710227272727272e-05,
+ "loss": 0.3404,
"step": 1227
},
{
- "epoch": 24.85,
- "learning_rate": 4.336734693877551e-05,
- "loss": 0.9025,
+ "epoch": 13.87,
+ "learning_rate": 2.5568181818181817e-05,
+ "loss": 0.34,
"step": 1228
},
{
- "epoch": 24.87,
- "learning_rate": 4.323979591836735e-05,
- "loss": 0.9415,
+ "epoch": 13.88,
+ "learning_rate": 2.5426136363636366e-05,
+ "loss": 0.3615,
"step": 1229
},
{
- "epoch": 24.89,
- "learning_rate": 4.311224489795919e-05,
- "loss": 0.9146,
+ "epoch": 13.9,
+ "learning_rate": 2.5284090909090914e-05,
+ "loss": 0.3473,
"step": 1230
},
{
- "epoch": 24.91,
- "learning_rate": 4.2984693877551025e-05,
- "loss": 0.9144,
+ "epoch": 13.91,
+ "learning_rate": 2.5142045454545453e-05,
+ "loss": 0.3532,
"step": 1231
},
{
- "epoch": 24.93,
- "learning_rate": 4.2857142857142856e-05,
- "loss": 0.9138,
+ "epoch": 13.92,
+ "learning_rate": 2.5e-05,
+ "loss": 0.3524,
"step": 1232
},
{
- "epoch": 24.95,
- "learning_rate": 4.2729591836734694e-05,
- "loss": 0.9372,
+ "epoch": 13.93,
+ "learning_rate": 2.4857954545454546e-05,
+ "loss": 0.3681,
"step": 1233
},
{
- "epoch": 24.97,
- "learning_rate": 4.260204081632653e-05,
- "loss": 0.8701,
+ "epoch": 13.94,
+ "learning_rate": 2.471590909090909e-05,
+ "loss": 0.3432,
"step": 1234
},
{
- "epoch": 24.99,
- "learning_rate": 4.247448979591837e-05,
- "loss": 0.9278,
+ "epoch": 13.95,
+ "learning_rate": 2.4573863636363636e-05,
+ "loss": 0.3507,
"step": 1235
},
{
- "epoch": 25.01,
- "learning_rate": 4.234693877551021e-05,
- "loss": 0.9157,
+ "epoch": 13.96,
+ "learning_rate": 2.4431818181818185e-05,
+ "loss": 0.3448,
"step": 1236
},
{
- "epoch": 25.03,
- "learning_rate": 4.2219387755102045e-05,
- "loss": 0.8852,
+ "epoch": 13.97,
+ "learning_rate": 2.4289772727272727e-05,
+ "loss": 0.3501,
"step": 1237
},
{
- "epoch": 25.05,
- "learning_rate": 4.209183673469388e-05,
- "loss": 0.855,
+ "epoch": 13.99,
+ "learning_rate": 2.4147727272727275e-05,
+ "loss": 0.3624,
"step": 1238
},
{
- "epoch": 25.07,
- "learning_rate": 4.196428571428572e-05,
- "loss": 0.8547,
+ "epoch": 14.0,
+ "learning_rate": 2.400568181818182e-05,
+ "loss": 0.3446,
"step": 1239
},
{
- "epoch": 25.09,
- "learning_rate": 4.183673469387756e-05,
- "loss": 0.8691,
+ "epoch": 14.01,
+ "learning_rate": 2.3863636363636365e-05,
+ "loss": 0.3463,
"step": 1240
},
{
- "epoch": 25.11,
- "learning_rate": 4.170918367346939e-05,
- "loss": 0.9101,
+ "epoch": 14.02,
+ "learning_rate": 2.372159090909091e-05,
+ "loss": 0.3492,
"step": 1241
},
{
- "epoch": 25.13,
- "learning_rate": 4.1581632653061226e-05,
- "loss": 0.8408,
+ "epoch": 14.03,
+ "learning_rate": 2.3579545454545455e-05,
+ "loss": 0.3352,
"step": 1242
},
{
- "epoch": 25.15,
- "learning_rate": 4.1454081632653064e-05,
- "loss": 0.9008,
+ "epoch": 14.04,
+ "learning_rate": 2.34375e-05,
+ "loss": 0.3368,
"step": 1243
},
{
- "epoch": 25.17,
- "learning_rate": 4.13265306122449e-05,
- "loss": 0.859,
+ "epoch": 14.05,
+ "learning_rate": 2.3295454545454546e-05,
+ "loss": 0.3295,
"step": 1244
},
{
- "epoch": 25.19,
- "learning_rate": 4.119897959183674e-05,
- "loss": 0.8525,
+ "epoch": 14.07,
+ "learning_rate": 2.315340909090909e-05,
+ "loss": 0.3426,
"step": 1245
},
{
- "epoch": 25.21,
- "learning_rate": 4.107142857142857e-05,
- "loss": 0.8682,
+ "epoch": 14.08,
+ "learning_rate": 2.3011363636363636e-05,
+ "loss": 0.3284,
"step": 1246
},
{
- "epoch": 25.23,
- "learning_rate": 4.094387755102041e-05,
- "loss": 0.8426,
+ "epoch": 14.09,
+ "learning_rate": 2.2869318181818184e-05,
+ "loss": 0.3305,
"step": 1247
},
{
- "epoch": 25.25,
- "learning_rate": 4.0816326530612245e-05,
- "loss": 0.8948,
+ "epoch": 14.1,
+ "learning_rate": 2.272727272727273e-05,
+ "loss": 0.3447,
"step": 1248
},
{
- "epoch": 25.27,
- "learning_rate": 4.068877551020408e-05,
- "loss": 0.8333,
+ "epoch": 14.11,
+ "learning_rate": 2.2585227272727274e-05,
+ "loss": 0.344,
"step": 1249
},
{
- "epoch": 25.29,
- "learning_rate": 4.056122448979592e-05,
- "loss": 0.87,
+ "epoch": 14.12,
+ "learning_rate": 2.244318181818182e-05,
+ "loss": 0.3516,
"step": 1250
},
{
- "epoch": 25.31,
- "learning_rate": 4.043367346938776e-05,
- "loss": 0.8215,
+ "epoch": 14.13,
+ "learning_rate": 2.2301136363636365e-05,
+ "loss": 0.3417,
"step": 1251
},
{
- "epoch": 25.33,
- "learning_rate": 4.0306122448979596e-05,
- "loss": 0.862,
+ "epoch": 14.14,
+ "learning_rate": 2.215909090909091e-05,
+ "loss": 0.3353,
"step": 1252
},
{
- "epoch": 25.35,
- "learning_rate": 4.017857142857143e-05,
- "loss": 0.8607,
+ "epoch": 14.16,
+ "learning_rate": 2.2017045454545458e-05,
+ "loss": 0.3363,
"step": 1253
},
{
- "epoch": 25.37,
- "learning_rate": 4.0051020408163264e-05,
- "loss": 0.8218,
+ "epoch": 14.17,
+ "learning_rate": 2.1875e-05,
+ "loss": 0.3342,
"step": 1254
},
{
- "epoch": 25.39,
- "learning_rate": 3.99234693877551e-05,
- "loss": 0.806,
+ "epoch": 14.18,
+ "learning_rate": 2.1732954545454545e-05,
+ "loss": 0.3366,
"step": 1255
},
{
- "epoch": 25.41,
- "learning_rate": 3.979591836734694e-05,
- "loss": 0.8929,
+ "epoch": 14.19,
+ "learning_rate": 2.1590909090909093e-05,
+ "loss": 0.3333,
"step": 1256
},
{
- "epoch": 25.43,
- "learning_rate": 3.966836734693878e-05,
- "loss": 0.8551,
+ "epoch": 14.2,
+ "learning_rate": 2.1448863636363635e-05,
+ "loss": 0.3425,
"step": 1257
},
{
- "epoch": 25.45,
- "learning_rate": 3.9540816326530615e-05,
- "loss": 0.8408,
+ "epoch": 14.21,
+ "learning_rate": 2.1306818181818183e-05,
+ "loss": 0.3366,
"step": 1258
},
{
- "epoch": 25.47,
- "learning_rate": 3.9413265306122446e-05,
- "loss": 0.8819,
+ "epoch": 14.22,
+ "learning_rate": 2.116477272727273e-05,
+ "loss": 0.3324,
"step": 1259
},
{
- "epoch": 25.49,
- "learning_rate": 3.928571428571429e-05,
- "loss": 0.8757,
+ "epoch": 14.23,
+ "learning_rate": 2.1022727272727274e-05,
+ "loss": 0.3527,
"step": 1260
},
{
- "epoch": 25.52,
- "learning_rate": 3.915816326530613e-05,
- "loss": 0.8778,
+ "epoch": 14.25,
+ "learning_rate": 2.088068181818182e-05,
+ "loss": 0.3399,
"step": 1261
},
{
- "epoch": 25.54,
- "learning_rate": 3.9030612244897965e-05,
- "loss": 0.8524,
+ "epoch": 14.26,
+ "learning_rate": 2.0738636363636367e-05,
+ "loss": 0.3651,
"step": 1262
},
{
- "epoch": 25.56,
- "learning_rate": 3.8903061224489796e-05,
- "loss": 0.846,
+ "epoch": 14.27,
+ "learning_rate": 2.059659090909091e-05,
+ "loss": 0.3381,
"step": 1263
},
{
- "epoch": 25.58,
- "learning_rate": 3.8775510204081634e-05,
- "loss": 0.8757,
+ "epoch": 14.28,
+ "learning_rate": 2.0454545454545457e-05,
+ "loss": 0.3408,
"step": 1264
},
{
- "epoch": 25.6,
- "learning_rate": 3.864795918367347e-05,
- "loss": 0.9084,
+ "epoch": 14.29,
+ "learning_rate": 2.0312500000000002e-05,
+ "loss": 0.3237,
"step": 1265
},
{
- "epoch": 25.62,
- "learning_rate": 3.852040816326531e-05,
- "loss": 0.8826,
+ "epoch": 14.3,
+ "learning_rate": 2.0170454545454544e-05,
+ "loss": 0.3421,
"step": 1266
},
{
- "epoch": 25.64,
- "learning_rate": 3.839285714285715e-05,
- "loss": 0.8619,
+ "epoch": 14.31,
+ "learning_rate": 2.0028409090909093e-05,
+ "loss": 0.3361,
"step": 1267
},
{
- "epoch": 25.66,
- "learning_rate": 3.826530612244898e-05,
- "loss": 0.8942,
+ "epoch": 14.33,
+ "learning_rate": 1.9886363636363638e-05,
+ "loss": 0.3475,
"step": 1268
},
{
- "epoch": 25.68,
- "learning_rate": 3.8137755102040815e-05,
- "loss": 0.8342,
+ "epoch": 14.34,
+ "learning_rate": 1.9744318181818183e-05,
+ "loss": 0.3337,
"step": 1269
},
{
- "epoch": 25.7,
- "learning_rate": 3.801020408163265e-05,
- "loss": 0.8512,
+ "epoch": 14.35,
+ "learning_rate": 1.9602272727272728e-05,
+ "loss": 0.3384,
"step": 1270
},
{
- "epoch": 25.72,
- "learning_rate": 3.788265306122449e-05,
- "loss": 0.8393,
+ "epoch": 14.36,
+ "learning_rate": 1.9460227272727273e-05,
+ "loss": 0.3255,
"step": 1271
},
{
- "epoch": 25.74,
- "learning_rate": 3.775510204081633e-05,
- "loss": 0.8508,
+ "epoch": 14.37,
+ "learning_rate": 1.9318181818181818e-05,
+ "loss": 0.3568,
"step": 1272
},
{
- "epoch": 25.76,
- "learning_rate": 3.7627551020408166e-05,
- "loss": 0.9094,
+ "epoch": 14.38,
+ "learning_rate": 1.9176136363636366e-05,
+ "loss": 0.3427,
"step": 1273
},
{
- "epoch": 25.78,
- "learning_rate": 3.7500000000000003e-05,
- "loss": 0.9175,
+ "epoch": 14.39,
+ "learning_rate": 1.9034090909090908e-05,
+ "loss": 0.3468,
"step": 1274
},
{
- "epoch": 25.8,
- "learning_rate": 3.737244897959184e-05,
- "loss": 0.9179,
+ "epoch": 14.4,
+ "learning_rate": 1.8892045454545457e-05,
+ "loss": 0.3312,
"step": 1275
},
{
- "epoch": 25.82,
- "learning_rate": 3.724489795918368e-05,
- "loss": 0.869,
+ "epoch": 14.42,
+ "learning_rate": 1.8750000000000002e-05,
+ "loss": 0.3376,
"step": 1276
},
{
- "epoch": 25.84,
- "learning_rate": 3.711734693877551e-05,
- "loss": 0.8568,
+ "epoch": 14.43,
+ "learning_rate": 1.8607954545454543e-05,
+ "loss": 0.3284,
"step": 1277
},
{
- "epoch": 25.86,
- "learning_rate": 3.698979591836735e-05,
- "loss": 0.9104,
+ "epoch": 14.44,
+ "learning_rate": 1.8465909090909092e-05,
+ "loss": 0.3378,
"step": 1278
},
{
- "epoch": 25.88,
- "learning_rate": 3.6862244897959185e-05,
- "loss": 0.8912,
+ "epoch": 14.45,
+ "learning_rate": 1.8323863636363637e-05,
+ "loss": 0.3331,
"step": 1279
},
{
- "epoch": 25.9,
- "learning_rate": 3.673469387755102e-05,
- "loss": 0.878,
+ "epoch": 14.46,
+ "learning_rate": 1.8181818181818182e-05,
+ "loss": 0.3297,
"step": 1280
},
{
- "epoch": 25.92,
- "learning_rate": 3.6607142857142853e-05,
- "loss": 0.8711,
+ "epoch": 14.47,
+ "learning_rate": 1.8039772727272727e-05,
+ "loss": 0.3491,
"step": 1281
},
{
- "epoch": 25.94,
- "learning_rate": 3.64795918367347e-05,
- "loss": 0.9404,
+ "epoch": 14.48,
+ "learning_rate": 1.7897727272727276e-05,
+ "loss": 0.3354,
"step": 1282
},
{
- "epoch": 25.96,
- "learning_rate": 3.6352040816326536e-05,
- "loss": 0.9302,
+ "epoch": 14.49,
+ "learning_rate": 1.7755681818181817e-05,
+ "loss": 0.3292,
"step": 1283
},
{
- "epoch": 25.98,
- "learning_rate": 3.622448979591837e-05,
- "loss": 0.8907,
+ "epoch": 14.51,
+ "learning_rate": 1.7613636363636366e-05,
+ "loss": 0.3419,
"step": 1284
},
{
- "epoch": 26.0,
- "learning_rate": 3.609693877551021e-05,
- "loss": 0.8473,
+ "epoch": 14.52,
+ "learning_rate": 1.747159090909091e-05,
+ "loss": 0.329,
"step": 1285
},
{
- "epoch": 26.02,
- "learning_rate": 3.596938775510204e-05,
- "loss": 0.8482,
+ "epoch": 14.53,
+ "learning_rate": 1.7329545454545456e-05,
+ "loss": 0.345,
"step": 1286
},
{
- "epoch": 26.04,
- "learning_rate": 3.584183673469388e-05,
- "loss": 0.8683,
+ "epoch": 14.54,
+ "learning_rate": 1.71875e-05,
+ "loss": 0.3369,
"step": 1287
},
{
- "epoch": 26.06,
- "learning_rate": 3.571428571428572e-05,
- "loss": 0.8443,
+ "epoch": 14.55,
+ "learning_rate": 1.7045454545454546e-05,
+ "loss": 0.3537,
"step": 1288
},
{
- "epoch": 26.08,
- "learning_rate": 3.5586734693877555e-05,
- "loss": 0.8462,
+ "epoch": 14.56,
+ "learning_rate": 1.690340909090909e-05,
+ "loss": 0.3418,
"step": 1289
},
{
- "epoch": 26.1,
- "learning_rate": 3.5459183673469385e-05,
- "loss": 0.8204,
+ "epoch": 14.57,
+ "learning_rate": 1.6761363636363636e-05,
+ "loss": 0.3514,
"step": 1290
},
{
- "epoch": 26.12,
- "learning_rate": 3.533163265306122e-05,
- "loss": 0.8632,
+ "epoch": 14.58,
+ "learning_rate": 1.6619318181818185e-05,
+ "loss": 0.3325,
"step": 1291
},
{
- "epoch": 26.14,
- "learning_rate": 3.520408163265306e-05,
- "loss": 0.8883,
+ "epoch": 14.6,
+ "learning_rate": 1.6477272727272726e-05,
+ "loss": 0.3492,
"step": 1292
},
{
- "epoch": 26.16,
- "learning_rate": 3.50765306122449e-05,
- "loss": 0.8369,
+ "epoch": 14.61,
+ "learning_rate": 1.6335227272727275e-05,
+ "loss": 0.3439,
"step": 1293
},
{
- "epoch": 26.18,
- "learning_rate": 3.4948979591836736e-05,
- "loss": 0.8369,
+ "epoch": 14.62,
+ "learning_rate": 1.619318181818182e-05,
+ "loss": 0.3401,
"step": 1294
},
{
- "epoch": 26.2,
- "learning_rate": 3.4821428571428574e-05,
- "loss": 0.8506,
+ "epoch": 14.63,
+ "learning_rate": 1.6051136363636365e-05,
+ "loss": 0.3373,
"step": 1295
},
{
- "epoch": 26.22,
- "learning_rate": 3.469387755102041e-05,
- "loss": 0.839,
+ "epoch": 14.64,
+ "learning_rate": 1.590909090909091e-05,
+ "loss": 0.339,
"step": 1296
},
{
- "epoch": 26.24,
- "learning_rate": 3.456632653061225e-05,
- "loss": 0.8421,
+ "epoch": 14.65,
+ "learning_rate": 1.5767045454545455e-05,
+ "loss": 0.3229,
"step": 1297
},
{
- "epoch": 26.26,
- "learning_rate": 3.443877551020409e-05,
- "loss": 0.8292,
+ "epoch": 14.66,
+ "learning_rate": 1.5625e-05,
+ "loss": 0.3369,
"step": 1298
},
{
- "epoch": 26.28,
- "learning_rate": 3.431122448979592e-05,
- "loss": 0.8412,
+ "epoch": 14.68,
+ "learning_rate": 1.5482954545454545e-05,
+ "loss": 0.3295,
"step": 1299
},
{
- "epoch": 26.3,
- "learning_rate": 3.4183673469387755e-05,
- "loss": 0.8305,
+ "epoch": 14.69,
+ "learning_rate": 1.534090909090909e-05,
+ "loss": 0.3333,
"step": 1300
}
],
"logging_steps": 1,
- "max_steps": 1568,
- "num_train_epochs": 32,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
"save_steps": 100,
- "total_flos": 1.9253105037500006e+18,
+ "total_flos": 1.7745797986691174e+18,
"trial_name": null,
"trial_params": null
}
diff --git a/checkpoint-1300/training_args.bin b/checkpoint-1300/training_args.bin
index db23e07d097c18532e52f58a70eb72d22e39c8c1..ee7ddb867f05d9a969f71467a8eb88994865cf51 100644
--- a/checkpoint-1300/training_args.bin
+++ b/checkpoint-1300/training_args.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
size 4155
diff --git a/checkpoint-1400/adapter_model.bin b/checkpoint-1400/adapter_model.bin
index 4745aee31110084e19714506670916f3c62d1f94..9ce03b063e69bd157fb884b8d6d13fa2d3cbc9eb 100644
--- a/checkpoint-1400/adapter_model.bin
+++ b/checkpoint-1400/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:019860e9604c2bce3e1eb82f3a576a7272afd222d602f5fba5c803b83043ee76
+oid sha256:e9fe5245989faeee0c2750a2146ba97c670136934dbaf55c59859a18ae47f724
size 39409357
diff --git a/checkpoint-1400/optimizer.pt b/checkpoint-1400/optimizer.pt
index 1a5d1001a74ae6e7fcb4afa45ee820537e022650..2466949c474a16c07b671601ea3e3d28a117f673 100644
--- a/checkpoint-1400/optimizer.pt
+++ b/checkpoint-1400/optimizer.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:dff811fb285c320d3235ecb226a73a05ba2c9fa3c8dcea292fb556c245eba3c7
+oid sha256:9aaac4c5de0c70c37dba56a1293e33680564febdb0dd9e90b3edc151a02b5c6f
size 78844421
diff --git a/checkpoint-1400/rng_state.pth b/checkpoint-1400/rng_state.pth
index 55458251cf9b9dd5303788f73cb2ddd459a88907..ce32862861da12da23bbb01ee9f59c5232cb111d 100644
--- a/checkpoint-1400/rng_state.pth
+++ b/checkpoint-1400/rng_state.pth
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:feeeda336ac9687793442afff9ff589b66dc74c1c2b27bafbcd1072d4b5fa37d
+oid sha256:51f3c17c1e7ce128318be2166e96b6dda4d1ff79c8b44e6fb06488bf0bbfcf8d
size 14575
diff --git a/checkpoint-1400/scheduler.pt b/checkpoint-1400/scheduler.pt
index 8c0bb19c7480c9e99af2b0ca613475fbdd4e6141..bc56c0fa05b89cade570ebaad0a9d0302f454057 100644
--- a/checkpoint-1400/scheduler.pt
+++ b/checkpoint-1400/scheduler.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:fc463b7a5519b8283bc8f09760b55dbcf1be2f24e13b19140789bdc09c3e1d5d
+oid sha256:d2781c7d6f9147f112526f8c8a2660aa0c2e5cae1ef90b804b4446ea6776f625
size 627
diff --git a/checkpoint-1400/trainer_state.json b/checkpoint-1400/trainer_state.json
index 8d441a440c3a045965abb373837074c2d4d12482..5d2cc80d3dd6c220ca130dd80d5976114a96a0e0 100644
--- a/checkpoint-1400/trainer_state.json
+++ b/checkpoint-1400/trainer_state.json
@@ -1,7 +1,7 @@
{
"best_metric": null,
"best_model_checkpoint": null,
- "epoch": 28.327537148276953,
+ "epoch": 15.816416593115623,
"eval_steps": 500,
"global_step": 1400,
"is_hyper_param_search": false,
@@ -9,8411 +9,8411 @@
"is_world_process_zero": true,
"log_history": [
{
- "epoch": 0.02,
- "learning_rate": 0.00019987244897959184,
- "loss": 3.2215,
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
"step": 1
},
{
- "epoch": 0.04,
- "learning_rate": 0.00019974489795918367,
- "loss": 2.8365,
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
"step": 2
},
{
- "epoch": 0.06,
- "learning_rate": 0.00019961734693877553,
- "loss": 2.602,
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
"step": 3
},
{
- "epoch": 0.08,
- "learning_rate": 0.00019948979591836736,
- "loss": 2.4196,
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
"step": 4
},
{
- "epoch": 0.1,
- "learning_rate": 0.0001993622448979592,
- "loss": 2.2574,
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
"step": 5
},
{
- "epoch": 0.12,
- "learning_rate": 0.00019923469387755102,
- "loss": 2.2239,
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
"step": 6
},
{
- "epoch": 0.14,
- "learning_rate": 0.00019910714285714288,
- "loss": 2.1661,
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
"step": 7
},
{
- "epoch": 0.16,
- "learning_rate": 0.0001989795918367347,
- "loss": 2.0987,
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
"step": 8
},
{
- "epoch": 0.18,
- "learning_rate": 0.00019885204081632654,
- "loss": 2.015,
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
"step": 9
},
{
- "epoch": 0.2,
- "learning_rate": 0.00019872448979591837,
- "loss": 1.9771,
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
"step": 10
},
{
- "epoch": 0.22,
- "learning_rate": 0.00019859693877551023,
- "loss": 2.0271,
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
"step": 11
},
{
- "epoch": 0.24,
- "learning_rate": 0.00019846938775510203,
- "loss": 1.9812,
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
"step": 12
},
{
- "epoch": 0.26,
- "learning_rate": 0.0001983418367346939,
- "loss": 2.0834,
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
"step": 13
},
{
- "epoch": 0.28,
- "learning_rate": 0.00019821428571428572,
- "loss": 1.9174,
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
"step": 14
},
{
- "epoch": 0.3,
- "learning_rate": 0.00019808673469387755,
- "loss": 1.8409,
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
"step": 15
},
{
- "epoch": 0.32,
- "learning_rate": 0.00019795918367346938,
- "loss": 1.929,
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
"step": 16
},
{
- "epoch": 0.34,
- "learning_rate": 0.00019783163265306124,
- "loss": 2.0041,
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
"step": 17
},
{
- "epoch": 0.36,
- "learning_rate": 0.00019770408163265305,
- "loss": 1.9385,
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
"step": 18
},
{
- "epoch": 0.38,
- "learning_rate": 0.0001975765306122449,
- "loss": 1.9592,
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
"step": 19
},
{
- "epoch": 0.4,
- "learning_rate": 0.00019744897959183674,
- "loss": 1.9701,
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
"step": 20
},
{
- "epoch": 0.42,
- "learning_rate": 0.0001973214285714286,
- "loss": 1.9277,
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
"step": 21
},
{
- "epoch": 0.45,
- "learning_rate": 0.00019719387755102042,
- "loss": 1.8394,
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
"step": 22
},
{
- "epoch": 0.47,
- "learning_rate": 0.00019706632653061226,
- "loss": 1.8666,
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
"step": 23
},
{
- "epoch": 0.49,
- "learning_rate": 0.00019693877551020409,
- "loss": 1.8997,
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
"step": 24
},
{
- "epoch": 0.51,
- "learning_rate": 0.00019681122448979592,
- "loss": 1.9432,
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
"step": 25
},
{
- "epoch": 0.53,
- "learning_rate": 0.00019668367346938777,
- "loss": 1.9137,
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
"step": 26
},
{
- "epoch": 0.55,
- "learning_rate": 0.0001965561224489796,
- "loss": 1.905,
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
"step": 27
},
{
- "epoch": 0.57,
- "learning_rate": 0.00019642857142857144,
- "loss": 1.8708,
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
"step": 28
},
{
- "epoch": 0.59,
- "learning_rate": 0.00019630102040816327,
- "loss": 1.9097,
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
"step": 29
},
{
- "epoch": 0.61,
- "learning_rate": 0.00019617346938775513,
- "loss": 1.896,
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
"step": 30
},
{
- "epoch": 0.63,
- "learning_rate": 0.00019604591836734696,
- "loss": 1.8834,
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
"step": 31
},
{
- "epoch": 0.65,
- "learning_rate": 0.0001959183673469388,
- "loss": 1.8323,
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
"step": 32
},
{
- "epoch": 0.67,
- "learning_rate": 0.00019579081632653062,
- "loss": 1.804,
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
"step": 33
},
{
- "epoch": 0.69,
- "learning_rate": 0.00019566326530612248,
- "loss": 1.8906,
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
"step": 34
},
{
- "epoch": 0.71,
- "learning_rate": 0.00019553571428571428,
- "loss": 1.8693,
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
"step": 35
},
{
- "epoch": 0.73,
- "learning_rate": 0.00019540816326530614,
- "loss": 1.9308,
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
"step": 36
},
{
- "epoch": 0.75,
- "learning_rate": 0.00019528061224489797,
- "loss": 1.8082,
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
"step": 37
},
{
- "epoch": 0.77,
- "learning_rate": 0.0001951530612244898,
- "loss": 1.848,
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
"step": 38
},
{
- "epoch": 0.79,
- "learning_rate": 0.00019502551020408163,
- "loss": 1.8866,
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
"step": 39
},
{
- "epoch": 0.81,
- "learning_rate": 0.0001948979591836735,
- "loss": 1.7844,
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
"step": 40
},
{
- "epoch": 0.83,
- "learning_rate": 0.0001947704081632653,
- "loss": 1.8485,
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
"step": 41
},
{
- "epoch": 0.85,
- "learning_rate": 0.00019464285714285715,
- "loss": 1.7917,
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
"step": 42
},
{
- "epoch": 0.87,
- "learning_rate": 0.00019451530612244898,
- "loss": 1.7342,
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
"step": 43
},
{
- "epoch": 0.89,
- "learning_rate": 0.00019438775510204084,
- "loss": 1.8479,
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
"step": 44
},
{
- "epoch": 0.91,
- "learning_rate": 0.00019426020408163267,
- "loss": 1.8639,
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
"step": 45
},
{
- "epoch": 0.93,
- "learning_rate": 0.0001941326530612245,
- "loss": 1.8166,
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
"step": 46
},
{
- "epoch": 0.95,
- "learning_rate": 0.00019400510204081633,
- "loss": 1.7566,
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
"step": 47
},
{
- "epoch": 0.97,
- "learning_rate": 0.00019387755102040816,
- "loss": 1.8071,
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
"step": 48
},
{
- "epoch": 0.99,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.8612,
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
"step": 49
},
{
- "epoch": 1.01,
- "learning_rate": 0.00019362244897959185,
- "loss": 1.7819,
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
"step": 50
},
{
- "epoch": 1.03,
- "learning_rate": 0.00019349489795918368,
- "loss": 1.8647,
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
"step": 51
},
{
- "epoch": 1.05,
- "learning_rate": 0.0001933673469387755,
- "loss": 1.8196,
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
"step": 52
},
{
- "epoch": 1.07,
- "learning_rate": 0.00019323979591836737,
- "loss": 1.8027,
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
"step": 53
},
{
- "epoch": 1.09,
- "learning_rate": 0.00019311224489795917,
- "loss": 1.8927,
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
"step": 54
},
{
- "epoch": 1.11,
- "learning_rate": 0.00019298469387755103,
- "loss": 1.8481,
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
"step": 55
},
{
- "epoch": 1.13,
- "learning_rate": 0.00019285714285714286,
- "loss": 1.7781,
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
"step": 56
},
{
- "epoch": 1.15,
- "learning_rate": 0.00019272959183673472,
- "loss": 1.8101,
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
"step": 57
},
{
- "epoch": 1.17,
- "learning_rate": 0.00019260204081632653,
- "loss": 1.7257,
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
"step": 58
},
{
- "epoch": 1.19,
- "learning_rate": 0.00019247448979591838,
- "loss": 1.8185,
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
"step": 59
},
{
- "epoch": 1.21,
- "learning_rate": 0.00019234693877551021,
- "loss": 1.8557,
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
"step": 60
},
{
- "epoch": 1.23,
- "learning_rate": 0.00019221938775510204,
- "loss": 1.7418,
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
"step": 61
},
{
- "epoch": 1.25,
- "learning_rate": 0.00019209183673469388,
- "loss": 1.6879,
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
"step": 62
},
{
- "epoch": 1.27,
- "learning_rate": 0.00019196428571428573,
- "loss": 1.7651,
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
"step": 63
},
{
- "epoch": 1.29,
- "learning_rate": 0.00019183673469387756,
- "loss": 1.7759,
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
"step": 64
},
{
- "epoch": 1.32,
- "learning_rate": 0.0001917091836734694,
- "loss": 1.7691,
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
"step": 65
},
{
- "epoch": 1.34,
- "learning_rate": 0.00019158163265306123,
- "loss": 1.7794,
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
"step": 66
},
{
- "epoch": 1.36,
- "learning_rate": 0.00019145408163265306,
- "loss": 1.8152,
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
"step": 67
},
{
- "epoch": 1.38,
- "learning_rate": 0.00019132653061224492,
- "loss": 1.8052,
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
"step": 68
},
{
- "epoch": 1.4,
- "learning_rate": 0.00019119897959183675,
- "loss": 1.8054,
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
"step": 69
},
{
- "epoch": 1.42,
- "learning_rate": 0.00019107142857142858,
- "loss": 1.8114,
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
"step": 70
},
{
- "epoch": 1.44,
- "learning_rate": 0.0001909438775510204,
- "loss": 1.7749,
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
"step": 71
},
{
- "epoch": 1.46,
- "learning_rate": 0.00019081632653061227,
- "loss": 1.777,
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
"step": 72
},
{
- "epoch": 1.48,
- "learning_rate": 0.0001906887755102041,
- "loss": 1.7896,
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
"step": 73
},
{
- "epoch": 1.5,
- "learning_rate": 0.00019056122448979593,
- "loss": 1.8335,
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
"step": 74
},
{
- "epoch": 1.52,
- "learning_rate": 0.00019043367346938776,
- "loss": 1.8155,
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
"step": 75
},
{
- "epoch": 1.54,
- "learning_rate": 0.00019030612244897962,
- "loss": 1.8224,
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
"step": 76
},
{
- "epoch": 1.56,
- "learning_rate": 0.00019017857142857142,
- "loss": 1.7889,
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
"step": 77
},
{
- "epoch": 1.58,
- "learning_rate": 0.00019005102040816328,
- "loss": 1.8866,
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
"step": 78
},
{
- "epoch": 1.6,
- "learning_rate": 0.0001899234693877551,
- "loss": 1.8439,
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
"step": 79
},
{
- "epoch": 1.62,
- "learning_rate": 0.00018979591836734697,
- "loss": 1.7906,
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
"step": 80
},
{
- "epoch": 1.64,
- "learning_rate": 0.00018966836734693877,
- "loss": 1.8627,
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
"step": 81
},
{
- "epoch": 1.66,
- "learning_rate": 0.00018954081632653063,
- "loss": 1.7497,
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
"step": 82
},
{
- "epoch": 1.68,
- "learning_rate": 0.00018941326530612246,
- "loss": 1.7936,
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
"step": 83
},
{
- "epoch": 1.7,
- "learning_rate": 0.0001892857142857143,
- "loss": 1.8341,
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
"step": 84
},
{
- "epoch": 1.72,
- "learning_rate": 0.00018915816326530612,
- "loss": 1.7868,
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
"step": 85
},
{
- "epoch": 1.74,
- "learning_rate": 0.00018903061224489798,
- "loss": 1.7493,
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
"step": 86
},
{
- "epoch": 1.76,
- "learning_rate": 0.0001889030612244898,
- "loss": 1.7926,
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
"step": 87
},
{
- "epoch": 1.78,
- "learning_rate": 0.00018877551020408164,
- "loss": 1.8278,
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
"step": 88
},
{
- "epoch": 1.8,
- "learning_rate": 0.00018864795918367347,
- "loss": 1.7387,
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
"step": 89
},
{
- "epoch": 1.82,
- "learning_rate": 0.0001885204081632653,
- "loss": 1.7669,
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
"step": 90
},
{
- "epoch": 1.84,
- "learning_rate": 0.00018839285714285716,
- "loss": 1.7686,
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
"step": 91
},
{
- "epoch": 1.86,
- "learning_rate": 0.000188265306122449,
- "loss": 1.7759,
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
"step": 92
},
{
- "epoch": 1.88,
- "learning_rate": 0.00018813775510204082,
- "loss": 1.7016,
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
"step": 93
},
{
- "epoch": 1.9,
- "learning_rate": 0.00018801020408163265,
- "loss": 1.8123,
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
"step": 94
},
{
- "epoch": 1.92,
- "learning_rate": 0.0001878826530612245,
- "loss": 1.8315,
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
"step": 95
},
{
- "epoch": 1.94,
- "learning_rate": 0.00018775510204081634,
- "loss": 1.7679,
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
"step": 96
},
{
- "epoch": 1.96,
- "learning_rate": 0.00018762755102040817,
- "loss": 1.7874,
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
"step": 97
},
{
- "epoch": 1.98,
- "learning_rate": 0.0001875,
- "loss": 1.8008,
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
"step": 98
},
{
- "epoch": 2.0,
- "learning_rate": 0.00018737244897959186,
- "loss": 1.7177,
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
"step": 99
},
{
- "epoch": 2.02,
- "learning_rate": 0.00018724489795918367,
- "loss": 1.7272,
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
"step": 100
},
{
- "epoch": 2.04,
- "learning_rate": 0.00018711734693877552,
- "loss": 1.7848,
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
"step": 101
},
{
- "epoch": 2.06,
- "learning_rate": 0.00018698979591836735,
- "loss": 1.744,
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
"step": 102
},
{
- "epoch": 2.08,
- "learning_rate": 0.00018686224489795919,
- "loss": 1.7005,
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
"step": 103
},
{
- "epoch": 2.1,
- "learning_rate": 0.00018673469387755102,
- "loss": 1.8247,
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
"step": 104
},
{
- "epoch": 2.12,
- "learning_rate": 0.00018660714285714287,
- "loss": 1.6855,
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
"step": 105
},
{
- "epoch": 2.14,
- "learning_rate": 0.0001864795918367347,
- "loss": 1.7627,
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
"step": 106
},
{
- "epoch": 2.17,
- "learning_rate": 0.00018635204081632654,
- "loss": 1.7564,
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
"step": 107
},
{
- "epoch": 2.19,
- "learning_rate": 0.00018622448979591837,
- "loss": 1.8237,
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
"step": 108
},
{
- "epoch": 2.21,
- "learning_rate": 0.00018609693877551022,
- "loss": 1.7421,
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
"step": 109
},
{
- "epoch": 2.23,
- "learning_rate": 0.00018596938775510206,
- "loss": 1.7517,
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
"step": 110
},
{
- "epoch": 2.25,
- "learning_rate": 0.0001858418367346939,
- "loss": 1.7515,
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
"step": 111
},
{
- "epoch": 2.27,
- "learning_rate": 0.00018571428571428572,
- "loss": 1.7842,
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
"step": 112
},
{
- "epoch": 2.29,
- "learning_rate": 0.00018558673469387755,
- "loss": 1.8001,
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
"step": 113
},
{
- "epoch": 2.31,
- "learning_rate": 0.0001854591836734694,
- "loss": 1.7653,
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
"step": 114
},
{
- "epoch": 2.33,
- "learning_rate": 0.00018533163265306124,
- "loss": 1.694,
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
"step": 115
},
{
- "epoch": 2.35,
- "learning_rate": 0.00018520408163265307,
- "loss": 1.7457,
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
"step": 116
},
{
- "epoch": 2.37,
- "learning_rate": 0.0001850765306122449,
- "loss": 1.7899,
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
"step": 117
},
{
- "epoch": 2.39,
- "learning_rate": 0.00018494897959183676,
- "loss": 1.7473,
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
"step": 118
},
{
- "epoch": 2.41,
- "learning_rate": 0.0001848214285714286,
- "loss": 1.6639,
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
"step": 119
},
{
- "epoch": 2.43,
- "learning_rate": 0.00018469387755102042,
- "loss": 1.762,
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
"step": 120
},
{
- "epoch": 2.45,
- "learning_rate": 0.00018456632653061225,
- "loss": 1.7378,
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
"step": 121
},
{
- "epoch": 2.47,
- "learning_rate": 0.0001844387755102041,
- "loss": 1.672,
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
"step": 122
},
{
- "epoch": 2.49,
- "learning_rate": 0.0001843112244897959,
- "loss": 1.7267,
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
"step": 123
},
{
- "epoch": 2.51,
- "learning_rate": 0.00018418367346938777,
- "loss": 1.7825,
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
"step": 124
},
{
- "epoch": 2.53,
- "learning_rate": 0.0001840561224489796,
- "loss": 1.7566,
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
"step": 125
},
{
- "epoch": 2.55,
- "learning_rate": 0.00018392857142857143,
- "loss": 1.8169,
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
"step": 126
},
{
- "epoch": 2.57,
- "learning_rate": 0.00018380102040816326,
- "loss": 1.6801,
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
"step": 127
},
{
- "epoch": 2.59,
- "learning_rate": 0.00018367346938775512,
- "loss": 1.7292,
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
"step": 128
},
{
- "epoch": 2.61,
- "learning_rate": 0.00018354591836734695,
- "loss": 1.737,
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
"step": 129
},
{
- "epoch": 2.63,
- "learning_rate": 0.00018341836734693878,
- "loss": 1.7696,
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
"step": 130
},
{
- "epoch": 2.65,
- "learning_rate": 0.0001832908163265306,
- "loss": 1.7239,
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
"step": 131
},
{
- "epoch": 2.67,
- "learning_rate": 0.00018316326530612247,
- "loss": 1.7441,
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
"step": 132
},
{
- "epoch": 2.69,
- "learning_rate": 0.0001830357142857143,
- "loss": 1.7825,
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
"step": 133
},
{
- "epoch": 2.71,
- "learning_rate": 0.00018290816326530613,
- "loss": 1.7411,
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
"step": 134
},
{
- "epoch": 2.73,
- "learning_rate": 0.00018278061224489796,
- "loss": 1.7119,
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
"step": 135
},
{
- "epoch": 2.75,
- "learning_rate": 0.0001826530612244898,
- "loss": 1.7443,
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
"step": 136
},
{
- "epoch": 2.77,
- "learning_rate": 0.00018252551020408165,
- "loss": 1.7197,
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
"step": 137
},
{
- "epoch": 2.79,
- "learning_rate": 0.00018239795918367348,
- "loss": 1.7273,
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
"step": 138
},
{
- "epoch": 2.81,
- "learning_rate": 0.0001822704081632653,
- "loss": 1.7681,
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
"step": 139
},
{
- "epoch": 2.83,
- "learning_rate": 0.00018214285714285714,
- "loss": 1.8088,
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
"step": 140
},
{
- "epoch": 2.85,
- "learning_rate": 0.000182015306122449,
- "loss": 1.7301,
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
"step": 141
},
{
- "epoch": 2.87,
- "learning_rate": 0.00018188775510204083,
- "loss": 1.6853,
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
"step": 142
},
{
- "epoch": 2.89,
- "learning_rate": 0.00018176020408163266,
- "loss": 1.6966,
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
"step": 143
},
{
- "epoch": 2.91,
- "learning_rate": 0.0001816326530612245,
- "loss": 1.7938,
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
"step": 144
},
{
- "epoch": 2.93,
- "learning_rate": 0.00018150510204081635,
- "loss": 1.7639,
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
"step": 145
},
{
- "epoch": 2.95,
- "learning_rate": 0.00018137755102040816,
- "loss": 1.7527,
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
"step": 146
},
{
- "epoch": 2.97,
- "learning_rate": 0.00018125000000000001,
- "loss": 1.7386,
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
"step": 147
},
{
- "epoch": 2.99,
- "learning_rate": 0.00018112244897959185,
- "loss": 1.7223,
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
"step": 148
},
{
- "epoch": 3.01,
- "learning_rate": 0.00018099489795918368,
- "loss": 1.7571,
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
"step": 149
},
{
- "epoch": 3.04,
- "learning_rate": 0.0001808673469387755,
- "loss": 1.7054,
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
"step": 150
},
{
- "epoch": 3.06,
- "learning_rate": 0.00018073979591836737,
- "loss": 1.6581,
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
"step": 151
},
{
- "epoch": 3.08,
- "learning_rate": 0.00018061224489795917,
- "loss": 1.681,
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
"step": 152
},
{
- "epoch": 3.1,
- "learning_rate": 0.00018048469387755103,
- "loss": 1.7425,
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
"step": 153
},
{
- "epoch": 3.12,
- "learning_rate": 0.00018035714285714286,
- "loss": 1.7108,
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
"step": 154
},
{
- "epoch": 3.14,
- "learning_rate": 0.00018022959183673472,
- "loss": 1.7194,
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
"step": 155
},
{
- "epoch": 3.16,
- "learning_rate": 0.00018010204081632655,
- "loss": 1.6953,
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
"step": 156
},
{
- "epoch": 3.18,
- "learning_rate": 0.00017997448979591838,
- "loss": 1.669,
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
"step": 157
},
{
- "epoch": 3.2,
- "learning_rate": 0.0001798469387755102,
- "loss": 1.744,
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
"step": 158
},
{
- "epoch": 3.22,
- "learning_rate": 0.00017971938775510204,
- "loss": 1.6467,
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
"step": 159
},
{
- "epoch": 3.24,
- "learning_rate": 0.0001795918367346939,
- "loss": 1.7103,
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
"step": 160
},
{
- "epoch": 3.26,
- "learning_rate": 0.00017946428571428573,
- "loss": 1.6662,
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
"step": 161
},
{
- "epoch": 3.28,
- "learning_rate": 0.00017933673469387756,
- "loss": 1.6657,
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
"step": 162
},
{
- "epoch": 3.3,
- "learning_rate": 0.0001792091836734694,
- "loss": 1.791,
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
"step": 163
},
{
- "epoch": 3.32,
- "learning_rate": 0.00017908163265306125,
- "loss": 1.7704,
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
"step": 164
},
{
- "epoch": 3.34,
- "learning_rate": 0.00017895408163265305,
- "loss": 1.7229,
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
"step": 165
},
{
- "epoch": 3.36,
- "learning_rate": 0.0001788265306122449,
- "loss": 1.76,
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
"step": 166
},
{
- "epoch": 3.38,
- "learning_rate": 0.00017869897959183674,
- "loss": 1.6482,
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
"step": 167
},
{
- "epoch": 3.4,
- "learning_rate": 0.0001785714285714286,
- "loss": 1.8076,
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
"step": 168
},
{
- "epoch": 3.42,
- "learning_rate": 0.0001784438775510204,
- "loss": 1.7368,
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
"step": 169
},
{
- "epoch": 3.44,
- "learning_rate": 0.00017831632653061226,
- "loss": 1.6264,
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
"step": 170
},
{
- "epoch": 3.46,
- "learning_rate": 0.0001781887755102041,
- "loss": 1.6289,
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
"step": 171
},
{
- "epoch": 3.48,
- "learning_rate": 0.00017806122448979592,
- "loss": 1.7913,
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
"step": 172
},
{
- "epoch": 3.5,
- "learning_rate": 0.00017793367346938775,
- "loss": 1.6985,
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
"step": 173
},
{
- "epoch": 3.52,
- "learning_rate": 0.0001778061224489796,
- "loss": 1.6936,
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
"step": 174
},
{
- "epoch": 3.54,
- "learning_rate": 0.00017767857142857141,
- "loss": 1.8068,
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
"step": 175
},
{
- "epoch": 3.56,
- "learning_rate": 0.00017755102040816327,
- "loss": 1.7243,
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
"step": 176
},
{
- "epoch": 3.58,
- "learning_rate": 0.0001774234693877551,
- "loss": 1.6893,
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
"step": 177
},
{
- "epoch": 3.6,
- "learning_rate": 0.00017729591836734696,
- "loss": 1.8122,
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
"step": 178
},
{
- "epoch": 3.62,
- "learning_rate": 0.0001771683673469388,
- "loss": 1.6562,
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
"step": 179
},
{
- "epoch": 3.64,
- "learning_rate": 0.00017704081632653062,
- "loss": 1.6999,
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
"step": 180
},
{
- "epoch": 3.66,
- "learning_rate": 0.00017691326530612245,
- "loss": 1.7229,
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
"step": 181
},
{
- "epoch": 3.68,
- "learning_rate": 0.00017678571428571428,
- "loss": 1.6764,
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
"step": 182
},
{
- "epoch": 3.7,
- "learning_rate": 0.00017665816326530614,
- "loss": 1.6982,
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
"step": 183
},
{
- "epoch": 3.72,
- "learning_rate": 0.00017653061224489797,
- "loss": 1.696,
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
"step": 184
},
{
- "epoch": 3.74,
- "learning_rate": 0.0001764030612244898,
- "loss": 1.6797,
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
"step": 185
},
{
- "epoch": 3.76,
- "learning_rate": 0.00017627551020408164,
- "loss": 1.637,
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
"step": 186
},
{
- "epoch": 3.78,
- "learning_rate": 0.0001761479591836735,
- "loss": 1.7074,
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
"step": 187
},
{
- "epoch": 3.8,
- "learning_rate": 0.0001760204081632653,
- "loss": 1.705,
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
"step": 188
},
{
- "epoch": 3.82,
- "learning_rate": 0.00017589285714285716,
- "loss": 1.6153,
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
"step": 189
},
{
- "epoch": 3.84,
- "learning_rate": 0.00017576530612244899,
- "loss": 1.7354,
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
"step": 190
},
{
- "epoch": 3.86,
- "learning_rate": 0.00017563775510204084,
- "loss": 1.6941,
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
"step": 191
},
{
- "epoch": 3.88,
- "learning_rate": 0.00017551020408163265,
- "loss": 1.7231,
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
"step": 192
},
{
- "epoch": 3.91,
- "learning_rate": 0.0001753826530612245,
- "loss": 1.7663,
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
"step": 193
},
{
- "epoch": 3.93,
- "learning_rate": 0.00017525510204081634,
- "loss": 1.6532,
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
"step": 194
},
{
- "epoch": 3.95,
- "learning_rate": 0.00017512755102040817,
- "loss": 1.7115,
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
"step": 195
},
{
- "epoch": 3.97,
- "learning_rate": 0.000175,
- "loss": 1.6955,
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
"step": 196
},
{
- "epoch": 3.99,
- "learning_rate": 0.00017487244897959186,
- "loss": 1.6863,
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
"step": 197
},
{
- "epoch": 4.01,
- "learning_rate": 0.00017474489795918366,
- "loss": 1.7012,
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
"step": 198
},
{
- "epoch": 4.03,
- "learning_rate": 0.00017461734693877552,
- "loss": 1.5927,
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
"step": 199
},
{
- "epoch": 4.05,
- "learning_rate": 0.00017448979591836735,
- "loss": 1.6272,
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
"step": 200
},
{
- "epoch": 4.07,
- "learning_rate": 0.00017436224489795918,
- "loss": 1.5994,
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
"step": 201
},
{
- "epoch": 4.09,
- "learning_rate": 0.00017423469387755104,
- "loss": 1.7141,
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
"step": 202
},
{
- "epoch": 4.11,
- "learning_rate": 0.00017410714285714287,
- "loss": 1.7547,
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
"step": 203
},
{
- "epoch": 4.13,
- "learning_rate": 0.0001739795918367347,
- "loss": 1.6254,
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
"step": 204
},
{
- "epoch": 4.15,
- "learning_rate": 0.00017385204081632653,
- "loss": 1.6686,
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
"step": 205
},
{
- "epoch": 4.17,
- "learning_rate": 0.0001737244897959184,
- "loss": 1.6684,
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
"step": 206
},
{
- "epoch": 4.19,
- "learning_rate": 0.00017359693877551022,
- "loss": 1.6724,
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
"step": 207
},
{
- "epoch": 4.21,
- "learning_rate": 0.00017346938775510205,
- "loss": 1.7361,
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
"step": 208
},
{
- "epoch": 4.23,
- "learning_rate": 0.00017334183673469388,
- "loss": 1.7167,
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
"step": 209
},
{
- "epoch": 4.25,
- "learning_rate": 0.00017321428571428574,
- "loss": 1.7226,
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
"step": 210
},
{
- "epoch": 4.27,
- "learning_rate": 0.00017308673469387754,
- "loss": 1.7133,
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
"step": 211
},
{
- "epoch": 4.29,
- "learning_rate": 0.0001729591836734694,
- "loss": 1.649,
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
"step": 212
},
{
- "epoch": 4.31,
- "learning_rate": 0.00017283163265306123,
- "loss": 1.7104,
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
"step": 213
},
{
- "epoch": 4.33,
- "learning_rate": 0.00017270408163265306,
- "loss": 1.6861,
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
"step": 214
},
{
- "epoch": 4.35,
- "learning_rate": 0.0001725765306122449,
- "loss": 1.648,
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
"step": 215
},
{
- "epoch": 4.37,
- "learning_rate": 0.00017244897959183675,
- "loss": 1.6215,
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
"step": 216
},
{
- "epoch": 4.39,
- "learning_rate": 0.00017232142857142858,
- "loss": 1.6334,
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
"step": 217
},
{
- "epoch": 4.41,
- "learning_rate": 0.0001721938775510204,
- "loss": 1.6283,
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
"step": 218
},
{
- "epoch": 4.43,
- "learning_rate": 0.00017206632653061224,
- "loss": 1.6462,
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
"step": 219
},
{
- "epoch": 4.45,
- "learning_rate": 0.0001719387755102041,
- "loss": 1.7233,
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
"step": 220
},
{
- "epoch": 4.47,
- "learning_rate": 0.0001718112244897959,
- "loss": 1.7839,
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
"step": 221
},
{
- "epoch": 4.49,
- "learning_rate": 0.00017168367346938776,
- "loss": 1.7204,
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
"step": 222
},
{
- "epoch": 4.51,
- "learning_rate": 0.0001715561224489796,
- "loss": 1.7671,
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
"step": 223
},
{
- "epoch": 4.53,
- "learning_rate": 0.00017142857142857143,
- "loss": 1.6824,
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
"step": 224
},
{
- "epoch": 4.55,
- "learning_rate": 0.00017130102040816328,
- "loss": 1.7068,
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
"step": 225
},
{
- "epoch": 4.57,
- "learning_rate": 0.00017117346938775511,
- "loss": 1.6515,
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
"step": 226
},
{
- "epoch": 4.59,
- "learning_rate": 0.00017104591836734694,
- "loss": 1.6586,
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
"step": 227
},
{
- "epoch": 4.61,
- "learning_rate": 0.00017091836734693878,
- "loss": 1.6355,
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
"step": 228
},
{
- "epoch": 4.63,
- "learning_rate": 0.00017079081632653063,
- "loss": 1.7173,
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
"step": 229
},
{
- "epoch": 4.65,
- "learning_rate": 0.00017066326530612246,
- "loss": 1.6585,
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
"step": 230
},
{
- "epoch": 4.67,
- "learning_rate": 0.0001705357142857143,
- "loss": 1.5856,
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
"step": 231
},
{
- "epoch": 4.69,
- "learning_rate": 0.00017040816326530613,
- "loss": 1.5923,
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
"step": 232
},
{
- "epoch": 4.71,
- "learning_rate": 0.00017028061224489798,
- "loss": 1.7128,
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
"step": 233
},
{
- "epoch": 4.73,
- "learning_rate": 0.0001701530612244898,
- "loss": 1.6971,
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
"step": 234
},
{
- "epoch": 4.75,
- "learning_rate": 0.00017002551020408165,
- "loss": 1.6416,
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
"step": 235
},
{
- "epoch": 4.78,
- "learning_rate": 0.00016989795918367348,
- "loss": 1.645,
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
"step": 236
},
{
- "epoch": 4.8,
- "learning_rate": 0.0001697704081632653,
- "loss": 1.6792,
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
"step": 237
},
{
- "epoch": 4.82,
- "learning_rate": 0.00016964285714285714,
- "loss": 1.6522,
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
"step": 238
},
{
- "epoch": 4.84,
- "learning_rate": 0.000169515306122449,
- "loss": 1.6315,
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
"step": 239
},
{
- "epoch": 4.86,
- "learning_rate": 0.00016938775510204083,
- "loss": 1.6622,
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
"step": 240
},
{
- "epoch": 4.88,
- "learning_rate": 0.00016926020408163266,
- "loss": 1.6566,
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
"step": 241
},
{
- "epoch": 4.9,
- "learning_rate": 0.0001691326530612245,
- "loss": 1.7141,
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
"step": 242
},
{
- "epoch": 4.92,
- "learning_rate": 0.00016900510204081635,
- "loss": 1.5873,
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
"step": 243
},
{
- "epoch": 4.94,
- "learning_rate": 0.00016887755102040818,
- "loss": 1.6571,
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
"step": 244
},
{
- "epoch": 4.96,
- "learning_rate": 0.00016875,
- "loss": 1.6829,
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
"step": 245
},
{
- "epoch": 4.98,
- "learning_rate": 0.00016862244897959184,
- "loss": 1.6935,
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
"step": 246
},
{
- "epoch": 5.0,
- "learning_rate": 0.00016849489795918367,
- "loss": 1.6782,
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
"step": 247
},
{
- "epoch": 5.02,
- "learning_rate": 0.00016836734693877553,
- "loss": 1.622,
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
"step": 248
},
{
- "epoch": 5.04,
- "learning_rate": 0.00016823979591836736,
- "loss": 1.6596,
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
"step": 249
},
{
- "epoch": 5.06,
- "learning_rate": 0.0001681122448979592,
- "loss": 1.5821,
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
"step": 250
},
{
- "epoch": 5.08,
- "learning_rate": 0.00016798469387755102,
- "loss": 1.7292,
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
"step": 251
},
{
- "epoch": 5.1,
- "learning_rate": 0.00016785714285714288,
- "loss": 1.646,
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
"step": 252
},
{
- "epoch": 5.12,
- "learning_rate": 0.0001677295918367347,
- "loss": 1.6969,
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
"step": 253
},
{
- "epoch": 5.14,
- "learning_rate": 0.00016760204081632654,
- "loss": 1.6082,
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
"step": 254
},
{
- "epoch": 5.16,
- "learning_rate": 0.00016747448979591837,
- "loss": 1.5843,
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
"step": 255
},
{
- "epoch": 5.18,
- "learning_rate": 0.00016734693877551023,
- "loss": 1.6827,
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
"step": 256
},
{
- "epoch": 5.2,
- "learning_rate": 0.00016721938775510203,
- "loss": 1.5824,
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
"step": 257
},
{
- "epoch": 5.22,
- "learning_rate": 0.0001670918367346939,
- "loss": 1.6795,
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
"step": 258
},
{
- "epoch": 5.24,
- "learning_rate": 0.00016696428571428572,
- "loss": 1.5639,
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
"step": 259
},
{
- "epoch": 5.26,
- "learning_rate": 0.00016683673469387755,
- "loss": 1.592,
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
"step": 260
},
{
- "epoch": 5.28,
- "learning_rate": 0.00016670918367346938,
- "loss": 1.65,
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
"step": 261
},
{
- "epoch": 5.3,
- "learning_rate": 0.00016658163265306124,
- "loss": 1.5592,
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
"step": 262
},
{
- "epoch": 5.32,
- "learning_rate": 0.00016645408163265305,
- "loss": 1.5091,
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
"step": 263
},
{
- "epoch": 5.34,
- "learning_rate": 0.0001663265306122449,
- "loss": 1.6138,
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
"step": 264
},
{
- "epoch": 5.36,
- "learning_rate": 0.00016619897959183673,
- "loss": 1.625,
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
"step": 265
},
{
- "epoch": 5.38,
- "learning_rate": 0.0001660714285714286,
- "loss": 1.5757,
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
"step": 266
},
{
- "epoch": 5.4,
- "learning_rate": 0.00016594387755102042,
- "loss": 1.6372,
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
"step": 267
},
{
- "epoch": 5.42,
- "learning_rate": 0.00016581632653061225,
- "loss": 1.5891,
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
"step": 268
},
{
- "epoch": 5.44,
- "learning_rate": 0.00016568877551020409,
- "loss": 1.6893,
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
"step": 269
},
{
- "epoch": 5.46,
- "learning_rate": 0.00016556122448979592,
- "loss": 1.6662,
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
"step": 270
},
{
- "epoch": 5.48,
- "learning_rate": 0.00016543367346938777,
- "loss": 1.7132,
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
"step": 271
},
{
- "epoch": 5.5,
- "learning_rate": 0.0001653061224489796,
- "loss": 1.5835,
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
"step": 272
},
{
- "epoch": 5.52,
- "learning_rate": 0.00016517857142857144,
- "loss": 1.6342,
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
"step": 273
},
{
- "epoch": 5.54,
- "learning_rate": 0.00016505102040816327,
- "loss": 1.6717,
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
"step": 274
},
{
- "epoch": 5.56,
- "learning_rate": 0.00016492346938775512,
- "loss": 1.6248,
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
"step": 275
},
{
- "epoch": 5.58,
- "learning_rate": 0.00016479591836734696,
- "loss": 1.6117,
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
"step": 276
},
{
- "epoch": 5.6,
- "learning_rate": 0.0001646683673469388,
- "loss": 1.6798,
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
"step": 277
},
{
- "epoch": 5.63,
- "learning_rate": 0.00016454081632653062,
- "loss": 1.6406,
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
"step": 278
},
{
- "epoch": 5.65,
- "learning_rate": 0.00016441326530612248,
- "loss": 1.6512,
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
"step": 279
},
{
- "epoch": 5.67,
- "learning_rate": 0.00016428571428571428,
- "loss": 1.6102,
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
"step": 280
},
{
- "epoch": 5.69,
- "learning_rate": 0.00016415816326530614,
- "loss": 1.6113,
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
"step": 281
},
{
- "epoch": 5.71,
- "learning_rate": 0.00016403061224489797,
- "loss": 1.7116,
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
"step": 282
},
{
- "epoch": 5.73,
- "learning_rate": 0.0001639030612244898,
- "loss": 1.6846,
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
"step": 283
},
{
- "epoch": 5.75,
- "learning_rate": 0.00016377551020408163,
- "loss": 1.6911,
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
"step": 284
},
{
- "epoch": 5.77,
- "learning_rate": 0.0001636479591836735,
- "loss": 1.6202,
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
"step": 285
},
{
- "epoch": 5.79,
- "learning_rate": 0.0001635204081632653,
- "loss": 1.5715,
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
"step": 286
},
{
- "epoch": 5.81,
- "learning_rate": 0.00016339285714285715,
- "loss": 1.6461,
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
"step": 287
},
{
- "epoch": 5.83,
- "learning_rate": 0.00016326530612244898,
- "loss": 1.6624,
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
"step": 288
},
{
- "epoch": 5.85,
- "learning_rate": 0.00016313775510204084,
- "loss": 1.6535,
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
"step": 289
},
{
- "epoch": 5.87,
- "learning_rate": 0.00016301020408163267,
- "loss": 1.6275,
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
"step": 290
},
{
- "epoch": 5.89,
- "learning_rate": 0.0001628826530612245,
- "loss": 1.6636,
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
"step": 291
},
{
- "epoch": 5.91,
- "learning_rate": 0.00016275510204081633,
- "loss": 1.6546,
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
"step": 292
},
{
- "epoch": 5.93,
- "learning_rate": 0.00016262755102040816,
- "loss": 1.7274,
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
"step": 293
},
{
- "epoch": 5.95,
- "learning_rate": 0.00016250000000000002,
- "loss": 1.5901,
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
"step": 294
},
{
- "epoch": 5.97,
- "learning_rate": 0.00016237244897959185,
- "loss": 1.6046,
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
"step": 295
},
{
- "epoch": 5.99,
- "learning_rate": 0.00016224489795918368,
- "loss": 1.5828,
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
"step": 296
},
{
- "epoch": 6.01,
- "learning_rate": 0.0001621173469387755,
- "loss": 1.6435,
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
"step": 297
},
{
- "epoch": 6.03,
- "learning_rate": 0.00016198979591836737,
- "loss": 1.6263,
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
"step": 298
},
{
- "epoch": 6.05,
- "learning_rate": 0.00016186224489795917,
- "loss": 1.4944,
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
"step": 299
},
{
- "epoch": 6.07,
- "learning_rate": 0.00016173469387755103,
- "loss": 1.6286,
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
"step": 300
},
{
- "epoch": 6.09,
- "learning_rate": 0.00016160714285714286,
- "loss": 1.694,
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
"step": 301
},
{
- "epoch": 6.11,
- "learning_rate": 0.00016147959183673472,
- "loss": 1.6197,
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
"step": 302
},
{
- "epoch": 6.13,
- "learning_rate": 0.00016135204081632652,
- "loss": 1.5597,
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
"step": 303
},
{
- "epoch": 6.15,
- "learning_rate": 0.00016122448979591838,
- "loss": 1.5487,
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
"step": 304
},
{
- "epoch": 6.17,
- "learning_rate": 0.0001610969387755102,
- "loss": 1.5769,
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
"step": 305
},
{
- "epoch": 6.19,
- "learning_rate": 0.00016096938775510204,
- "loss": 1.6367,
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
"step": 306
},
{
- "epoch": 6.21,
- "learning_rate": 0.00016084183673469388,
- "loss": 1.583,
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
"step": 307
},
{
- "epoch": 6.23,
- "learning_rate": 0.00016071428571428573,
- "loss": 1.6201,
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
"step": 308
},
{
- "epoch": 6.25,
- "learning_rate": 0.00016058673469387754,
- "loss": 1.6586,
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
"step": 309
},
{
- "epoch": 6.27,
- "learning_rate": 0.0001604591836734694,
- "loss": 1.6711,
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
"step": 310
},
{
- "epoch": 6.29,
- "learning_rate": 0.00016033163265306123,
- "loss": 1.6402,
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
"step": 311
},
{
- "epoch": 6.31,
- "learning_rate": 0.00016020408163265306,
- "loss": 1.5247,
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
"step": 312
},
{
- "epoch": 6.33,
- "learning_rate": 0.00016007653061224491,
- "loss": 1.5356,
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
"step": 313
},
{
- "epoch": 6.35,
- "learning_rate": 0.00015994897959183675,
- "loss": 1.564,
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
"step": 314
},
{
- "epoch": 6.37,
- "learning_rate": 0.00015982142857142858,
- "loss": 1.563,
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
"step": 315
},
{
- "epoch": 6.39,
- "learning_rate": 0.0001596938775510204,
- "loss": 1.5198,
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
"step": 316
},
{
- "epoch": 6.41,
- "learning_rate": 0.00015956632653061227,
- "loss": 1.6558,
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
"step": 317
},
{
- "epoch": 6.43,
- "learning_rate": 0.0001594387755102041,
- "loss": 1.5534,
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
"step": 318
},
{
- "epoch": 6.45,
- "learning_rate": 0.00015931122448979593,
- "loss": 1.6239,
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
"step": 319
},
{
- "epoch": 6.47,
- "learning_rate": 0.00015918367346938776,
- "loss": 1.5645,
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
"step": 320
},
{
- "epoch": 6.5,
- "learning_rate": 0.00015905612244897962,
- "loss": 1.5713,
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
"step": 321
},
{
- "epoch": 6.52,
- "learning_rate": 0.00015892857142857142,
- "loss": 1.6176,
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
"step": 322
},
{
- "epoch": 6.54,
- "learning_rate": 0.00015880102040816328,
- "loss": 1.502,
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
"step": 323
},
{
- "epoch": 6.56,
- "learning_rate": 0.0001586734693877551,
- "loss": 1.645,
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
"step": 324
},
{
- "epoch": 6.58,
- "learning_rate": 0.00015854591836734697,
- "loss": 1.5904,
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
"step": 325
},
{
- "epoch": 6.6,
- "learning_rate": 0.00015841836734693877,
- "loss": 1.6149,
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
"step": 326
},
{
- "epoch": 6.62,
- "learning_rate": 0.00015829081632653063,
- "loss": 1.6757,
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
"step": 327
},
{
- "epoch": 6.64,
- "learning_rate": 0.00015816326530612246,
- "loss": 1.541,
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
"step": 328
},
{
- "epoch": 6.66,
- "learning_rate": 0.0001580357142857143,
- "loss": 1.5898,
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
"step": 329
},
{
- "epoch": 6.68,
- "learning_rate": 0.00015790816326530612,
- "loss": 1.5441,
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
"step": 330
},
{
- "epoch": 6.7,
- "learning_rate": 0.00015778061224489798,
- "loss": 1.61,
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
"step": 331
},
{
- "epoch": 6.72,
- "learning_rate": 0.00015765306122448978,
- "loss": 1.615,
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
"step": 332
},
{
- "epoch": 6.74,
- "learning_rate": 0.00015752551020408164,
- "loss": 1.6575,
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
"step": 333
},
{
- "epoch": 6.76,
- "learning_rate": 0.00015739795918367347,
- "loss": 1.6702,
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
"step": 334
},
{
- "epoch": 6.78,
- "learning_rate": 0.0001572704081632653,
- "loss": 1.6009,
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
"step": 335
},
{
- "epoch": 6.8,
- "learning_rate": 0.00015714285714285716,
- "loss": 1.5568,
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
"step": 336
},
{
- "epoch": 6.82,
- "learning_rate": 0.000157015306122449,
- "loss": 1.619,
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
"step": 337
},
{
- "epoch": 6.84,
- "learning_rate": 0.00015688775510204082,
- "loss": 1.5563,
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
"step": 338
},
{
- "epoch": 6.86,
- "learning_rate": 0.00015676020408163265,
- "loss": 1.6328,
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
"step": 339
},
{
- "epoch": 6.88,
- "learning_rate": 0.0001566326530612245,
- "loss": 1.5726,
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
"step": 340
},
{
- "epoch": 6.9,
- "learning_rate": 0.00015650510204081634,
- "loss": 1.6199,
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
"step": 341
},
{
- "epoch": 6.92,
- "learning_rate": 0.00015637755102040817,
- "loss": 1.5722,
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
"step": 342
},
{
- "epoch": 6.94,
- "learning_rate": 0.00015625,
- "loss": 1.5685,
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
"step": 343
},
{
- "epoch": 6.96,
- "learning_rate": 0.00015612244897959186,
- "loss": 1.5615,
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
"step": 344
},
{
- "epoch": 6.98,
- "learning_rate": 0.00015599489795918366,
- "loss": 1.5994,
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
"step": 345
},
{
- "epoch": 7.0,
- "learning_rate": 0.00015586734693877552,
- "loss": 1.5579,
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
"step": 346
},
{
- "epoch": 7.02,
- "learning_rate": 0.00015573979591836735,
- "loss": 1.547,
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
"step": 347
},
{
- "epoch": 7.04,
- "learning_rate": 0.00015561224489795918,
- "loss": 1.5292,
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
"step": 348
},
{
- "epoch": 7.06,
- "learning_rate": 0.00015548469387755102,
- "loss": 1.6032,
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
"step": 349
},
{
- "epoch": 7.08,
- "learning_rate": 0.00015535714285714287,
- "loss": 1.5149,
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
"step": 350
},
{
- "epoch": 7.1,
- "learning_rate": 0.0001552295918367347,
- "loss": 1.6093,
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
"step": 351
},
{
- "epoch": 7.12,
- "learning_rate": 0.00015510204081632654,
- "loss": 1.5421,
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
"step": 352
},
{
- "epoch": 7.14,
- "learning_rate": 0.00015497448979591837,
- "loss": 1.5733,
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
"step": 353
},
{
- "epoch": 7.16,
- "learning_rate": 0.00015484693877551022,
- "loss": 1.5703,
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
"step": 354
},
{
- "epoch": 7.18,
- "learning_rate": 0.00015471938775510203,
- "loss": 1.6141,
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
"step": 355
},
{
- "epoch": 7.2,
- "learning_rate": 0.00015459183673469389,
- "loss": 1.5526,
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
"step": 356
},
{
- "epoch": 7.22,
- "learning_rate": 0.00015446428571428572,
- "loss": 1.5347,
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
"step": 357
},
{
- "epoch": 7.24,
- "learning_rate": 0.00015433673469387755,
- "loss": 1.5682,
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
"step": 358
},
{
- "epoch": 7.26,
- "learning_rate": 0.0001542091836734694,
- "loss": 1.5292,
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
"step": 359
},
{
- "epoch": 7.28,
- "learning_rate": 0.00015408163265306124,
- "loss": 1.499,
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
"step": 360
},
{
- "epoch": 7.3,
- "learning_rate": 0.00015395408163265307,
- "loss": 1.5624,
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
"step": 361
},
{
- "epoch": 7.32,
- "learning_rate": 0.0001538265306122449,
- "loss": 1.627,
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
"step": 362
},
{
- "epoch": 7.34,
- "learning_rate": 0.00015369897959183676,
- "loss": 1.5327,
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
"step": 363
},
{
- "epoch": 7.37,
- "learning_rate": 0.0001535714285714286,
- "loss": 1.5622,
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
"step": 364
},
{
- "epoch": 7.39,
- "learning_rate": 0.00015344387755102042,
- "loss": 1.5659,
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
"step": 365
},
{
- "epoch": 7.41,
- "learning_rate": 0.00015331632653061225,
- "loss": 1.5019,
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
"step": 366
},
{
- "epoch": 7.43,
- "learning_rate": 0.0001531887755102041,
- "loss": 1.5921,
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
"step": 367
},
{
- "epoch": 7.45,
- "learning_rate": 0.0001530612244897959,
- "loss": 1.5914,
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
"step": 368
},
{
- "epoch": 7.47,
- "learning_rate": 0.00015293367346938777,
- "loss": 1.5045,
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
"step": 369
},
{
- "epoch": 7.49,
- "learning_rate": 0.0001528061224489796,
- "loss": 1.6209,
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
"step": 370
},
{
- "epoch": 7.51,
- "learning_rate": 0.00015267857142857143,
- "loss": 1.5198,
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
"step": 371
},
{
- "epoch": 7.53,
- "learning_rate": 0.00015255102040816326,
- "loss": 1.5363,
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
"step": 372
},
{
- "epoch": 7.55,
- "learning_rate": 0.00015242346938775512,
- "loss": 1.5391,
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
"step": 373
},
{
- "epoch": 7.57,
- "learning_rate": 0.00015229591836734695,
- "loss": 1.4546,
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
"step": 374
},
{
- "epoch": 7.59,
- "learning_rate": 0.00015216836734693878,
- "loss": 1.5546,
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
"step": 375
},
{
- "epoch": 7.61,
- "learning_rate": 0.0001520408163265306,
- "loss": 1.5629,
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
"step": 376
},
{
- "epoch": 7.63,
- "learning_rate": 0.00015191326530612247,
- "loss": 1.6002,
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
"step": 377
},
{
- "epoch": 7.65,
- "learning_rate": 0.00015178571428571427,
- "loss": 1.5543,
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
"step": 378
},
{
- "epoch": 7.67,
- "learning_rate": 0.00015165816326530613,
- "loss": 1.5925,
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
"step": 379
},
{
- "epoch": 7.69,
- "learning_rate": 0.00015153061224489796,
- "loss": 1.5631,
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
"step": 380
},
{
- "epoch": 7.71,
- "learning_rate": 0.0001514030612244898,
- "loss": 1.5677,
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
"step": 381
},
{
- "epoch": 7.73,
- "learning_rate": 0.00015127551020408165,
- "loss": 1.5828,
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
"step": 382
},
{
- "epoch": 7.75,
- "learning_rate": 0.00015114795918367348,
- "loss": 1.6494,
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
"step": 383
},
{
- "epoch": 7.77,
- "learning_rate": 0.0001510204081632653,
- "loss": 1.553,
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
"step": 384
},
{
- "epoch": 7.79,
- "learning_rate": 0.00015089285714285714,
- "loss": 1.6156,
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
"step": 385
},
{
- "epoch": 7.81,
- "learning_rate": 0.000150765306122449,
- "loss": 1.5001,
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
"step": 386
},
{
- "epoch": 7.83,
- "learning_rate": 0.00015063775510204083,
- "loss": 1.5321,
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
"step": 387
},
{
- "epoch": 7.85,
- "learning_rate": 0.00015051020408163266,
- "loss": 1.5307,
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
"step": 388
},
{
- "epoch": 7.87,
- "learning_rate": 0.0001503826530612245,
- "loss": 1.5639,
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
"step": 389
},
{
- "epoch": 7.89,
- "learning_rate": 0.00015025510204081635,
- "loss": 1.517,
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
"step": 390
},
{
- "epoch": 7.91,
- "learning_rate": 0.00015012755102040816,
- "loss": 1.4776,
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
"step": 391
},
{
- "epoch": 7.93,
- "learning_rate": 0.00015000000000000001,
- "loss": 1.5368,
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
"step": 392
},
{
- "epoch": 7.95,
- "learning_rate": 0.00014987244897959184,
- "loss": 1.5636,
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
"step": 393
},
{
- "epoch": 7.97,
- "learning_rate": 0.00014974489795918368,
- "loss": 1.6004,
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
"step": 394
},
{
- "epoch": 7.99,
- "learning_rate": 0.0001496173469387755,
- "loss": 1.5524,
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
"step": 395
},
{
- "epoch": 8.01,
- "learning_rate": 0.00014948979591836736,
- "loss": 1.5307,
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
"step": 396
},
{
- "epoch": 8.03,
- "learning_rate": 0.00014936224489795917,
- "loss": 1.5123,
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
"step": 397
},
{
- "epoch": 8.05,
- "learning_rate": 0.00014923469387755103,
- "loss": 1.5132,
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
"step": 398
},
{
- "epoch": 8.07,
- "learning_rate": 0.00014910714285714286,
- "loss": 1.5109,
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
"step": 399
},
{
- "epoch": 8.09,
- "learning_rate": 0.00014897959183673472,
- "loss": 1.5302,
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
"step": 400
},
{
- "epoch": 8.11,
- "learning_rate": 0.00014885204081632652,
- "loss": 1.5238,
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
"step": 401
},
{
- "epoch": 8.13,
- "learning_rate": 0.00014872448979591838,
- "loss": 1.4781,
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
"step": 402
},
{
- "epoch": 8.15,
- "learning_rate": 0.0001485969387755102,
- "loss": 1.5446,
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
"step": 403
},
{
- "epoch": 8.17,
- "learning_rate": 0.00014846938775510204,
- "loss": 1.5,
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
"step": 404
},
{
- "epoch": 8.19,
- "learning_rate": 0.0001483418367346939,
- "loss": 1.5458,
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
"step": 405
},
{
- "epoch": 8.21,
- "learning_rate": 0.00014821428571428573,
- "loss": 1.5257,
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
"step": 406
},
{
- "epoch": 8.24,
- "learning_rate": 0.00014808673469387756,
- "loss": 1.4607,
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
"step": 407
},
{
- "epoch": 8.26,
- "learning_rate": 0.0001479591836734694,
- "loss": 1.4282,
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
"step": 408
},
{
- "epoch": 8.28,
- "learning_rate": 0.00014783163265306125,
- "loss": 1.4519,
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
"step": 409
},
{
- "epoch": 8.3,
- "learning_rate": 0.00014770408163265305,
- "loss": 1.475,
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
"step": 410
},
{
- "epoch": 8.32,
- "learning_rate": 0.0001475765306122449,
- "loss": 1.5425,
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
"step": 411
},
{
- "epoch": 8.34,
- "learning_rate": 0.00014744897959183674,
- "loss": 1.5407,
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
"step": 412
},
{
- "epoch": 8.36,
- "learning_rate": 0.0001473214285714286,
- "loss": 1.5698,
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
"step": 413
},
{
- "epoch": 8.38,
- "learning_rate": 0.0001471938775510204,
- "loss": 1.4282,
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
"step": 414
},
{
- "epoch": 8.4,
- "learning_rate": 0.00014706632653061226,
- "loss": 1.5301,
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
"step": 415
},
{
- "epoch": 8.42,
- "learning_rate": 0.0001469387755102041,
- "loss": 1.5083,
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
"step": 416
},
{
- "epoch": 8.44,
- "learning_rate": 0.00014681122448979592,
- "loss": 1.5712,
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
"step": 417
},
{
- "epoch": 8.46,
- "learning_rate": 0.00014668367346938775,
- "loss": 1.4363,
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
"step": 418
},
{
- "epoch": 8.48,
- "learning_rate": 0.0001465561224489796,
- "loss": 1.4463,
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
"step": 419
},
{
- "epoch": 8.5,
- "learning_rate": 0.00014642857142857141,
- "loss": 1.4738,
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
"step": 420
},
{
- "epoch": 8.52,
- "learning_rate": 0.00014630102040816327,
- "loss": 1.5396,
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
"step": 421
},
{
- "epoch": 8.54,
- "learning_rate": 0.0001461734693877551,
- "loss": 1.4384,
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
"step": 422
},
{
- "epoch": 8.56,
- "learning_rate": 0.00014604591836734696,
- "loss": 1.5345,
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
"step": 423
},
{
- "epoch": 8.58,
- "learning_rate": 0.0001459183673469388,
- "loss": 1.5355,
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
"step": 424
},
{
- "epoch": 8.6,
- "learning_rate": 0.00014579081632653062,
- "loss": 1.5188,
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
"step": 425
},
{
- "epoch": 8.62,
- "learning_rate": 0.00014566326530612245,
- "loss": 1.5575,
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
"step": 426
},
{
- "epoch": 8.64,
- "learning_rate": 0.00014553571428571428,
- "loss": 1.5279,
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
"step": 427
},
{
- "epoch": 8.66,
- "learning_rate": 0.00014540816326530614,
- "loss": 1.5484,
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
"step": 428
},
{
- "epoch": 8.68,
- "learning_rate": 0.00014528061224489797,
- "loss": 1.4878,
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
"step": 429
},
{
- "epoch": 8.7,
- "learning_rate": 0.0001451530612244898,
- "loss": 1.503,
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
"step": 430
},
{
- "epoch": 8.72,
- "learning_rate": 0.00014502551020408163,
- "loss": 1.4723,
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
"step": 431
},
{
- "epoch": 8.74,
- "learning_rate": 0.0001448979591836735,
- "loss": 1.5579,
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
"step": 432
},
{
- "epoch": 8.76,
- "learning_rate": 0.0001447704081632653,
- "loss": 1.4789,
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
"step": 433
},
{
- "epoch": 8.78,
- "learning_rate": 0.00014464285714285715,
- "loss": 1.5501,
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
"step": 434
},
{
- "epoch": 8.8,
- "learning_rate": 0.00014451530612244899,
- "loss": 1.5204,
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
"step": 435
},
{
- "epoch": 8.82,
- "learning_rate": 0.00014438775510204084,
- "loss": 1.5489,
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
"step": 436
},
{
- "epoch": 8.84,
- "learning_rate": 0.00014426020408163265,
- "loss": 1.5464,
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
"step": 437
},
{
- "epoch": 8.86,
- "learning_rate": 0.0001441326530612245,
- "loss": 1.5896,
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
"step": 438
},
{
- "epoch": 8.88,
- "learning_rate": 0.00014400510204081634,
- "loss": 1.5465,
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
"step": 439
},
{
- "epoch": 8.9,
- "learning_rate": 0.00014387755102040817,
- "loss": 1.5094,
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
"step": 440
},
{
- "epoch": 8.92,
- "learning_rate": 0.00014375,
- "loss": 1.5144,
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
"step": 441
},
{
- "epoch": 8.94,
- "learning_rate": 0.00014362244897959186,
- "loss": 1.4919,
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
"step": 442
},
{
- "epoch": 8.96,
- "learning_rate": 0.00014349489795918366,
- "loss": 1.4702,
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
"step": 443
},
{
- "epoch": 8.98,
- "learning_rate": 0.00014336734693877552,
- "loss": 1.4996,
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
"step": 444
},
{
- "epoch": 9.0,
- "learning_rate": 0.00014323979591836735,
- "loss": 1.5503,
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
"step": 445
},
{
- "epoch": 9.02,
- "learning_rate": 0.00014311224489795918,
- "loss": 1.4125,
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
"step": 446
},
{
- "epoch": 9.04,
- "learning_rate": 0.00014298469387755104,
- "loss": 1.4722,
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
"step": 447
},
{
- "epoch": 9.06,
- "learning_rate": 0.00014285714285714287,
- "loss": 1.5199,
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
"step": 448
},
{
- "epoch": 9.09,
- "learning_rate": 0.0001427295918367347,
- "loss": 1.4571,
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
"step": 449
},
{
- "epoch": 9.11,
- "learning_rate": 0.00014260204081632653,
- "loss": 1.4996,
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
"step": 450
},
{
- "epoch": 9.13,
- "learning_rate": 0.0001424744897959184,
- "loss": 1.4092,
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
"step": 451
},
{
- "epoch": 9.15,
- "learning_rate": 0.00014234693877551022,
- "loss": 1.4198,
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
"step": 452
},
{
- "epoch": 9.17,
- "learning_rate": 0.00014221938775510205,
- "loss": 1.4916,
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
"step": 453
},
{
- "epoch": 9.19,
- "learning_rate": 0.00014209183673469388,
- "loss": 1.5051,
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
"step": 454
},
{
- "epoch": 9.21,
- "learning_rate": 0.00014196428571428574,
- "loss": 1.4321,
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
"step": 455
},
{
- "epoch": 9.23,
- "learning_rate": 0.00014183673469387754,
- "loss": 1.4097,
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
"step": 456
},
{
- "epoch": 9.25,
- "learning_rate": 0.0001417091836734694,
- "loss": 1.4853,
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
"step": 457
},
{
- "epoch": 9.27,
- "learning_rate": 0.00014158163265306123,
- "loss": 1.4593,
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
"step": 458
},
{
- "epoch": 9.29,
- "learning_rate": 0.00014145408163265306,
- "loss": 1.3729,
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
"step": 459
},
{
- "epoch": 9.31,
- "learning_rate": 0.0001413265306122449,
- "loss": 1.4467,
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
"step": 460
},
{
- "epoch": 9.33,
- "learning_rate": 0.00014119897959183675,
- "loss": 1.4467,
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
"step": 461
},
{
- "epoch": 9.35,
- "learning_rate": 0.00014107142857142858,
- "loss": 1.4785,
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
"step": 462
},
{
- "epoch": 9.37,
- "learning_rate": 0.0001409438775510204,
- "loss": 1.4089,
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
"step": 463
},
{
- "epoch": 9.39,
- "learning_rate": 0.00014081632653061224,
- "loss": 1.5026,
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
"step": 464
},
{
- "epoch": 9.41,
- "learning_rate": 0.0001406887755102041,
- "loss": 1.4857,
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
"step": 465
},
{
- "epoch": 9.43,
- "learning_rate": 0.0001405612244897959,
- "loss": 1.3745,
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
"step": 466
},
{
- "epoch": 9.45,
- "learning_rate": 0.00014043367346938776,
- "loss": 1.4733,
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
"step": 467
},
{
- "epoch": 9.47,
- "learning_rate": 0.0001403061224489796,
- "loss": 1.5212,
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
"step": 468
},
{
- "epoch": 9.49,
- "learning_rate": 0.00014017857142857142,
- "loss": 1.5398,
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
"step": 469
},
{
- "epoch": 9.51,
- "learning_rate": 0.00014005102040816328,
- "loss": 1.478,
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
"step": 470
},
{
- "epoch": 9.53,
- "learning_rate": 0.0001399234693877551,
- "loss": 1.496,
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
"step": 471
},
{
- "epoch": 9.55,
- "learning_rate": 0.00013979591836734694,
- "loss": 1.4837,
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
"step": 472
},
{
- "epoch": 9.57,
- "learning_rate": 0.00013966836734693878,
- "loss": 1.4724,
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
"step": 473
},
{
- "epoch": 9.59,
- "learning_rate": 0.00013954081632653063,
- "loss": 1.4828,
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
"step": 474
},
{
- "epoch": 9.61,
- "learning_rate": 0.00013941326530612246,
- "loss": 1.5012,
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
"step": 475
},
{
- "epoch": 9.63,
- "learning_rate": 0.0001392857142857143,
- "loss": 1.4879,
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
"step": 476
},
{
- "epoch": 9.65,
- "learning_rate": 0.00013915816326530613,
- "loss": 1.4196,
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
"step": 477
},
{
- "epoch": 9.67,
- "learning_rate": 0.00013903061224489798,
- "loss": 1.4915,
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
"step": 478
},
{
- "epoch": 9.69,
- "learning_rate": 0.0001389030612244898,
- "loss": 1.3878,
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
"step": 479
},
{
- "epoch": 9.71,
- "learning_rate": 0.00013877551020408165,
- "loss": 1.466,
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
"step": 480
},
{
- "epoch": 9.73,
- "learning_rate": 0.00013864795918367348,
- "loss": 1.4582,
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
"step": 481
},
{
- "epoch": 9.75,
- "learning_rate": 0.0001385204081632653,
- "loss": 1.533,
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
"step": 482
},
{
- "epoch": 9.77,
- "learning_rate": 0.00013839285714285714,
- "loss": 1.4697,
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
"step": 483
},
{
- "epoch": 9.79,
- "learning_rate": 0.000138265306122449,
- "loss": 1.3989,
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
"step": 484
},
{
- "epoch": 9.81,
- "learning_rate": 0.00013813775510204083,
- "loss": 1.4361,
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
"step": 485
},
{
- "epoch": 9.83,
- "learning_rate": 0.00013801020408163266,
- "loss": 1.5271,
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
"step": 486
},
{
- "epoch": 9.85,
- "learning_rate": 0.0001378826530612245,
- "loss": 1.4905,
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
"step": 487
},
{
- "epoch": 9.87,
- "learning_rate": 0.00013775510204081635,
- "loss": 1.4757,
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
"step": 488
},
{
- "epoch": 9.89,
- "learning_rate": 0.00013762755102040815,
- "loss": 1.5485,
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
"step": 489
},
{
- "epoch": 9.91,
- "learning_rate": 0.0001375,
- "loss": 1.4783,
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
"step": 490
},
{
- "epoch": 9.93,
- "learning_rate": 0.00013737244897959184,
- "loss": 1.4849,
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
"step": 491
},
{
- "epoch": 9.96,
- "learning_rate": 0.00013724489795918367,
- "loss": 1.5382,
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
"step": 492
},
{
- "epoch": 9.98,
- "learning_rate": 0.00013711734693877553,
- "loss": 1.4902,
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
"step": 493
},
{
- "epoch": 10.0,
- "learning_rate": 0.00013698979591836736,
- "loss": 1.4865,
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
"step": 494
},
{
- "epoch": 10.02,
- "learning_rate": 0.0001368622448979592,
- "loss": 1.4436,
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
"step": 495
},
{
- "epoch": 10.04,
- "learning_rate": 0.00013673469387755102,
- "loss": 1.408,
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
"step": 496
},
{
- "epoch": 10.06,
- "learning_rate": 0.00013660714285714288,
- "loss": 1.4764,
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
"step": 497
},
{
- "epoch": 10.08,
- "learning_rate": 0.0001364795918367347,
- "loss": 1.4646,
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
"step": 498
},
{
- "epoch": 10.1,
- "learning_rate": 0.00013635204081632654,
- "loss": 1.406,
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
"step": 499
},
{
- "epoch": 10.12,
- "learning_rate": 0.00013622448979591837,
- "loss": 1.4785,
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
"step": 500
},
{
- "epoch": 10.14,
- "learning_rate": 0.00013609693877551023,
- "loss": 1.4117,
+ "epoch": 5.66,
+ "learning_rate": 0.00012883522727272727,
+ "loss": 1.0755,
"step": 501
},
{
- "epoch": 10.16,
- "learning_rate": 0.00013596938775510203,
- "loss": 1.4108,
+ "epoch": 5.67,
+ "learning_rate": 0.00012869318181818183,
+ "loss": 1.0755,
"step": 502
},
{
- "epoch": 10.18,
- "learning_rate": 0.0001358418367346939,
- "loss": 1.4155,
+ "epoch": 5.68,
+ "learning_rate": 0.00012855113636363636,
+ "loss": 1.0869,
"step": 503
},
{
- "epoch": 10.2,
- "learning_rate": 0.00013571428571428572,
- "loss": 1.4021,
+ "epoch": 5.69,
+ "learning_rate": 0.00012840909090909092,
+ "loss": 1.0673,
"step": 504
},
{
- "epoch": 10.22,
- "learning_rate": 0.00013558673469387755,
- "loss": 1.411,
+ "epoch": 5.71,
+ "learning_rate": 0.00012826704545454545,
+ "loss": 1.0692,
"step": 505
},
{
- "epoch": 10.24,
- "learning_rate": 0.00013545918367346938,
- "loss": 1.3851,
+ "epoch": 5.72,
+ "learning_rate": 0.000128125,
+ "loss": 1.0474,
"step": 506
},
{
- "epoch": 10.26,
- "learning_rate": 0.00013533163265306124,
- "loss": 1.387,
+ "epoch": 5.73,
+ "learning_rate": 0.00012798295454545454,
+ "loss": 1.0749,
"step": 507
},
{
- "epoch": 10.28,
- "learning_rate": 0.00013520408163265305,
- "loss": 1.4163,
+ "epoch": 5.74,
+ "learning_rate": 0.0001278409090909091,
+ "loss": 1.0519,
"step": 508
},
{
- "epoch": 10.3,
- "learning_rate": 0.0001350765306122449,
- "loss": 1.3343,
+ "epoch": 5.75,
+ "learning_rate": 0.00012769886363636366,
+ "loss": 1.0566,
"step": 509
},
{
- "epoch": 10.32,
- "learning_rate": 0.00013494897959183673,
- "loss": 1.4811,
+ "epoch": 5.76,
+ "learning_rate": 0.0001275568181818182,
+ "loss": 1.06,
"step": 510
},
{
- "epoch": 10.34,
- "learning_rate": 0.0001348214285714286,
- "loss": 1.4086,
+ "epoch": 5.77,
+ "learning_rate": 0.00012741477272727272,
+ "loss": 1.0618,
"step": 511
},
{
- "epoch": 10.36,
- "learning_rate": 0.0001346938775510204,
- "loss": 1.3879,
+ "epoch": 5.78,
+ "learning_rate": 0.00012727272727272728,
+ "loss": 1.0643,
"step": 512
},
{
- "epoch": 10.38,
- "learning_rate": 0.00013456632653061225,
- "loss": 1.4204,
+ "epoch": 5.8,
+ "learning_rate": 0.0001271306818181818,
+ "loss": 1.026,
"step": 513
},
{
- "epoch": 10.4,
- "learning_rate": 0.00013443877551020408,
- "loss": 1.4158,
+ "epoch": 5.81,
+ "learning_rate": 0.00012698863636363637,
+ "loss": 1.0335,
"step": 514
},
{
- "epoch": 10.42,
- "learning_rate": 0.00013431122448979592,
- "loss": 1.4521,
+ "epoch": 5.82,
+ "learning_rate": 0.00012684659090909093,
+ "loss": 1.0205,
"step": 515
},
{
- "epoch": 10.44,
- "learning_rate": 0.00013418367346938777,
- "loss": 1.4196,
+ "epoch": 5.83,
+ "learning_rate": 0.00012670454545454546,
+ "loss": 1.0594,
"step": 516
},
{
- "epoch": 10.46,
- "learning_rate": 0.0001340561224489796,
- "loss": 1.4361,
+ "epoch": 5.84,
+ "learning_rate": 0.0001265625,
+ "loss": 1.0136,
"step": 517
},
{
- "epoch": 10.48,
- "learning_rate": 0.00013392857142857144,
- "loss": 1.4482,
+ "epoch": 5.85,
+ "learning_rate": 0.00012642045454545455,
+ "loss": 1.0244,
"step": 518
},
{
- "epoch": 10.5,
- "learning_rate": 0.00013380102040816327,
- "loss": 1.4801,
+ "epoch": 5.86,
+ "learning_rate": 0.00012627840909090908,
+ "loss": 1.0569,
"step": 519
},
{
- "epoch": 10.52,
- "learning_rate": 0.00013367346938775512,
- "loss": 1.4556,
+ "epoch": 5.87,
+ "learning_rate": 0.00012613636363636364,
+ "loss": 1.0416,
"step": 520
},
{
- "epoch": 10.54,
- "learning_rate": 0.00013354591836734695,
- "loss": 1.3902,
+ "epoch": 5.89,
+ "learning_rate": 0.0001259943181818182,
+ "loss": 0.9884,
"step": 521
},
{
- "epoch": 10.56,
- "learning_rate": 0.00013341836734693879,
- "loss": 1.4269,
+ "epoch": 5.9,
+ "learning_rate": 0.00012585227272727273,
+ "loss": 1.0351,
"step": 522
},
{
- "epoch": 10.58,
- "learning_rate": 0.00013329081632653062,
- "loss": 1.4899,
+ "epoch": 5.91,
+ "learning_rate": 0.00012571022727272726,
+ "loss": 1.0037,
"step": 523
},
{
- "epoch": 10.6,
- "learning_rate": 0.00013316326530612247,
- "loss": 1.3952,
+ "epoch": 5.92,
+ "learning_rate": 0.00012556818181818182,
+ "loss": 1.0219,
"step": 524
},
{
- "epoch": 10.62,
- "learning_rate": 0.00013303571428571428,
- "loss": 1.4116,
+ "epoch": 5.93,
+ "learning_rate": 0.00012542613636363635,
+ "loss": 1.0533,
"step": 525
},
{
- "epoch": 10.64,
- "learning_rate": 0.00013290816326530614,
- "loss": 1.4583,
+ "epoch": 5.94,
+ "learning_rate": 0.0001252840909090909,
+ "loss": 1.0031,
"step": 526
},
{
- "epoch": 10.66,
- "learning_rate": 0.00013278061224489797,
- "loss": 1.4466,
+ "epoch": 5.95,
+ "learning_rate": 0.00012514204545454547,
+ "loss": 1.0454,
"step": 527
},
{
- "epoch": 10.68,
- "learning_rate": 0.0001326530612244898,
- "loss": 1.4242,
+ "epoch": 5.97,
+ "learning_rate": 0.000125,
+ "loss": 1.0195,
"step": 528
},
{
- "epoch": 10.7,
- "learning_rate": 0.00013252551020408163,
- "loss": 1.3717,
+ "epoch": 5.98,
+ "learning_rate": 0.00012485795454545453,
+ "loss": 1.0076,
"step": 529
},
{
- "epoch": 10.72,
- "learning_rate": 0.0001323979591836735,
- "loss": 1.4583,
+ "epoch": 5.99,
+ "learning_rate": 0.0001247159090909091,
+ "loss": 1.0378,
"step": 530
},
{
- "epoch": 10.74,
- "learning_rate": 0.0001322704081632653,
- "loss": 1.4185,
+ "epoch": 6.0,
+ "learning_rate": 0.00012457386363636365,
+ "loss": 0.9795,
"step": 531
},
{
- "epoch": 10.76,
- "learning_rate": 0.00013214285714285715,
- "loss": 1.4287,
+ "epoch": 6.01,
+ "learning_rate": 0.00012443181818181818,
+ "loss": 0.9405,
"step": 532
},
{
- "epoch": 10.78,
- "learning_rate": 0.00013201530612244898,
- "loss": 1.4385,
+ "epoch": 6.02,
+ "learning_rate": 0.00012428977272727274,
+ "loss": 0.9503,
"step": 533
},
{
- "epoch": 10.8,
- "learning_rate": 0.00013188775510204084,
- "loss": 1.453,
+ "epoch": 6.03,
+ "learning_rate": 0.00012414772727272727,
+ "loss": 0.9456,
"step": 534
},
{
- "epoch": 10.83,
- "learning_rate": 0.00013176020408163264,
- "loss": 1.4161,
+ "epoch": 6.04,
+ "learning_rate": 0.0001240056818181818,
+ "loss": 0.9536,
"step": 535
},
{
- "epoch": 10.85,
- "learning_rate": 0.0001316326530612245,
- "loss": 1.457,
+ "epoch": 6.06,
+ "learning_rate": 0.00012386363636363636,
+ "loss": 0.9412,
"step": 536
},
{
- "epoch": 10.87,
- "learning_rate": 0.00013150510204081633,
- "loss": 1.4367,
+ "epoch": 6.07,
+ "learning_rate": 0.00012372159090909092,
+ "loss": 0.9315,
"step": 537
},
{
- "epoch": 10.89,
- "learning_rate": 0.00013137755102040816,
- "loss": 1.4256,
+ "epoch": 6.08,
+ "learning_rate": 0.00012357954545454545,
+ "loss": 0.9486,
"step": 538
},
{
- "epoch": 10.91,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.424,
+ "epoch": 6.09,
+ "learning_rate": 0.0001234375,
+ "loss": 0.9405,
"step": 539
},
{
- "epoch": 10.93,
- "learning_rate": 0.00013112244897959185,
- "loss": 1.3923,
+ "epoch": 6.1,
+ "learning_rate": 0.00012329545454545454,
+ "loss": 0.9269,
"step": 540
},
{
- "epoch": 10.95,
- "learning_rate": 0.00013099489795918368,
- "loss": 1.4225,
+ "epoch": 6.11,
+ "learning_rate": 0.0001231534090909091,
+ "loss": 0.9378,
"step": 541
},
{
- "epoch": 10.97,
- "learning_rate": 0.0001308673469387755,
- "loss": 1.3969,
+ "epoch": 6.12,
+ "learning_rate": 0.00012301136363636366,
+ "loss": 0.9431,
"step": 542
},
{
- "epoch": 10.99,
- "learning_rate": 0.00013073979591836737,
- "loss": 1.4446,
+ "epoch": 6.13,
+ "learning_rate": 0.0001228693181818182,
+ "loss": 0.9256,
"step": 543
},
{
- "epoch": 11.01,
- "learning_rate": 0.00013061224489795917,
- "loss": 1.4375,
+ "epoch": 6.15,
+ "learning_rate": 0.00012272727272727272,
+ "loss": 0.919,
"step": 544
},
{
- "epoch": 11.03,
- "learning_rate": 0.00013048469387755103,
- "loss": 1.4064,
+ "epoch": 6.16,
+ "learning_rate": 0.00012258522727272728,
+ "loss": 0.9188,
"step": 545
},
{
- "epoch": 11.05,
- "learning_rate": 0.00013035714285714286,
- "loss": 1.3454,
+ "epoch": 6.17,
+ "learning_rate": 0.00012244318181818181,
+ "loss": 0.9447,
"step": 546
},
{
- "epoch": 11.07,
- "learning_rate": 0.00013022959183673472,
- "loss": 1.3234,
+ "epoch": 6.18,
+ "learning_rate": 0.00012230113636363637,
+ "loss": 0.9261,
"step": 547
},
{
- "epoch": 11.09,
- "learning_rate": 0.00013010204081632652,
- "loss": 1.3759,
+ "epoch": 6.19,
+ "learning_rate": 0.00012215909090909093,
+ "loss": 0.9302,
"step": 548
},
{
- "epoch": 11.11,
- "learning_rate": 0.00012997448979591838,
- "loss": 1.4221,
+ "epoch": 6.2,
+ "learning_rate": 0.00012201704545454546,
+ "loss": 0.9161,
"step": 549
},
{
- "epoch": 11.13,
- "learning_rate": 0.0001298469387755102,
- "loss": 1.4261,
+ "epoch": 6.21,
+ "learning_rate": 0.00012187500000000001,
+ "loss": 0.9521,
"step": 550
},
{
- "epoch": 11.15,
- "learning_rate": 0.00012971938775510204,
- "loss": 1.3341,
+ "epoch": 6.22,
+ "learning_rate": 0.00012173295454545455,
+ "loss": 0.9026,
"step": 551
},
{
- "epoch": 11.17,
- "learning_rate": 0.00012959183673469387,
- "loss": 1.3994,
+ "epoch": 6.24,
+ "learning_rate": 0.00012159090909090908,
+ "loss": 0.9361,
"step": 552
},
{
- "epoch": 11.19,
- "learning_rate": 0.00012946428571428573,
- "loss": 1.3894,
+ "epoch": 6.25,
+ "learning_rate": 0.00012144886363636366,
+ "loss": 0.8944,
"step": 553
},
{
- "epoch": 11.21,
- "learning_rate": 0.00012933673469387754,
- "loss": 1.3585,
+ "epoch": 6.26,
+ "learning_rate": 0.00012130681818181819,
+ "loss": 0.895,
"step": 554
},
{
- "epoch": 11.23,
- "learning_rate": 0.0001292091836734694,
- "loss": 1.3763,
+ "epoch": 6.27,
+ "learning_rate": 0.00012116477272727273,
+ "loss": 0.8956,
"step": 555
},
{
- "epoch": 11.25,
- "learning_rate": 0.00012908163265306123,
- "loss": 1.3623,
+ "epoch": 6.28,
+ "learning_rate": 0.00012102272727272728,
+ "loss": 0.8998,
"step": 556
},
{
- "epoch": 11.27,
- "learning_rate": 0.00012895408163265306,
- "loss": 1.3907,
+ "epoch": 6.29,
+ "learning_rate": 0.00012088068181818182,
+ "loss": 0.915,
"step": 557
},
{
- "epoch": 11.29,
- "learning_rate": 0.0001288265306122449,
- "loss": 1.3807,
+ "epoch": 6.3,
+ "learning_rate": 0.00012073863636363636,
+ "loss": 0.9282,
"step": 558
},
{
- "epoch": 11.31,
- "learning_rate": 0.00012869897959183674,
- "loss": 1.4045,
+ "epoch": 6.32,
+ "learning_rate": 0.00012059659090909093,
+ "loss": 0.8938,
"step": 559
},
{
- "epoch": 11.33,
- "learning_rate": 0.00012857142857142858,
- "loss": 1.4038,
+ "epoch": 6.33,
+ "learning_rate": 0.00012045454545454546,
+ "loss": 0.8886,
"step": 560
},
{
- "epoch": 11.35,
- "learning_rate": 0.0001284438775510204,
- "loss": 1.3466,
+ "epoch": 6.34,
+ "learning_rate": 0.0001203125,
+ "loss": 0.8988,
"step": 561
},
{
- "epoch": 11.37,
- "learning_rate": 0.00012831632653061226,
- "loss": 1.3449,
+ "epoch": 6.35,
+ "learning_rate": 0.00012017045454545455,
+ "loss": 0.8852,
"step": 562
},
{
- "epoch": 11.39,
- "learning_rate": 0.0001281887755102041,
- "loss": 1.3866,
+ "epoch": 6.36,
+ "learning_rate": 0.0001200284090909091,
+ "loss": 0.8818,
"step": 563
},
{
- "epoch": 11.41,
- "learning_rate": 0.00012806122448979593,
- "loss": 1.3106,
+ "epoch": 6.37,
+ "learning_rate": 0.00011988636363636365,
+ "loss": 0.8881,
"step": 564
},
{
- "epoch": 11.43,
- "learning_rate": 0.00012793367346938776,
- "loss": 1.4414,
+ "epoch": 6.38,
+ "learning_rate": 0.0001197443181818182,
+ "loss": 0.9226,
"step": 565
},
{
- "epoch": 11.45,
- "learning_rate": 0.00012780612244897962,
- "loss": 1.3737,
+ "epoch": 6.39,
+ "learning_rate": 0.00011960227272727273,
+ "loss": 0.8849,
"step": 566
},
{
- "epoch": 11.47,
- "learning_rate": 0.00012767857142857142,
- "loss": 1.4053,
+ "epoch": 6.41,
+ "learning_rate": 0.00011946022727272727,
+ "loss": 0.8894,
"step": 567
},
{
- "epoch": 11.49,
- "learning_rate": 0.00012755102040816328,
- "loss": 1.4561,
+ "epoch": 6.42,
+ "learning_rate": 0.00011931818181818182,
+ "loss": 0.9207,
"step": 568
},
{
- "epoch": 11.51,
- "learning_rate": 0.0001274234693877551,
- "loss": 1.3684,
+ "epoch": 6.43,
+ "learning_rate": 0.00011917613636363636,
+ "loss": 0.9105,
"step": 569
},
{
- "epoch": 11.53,
- "learning_rate": 0.00012729591836734697,
- "loss": 1.3117,
+ "epoch": 6.44,
+ "learning_rate": 0.00011903409090909092,
+ "loss": 0.8762,
"step": 570
},
{
- "epoch": 11.55,
- "learning_rate": 0.00012716836734693877,
- "loss": 1.3474,
+ "epoch": 6.45,
+ "learning_rate": 0.00011889204545454547,
+ "loss": 0.8926,
"step": 571
},
{
- "epoch": 11.57,
- "learning_rate": 0.00012704081632653063,
- "loss": 1.3804,
+ "epoch": 6.46,
+ "learning_rate": 0.00011875,
+ "loss": 0.8719,
"step": 572
},
{
- "epoch": 11.59,
- "learning_rate": 0.00012691326530612246,
- "loss": 1.3656,
+ "epoch": 6.47,
+ "learning_rate": 0.00011860795454545454,
+ "loss": 0.9198,
"step": 573
},
{
- "epoch": 11.61,
- "learning_rate": 0.0001267857142857143,
- "loss": 1.3133,
+ "epoch": 6.48,
+ "learning_rate": 0.00011846590909090909,
+ "loss": 0.8846,
"step": 574
},
{
- "epoch": 11.63,
- "learning_rate": 0.00012665816326530612,
- "loss": 1.4077,
+ "epoch": 6.5,
+ "learning_rate": 0.00011832386363636365,
+ "loss": 0.8495,
"step": 575
},
{
- "epoch": 11.65,
- "learning_rate": 0.00012653061224489798,
- "loss": 1.4087,
+ "epoch": 6.51,
+ "learning_rate": 0.0001181818181818182,
+ "loss": 0.8953,
"step": 576
},
{
- "epoch": 11.67,
- "learning_rate": 0.00012640306122448978,
- "loss": 1.3524,
+ "epoch": 6.52,
+ "learning_rate": 0.00011803977272727274,
+ "loss": 0.8686,
"step": 577
},
{
- "epoch": 11.7,
- "learning_rate": 0.00012627551020408164,
- "loss": 1.3481,
+ "epoch": 6.53,
+ "learning_rate": 0.00011789772727272727,
+ "loss": 0.8841,
"step": 578
},
{
- "epoch": 11.72,
- "learning_rate": 0.00012614795918367347,
- "loss": 1.4497,
+ "epoch": 6.54,
+ "learning_rate": 0.00011775568181818182,
+ "loss": 0.8681,
"step": 579
},
{
- "epoch": 11.74,
- "learning_rate": 0.0001260204081632653,
- "loss": 1.3866,
+ "epoch": 6.55,
+ "learning_rate": 0.00011761363636363636,
+ "loss": 0.8732,
"step": 580
},
{
- "epoch": 11.76,
- "learning_rate": 0.00012589285714285713,
- "loss": 1.42,
+ "epoch": 6.56,
+ "learning_rate": 0.00011747159090909092,
+ "loss": 0.8582,
"step": 581
},
{
- "epoch": 11.78,
- "learning_rate": 0.000125765306122449,
- "loss": 1.3562,
+ "epoch": 6.58,
+ "learning_rate": 0.00011732954545454546,
+ "loss": 0.8744,
"step": 582
},
{
- "epoch": 11.8,
- "learning_rate": 0.00012563775510204082,
- "loss": 1.3249,
+ "epoch": 6.59,
+ "learning_rate": 0.00011718750000000001,
+ "loss": 0.8694,
"step": 583
},
{
- "epoch": 11.82,
- "learning_rate": 0.00012551020408163265,
- "loss": 1.4277,
+ "epoch": 6.6,
+ "learning_rate": 0.00011704545454545454,
+ "loss": 0.8565,
"step": 584
},
{
- "epoch": 11.84,
- "learning_rate": 0.0001253826530612245,
- "loss": 1.3734,
+ "epoch": 6.61,
+ "learning_rate": 0.00011690340909090909,
+ "loss": 0.8584,
"step": 585
},
{
- "epoch": 11.86,
- "learning_rate": 0.00012525510204081634,
- "loss": 1.3765,
+ "epoch": 6.62,
+ "learning_rate": 0.00011676136363636366,
+ "loss": 0.8859,
"step": 586
},
{
- "epoch": 11.88,
- "learning_rate": 0.00012512755102040817,
- "loss": 1.4153,
+ "epoch": 6.63,
+ "learning_rate": 0.00011661931818181819,
+ "loss": 0.8452,
"step": 587
},
{
- "epoch": 11.9,
- "learning_rate": 0.000125,
- "loss": 1.3847,
+ "epoch": 6.64,
+ "learning_rate": 0.00011647727272727273,
+ "loss": 0.8323,
"step": 588
},
{
- "epoch": 11.92,
- "learning_rate": 0.00012487244897959186,
- "loss": 1.3824,
+ "epoch": 6.65,
+ "learning_rate": 0.00011633522727272728,
+ "loss": 0.8548,
"step": 589
},
{
- "epoch": 11.94,
- "learning_rate": 0.00012474489795918366,
- "loss": 1.3938,
+ "epoch": 6.67,
+ "learning_rate": 0.00011619318181818181,
+ "loss": 0.8506,
"step": 590
},
{
- "epoch": 11.96,
- "learning_rate": 0.00012461734693877552,
- "loss": 1.4143,
+ "epoch": 6.68,
+ "learning_rate": 0.00011605113636363636,
+ "loss": 0.8556,
"step": 591
},
{
- "epoch": 11.98,
- "learning_rate": 0.00012448979591836735,
- "loss": 1.3794,
+ "epoch": 6.69,
+ "learning_rate": 0.00011590909090909093,
+ "loss": 0.8459,
"step": 592
},
{
- "epoch": 12.0,
- "learning_rate": 0.00012436224489795918,
- "loss": 1.3755,
+ "epoch": 6.7,
+ "learning_rate": 0.00011576704545454546,
+ "loss": 0.8432,
"step": 593
},
{
- "epoch": 12.02,
- "learning_rate": 0.00012423469387755101,
- "loss": 1.3736,
+ "epoch": 6.71,
+ "learning_rate": 0.000115625,
+ "loss": 0.8645,
"step": 594
},
{
- "epoch": 12.04,
- "learning_rate": 0.00012410714285714287,
- "loss": 1.2957,
+ "epoch": 6.72,
+ "learning_rate": 0.00011548295454545455,
+ "loss": 0.86,
"step": 595
},
{
- "epoch": 12.06,
- "learning_rate": 0.0001239795918367347,
- "loss": 1.2996,
+ "epoch": 6.73,
+ "learning_rate": 0.00011534090909090908,
+ "loss": 0.8161,
"step": 596
},
{
- "epoch": 12.08,
- "learning_rate": 0.00012385204081632653,
- "loss": 1.3648,
+ "epoch": 6.74,
+ "learning_rate": 0.00011519886363636365,
+ "loss": 0.8133,
"step": 597
},
{
- "epoch": 12.1,
- "learning_rate": 0.00012372448979591837,
- "loss": 1.3031,
+ "epoch": 6.76,
+ "learning_rate": 0.0001150568181818182,
+ "loss": 0.8372,
"step": 598
},
{
- "epoch": 12.12,
- "learning_rate": 0.00012359693877551022,
- "loss": 1.2933,
+ "epoch": 6.77,
+ "learning_rate": 0.00011491477272727273,
+ "loss": 0.8222,
"step": 599
},
{
- "epoch": 12.14,
- "learning_rate": 0.00012346938775510203,
- "loss": 1.322,
+ "epoch": 6.78,
+ "learning_rate": 0.00011477272727272728,
+ "loss": 0.8372,
"step": 600
},
{
- "epoch": 12.16,
- "learning_rate": 0.00012334183673469389,
- "loss": 1.3123,
+ "epoch": 6.79,
+ "learning_rate": 0.00011463068181818182,
+ "loss": 0.837,
"step": 601
},
{
- "epoch": 12.18,
- "learning_rate": 0.00012321428571428572,
- "loss": 1.3187,
+ "epoch": 6.8,
+ "learning_rate": 0.00011448863636363637,
+ "loss": 0.8406,
"step": 602
},
{
- "epoch": 12.2,
- "learning_rate": 0.00012308673469387755,
- "loss": 1.3353,
+ "epoch": 6.81,
+ "learning_rate": 0.00011434659090909092,
+ "loss": 0.836,
"step": 603
},
{
- "epoch": 12.22,
- "learning_rate": 0.0001229591836734694,
- "loss": 1.3221,
+ "epoch": 6.82,
+ "learning_rate": 0.00011420454545454547,
+ "loss": 0.8476,
"step": 604
},
{
- "epoch": 12.24,
- "learning_rate": 0.00012283163265306124,
- "loss": 1.3458,
+ "epoch": 6.83,
+ "learning_rate": 0.0001140625,
+ "loss": 0.8368,
"step": 605
},
{
- "epoch": 12.26,
- "learning_rate": 0.00012270408163265307,
- "loss": 1.275,
+ "epoch": 6.85,
+ "learning_rate": 0.00011392045454545455,
+ "loss": 0.822,
"step": 606
},
{
- "epoch": 12.28,
- "learning_rate": 0.0001225765306122449,
- "loss": 1.3455,
+ "epoch": 6.86,
+ "learning_rate": 0.00011377840909090909,
+ "loss": 0.8107,
"step": 607
},
{
- "epoch": 12.3,
- "learning_rate": 0.00012244897959183676,
- "loss": 1.2769,
+ "epoch": 6.87,
+ "learning_rate": 0.00011363636363636365,
+ "loss": 0.8395,
"step": 608
},
{
- "epoch": 12.32,
- "learning_rate": 0.00012232142857142859,
- "loss": 1.3201,
+ "epoch": 6.88,
+ "learning_rate": 0.0001134943181818182,
+ "loss": 0.8083,
"step": 609
},
{
- "epoch": 12.34,
- "learning_rate": 0.00012219387755102042,
- "loss": 1.3073,
+ "epoch": 6.89,
+ "learning_rate": 0.00011335227272727274,
+ "loss": 0.828,
"step": 610
},
{
- "epoch": 12.36,
- "learning_rate": 0.00012206632653061225,
- "loss": 1.3103,
+ "epoch": 6.9,
+ "learning_rate": 0.00011321022727272727,
+ "loss": 0.8494,
"step": 611
},
{
- "epoch": 12.38,
- "learning_rate": 0.00012193877551020409,
- "loss": 1.4437,
+ "epoch": 6.91,
+ "learning_rate": 0.00011306818181818182,
+ "loss": 0.8169,
"step": 612
},
{
- "epoch": 12.4,
- "learning_rate": 0.00012181122448979591,
- "loss": 1.3086,
+ "epoch": 6.93,
+ "learning_rate": 0.00011292613636363636,
+ "loss": 0.8224,
"step": 613
},
{
- "epoch": 12.42,
- "learning_rate": 0.00012168367346938775,
- "loss": 1.3867,
+ "epoch": 6.94,
+ "learning_rate": 0.00011278409090909092,
+ "loss": 0.8173,
"step": 614
},
{
- "epoch": 12.44,
- "learning_rate": 0.0001215561224489796,
- "loss": 1.2565,
+ "epoch": 6.95,
+ "learning_rate": 0.00011264204545454547,
+ "loss": 0.7961,
"step": 615
},
{
- "epoch": 12.46,
- "learning_rate": 0.00012142857142857143,
- "loss": 1.335,
+ "epoch": 6.96,
+ "learning_rate": 0.00011250000000000001,
+ "loss": 0.7948,
"step": 616
},
{
- "epoch": 12.48,
- "learning_rate": 0.00012130102040816327,
- "loss": 1.3423,
+ "epoch": 6.97,
+ "learning_rate": 0.00011235795454545454,
+ "loss": 0.7746,
"step": 617
},
{
- "epoch": 12.5,
- "learning_rate": 0.00012117346938775512,
- "loss": 1.3433,
+ "epoch": 6.98,
+ "learning_rate": 0.00011221590909090909,
+ "loss": 0.8325,
"step": 618
},
{
- "epoch": 12.52,
- "learning_rate": 0.00012104591836734695,
- "loss": 1.3387,
+ "epoch": 6.99,
+ "learning_rate": 0.00011207386363636365,
+ "loss": 0.8149,
"step": 619
},
{
- "epoch": 12.55,
- "learning_rate": 0.00012091836734693878,
- "loss": 1.3923,
+ "epoch": 7.0,
+ "learning_rate": 0.00011193181818181819,
+ "loss": 0.7516,
"step": 620
},
{
- "epoch": 12.57,
- "learning_rate": 0.00012079081632653062,
- "loss": 1.3774,
+ "epoch": 7.02,
+ "learning_rate": 0.00011178977272727274,
+ "loss": 0.7571,
"step": 621
},
{
- "epoch": 12.59,
- "learning_rate": 0.00012066326530612247,
- "loss": 1.3203,
+ "epoch": 7.03,
+ "learning_rate": 0.00011164772727272728,
+ "loss": 0.7397,
"step": 622
},
{
- "epoch": 12.61,
- "learning_rate": 0.00012053571428571429,
- "loss": 1.2924,
+ "epoch": 7.04,
+ "learning_rate": 0.00011150568181818181,
+ "loss": 0.761,
"step": 623
},
{
- "epoch": 12.63,
- "learning_rate": 0.00012040816326530613,
- "loss": 1.3292,
+ "epoch": 7.05,
+ "learning_rate": 0.00011136363636363636,
+ "loss": 0.7783,
"step": 624
},
{
- "epoch": 12.65,
- "learning_rate": 0.00012028061224489798,
- "loss": 1.3161,
+ "epoch": 7.06,
+ "learning_rate": 0.00011122159090909092,
+ "loss": 0.7571,
"step": 625
},
{
- "epoch": 12.67,
- "learning_rate": 0.00012015306122448979,
- "loss": 1.352,
+ "epoch": 7.07,
+ "learning_rate": 0.00011107954545454546,
+ "loss": 0.7628,
"step": 626
},
{
- "epoch": 12.69,
- "learning_rate": 0.00012002551020408164,
- "loss": 1.3577,
+ "epoch": 7.08,
+ "learning_rate": 0.0001109375,
+ "loss": 0.7561,
"step": 627
},
{
- "epoch": 12.71,
- "learning_rate": 0.00011989795918367348,
- "loss": 1.3575,
+ "epoch": 7.09,
+ "learning_rate": 0.00011079545454545455,
+ "loss": 0.7432,
"step": 628
},
{
- "epoch": 12.73,
- "learning_rate": 0.0001197704081632653,
- "loss": 1.3727,
+ "epoch": 7.11,
+ "learning_rate": 0.00011065340909090908,
+ "loss": 0.7245,
"step": 629
},
{
- "epoch": 12.75,
- "learning_rate": 0.00011964285714285714,
- "loss": 1.3312,
+ "epoch": 7.12,
+ "learning_rate": 0.00011051136363636366,
+ "loss": 0.7279,
"step": 630
},
{
- "epoch": 12.77,
- "learning_rate": 0.00011951530612244899,
- "loss": 1.3378,
+ "epoch": 7.13,
+ "learning_rate": 0.00011036931818181819,
+ "loss": 0.7347,
"step": 631
},
{
- "epoch": 12.79,
- "learning_rate": 0.00011938775510204083,
- "loss": 1.295,
+ "epoch": 7.14,
+ "learning_rate": 0.00011022727272727273,
+ "loss": 0.7427,
"step": 632
},
{
- "epoch": 12.81,
- "learning_rate": 0.00011926020408163265,
- "loss": 1.3447,
+ "epoch": 7.15,
+ "learning_rate": 0.00011008522727272728,
+ "loss": 0.7339,
"step": 633
},
{
- "epoch": 12.83,
- "learning_rate": 0.0001191326530612245,
- "loss": 1.3835,
+ "epoch": 7.16,
+ "learning_rate": 0.00010994318181818182,
+ "loss": 0.7375,
"step": 634
},
{
- "epoch": 12.85,
- "learning_rate": 0.00011900510204081634,
- "loss": 1.3222,
+ "epoch": 7.17,
+ "learning_rate": 0.00010980113636363635,
+ "loss": 0.7182,
"step": 635
},
{
- "epoch": 12.87,
- "learning_rate": 0.00011887755102040817,
- "loss": 1.2851,
+ "epoch": 7.19,
+ "learning_rate": 0.00010965909090909093,
+ "loss": 0.7452,
"step": 636
},
{
- "epoch": 12.89,
- "learning_rate": 0.00011875,
- "loss": 1.2723,
+ "epoch": 7.2,
+ "learning_rate": 0.00010951704545454546,
+ "loss": 0.7565,
"step": 637
},
{
- "epoch": 12.91,
- "learning_rate": 0.00011862244897959184,
- "loss": 1.3924,
+ "epoch": 7.21,
+ "learning_rate": 0.000109375,
+ "loss": 0.7296,
"step": 638
},
{
- "epoch": 12.93,
- "learning_rate": 0.00011849489795918368,
- "loss": 1.4625,
+ "epoch": 7.22,
+ "learning_rate": 0.00010923295454545455,
+ "loss": 0.7484,
"step": 639
},
{
- "epoch": 12.95,
- "learning_rate": 0.00011836734693877552,
- "loss": 1.3245,
+ "epoch": 7.23,
+ "learning_rate": 0.00010909090909090909,
+ "loss": 0.732,
"step": 640
},
{
- "epoch": 12.97,
- "learning_rate": 0.00011823979591836736,
- "loss": 1.4042,
+ "epoch": 7.24,
+ "learning_rate": 0.00010894886363636365,
+ "loss": 0.7415,
"step": 641
},
{
- "epoch": 12.99,
- "learning_rate": 0.00011811224489795918,
- "loss": 1.3761,
+ "epoch": 7.25,
+ "learning_rate": 0.0001088068181818182,
+ "loss": 0.7344,
"step": 642
},
{
- "epoch": 13.01,
- "learning_rate": 0.00011798469387755103,
- "loss": 1.3376,
+ "epoch": 7.26,
+ "learning_rate": 0.00010866477272727274,
+ "loss": 0.7267,
"step": 643
},
{
- "epoch": 13.03,
- "learning_rate": 0.00011785714285714287,
- "loss": 1.2174,
+ "epoch": 7.28,
+ "learning_rate": 0.00010852272727272727,
+ "loss": 0.7543,
"step": 644
},
{
- "epoch": 13.05,
- "learning_rate": 0.00011772959183673471,
- "loss": 1.3602,
+ "epoch": 7.29,
+ "learning_rate": 0.00010838068181818182,
+ "loss": 0.7266,
"step": 645
},
{
- "epoch": 13.07,
- "learning_rate": 0.00011760204081632653,
- "loss": 1.3002,
+ "epoch": 7.3,
+ "learning_rate": 0.00010823863636363636,
+ "loss": 0.7449,
"step": 646
},
{
- "epoch": 13.09,
- "learning_rate": 0.00011747448979591838,
- "loss": 1.2262,
+ "epoch": 7.31,
+ "learning_rate": 0.00010809659090909092,
+ "loss": 0.7324,
"step": 647
},
{
- "epoch": 13.11,
- "learning_rate": 0.00011734693877551022,
- "loss": 1.3048,
+ "epoch": 7.32,
+ "learning_rate": 0.00010795454545454547,
+ "loss": 0.7268,
"step": 648
},
{
- "epoch": 13.13,
- "learning_rate": 0.00011721938775510204,
- "loss": 1.2231,
+ "epoch": 7.33,
+ "learning_rate": 0.00010781250000000001,
+ "loss": 0.7172,
"step": 649
},
{
- "epoch": 13.15,
- "learning_rate": 0.00011709183673469388,
- "loss": 1.2996,
+ "epoch": 7.34,
+ "learning_rate": 0.00010767045454545454,
+ "loss": 0.7169,
"step": 650
},
{
- "epoch": 13.17,
- "learning_rate": 0.00011696428571428573,
- "loss": 1.2708,
+ "epoch": 7.35,
+ "learning_rate": 0.00010752840909090909,
+ "loss": 0.7194,
"step": 651
},
{
- "epoch": 13.19,
- "learning_rate": 0.00011683673469387754,
- "loss": 1.2776,
+ "epoch": 7.37,
+ "learning_rate": 0.00010738636363636365,
+ "loss": 0.7223,
"step": 652
},
{
- "epoch": 13.21,
- "learning_rate": 0.00011670918367346939,
- "loss": 1.248,
+ "epoch": 7.38,
+ "learning_rate": 0.00010724431818181819,
+ "loss": 0.7158,
"step": 653
},
{
- "epoch": 13.23,
- "learning_rate": 0.00011658163265306123,
- "loss": 1.2582,
+ "epoch": 7.39,
+ "learning_rate": 0.00010710227272727274,
+ "loss": 0.7122,
"step": 654
},
{
- "epoch": 13.25,
- "learning_rate": 0.00011645408163265305,
- "loss": 1.3011,
+ "epoch": 7.4,
+ "learning_rate": 0.00010696022727272728,
+ "loss": 0.7225,
"step": 655
},
{
- "epoch": 13.27,
- "learning_rate": 0.0001163265306122449,
- "loss": 1.2969,
+ "epoch": 7.41,
+ "learning_rate": 0.00010681818181818181,
+ "loss": 0.7102,
"step": 656
},
{
- "epoch": 13.29,
- "learning_rate": 0.00011619897959183674,
- "loss": 1.2454,
+ "epoch": 7.42,
+ "learning_rate": 0.00010667613636363636,
+ "loss": 0.7251,
"step": 657
},
{
- "epoch": 13.31,
- "learning_rate": 0.00011607142857142858,
- "loss": 1.1914,
+ "epoch": 7.43,
+ "learning_rate": 0.00010653409090909092,
+ "loss": 0.7191,
"step": 658
},
{
- "epoch": 13.33,
- "learning_rate": 0.00011594387755102041,
- "loss": 1.34,
+ "epoch": 7.45,
+ "learning_rate": 0.00010639204545454546,
+ "loss": 0.7015,
"step": 659
},
{
- "epoch": 13.35,
- "learning_rate": 0.00011581632653061225,
- "loss": 1.2828,
+ "epoch": 7.46,
+ "learning_rate": 0.00010625000000000001,
+ "loss": 0.693,
"step": 660
},
{
- "epoch": 13.37,
- "learning_rate": 0.00011568877551020409,
- "loss": 1.2962,
+ "epoch": 7.47,
+ "learning_rate": 0.00010610795454545455,
+ "loss": 0.7039,
"step": 661
},
{
- "epoch": 13.39,
- "learning_rate": 0.00011556122448979592,
- "loss": 1.3334,
+ "epoch": 7.48,
+ "learning_rate": 0.00010596590909090908,
+ "loss": 0.7305,
"step": 662
},
{
- "epoch": 13.42,
- "learning_rate": 0.00011543367346938776,
- "loss": 1.2832,
+ "epoch": 7.49,
+ "learning_rate": 0.00010582386363636366,
+ "loss": 0.6978,
"step": 663
},
{
- "epoch": 13.44,
- "learning_rate": 0.00011530612244897961,
- "loss": 1.3012,
+ "epoch": 7.5,
+ "learning_rate": 0.00010568181818181819,
+ "loss": 0.7219,
"step": 664
},
{
- "epoch": 13.46,
- "learning_rate": 0.00011517857142857143,
- "loss": 1.2857,
+ "epoch": 7.51,
+ "learning_rate": 0.00010553977272727273,
+ "loss": 0.7199,
"step": 665
},
{
- "epoch": 13.48,
- "learning_rate": 0.00011505102040816327,
- "loss": 1.2855,
+ "epoch": 7.52,
+ "learning_rate": 0.00010539772727272728,
+ "loss": 0.6979,
"step": 666
},
{
- "epoch": 13.5,
- "learning_rate": 0.00011492346938775512,
- "loss": 1.3077,
+ "epoch": 7.54,
+ "learning_rate": 0.00010525568181818182,
+ "loss": 0.7058,
"step": 667
},
{
- "epoch": 13.52,
- "learning_rate": 0.00011479591836734696,
- "loss": 1.3139,
+ "epoch": 7.55,
+ "learning_rate": 0.00010511363636363635,
+ "loss": 0.6994,
"step": 668
},
{
- "epoch": 13.54,
- "learning_rate": 0.00011466836734693878,
- "loss": 1.3138,
+ "epoch": 7.56,
+ "learning_rate": 0.00010497159090909093,
+ "loss": 0.7141,
"step": 669
},
{
- "epoch": 13.56,
- "learning_rate": 0.00011454081632653062,
- "loss": 1.2808,
+ "epoch": 7.57,
+ "learning_rate": 0.00010482954545454546,
+ "loss": 0.7092,
"step": 670
},
{
- "epoch": 13.58,
- "learning_rate": 0.00011441326530612247,
- "loss": 1.2492,
+ "epoch": 7.58,
+ "learning_rate": 0.0001046875,
+ "loss": 0.7059,
"step": 671
},
{
- "epoch": 13.6,
- "learning_rate": 0.00011428571428571428,
- "loss": 1.2027,
+ "epoch": 7.59,
+ "learning_rate": 0.00010454545454545455,
+ "loss": 0.6904,
"step": 672
},
{
- "epoch": 13.62,
- "learning_rate": 0.00011415816326530613,
- "loss": 1.33,
+ "epoch": 7.6,
+ "learning_rate": 0.0001044034090909091,
+ "loss": 0.7115,
"step": 673
},
{
- "epoch": 13.64,
- "learning_rate": 0.00011403061224489797,
- "loss": 1.3112,
+ "epoch": 7.61,
+ "learning_rate": 0.00010426136363636365,
+ "loss": 0.7254,
"step": 674
},
{
- "epoch": 13.66,
- "learning_rate": 0.00011390306122448979,
- "loss": 1.2772,
+ "epoch": 7.63,
+ "learning_rate": 0.0001041193181818182,
+ "loss": 0.7181,
"step": 675
},
{
- "epoch": 13.68,
- "learning_rate": 0.00011377551020408163,
- "loss": 1.2701,
+ "epoch": 7.64,
+ "learning_rate": 0.00010397727272727273,
+ "loss": 0.6867,
"step": 676
},
{
- "epoch": 13.7,
- "learning_rate": 0.00011364795918367348,
- "loss": 1.1973,
+ "epoch": 7.65,
+ "learning_rate": 0.00010383522727272727,
+ "loss": 0.6917,
"step": 677
},
{
- "epoch": 13.72,
- "learning_rate": 0.0001135204081632653,
- "loss": 1.3124,
+ "epoch": 7.66,
+ "learning_rate": 0.00010369318181818182,
+ "loss": 0.6908,
"step": 678
},
{
- "epoch": 13.74,
- "learning_rate": 0.00011339285714285714,
- "loss": 1.3085,
+ "epoch": 7.67,
+ "learning_rate": 0.00010355113636363636,
+ "loss": 0.6871,
"step": 679
},
{
- "epoch": 13.76,
- "learning_rate": 0.00011326530612244898,
- "loss": 1.3457,
+ "epoch": 7.68,
+ "learning_rate": 0.00010340909090909092,
+ "loss": 0.682,
"step": 680
},
{
- "epoch": 13.78,
- "learning_rate": 0.00011313775510204083,
- "loss": 1.3338,
+ "epoch": 7.69,
+ "learning_rate": 0.00010326704545454547,
+ "loss": 0.6737,
"step": 681
},
{
- "epoch": 13.8,
- "learning_rate": 0.00011301020408163266,
- "loss": 1.2753,
+ "epoch": 7.7,
+ "learning_rate": 0.000103125,
+ "loss": 0.7023,
"step": 682
},
{
- "epoch": 13.82,
- "learning_rate": 0.00011288265306122449,
- "loss": 1.2786,
+ "epoch": 7.72,
+ "learning_rate": 0.00010298295454545454,
+ "loss": 0.7079,
"step": 683
},
{
- "epoch": 13.84,
- "learning_rate": 0.00011275510204081634,
- "loss": 1.2584,
+ "epoch": 7.73,
+ "learning_rate": 0.00010284090909090909,
+ "loss": 0.6954,
"step": 684
},
{
- "epoch": 13.86,
- "learning_rate": 0.00011262755102040817,
- "loss": 1.2779,
+ "epoch": 7.74,
+ "learning_rate": 0.00010269886363636365,
+ "loss": 0.6834,
"step": 685
},
{
- "epoch": 13.88,
- "learning_rate": 0.00011250000000000001,
- "loss": 1.3502,
+ "epoch": 7.75,
+ "learning_rate": 0.0001025568181818182,
+ "loss": 0.6706,
"step": 686
},
{
- "epoch": 13.9,
- "learning_rate": 0.00011237244897959185,
- "loss": 1.3251,
+ "epoch": 7.76,
+ "learning_rate": 0.00010241477272727274,
+ "loss": 0.6706,
"step": 687
},
{
- "epoch": 13.92,
- "learning_rate": 0.00011224489795918367,
- "loss": 1.273,
+ "epoch": 7.77,
+ "learning_rate": 0.00010227272727272727,
+ "loss": 0.681,
"step": 688
},
{
- "epoch": 13.94,
- "learning_rate": 0.00011211734693877552,
- "loss": 1.3341,
+ "epoch": 7.78,
+ "learning_rate": 0.00010213068181818182,
+ "loss": 0.6853,
"step": 689
},
{
- "epoch": 13.96,
- "learning_rate": 0.00011198979591836736,
- "loss": 1.2654,
+ "epoch": 7.8,
+ "learning_rate": 0.00010198863636363636,
+ "loss": 0.6772,
"step": 690
},
{
- "epoch": 13.98,
- "learning_rate": 0.00011186224489795918,
- "loss": 1.3333,
+ "epoch": 7.81,
+ "learning_rate": 0.00010184659090909092,
+ "loss": 0.6635,
"step": 691
},
{
- "epoch": 14.0,
- "learning_rate": 0.00011173469387755102,
- "loss": 1.3246,
+ "epoch": 7.82,
+ "learning_rate": 0.00010170454545454546,
+ "loss": 0.6712,
"step": 692
},
{
- "epoch": 14.02,
- "learning_rate": 0.00011160714285714287,
- "loss": 1.2547,
+ "epoch": 7.83,
+ "learning_rate": 0.00010156250000000001,
+ "loss": 0.6884,
"step": 693
},
{
- "epoch": 14.04,
- "learning_rate": 0.00011147959183673471,
- "loss": 1.208,
+ "epoch": 7.84,
+ "learning_rate": 0.00010142045454545454,
+ "loss": 0.6641,
"step": 694
},
{
- "epoch": 14.06,
- "learning_rate": 0.00011135204081632653,
- "loss": 1.223,
+ "epoch": 7.85,
+ "learning_rate": 0.00010127840909090909,
+ "loss": 0.6838,
"step": 695
},
{
- "epoch": 14.08,
- "learning_rate": 0.00011122448979591837,
- "loss": 1.2483,
+ "epoch": 7.86,
+ "learning_rate": 0.00010113636363636366,
+ "loss": 0.675,
"step": 696
},
{
- "epoch": 14.1,
- "learning_rate": 0.00011109693877551022,
- "loss": 1.2823,
+ "epoch": 7.87,
+ "learning_rate": 0.00010099431818181819,
+ "loss": 0.6626,
"step": 697
},
{
- "epoch": 14.12,
- "learning_rate": 0.00011096938775510204,
- "loss": 1.2013,
+ "epoch": 7.89,
+ "learning_rate": 0.00010085227272727273,
+ "loss": 0.6605,
"step": 698
},
{
- "epoch": 14.14,
- "learning_rate": 0.00011084183673469388,
- "loss": 1.1883,
+ "epoch": 7.9,
+ "learning_rate": 0.00010071022727272728,
+ "loss": 0.6777,
"step": 699
},
{
- "epoch": 14.16,
- "learning_rate": 0.00011071428571428572,
- "loss": 1.2364,
+ "epoch": 7.91,
+ "learning_rate": 0.00010056818181818181,
+ "loss": 0.6347,
"step": 700
},
{
- "epoch": 14.18,
- "learning_rate": 0.00011058673469387754,
- "loss": 1.2069,
+ "epoch": 7.92,
+ "learning_rate": 0.00010042613636363636,
+ "loss": 0.6857,
"step": 701
},
{
- "epoch": 14.2,
- "learning_rate": 0.00011045918367346939,
- "loss": 1.1968,
+ "epoch": 7.93,
+ "learning_rate": 0.00010028409090909093,
+ "loss": 0.6677,
"step": 702
},
{
- "epoch": 14.22,
- "learning_rate": 0.00011033163265306123,
- "loss": 1.2236,
+ "epoch": 7.94,
+ "learning_rate": 0.00010014204545454546,
+ "loss": 0.6697,
"step": 703
},
{
- "epoch": 14.24,
- "learning_rate": 0.00011020408163265306,
- "loss": 1.1942,
+ "epoch": 7.95,
+ "learning_rate": 0.0001,
+ "loss": 0.6375,
"step": 704
},
{
- "epoch": 14.26,
- "learning_rate": 0.0001100765306122449,
- "loss": 1.2561,
+ "epoch": 7.96,
+ "learning_rate": 9.985795454545455e-05,
+ "loss": 0.6572,
"step": 705
},
{
- "epoch": 14.29,
- "learning_rate": 0.00010994897959183674,
- "loss": 1.1839,
+ "epoch": 7.98,
+ "learning_rate": 9.97159090909091e-05,
+ "loss": 0.668,
"step": 706
},
{
- "epoch": 14.31,
- "learning_rate": 0.00010982142857142858,
- "loss": 1.2128,
+ "epoch": 7.99,
+ "learning_rate": 9.957386363636364e-05,
+ "loss": 0.6797,
"step": 707
},
{
- "epoch": 14.33,
- "learning_rate": 0.00010969387755102041,
- "loss": 1.3086,
+ "epoch": 8.0,
+ "learning_rate": 9.943181818181819e-05,
+ "loss": 0.6784,
"step": 708
},
{
- "epoch": 14.35,
- "learning_rate": 0.00010956632653061226,
- "loss": 1.2379,
+ "epoch": 8.01,
+ "learning_rate": 9.928977272727273e-05,
+ "loss": 0.6192,
"step": 709
},
{
- "epoch": 14.37,
- "learning_rate": 0.0001094387755102041,
- "loss": 1.176,
+ "epoch": 8.02,
+ "learning_rate": 9.914772727272728e-05,
+ "loss": 0.6287,
"step": 710
},
{
- "epoch": 14.39,
- "learning_rate": 0.00010931122448979592,
- "loss": 1.2105,
+ "epoch": 8.03,
+ "learning_rate": 9.900568181818183e-05,
+ "loss": 0.6034,
"step": 711
},
{
- "epoch": 14.41,
- "learning_rate": 0.00010918367346938776,
- "loss": 1.2149,
+ "epoch": 8.04,
+ "learning_rate": 9.886363636363637e-05,
+ "loss": 0.6167,
"step": 712
},
{
- "epoch": 14.43,
- "learning_rate": 0.0001090561224489796,
- "loss": 1.2392,
+ "epoch": 8.06,
+ "learning_rate": 9.872159090909091e-05,
+ "loss": 0.6353,
"step": 713
},
{
- "epoch": 14.45,
- "learning_rate": 0.00010892857142857142,
- "loss": 1.2471,
+ "epoch": 8.07,
+ "learning_rate": 9.857954545454547e-05,
+ "loss": 0.6222,
"step": 714
},
{
- "epoch": 14.47,
- "learning_rate": 0.00010880102040816327,
- "loss": 1.2561,
+ "epoch": 8.08,
+ "learning_rate": 9.84375e-05,
+ "loss": 0.5963,
"step": 715
},
{
- "epoch": 14.49,
- "learning_rate": 0.00010867346938775511,
- "loss": 1.2179,
+ "epoch": 8.09,
+ "learning_rate": 9.829545454545455e-05,
+ "loss": 0.6042,
"step": 716
},
{
- "epoch": 14.51,
- "learning_rate": 0.00010854591836734696,
- "loss": 1.2459,
+ "epoch": 8.1,
+ "learning_rate": 9.81534090909091e-05,
+ "loss": 0.612,
"step": 717
},
{
- "epoch": 14.53,
- "learning_rate": 0.00010841836734693877,
- "loss": 1.2933,
+ "epoch": 8.11,
+ "learning_rate": 9.801136363636364e-05,
+ "loss": 0.6069,
"step": 718
},
{
- "epoch": 14.55,
- "learning_rate": 0.00010829081632653062,
- "loss": 1.2862,
+ "epoch": 8.12,
+ "learning_rate": 9.786931818181818e-05,
+ "loss": 0.6001,
"step": 719
},
{
- "epoch": 14.57,
- "learning_rate": 0.00010816326530612246,
- "loss": 1.2976,
+ "epoch": 8.13,
+ "learning_rate": 9.772727272727274e-05,
+ "loss": 0.6007,
"step": 720
},
{
- "epoch": 14.59,
- "learning_rate": 0.00010803571428571428,
- "loss": 1.231,
+ "epoch": 8.15,
+ "learning_rate": 9.758522727272727e-05,
+ "loss": 0.6079,
"step": 721
},
{
- "epoch": 14.61,
- "learning_rate": 0.00010790816326530613,
- "loss": 1.2464,
+ "epoch": 8.16,
+ "learning_rate": 9.744318181818183e-05,
+ "loss": 0.6216,
"step": 722
},
{
- "epoch": 14.63,
- "learning_rate": 0.00010778061224489797,
- "loss": 1.2181,
+ "epoch": 8.17,
+ "learning_rate": 9.730113636363637e-05,
+ "loss": 0.6321,
"step": 723
},
{
- "epoch": 14.65,
- "learning_rate": 0.00010765306122448979,
- "loss": 1.3307,
+ "epoch": 8.18,
+ "learning_rate": 9.71590909090909e-05,
+ "loss": 0.6044,
"step": 724
},
{
- "epoch": 14.67,
- "learning_rate": 0.00010752551020408163,
- "loss": 1.1723,
+ "epoch": 8.19,
+ "learning_rate": 9.701704545454547e-05,
+ "loss": 0.6028,
"step": 725
},
{
- "epoch": 14.69,
- "learning_rate": 0.00010739795918367348,
- "loss": 1.1528,
+ "epoch": 8.2,
+ "learning_rate": 9.687500000000001e-05,
+ "loss": 0.6098,
"step": 726
},
{
- "epoch": 14.71,
- "learning_rate": 0.0001072704081632653,
- "loss": 1.215,
+ "epoch": 8.21,
+ "learning_rate": 9.673295454545454e-05,
+ "loss": 0.6032,
"step": 727
},
{
- "epoch": 14.73,
- "learning_rate": 0.00010714285714285715,
- "loss": 1.2624,
+ "epoch": 8.22,
+ "learning_rate": 9.65909090909091e-05,
+ "loss": 0.6298,
"step": 728
},
{
- "epoch": 14.75,
- "learning_rate": 0.00010701530612244898,
- "loss": 1.3117,
+ "epoch": 8.24,
+ "learning_rate": 9.644886363636365e-05,
+ "loss": 0.6115,
"step": 729
},
{
- "epoch": 14.77,
- "learning_rate": 0.00010688775510204083,
- "loss": 1.2572,
+ "epoch": 8.25,
+ "learning_rate": 9.630681818181818e-05,
+ "loss": 0.6052,
"step": 730
},
{
- "epoch": 14.79,
- "learning_rate": 0.00010676020408163266,
- "loss": 1.222,
+ "epoch": 8.26,
+ "learning_rate": 9.616477272727274e-05,
+ "loss": 0.6097,
"step": 731
},
{
- "epoch": 14.81,
- "learning_rate": 0.0001066326530612245,
- "loss": 1.2881,
+ "epoch": 8.27,
+ "learning_rate": 9.602272727272728e-05,
+ "loss": 0.6062,
"step": 732
},
{
- "epoch": 14.83,
- "learning_rate": 0.00010650510204081635,
- "loss": 1.2676,
+ "epoch": 8.28,
+ "learning_rate": 9.588068181818183e-05,
+ "loss": 0.5984,
"step": 733
},
{
- "epoch": 14.85,
- "learning_rate": 0.00010637755102040816,
- "loss": 1.2734,
+ "epoch": 8.29,
+ "learning_rate": 9.573863636363637e-05,
+ "loss": 0.6432,
"step": 734
},
{
- "epoch": 14.87,
- "learning_rate": 0.00010625000000000001,
- "loss": 1.2885,
+ "epoch": 8.3,
+ "learning_rate": 9.559659090909092e-05,
+ "loss": 0.5814,
"step": 735
},
{
- "epoch": 14.89,
- "learning_rate": 0.00010612244897959185,
- "loss": 1.2764,
+ "epoch": 8.31,
+ "learning_rate": 9.545454545454546e-05,
+ "loss": 0.5965,
"step": 736
},
{
- "epoch": 14.91,
- "learning_rate": 0.00010599489795918367,
- "loss": 1.3267,
+ "epoch": 8.33,
+ "learning_rate": 9.53125e-05,
+ "loss": 0.6102,
"step": 737
},
{
- "epoch": 14.93,
- "learning_rate": 0.00010586734693877551,
- "loss": 1.2445,
+ "epoch": 8.34,
+ "learning_rate": 9.517045454545455e-05,
+ "loss": 0.5849,
"step": 738
},
{
- "epoch": 14.95,
- "learning_rate": 0.00010573979591836736,
- "loss": 1.3359,
+ "epoch": 8.35,
+ "learning_rate": 9.50284090909091e-05,
+ "loss": 0.6062,
"step": 739
},
{
- "epoch": 14.97,
- "learning_rate": 0.00010561224489795918,
- "loss": 1.2508,
+ "epoch": 8.36,
+ "learning_rate": 9.488636363636364e-05,
+ "loss": 0.6031,
"step": 740
},
{
- "epoch": 14.99,
- "learning_rate": 0.00010548469387755102,
- "loss": 1.2227,
+ "epoch": 8.37,
+ "learning_rate": 9.474431818181819e-05,
+ "loss": 0.5932,
"step": 741
},
{
- "epoch": 15.01,
- "learning_rate": 0.00010535714285714286,
- "loss": 1.1889,
+ "epoch": 8.38,
+ "learning_rate": 9.460227272727273e-05,
+ "loss": 0.589,
"step": 742
},
{
- "epoch": 15.03,
- "learning_rate": 0.00010522959183673471,
- "loss": 1.1919,
+ "epoch": 8.39,
+ "learning_rate": 9.446022727272728e-05,
+ "loss": 0.6096,
"step": 743
},
{
- "epoch": 15.05,
- "learning_rate": 0.00010510204081632653,
- "loss": 1.2383,
+ "epoch": 8.41,
+ "learning_rate": 9.431818181818182e-05,
+ "loss": 0.601,
"step": 744
},
{
- "epoch": 15.07,
- "learning_rate": 0.00010497448979591837,
- "loss": 1.2401,
+ "epoch": 8.42,
+ "learning_rate": 9.417613636363637e-05,
+ "loss": 0.5798,
"step": 745
},
{
- "epoch": 15.09,
- "learning_rate": 0.00010484693877551021,
- "loss": 1.2015,
+ "epoch": 8.43,
+ "learning_rate": 9.403409090909091e-05,
+ "loss": 0.59,
"step": 746
},
{
- "epoch": 15.11,
- "learning_rate": 0.00010471938775510203,
- "loss": 1.1509,
+ "epoch": 8.44,
+ "learning_rate": 9.389204545454546e-05,
+ "loss": 0.5988,
"step": 747
},
{
- "epoch": 15.13,
- "learning_rate": 0.00010459183673469388,
- "loss": 1.1878,
+ "epoch": 8.45,
+ "learning_rate": 9.375e-05,
+ "loss": 0.5591,
"step": 748
},
{
- "epoch": 15.16,
- "learning_rate": 0.00010446428571428572,
- "loss": 1.1706,
+ "epoch": 8.46,
+ "learning_rate": 9.360795454545455e-05,
+ "loss": 0.5939,
"step": 749
},
{
- "epoch": 15.18,
- "learning_rate": 0.00010433673469387755,
- "loss": 1.1285,
+ "epoch": 8.47,
+ "learning_rate": 9.346590909090909e-05,
+ "loss": 0.5886,
"step": 750
},
{
- "epoch": 15.2,
- "learning_rate": 0.0001042091836734694,
- "loss": 1.1608,
+ "epoch": 8.48,
+ "learning_rate": 9.332386363636364e-05,
+ "loss": 0.5994,
"step": 751
},
{
- "epoch": 15.22,
- "learning_rate": 0.00010408163265306123,
- "loss": 1.1178,
+ "epoch": 8.5,
+ "learning_rate": 9.318181818181818e-05,
+ "loss": 0.5821,
"step": 752
},
{
- "epoch": 15.24,
- "learning_rate": 0.00010395408163265306,
- "loss": 1.1293,
+ "epoch": 8.51,
+ "learning_rate": 9.303977272727273e-05,
+ "loss": 0.602,
"step": 753
},
{
- "epoch": 15.26,
- "learning_rate": 0.0001038265306122449,
- "loss": 1.2306,
+ "epoch": 8.52,
+ "learning_rate": 9.289772727272727e-05,
+ "loss": 0.5708,
"step": 754
},
{
- "epoch": 15.28,
- "learning_rate": 0.00010369897959183675,
- "loss": 1.1541,
+ "epoch": 8.53,
+ "learning_rate": 9.275568181818183e-05,
+ "loss": 0.5902,
"step": 755
},
{
- "epoch": 15.3,
- "learning_rate": 0.00010357142857142859,
- "loss": 1.1702,
+ "epoch": 8.54,
+ "learning_rate": 9.261363636363636e-05,
+ "loss": 0.6053,
"step": 756
},
{
- "epoch": 15.32,
- "learning_rate": 0.00010344387755102041,
- "loss": 1.2119,
+ "epoch": 8.55,
+ "learning_rate": 9.247159090909091e-05,
+ "loss": 0.5797,
"step": 757
},
{
- "epoch": 15.34,
- "learning_rate": 0.00010331632653061225,
- "loss": 1.2239,
+ "epoch": 8.56,
+ "learning_rate": 9.232954545454547e-05,
+ "loss": 0.5965,
"step": 758
},
{
- "epoch": 15.36,
- "learning_rate": 0.0001031887755102041,
- "loss": 1.2019,
+ "epoch": 8.57,
+ "learning_rate": 9.21875e-05,
+ "loss": 0.5738,
"step": 759
},
{
- "epoch": 15.38,
- "learning_rate": 0.00010306122448979591,
- "loss": 1.2197,
+ "epoch": 8.59,
+ "learning_rate": 9.204545454545454e-05,
+ "loss": 0.5819,
"step": 760
},
{
- "epoch": 15.4,
- "learning_rate": 0.00010293367346938776,
- "loss": 1.1769,
+ "epoch": 8.6,
+ "learning_rate": 9.19034090909091e-05,
+ "loss": 0.5994,
"step": 761
},
{
- "epoch": 15.42,
- "learning_rate": 0.0001028061224489796,
- "loss": 1.1907,
+ "epoch": 8.61,
+ "learning_rate": 9.176136363636363e-05,
+ "loss": 0.5738,
"step": 762
},
{
- "epoch": 15.44,
- "learning_rate": 0.00010267857142857142,
- "loss": 1.2089,
+ "epoch": 8.62,
+ "learning_rate": 9.161931818181818e-05,
+ "loss": 0.5663,
"step": 763
},
{
- "epoch": 15.46,
- "learning_rate": 0.00010255102040816327,
- "loss": 1.1335,
+ "epoch": 8.63,
+ "learning_rate": 9.147727272727274e-05,
+ "loss": 0.5798,
"step": 764
},
{
- "epoch": 15.48,
- "learning_rate": 0.00010242346938775511,
- "loss": 1.1633,
+ "epoch": 8.64,
+ "learning_rate": 9.133522727272727e-05,
+ "loss": 0.5705,
"step": 765
},
{
- "epoch": 15.5,
- "learning_rate": 0.00010229591836734695,
- "loss": 1.1578,
+ "epoch": 8.65,
+ "learning_rate": 9.119318181818183e-05,
+ "loss": 0.5943,
"step": 766
},
{
- "epoch": 15.52,
- "learning_rate": 0.00010216836734693877,
- "loss": 1.2236,
+ "epoch": 8.67,
+ "learning_rate": 9.105113636363637e-05,
+ "loss": 0.6019,
"step": 767
},
{
- "epoch": 15.54,
- "learning_rate": 0.00010204081632653062,
- "loss": 1.1941,
+ "epoch": 8.68,
+ "learning_rate": 9.090909090909092e-05,
+ "loss": 0.5733,
"step": 768
},
{
- "epoch": 15.56,
- "learning_rate": 0.00010191326530612246,
- "loss": 1.2666,
+ "epoch": 8.69,
+ "learning_rate": 9.076704545454546e-05,
+ "loss": 0.575,
"step": 769
},
{
- "epoch": 15.58,
- "learning_rate": 0.00010178571428571428,
- "loss": 1.1232,
+ "epoch": 8.7,
+ "learning_rate": 9.062500000000001e-05,
+ "loss": 0.5675,
"step": 770
},
{
- "epoch": 15.6,
- "learning_rate": 0.00010165816326530612,
- "loss": 1.2242,
+ "epoch": 8.71,
+ "learning_rate": 9.048295454545455e-05,
+ "loss": 0.566,
"step": 771
},
{
- "epoch": 15.62,
- "learning_rate": 0.00010153061224489797,
- "loss": 1.1852,
+ "epoch": 8.72,
+ "learning_rate": 9.03409090909091e-05,
+ "loss": 0.5513,
"step": 772
},
{
- "epoch": 15.64,
- "learning_rate": 0.0001014030612244898,
- "loss": 1.2626,
+ "epoch": 8.73,
+ "learning_rate": 9.019886363636364e-05,
+ "loss": 0.5682,
"step": 773
},
{
- "epoch": 15.66,
- "learning_rate": 0.00010127551020408164,
- "loss": 1.1873,
+ "epoch": 8.74,
+ "learning_rate": 9.005681818181819e-05,
+ "loss": 0.5508,
"step": 774
},
{
- "epoch": 15.68,
- "learning_rate": 0.00010114795918367349,
- "loss": 1.3005,
+ "epoch": 8.76,
+ "learning_rate": 8.991477272727273e-05,
+ "loss": 0.5668,
"step": 775
},
{
- "epoch": 15.7,
- "learning_rate": 0.0001010204081632653,
- "loss": 1.1904,
+ "epoch": 8.77,
+ "learning_rate": 8.977272727272728e-05,
+ "loss": 0.569,
"step": 776
},
{
- "epoch": 15.72,
- "learning_rate": 0.00010089285714285715,
- "loss": 1.2927,
+ "epoch": 8.78,
+ "learning_rate": 8.963068181818182e-05,
+ "loss": 0.5897,
"step": 777
},
{
- "epoch": 15.74,
- "learning_rate": 0.00010076530612244899,
- "loss": 1.179,
+ "epoch": 8.79,
+ "learning_rate": 8.948863636363637e-05,
+ "loss": 0.5738,
"step": 778
},
{
- "epoch": 15.76,
- "learning_rate": 0.00010063775510204084,
- "loss": 1.2027,
+ "epoch": 8.8,
+ "learning_rate": 8.934659090909091e-05,
+ "loss": 0.5511,
"step": 779
},
{
- "epoch": 15.78,
- "learning_rate": 0.00010051020408163265,
- "loss": 1.2428,
+ "epoch": 8.81,
+ "learning_rate": 8.920454545454546e-05,
+ "loss": 0.5659,
"step": 780
},
{
- "epoch": 15.8,
- "learning_rate": 0.0001003826530612245,
- "loss": 1.2324,
+ "epoch": 8.82,
+ "learning_rate": 8.90625e-05,
+ "loss": 0.5649,
"step": 781
},
{
- "epoch": 15.82,
- "learning_rate": 0.00010025510204081634,
- "loss": 1.1251,
+ "epoch": 8.83,
+ "learning_rate": 8.892045454545455e-05,
+ "loss": 0.5618,
"step": 782
},
{
- "epoch": 15.84,
- "learning_rate": 0.00010012755102040816,
- "loss": 1.2405,
+ "epoch": 8.85,
+ "learning_rate": 8.87784090909091e-05,
+ "loss": 0.5602,
"step": 783
},
{
- "epoch": 15.86,
- "learning_rate": 0.0001,
- "loss": 1.2005,
+ "epoch": 8.86,
+ "learning_rate": 8.863636363636364e-05,
+ "loss": 0.5723,
"step": 784
},
{
- "epoch": 15.88,
- "learning_rate": 9.987244897959184e-05,
- "loss": 1.2259,
+ "epoch": 8.87,
+ "learning_rate": 8.849431818181818e-05,
+ "loss": 0.5816,
"step": 785
},
{
- "epoch": 15.9,
- "learning_rate": 9.974489795918368e-05,
- "loss": 1.1576,
+ "epoch": 8.88,
+ "learning_rate": 8.835227272727273e-05,
+ "loss": 0.555,
"step": 786
},
{
- "epoch": 15.92,
- "learning_rate": 9.961734693877551e-05,
- "loss": 1.1834,
+ "epoch": 8.89,
+ "learning_rate": 8.821022727272727e-05,
+ "loss": 0.5563,
"step": 787
},
{
- "epoch": 15.94,
- "learning_rate": 9.948979591836736e-05,
- "loss": 1.2396,
+ "epoch": 8.9,
+ "learning_rate": 8.806818181818183e-05,
+ "loss": 0.554,
"step": 788
},
{
- "epoch": 15.96,
- "learning_rate": 9.936224489795919e-05,
- "loss": 1.1865,
+ "epoch": 8.91,
+ "learning_rate": 8.792613636363636e-05,
+ "loss": 0.5671,
"step": 789
},
{
- "epoch": 15.98,
- "learning_rate": 9.923469387755102e-05,
- "loss": 1.2356,
+ "epoch": 8.92,
+ "learning_rate": 8.778409090909091e-05,
+ "loss": 0.5485,
"step": 790
},
{
- "epoch": 16.01,
- "learning_rate": 9.910714285714286e-05,
- "loss": 1.2639,
+ "epoch": 8.94,
+ "learning_rate": 8.764204545454547e-05,
+ "loss": 0.5712,
"step": 791
},
{
- "epoch": 16.03,
- "learning_rate": 9.897959183673469e-05,
- "loss": 1.1216,
+ "epoch": 8.95,
+ "learning_rate": 8.75e-05,
+ "loss": 0.5507,
"step": 792
},
{
- "epoch": 16.05,
- "learning_rate": 9.885204081632652e-05,
- "loss": 1.1051,
+ "epoch": 8.96,
+ "learning_rate": 8.735795454545454e-05,
+ "loss": 0.5718,
"step": 793
},
{
- "epoch": 16.07,
- "learning_rate": 9.872448979591837e-05,
- "loss": 1.0864,
+ "epoch": 8.97,
+ "learning_rate": 8.72159090909091e-05,
+ "loss": 0.5585,
"step": 794
},
{
- "epoch": 16.09,
- "learning_rate": 9.859693877551021e-05,
- "loss": 1.182,
+ "epoch": 8.98,
+ "learning_rate": 8.707386363636363e-05,
+ "loss": 0.5563,
"step": 795
},
{
- "epoch": 16.11,
- "learning_rate": 9.846938775510204e-05,
- "loss": 1.1272,
+ "epoch": 8.99,
+ "learning_rate": 8.693181818181818e-05,
+ "loss": 0.581,
"step": 796
},
{
- "epoch": 16.13,
- "learning_rate": 9.834183673469389e-05,
- "loss": 1.1946,
+ "epoch": 9.0,
+ "learning_rate": 8.678977272727274e-05,
+ "loss": 0.5511,
"step": 797
},
{
- "epoch": 16.15,
- "learning_rate": 9.821428571428572e-05,
- "loss": 1.0875,
+ "epoch": 9.02,
+ "learning_rate": 8.664772727272727e-05,
+ "loss": 0.5103,
"step": 798
},
{
- "epoch": 16.17,
- "learning_rate": 9.808673469387756e-05,
- "loss": 1.1671,
+ "epoch": 9.03,
+ "learning_rate": 8.650568181818183e-05,
+ "loss": 0.5323,
"step": 799
},
{
- "epoch": 16.19,
- "learning_rate": 9.79591836734694e-05,
- "loss": 1.1502,
+ "epoch": 9.04,
+ "learning_rate": 8.636363636363637e-05,
+ "loss": 0.5092,
"step": 800
},
{
- "epoch": 16.21,
- "learning_rate": 9.783163265306124e-05,
- "loss": 1.19,
+ "epoch": 9.05,
+ "learning_rate": 8.62215909090909e-05,
+ "loss": 0.5247,
"step": 801
},
{
- "epoch": 16.23,
- "learning_rate": 9.770408163265307e-05,
- "loss": 1.1258,
+ "epoch": 9.06,
+ "learning_rate": 8.607954545454546e-05,
+ "loss": 0.5403,
"step": 802
},
{
- "epoch": 16.25,
- "learning_rate": 9.75765306122449e-05,
- "loss": 1.1765,
+ "epoch": 9.07,
+ "learning_rate": 8.593750000000001e-05,
+ "loss": 0.5252,
"step": 803
},
{
- "epoch": 16.27,
- "learning_rate": 9.744897959183674e-05,
- "loss": 1.1217,
+ "epoch": 9.08,
+ "learning_rate": 8.579545454545454e-05,
+ "loss": 0.5296,
"step": 804
},
{
- "epoch": 16.29,
- "learning_rate": 9.732142857142858e-05,
- "loss": 1.1293,
+ "epoch": 9.09,
+ "learning_rate": 8.56534090909091e-05,
+ "loss": 0.5223,
"step": 805
},
{
- "epoch": 16.31,
- "learning_rate": 9.719387755102042e-05,
- "loss": 1.17,
+ "epoch": 9.11,
+ "learning_rate": 8.551136363636364e-05,
+ "loss": 0.4972,
"step": 806
},
{
- "epoch": 16.33,
- "learning_rate": 9.706632653061225e-05,
- "loss": 1.17,
+ "epoch": 9.12,
+ "learning_rate": 8.536931818181818e-05,
+ "loss": 0.5005,
"step": 807
},
{
- "epoch": 16.35,
- "learning_rate": 9.693877551020408e-05,
- "loss": 1.2004,
+ "epoch": 9.13,
+ "learning_rate": 8.522727272727273e-05,
+ "loss": 0.5249,
"step": 808
},
{
- "epoch": 16.37,
- "learning_rate": 9.681122448979593e-05,
- "loss": 1.1648,
+ "epoch": 9.14,
+ "learning_rate": 8.508522727272728e-05,
+ "loss": 0.5135,
"step": 809
},
{
- "epoch": 16.39,
- "learning_rate": 9.668367346938776e-05,
- "loss": 1.0688,
+ "epoch": 9.15,
+ "learning_rate": 8.494318181818182e-05,
+ "loss": 0.5053,
"step": 810
},
{
- "epoch": 16.41,
- "learning_rate": 9.655612244897959e-05,
- "loss": 1.1607,
+ "epoch": 9.16,
+ "learning_rate": 8.480113636363637e-05,
+ "loss": 0.5158,
"step": 811
},
{
- "epoch": 16.43,
- "learning_rate": 9.642857142857143e-05,
- "loss": 1.1298,
+ "epoch": 9.17,
+ "learning_rate": 8.465909090909091e-05,
+ "loss": 0.5061,
"step": 812
},
{
- "epoch": 16.45,
- "learning_rate": 9.630102040816326e-05,
- "loss": 1.1064,
+ "epoch": 9.18,
+ "learning_rate": 8.451704545454546e-05,
+ "loss": 0.4988,
"step": 813
},
{
- "epoch": 16.47,
- "learning_rate": 9.617346938775511e-05,
- "loss": 1.1472,
+ "epoch": 9.2,
+ "learning_rate": 8.4375e-05,
+ "loss": 0.5273,
"step": 814
},
{
- "epoch": 16.49,
- "learning_rate": 9.604591836734694e-05,
- "loss": 1.1577,
+ "epoch": 9.21,
+ "learning_rate": 8.423295454545455e-05,
+ "loss": 0.5332,
"step": 815
},
{
- "epoch": 16.51,
- "learning_rate": 9.591836734693878e-05,
- "loss": 1.1436,
+ "epoch": 9.22,
+ "learning_rate": 8.40909090909091e-05,
+ "loss": 0.5181,
"step": 816
},
{
- "epoch": 16.53,
- "learning_rate": 9.579081632653061e-05,
- "loss": 1.1657,
+ "epoch": 9.23,
+ "learning_rate": 8.394886363636364e-05,
+ "loss": 0.5085,
"step": 817
},
{
- "epoch": 16.55,
- "learning_rate": 9.566326530612246e-05,
- "loss": 1.1147,
+ "epoch": 9.24,
+ "learning_rate": 8.380681818181818e-05,
+ "loss": 0.5137,
"step": 818
},
{
- "epoch": 16.57,
- "learning_rate": 9.553571428571429e-05,
- "loss": 1.1839,
+ "epoch": 9.25,
+ "learning_rate": 8.366477272727273e-05,
+ "loss": 0.5195,
"step": 819
},
{
- "epoch": 16.59,
- "learning_rate": 9.540816326530613e-05,
- "loss": 1.1298,
+ "epoch": 9.26,
+ "learning_rate": 8.352272727272727e-05,
+ "loss": 0.5077,
"step": 820
},
{
- "epoch": 16.61,
- "learning_rate": 9.528061224489796e-05,
- "loss": 1.2141,
+ "epoch": 9.28,
+ "learning_rate": 8.338068181818183e-05,
+ "loss": 0.5074,
"step": 821
},
{
- "epoch": 16.63,
- "learning_rate": 9.515306122448981e-05,
- "loss": 1.2045,
+ "epoch": 9.29,
+ "learning_rate": 8.323863636363637e-05,
+ "loss": 0.5142,
"step": 822
},
{
- "epoch": 16.65,
- "learning_rate": 9.502551020408164e-05,
- "loss": 1.1791,
+ "epoch": 9.3,
+ "learning_rate": 8.309659090909091e-05,
+ "loss": 0.5116,
"step": 823
},
{
- "epoch": 16.67,
- "learning_rate": 9.489795918367348e-05,
- "loss": 1.1137,
+ "epoch": 9.31,
+ "learning_rate": 8.295454545454547e-05,
+ "loss": 0.4974,
"step": 824
},
{
- "epoch": 16.69,
- "learning_rate": 9.477040816326531e-05,
- "loss": 1.1312,
+ "epoch": 9.32,
+ "learning_rate": 8.28125e-05,
+ "loss": 0.5117,
"step": 825
},
{
- "epoch": 16.71,
- "learning_rate": 9.464285714285715e-05,
- "loss": 1.1102,
+ "epoch": 9.33,
+ "learning_rate": 8.267045454545455e-05,
+ "loss": 0.5114,
"step": 826
},
{
- "epoch": 16.73,
- "learning_rate": 9.451530612244899e-05,
- "loss": 1.1865,
+ "epoch": 9.34,
+ "learning_rate": 8.25284090909091e-05,
+ "loss": 0.5039,
"step": 827
},
{
- "epoch": 16.75,
- "learning_rate": 9.438775510204082e-05,
- "loss": 1.1232,
+ "epoch": 9.35,
+ "learning_rate": 8.238636363636364e-05,
+ "loss": 0.498,
"step": 828
},
{
- "epoch": 16.77,
- "learning_rate": 9.426020408163265e-05,
- "loss": 1.2068,
+ "epoch": 9.37,
+ "learning_rate": 8.224431818181818e-05,
+ "loss": 0.5042,
"step": 829
},
{
- "epoch": 16.79,
- "learning_rate": 9.41326530612245e-05,
- "loss": 1.1864,
+ "epoch": 9.38,
+ "learning_rate": 8.210227272727274e-05,
+ "loss": 0.5049,
"step": 830
},
{
- "epoch": 16.81,
- "learning_rate": 9.400510204081633e-05,
- "loss": 1.2195,
+ "epoch": 9.39,
+ "learning_rate": 8.196022727272727e-05,
+ "loss": 0.5123,
"step": 831
},
{
- "epoch": 16.83,
- "learning_rate": 9.387755102040817e-05,
- "loss": 1.2063,
+ "epoch": 9.4,
+ "learning_rate": 8.181818181818183e-05,
+ "loss": 0.4907,
"step": 832
},
{
- "epoch": 16.85,
- "learning_rate": 9.375e-05,
- "loss": 1.1455,
+ "epoch": 9.41,
+ "learning_rate": 8.167613636363637e-05,
+ "loss": 0.5267,
"step": 833
},
{
- "epoch": 16.88,
- "learning_rate": 9.362244897959183e-05,
- "loss": 1.1819,
+ "epoch": 9.42,
+ "learning_rate": 8.15340909090909e-05,
+ "loss": 0.5314,
"step": 834
},
{
- "epoch": 16.9,
- "learning_rate": 9.349489795918368e-05,
- "loss": 1.1887,
+ "epoch": 9.43,
+ "learning_rate": 8.139204545454546e-05,
+ "loss": 0.4952,
"step": 835
},
{
- "epoch": 16.92,
- "learning_rate": 9.336734693877551e-05,
- "loss": 1.1557,
+ "epoch": 9.44,
+ "learning_rate": 8.125000000000001e-05,
+ "loss": 0.5014,
"step": 836
},
{
- "epoch": 16.94,
- "learning_rate": 9.323979591836735e-05,
- "loss": 1.2094,
+ "epoch": 9.46,
+ "learning_rate": 8.110795454545454e-05,
+ "loss": 0.4967,
"step": 837
},
{
- "epoch": 16.96,
- "learning_rate": 9.311224489795918e-05,
- "loss": 1.1512,
+ "epoch": 9.47,
+ "learning_rate": 8.09659090909091e-05,
+ "loss": 0.5116,
"step": 838
},
{
- "epoch": 16.98,
- "learning_rate": 9.298469387755103e-05,
- "loss": 1.1463,
+ "epoch": 9.48,
+ "learning_rate": 8.082386363636365e-05,
+ "loss": 0.5119,
"step": 839
},
{
- "epoch": 17.0,
- "learning_rate": 9.285714285714286e-05,
- "loss": 1.155,
+ "epoch": 9.49,
+ "learning_rate": 8.068181818181818e-05,
+ "loss": 0.4987,
"step": 840
},
{
- "epoch": 17.02,
- "learning_rate": 9.27295918367347e-05,
- "loss": 1.1292,
+ "epoch": 9.5,
+ "learning_rate": 8.053977272727274e-05,
+ "loss": 0.5063,
"step": 841
},
{
- "epoch": 17.04,
- "learning_rate": 9.260204081632653e-05,
- "loss": 1.0996,
+ "epoch": 9.51,
+ "learning_rate": 8.039772727272728e-05,
+ "loss": 0.5019,
"step": 842
},
{
- "epoch": 17.06,
- "learning_rate": 9.247448979591838e-05,
- "loss": 1.0662,
+ "epoch": 9.52,
+ "learning_rate": 8.025568181818183e-05,
+ "loss": 0.5272,
"step": 843
},
{
- "epoch": 17.08,
- "learning_rate": 9.234693877551021e-05,
- "loss": 1.0931,
+ "epoch": 9.54,
+ "learning_rate": 8.011363636363637e-05,
+ "loss": 0.4969,
"step": 844
},
{
- "epoch": 17.1,
- "learning_rate": 9.221938775510205e-05,
- "loss": 1.0727,
+ "epoch": 9.55,
+ "learning_rate": 7.997159090909092e-05,
+ "loss": 0.5222,
"step": 845
},
{
- "epoch": 17.12,
- "learning_rate": 9.209183673469388e-05,
- "loss": 1.1043,
+ "epoch": 9.56,
+ "learning_rate": 7.982954545454546e-05,
+ "loss": 0.4729,
"step": 846
},
{
- "epoch": 17.14,
- "learning_rate": 9.196428571428572e-05,
- "loss": 1.0594,
+ "epoch": 9.57,
+ "learning_rate": 7.96875e-05,
+ "loss": 0.4976,
"step": 847
},
{
- "epoch": 17.16,
- "learning_rate": 9.183673469387756e-05,
- "loss": 1.0952,
+ "epoch": 9.58,
+ "learning_rate": 7.954545454545455e-05,
+ "loss": 0.4974,
"step": 848
},
{
- "epoch": 17.18,
- "learning_rate": 9.170918367346939e-05,
- "loss": 1.0639,
+ "epoch": 9.59,
+ "learning_rate": 7.94034090909091e-05,
+ "loss": 0.4849,
"step": 849
},
{
- "epoch": 17.2,
- "learning_rate": 9.158163265306124e-05,
- "loss": 1.132,
+ "epoch": 9.6,
+ "learning_rate": 7.926136363636364e-05,
+ "loss": 0.4897,
"step": 850
},
{
- "epoch": 17.22,
- "learning_rate": 9.145408163265307e-05,
- "loss": 1.1083,
+ "epoch": 9.61,
+ "learning_rate": 7.911931818181819e-05,
+ "loss": 0.4962,
"step": 851
},
{
- "epoch": 17.24,
- "learning_rate": 9.13265306122449e-05,
- "loss": 1.1282,
+ "epoch": 9.63,
+ "learning_rate": 7.897727272727273e-05,
+ "loss": 0.4877,
"step": 852
},
{
- "epoch": 17.26,
- "learning_rate": 9.119897959183674e-05,
- "loss": 1.0474,
+ "epoch": 9.64,
+ "learning_rate": 7.883522727272728e-05,
+ "loss": 0.4921,
"step": 853
},
{
- "epoch": 17.28,
- "learning_rate": 9.107142857142857e-05,
- "loss": 1.1138,
+ "epoch": 9.65,
+ "learning_rate": 7.869318181818182e-05,
+ "loss": 0.4969,
"step": 854
},
{
- "epoch": 17.3,
- "learning_rate": 9.094387755102042e-05,
- "loss": 1.1025,
+ "epoch": 9.66,
+ "learning_rate": 7.855113636363637e-05,
+ "loss": 0.5045,
"step": 855
},
{
- "epoch": 17.32,
- "learning_rate": 9.081632653061225e-05,
- "loss": 1.0968,
+ "epoch": 9.67,
+ "learning_rate": 7.840909090909091e-05,
+ "loss": 0.5207,
"step": 856
},
{
- "epoch": 17.34,
- "learning_rate": 9.068877551020408e-05,
- "loss": 1.1683,
+ "epoch": 9.68,
+ "learning_rate": 7.826704545454546e-05,
+ "loss": 0.5098,
"step": 857
},
{
- "epoch": 17.36,
- "learning_rate": 9.056122448979592e-05,
- "loss": 1.0975,
+ "epoch": 9.69,
+ "learning_rate": 7.8125e-05,
+ "loss": 0.5005,
"step": 858
},
{
- "epoch": 17.38,
- "learning_rate": 9.043367346938775e-05,
- "loss": 1.1274,
+ "epoch": 9.7,
+ "learning_rate": 7.798295454545455e-05,
+ "loss": 0.5028,
"step": 859
},
{
- "epoch": 17.4,
- "learning_rate": 9.030612244897958e-05,
- "loss": 1.0916,
+ "epoch": 9.72,
+ "learning_rate": 7.784090909090909e-05,
+ "loss": 0.5067,
"step": 860
},
{
- "epoch": 17.42,
- "learning_rate": 9.017857142857143e-05,
- "loss": 1.0912,
+ "epoch": 9.73,
+ "learning_rate": 7.769886363636364e-05,
+ "loss": 0.484,
"step": 861
},
{
- "epoch": 17.44,
- "learning_rate": 9.005102040816327e-05,
- "loss": 1.0875,
+ "epoch": 9.74,
+ "learning_rate": 7.755681818181818e-05,
+ "loss": 0.5029,
"step": 862
},
{
- "epoch": 17.46,
- "learning_rate": 8.99234693877551e-05,
- "loss": 1.05,
+ "epoch": 9.75,
+ "learning_rate": 7.741477272727273e-05,
+ "loss": 0.5077,
"step": 863
},
{
- "epoch": 17.48,
- "learning_rate": 8.979591836734695e-05,
- "loss": 1.1418,
+ "epoch": 9.76,
+ "learning_rate": 7.727272727272727e-05,
+ "loss": 0.5091,
"step": 864
},
{
- "epoch": 17.5,
- "learning_rate": 8.966836734693878e-05,
- "loss": 1.0609,
+ "epoch": 9.77,
+ "learning_rate": 7.713068181818183e-05,
+ "loss": 0.4781,
"step": 865
},
{
- "epoch": 17.52,
- "learning_rate": 8.954081632653062e-05,
- "loss": 1.1611,
+ "epoch": 9.78,
+ "learning_rate": 7.698863636363636e-05,
+ "loss": 0.5124,
"step": 866
},
{
- "epoch": 17.54,
- "learning_rate": 8.941326530612245e-05,
- "loss": 1.1065,
+ "epoch": 9.79,
+ "learning_rate": 7.684659090909091e-05,
+ "loss": 0.4859,
"step": 867
},
{
- "epoch": 17.56,
- "learning_rate": 8.92857142857143e-05,
- "loss": 1.1611,
+ "epoch": 9.81,
+ "learning_rate": 7.670454545454547e-05,
+ "loss": 0.4872,
"step": 868
},
{
- "epoch": 17.58,
- "learning_rate": 8.915816326530613e-05,
- "loss": 1.1398,
+ "epoch": 9.82,
+ "learning_rate": 7.65625e-05,
+ "loss": 0.4675,
"step": 869
},
{
- "epoch": 17.6,
- "learning_rate": 8.903061224489796e-05,
- "loss": 1.1055,
+ "epoch": 9.83,
+ "learning_rate": 7.642045454545454e-05,
+ "loss": 0.5056,
"step": 870
},
{
- "epoch": 17.62,
- "learning_rate": 8.89030612244898e-05,
- "loss": 1.1314,
+ "epoch": 9.84,
+ "learning_rate": 7.62784090909091e-05,
+ "loss": 0.4868,
"step": 871
},
{
- "epoch": 17.64,
- "learning_rate": 8.877551020408164e-05,
- "loss": 1.1084,
+ "epoch": 9.85,
+ "learning_rate": 7.613636363636363e-05,
+ "loss": 0.4907,
"step": 872
},
{
- "epoch": 17.66,
- "learning_rate": 8.864795918367348e-05,
- "loss": 1.1254,
+ "epoch": 9.86,
+ "learning_rate": 7.599431818181818e-05,
+ "loss": 0.474,
"step": 873
},
{
- "epoch": 17.68,
- "learning_rate": 8.852040816326531e-05,
- "loss": 1.142,
+ "epoch": 9.87,
+ "learning_rate": 7.585227272727274e-05,
+ "loss": 0.4813,
"step": 874
},
{
- "epoch": 17.7,
- "learning_rate": 8.839285714285714e-05,
- "loss": 1.1371,
+ "epoch": 9.89,
+ "learning_rate": 7.571022727272727e-05,
+ "loss": 0.4838,
"step": 875
},
{
- "epoch": 17.72,
- "learning_rate": 8.826530612244899e-05,
- "loss": 1.1092,
+ "epoch": 9.9,
+ "learning_rate": 7.556818181818183e-05,
+ "loss": 0.4935,
"step": 876
},
{
- "epoch": 17.75,
- "learning_rate": 8.813775510204082e-05,
- "loss": 1.161,
+ "epoch": 9.91,
+ "learning_rate": 7.542613636363637e-05,
+ "loss": 0.4884,
"step": 877
},
{
- "epoch": 17.77,
- "learning_rate": 8.801020408163265e-05,
- "loss": 1.1044,
+ "epoch": 9.92,
+ "learning_rate": 7.52840909090909e-05,
+ "loss": 0.4797,
"step": 878
},
{
- "epoch": 17.79,
- "learning_rate": 8.788265306122449e-05,
- "loss": 1.117,
+ "epoch": 9.93,
+ "learning_rate": 7.514204545454546e-05,
+ "loss": 0.479,
"step": 879
},
{
- "epoch": 17.81,
- "learning_rate": 8.775510204081632e-05,
- "loss": 1.1262,
+ "epoch": 9.94,
+ "learning_rate": 7.500000000000001e-05,
+ "loss": 0.4727,
"step": 880
},
{
- "epoch": 17.83,
- "learning_rate": 8.762755102040817e-05,
- "loss": 1.0829,
+ "epoch": 9.95,
+ "learning_rate": 7.485795454545454e-05,
+ "loss": 0.4758,
"step": 881
},
{
- "epoch": 17.85,
- "learning_rate": 8.75e-05,
- "loss": 1.1393,
+ "epoch": 9.96,
+ "learning_rate": 7.47159090909091e-05,
+ "loss": 0.482,
"step": 882
},
{
- "epoch": 17.87,
- "learning_rate": 8.737244897959183e-05,
- "loss": 1.1781,
+ "epoch": 9.98,
+ "learning_rate": 7.457386363636364e-05,
+ "loss": 0.4951,
"step": 883
},
{
- "epoch": 17.89,
- "learning_rate": 8.724489795918367e-05,
- "loss": 1.1582,
+ "epoch": 9.99,
+ "learning_rate": 7.443181818181817e-05,
+ "loss": 0.4823,
"step": 884
},
{
- "epoch": 17.91,
- "learning_rate": 8.711734693877552e-05,
- "loss": 1.1469,
+ "epoch": 10.0,
+ "learning_rate": 7.428977272727273e-05,
+ "loss": 0.4638,
"step": 885
},
{
- "epoch": 17.93,
- "learning_rate": 8.698979591836735e-05,
- "loss": 1.1494,
+ "epoch": 10.01,
+ "learning_rate": 7.414772727272728e-05,
+ "loss": 0.4715,
"step": 886
},
{
- "epoch": 17.95,
- "learning_rate": 8.68622448979592e-05,
- "loss": 1.1251,
+ "epoch": 10.02,
+ "learning_rate": 7.400568181818182e-05,
+ "loss": 0.461,
"step": 887
},
{
- "epoch": 17.97,
- "learning_rate": 8.673469387755102e-05,
- "loss": 1.1624,
+ "epoch": 10.03,
+ "learning_rate": 7.386363636363637e-05,
+ "loss": 0.4429,
"step": 888
},
{
- "epoch": 17.99,
- "learning_rate": 8.660714285714287e-05,
- "loss": 1.0842,
+ "epoch": 10.04,
+ "learning_rate": 7.372159090909091e-05,
+ "loss": 0.4403,
"step": 889
},
{
- "epoch": 18.01,
- "learning_rate": 8.64795918367347e-05,
- "loss": 1.1944,
+ "epoch": 10.05,
+ "learning_rate": 7.357954545454546e-05,
+ "loss": 0.4519,
"step": 890
},
{
- "epoch": 18.03,
- "learning_rate": 8.635204081632653e-05,
- "loss": 1.0642,
+ "epoch": 10.07,
+ "learning_rate": 7.34375e-05,
+ "loss": 0.4611,
"step": 891
},
{
- "epoch": 18.05,
- "learning_rate": 8.622448979591838e-05,
- "loss": 1.0459,
+ "epoch": 10.08,
+ "learning_rate": 7.329545454545455e-05,
+ "loss": 0.4543,
"step": 892
},
{
- "epoch": 18.07,
- "learning_rate": 8.60969387755102e-05,
- "loss": 1.0941,
+ "epoch": 10.09,
+ "learning_rate": 7.315340909090909e-05,
+ "loss": 0.4528,
"step": 893
},
{
- "epoch": 18.09,
- "learning_rate": 8.596938775510205e-05,
- "loss": 1.0457,
+ "epoch": 10.1,
+ "learning_rate": 7.301136363636364e-05,
+ "loss": 0.4586,
"step": 894
},
{
- "epoch": 18.11,
- "learning_rate": 8.584183673469388e-05,
- "loss": 1.1033,
+ "epoch": 10.11,
+ "learning_rate": 7.286931818181818e-05,
+ "loss": 0.4418,
"step": 895
},
{
- "epoch": 18.13,
- "learning_rate": 8.571428571428571e-05,
- "loss": 1.0756,
+ "epoch": 10.12,
+ "learning_rate": 7.272727272727273e-05,
+ "loss": 0.4435,
"step": 896
},
{
- "epoch": 18.15,
- "learning_rate": 8.558673469387756e-05,
- "loss": 1.0615,
+ "epoch": 10.13,
+ "learning_rate": 7.258522727272727e-05,
+ "loss": 0.44,
"step": 897
},
{
- "epoch": 18.17,
- "learning_rate": 8.545918367346939e-05,
- "loss": 1.0828,
+ "epoch": 10.15,
+ "learning_rate": 7.244318181818183e-05,
+ "loss": 0.4589,
"step": 898
},
{
- "epoch": 18.19,
- "learning_rate": 8.533163265306123e-05,
- "loss": 1.1158,
+ "epoch": 10.16,
+ "learning_rate": 7.230113636363636e-05,
+ "loss": 0.4597,
"step": 899
},
{
- "epoch": 18.21,
- "learning_rate": 8.520408163265306e-05,
- "loss": 1.0133,
+ "epoch": 10.17,
+ "learning_rate": 7.215909090909091e-05,
+ "loss": 0.4479,
"step": 900
},
{
- "epoch": 18.23,
- "learning_rate": 8.50765306122449e-05,
- "loss": 1.0437,
+ "epoch": 10.18,
+ "learning_rate": 7.201704545454547e-05,
+ "loss": 0.4477,
"step": 901
},
{
- "epoch": 18.25,
- "learning_rate": 8.494897959183674e-05,
- "loss": 1.0372,
+ "epoch": 10.19,
+ "learning_rate": 7.1875e-05,
+ "loss": 0.446,
"step": 902
},
{
- "epoch": 18.27,
- "learning_rate": 8.482142857142857e-05,
- "loss": 1.1012,
+ "epoch": 10.2,
+ "learning_rate": 7.173295454545454e-05,
+ "loss": 0.4546,
"step": 903
},
{
- "epoch": 18.29,
- "learning_rate": 8.469387755102041e-05,
- "loss": 1.0777,
+ "epoch": 10.21,
+ "learning_rate": 7.15909090909091e-05,
+ "loss": 0.4347,
"step": 904
},
{
- "epoch": 18.31,
- "learning_rate": 8.456632653061224e-05,
- "loss": 1.0799,
+ "epoch": 10.22,
+ "learning_rate": 7.144886363636363e-05,
+ "loss": 0.452,
"step": 905
},
{
- "epoch": 18.33,
- "learning_rate": 8.443877551020409e-05,
- "loss": 0.9846,
+ "epoch": 10.24,
+ "learning_rate": 7.130681818181818e-05,
+ "loss": 0.4536,
"step": 906
},
{
- "epoch": 18.35,
- "learning_rate": 8.431122448979592e-05,
- "loss": 1.1,
+ "epoch": 10.25,
+ "learning_rate": 7.116477272727274e-05,
+ "loss": 0.4492,
"step": 907
},
{
- "epoch": 18.37,
- "learning_rate": 8.418367346938776e-05,
- "loss": 1.0787,
+ "epoch": 10.26,
+ "learning_rate": 7.102272727272727e-05,
+ "loss": 0.4401,
"step": 908
},
{
- "epoch": 18.39,
- "learning_rate": 8.40561224489796e-05,
- "loss": 1.0647,
+ "epoch": 10.27,
+ "learning_rate": 7.088068181818183e-05,
+ "loss": 0.4609,
"step": 909
},
{
- "epoch": 18.41,
- "learning_rate": 8.392857142857144e-05,
- "loss": 1.056,
+ "epoch": 10.28,
+ "learning_rate": 7.073863636363637e-05,
+ "loss": 0.4544,
"step": 910
},
{
- "epoch": 18.43,
- "learning_rate": 8.380102040816327e-05,
- "loss": 1.1131,
+ "epoch": 10.29,
+ "learning_rate": 7.05965909090909e-05,
+ "loss": 0.4477,
"step": 911
},
{
- "epoch": 18.45,
- "learning_rate": 8.367346938775511e-05,
- "loss": 1.0825,
+ "epoch": 10.3,
+ "learning_rate": 7.045454545454546e-05,
+ "loss": 0.4445,
"step": 912
},
{
- "epoch": 18.47,
- "learning_rate": 8.354591836734695e-05,
- "loss": 1.0681,
+ "epoch": 10.31,
+ "learning_rate": 7.031250000000001e-05,
+ "loss": 0.4544,
"step": 913
},
{
- "epoch": 18.49,
- "learning_rate": 8.341836734693878e-05,
- "loss": 1.0479,
+ "epoch": 10.33,
+ "learning_rate": 7.017045454545454e-05,
+ "loss": 0.4634,
"step": 914
},
{
- "epoch": 18.51,
- "learning_rate": 8.329081632653062e-05,
- "loss": 1.0921,
+ "epoch": 10.34,
+ "learning_rate": 7.00284090909091e-05,
+ "loss": 0.4499,
"step": 915
},
{
- "epoch": 18.53,
- "learning_rate": 8.316326530612245e-05,
- "loss": 1.0626,
+ "epoch": 10.35,
+ "learning_rate": 6.988636363636364e-05,
+ "loss": 0.4354,
"step": 916
},
{
- "epoch": 18.55,
- "learning_rate": 8.30357142857143e-05,
- "loss": 1.0518,
+ "epoch": 10.36,
+ "learning_rate": 6.974431818181818e-05,
+ "loss": 0.454,
"step": 917
},
{
- "epoch": 18.57,
- "learning_rate": 8.290816326530613e-05,
- "loss": 1.0557,
+ "epoch": 10.37,
+ "learning_rate": 6.960227272727273e-05,
+ "loss": 0.4473,
"step": 918
},
{
- "epoch": 18.6,
- "learning_rate": 8.278061224489796e-05,
- "loss": 1.0831,
+ "epoch": 10.38,
+ "learning_rate": 6.946022727272728e-05,
+ "loss": 0.4347,
"step": 919
},
{
- "epoch": 18.62,
- "learning_rate": 8.26530612244898e-05,
- "loss": 1.0307,
+ "epoch": 10.39,
+ "learning_rate": 6.931818181818182e-05,
+ "loss": 0.441,
"step": 920
},
{
- "epoch": 18.64,
- "learning_rate": 8.252551020408163e-05,
- "loss": 1.0455,
+ "epoch": 10.4,
+ "learning_rate": 6.917613636363637e-05,
+ "loss": 0.4545,
"step": 921
},
{
- "epoch": 18.66,
- "learning_rate": 8.239795918367348e-05,
- "loss": 1.0667,
+ "epoch": 10.42,
+ "learning_rate": 6.903409090909091e-05,
+ "loss": 0.458,
"step": 922
},
{
- "epoch": 18.68,
- "learning_rate": 8.227040816326531e-05,
- "loss": 1.0736,
+ "epoch": 10.43,
+ "learning_rate": 6.889204545454546e-05,
+ "loss": 0.4381,
"step": 923
},
{
- "epoch": 18.7,
- "learning_rate": 8.214285714285714e-05,
- "loss": 1.0108,
+ "epoch": 10.44,
+ "learning_rate": 6.875e-05,
+ "loss": 0.441,
"step": 924
},
{
- "epoch": 18.72,
- "learning_rate": 8.201530612244898e-05,
- "loss": 1.0458,
+ "epoch": 10.45,
+ "learning_rate": 6.860795454545455e-05,
+ "loss": 0.4446,
"step": 925
},
{
- "epoch": 18.74,
- "learning_rate": 8.188775510204081e-05,
- "loss": 1.0852,
+ "epoch": 10.46,
+ "learning_rate": 6.84659090909091e-05,
+ "loss": 0.4548,
"step": 926
},
{
- "epoch": 18.76,
- "learning_rate": 8.176020408163265e-05,
- "loss": 1.1207,
+ "epoch": 10.47,
+ "learning_rate": 6.832386363636364e-05,
+ "loss": 0.4404,
"step": 927
},
{
- "epoch": 18.78,
- "learning_rate": 8.163265306122449e-05,
- "loss": 1.0914,
+ "epoch": 10.48,
+ "learning_rate": 6.818181818181818e-05,
+ "loss": 0.4446,
"step": 928
},
{
- "epoch": 18.8,
- "learning_rate": 8.150510204081633e-05,
- "loss": 1.1108,
+ "epoch": 10.5,
+ "learning_rate": 6.803977272727273e-05,
+ "loss": 0.4434,
"step": 929
},
{
- "epoch": 18.82,
- "learning_rate": 8.137755102040817e-05,
- "loss": 1.1394,
+ "epoch": 10.51,
+ "learning_rate": 6.789772727272727e-05,
+ "loss": 0.4778,
"step": 930
},
{
- "epoch": 18.84,
- "learning_rate": 8.125000000000001e-05,
- "loss": 1.029,
+ "epoch": 10.52,
+ "learning_rate": 6.775568181818182e-05,
+ "loss": 0.4356,
"step": 931
},
{
- "epoch": 18.86,
- "learning_rate": 8.112244897959184e-05,
- "loss": 1.0661,
+ "epoch": 10.53,
+ "learning_rate": 6.761363636363636e-05,
+ "loss": 0.4464,
"step": 932
},
{
- "epoch": 18.88,
- "learning_rate": 8.099489795918369e-05,
- "loss": 1.0303,
+ "epoch": 10.54,
+ "learning_rate": 6.747159090909091e-05,
+ "loss": 0.4387,
"step": 933
},
{
- "epoch": 18.9,
- "learning_rate": 8.086734693877552e-05,
- "loss": 1.1144,
+ "epoch": 10.55,
+ "learning_rate": 6.732954545454547e-05,
+ "loss": 0.456,
"step": 934
},
{
- "epoch": 18.92,
- "learning_rate": 8.073979591836736e-05,
- "loss": 1.1096,
+ "epoch": 10.56,
+ "learning_rate": 6.71875e-05,
+ "loss": 0.453,
"step": 935
},
{
- "epoch": 18.94,
- "learning_rate": 8.061224489795919e-05,
- "loss": 1.123,
+ "epoch": 10.57,
+ "learning_rate": 6.704545454545455e-05,
+ "loss": 0.4611,
"step": 936
},
{
- "epoch": 18.96,
- "learning_rate": 8.048469387755102e-05,
- "loss": 1.1002,
+ "epoch": 10.59,
+ "learning_rate": 6.69034090909091e-05,
+ "loss": 0.4354,
"step": 937
},
{
- "epoch": 18.98,
- "learning_rate": 8.035714285714287e-05,
- "loss": 1.1016,
+ "epoch": 10.6,
+ "learning_rate": 6.676136363636364e-05,
+ "loss": 0.4519,
"step": 938
},
{
- "epoch": 19.0,
- "learning_rate": 8.02295918367347e-05,
- "loss": 1.0847,
+ "epoch": 10.61,
+ "learning_rate": 6.661931818181818e-05,
+ "loss": 0.4435,
"step": 939
},
{
- "epoch": 19.02,
- "learning_rate": 8.010204081632653e-05,
- "loss": 1.1029,
+ "epoch": 10.62,
+ "learning_rate": 6.647727272727274e-05,
+ "loss": 0.4422,
"step": 940
},
{
- "epoch": 19.04,
- "learning_rate": 7.997448979591837e-05,
- "loss": 1.041,
+ "epoch": 10.63,
+ "learning_rate": 6.633522727272727e-05,
+ "loss": 0.4344,
"step": 941
},
{
- "epoch": 19.06,
- "learning_rate": 7.98469387755102e-05,
- "loss": 1.01,
+ "epoch": 10.64,
+ "learning_rate": 6.619318181818183e-05,
+ "loss": 0.4419,
"step": 942
},
{
- "epoch": 19.08,
- "learning_rate": 7.971938775510205e-05,
- "loss": 1.0197,
+ "epoch": 10.65,
+ "learning_rate": 6.605113636363637e-05,
+ "loss": 0.4308,
"step": 943
},
{
- "epoch": 19.1,
- "learning_rate": 7.959183673469388e-05,
- "loss": 1.0543,
+ "epoch": 10.66,
+ "learning_rate": 6.59090909090909e-05,
+ "loss": 0.4043,
"step": 944
},
{
- "epoch": 19.12,
- "learning_rate": 7.946428571428571e-05,
- "loss": 1.0369,
+ "epoch": 10.68,
+ "learning_rate": 6.576704545454546e-05,
+ "loss": 0.4626,
"step": 945
},
{
- "epoch": 19.14,
- "learning_rate": 7.933673469387755e-05,
- "loss": 1.0154,
+ "epoch": 10.69,
+ "learning_rate": 6.562500000000001e-05,
+ "loss": 0.4365,
"step": 946
},
{
- "epoch": 19.16,
- "learning_rate": 7.920918367346939e-05,
- "loss": 0.9546,
+ "epoch": 10.7,
+ "learning_rate": 6.548295454545454e-05,
+ "loss": 0.4397,
"step": 947
},
{
- "epoch": 19.18,
- "learning_rate": 7.908163265306123e-05,
- "loss": 0.9982,
+ "epoch": 10.71,
+ "learning_rate": 6.53409090909091e-05,
+ "loss": 0.4463,
"step": 948
},
{
- "epoch": 19.2,
- "learning_rate": 7.895408163265306e-05,
- "loss": 1.0748,
+ "epoch": 10.72,
+ "learning_rate": 6.519886363636364e-05,
+ "loss": 0.4394,
"step": 949
},
{
- "epoch": 19.22,
- "learning_rate": 7.882653061224489e-05,
- "loss": 1.0562,
+ "epoch": 10.73,
+ "learning_rate": 6.505681818181818e-05,
+ "loss": 0.45,
"step": 950
},
{
- "epoch": 19.24,
- "learning_rate": 7.869897959183674e-05,
- "loss": 1.0352,
+ "epoch": 10.74,
+ "learning_rate": 6.491477272727273e-05,
+ "loss": 0.4363,
"step": 951
},
{
- "epoch": 19.26,
- "learning_rate": 7.857142857142858e-05,
- "loss": 0.9976,
+ "epoch": 10.76,
+ "learning_rate": 6.477272727272728e-05,
+ "loss": 0.4566,
"step": 952
},
{
- "epoch": 19.28,
- "learning_rate": 7.844387755102041e-05,
- "loss": 1.0221,
+ "epoch": 10.77,
+ "learning_rate": 6.463068181818183e-05,
+ "loss": 0.4235,
"step": 953
},
{
- "epoch": 19.3,
- "learning_rate": 7.831632653061226e-05,
- "loss": 1.0119,
+ "epoch": 10.78,
+ "learning_rate": 6.448863636363637e-05,
+ "loss": 0.4458,
"step": 954
},
{
- "epoch": 19.32,
- "learning_rate": 7.818877551020409e-05,
- "loss": 1.0657,
+ "epoch": 10.79,
+ "learning_rate": 6.434659090909092e-05,
+ "loss": 0.423,
"step": 955
},
{
- "epoch": 19.34,
- "learning_rate": 7.806122448979593e-05,
- "loss": 0.9591,
+ "epoch": 10.8,
+ "learning_rate": 6.420454545454546e-05,
+ "loss": 0.445,
"step": 956
},
{
- "epoch": 19.36,
- "learning_rate": 7.793367346938776e-05,
- "loss": 1.0101,
+ "epoch": 10.81,
+ "learning_rate": 6.40625e-05,
+ "loss": 0.424,
"step": 957
},
{
- "epoch": 19.38,
- "learning_rate": 7.780612244897959e-05,
- "loss": 1.0453,
+ "epoch": 10.82,
+ "learning_rate": 6.392045454545455e-05,
+ "loss": 0.4224,
"step": 958
},
{
- "epoch": 19.4,
- "learning_rate": 7.767857142857144e-05,
- "loss": 1.0461,
+ "epoch": 10.83,
+ "learning_rate": 6.37784090909091e-05,
+ "loss": 0.4223,
"step": 959
},
{
- "epoch": 19.42,
- "learning_rate": 7.755102040816327e-05,
- "loss": 1.0959,
+ "epoch": 10.85,
+ "learning_rate": 6.363636363636364e-05,
+ "loss": 0.4314,
"step": 960
},
{
- "epoch": 19.44,
- "learning_rate": 7.742346938775511e-05,
- "loss": 1.0608,
+ "epoch": 10.86,
+ "learning_rate": 6.349431818181819e-05,
+ "loss": 0.4488,
"step": 961
},
{
- "epoch": 19.47,
- "learning_rate": 7.729591836734694e-05,
- "loss": 1.1177,
+ "epoch": 10.87,
+ "learning_rate": 6.335227272727273e-05,
+ "loss": 0.423,
"step": 962
},
{
- "epoch": 19.49,
- "learning_rate": 7.716836734693877e-05,
- "loss": 1.0354,
+ "epoch": 10.88,
+ "learning_rate": 6.321022727272728e-05,
+ "loss": 0.4416,
"step": 963
},
{
- "epoch": 19.51,
- "learning_rate": 7.704081632653062e-05,
- "loss": 1.0507,
+ "epoch": 10.89,
+ "learning_rate": 6.306818181818182e-05,
+ "loss": 0.423,
"step": 964
},
{
- "epoch": 19.53,
- "learning_rate": 7.691326530612245e-05,
- "loss": 1.0313,
+ "epoch": 10.9,
+ "learning_rate": 6.292613636363637e-05,
+ "loss": 0.4502,
"step": 965
},
{
- "epoch": 19.55,
- "learning_rate": 7.67857142857143e-05,
- "loss": 1.0569,
+ "epoch": 10.91,
+ "learning_rate": 6.278409090909091e-05,
+ "loss": 0.4266,
"step": 966
},
{
- "epoch": 19.57,
- "learning_rate": 7.665816326530612e-05,
- "loss": 1.0862,
+ "epoch": 10.92,
+ "learning_rate": 6.264204545454546e-05,
+ "loss": 0.4344,
"step": 967
},
{
- "epoch": 19.59,
- "learning_rate": 7.653061224489796e-05,
- "loss": 1.0593,
+ "epoch": 10.94,
+ "learning_rate": 6.25e-05,
+ "loss": 0.434,
"step": 968
},
{
- "epoch": 19.61,
- "learning_rate": 7.64030612244898e-05,
- "loss": 1.0602,
+ "epoch": 10.95,
+ "learning_rate": 6.235795454545455e-05,
+ "loss": 0.4269,
"step": 969
},
{
- "epoch": 19.63,
- "learning_rate": 7.627551020408163e-05,
- "loss": 1.0048,
+ "epoch": 10.96,
+ "learning_rate": 6.221590909090909e-05,
+ "loss": 0.4158,
"step": 970
},
{
- "epoch": 19.65,
- "learning_rate": 7.614795918367347e-05,
- "loss": 1.0346,
+ "epoch": 10.97,
+ "learning_rate": 6.207386363636364e-05,
+ "loss": 0.4231,
"step": 971
},
{
- "epoch": 19.67,
- "learning_rate": 7.60204081632653e-05,
- "loss": 1.0172,
+ "epoch": 10.98,
+ "learning_rate": 6.193181818181818e-05,
+ "loss": 0.4235,
"step": 972
},
{
- "epoch": 19.69,
- "learning_rate": 7.589285714285714e-05,
- "loss": 1.02,
+ "epoch": 10.99,
+ "learning_rate": 6.178977272727273e-05,
+ "loss": 0.4504,
"step": 973
},
{
- "epoch": 19.71,
- "learning_rate": 7.576530612244898e-05,
- "loss": 1.0028,
+ "epoch": 11.0,
+ "learning_rate": 6.164772727272727e-05,
+ "loss": 0.4394,
"step": 974
},
{
- "epoch": 19.73,
- "learning_rate": 7.563775510204083e-05,
- "loss": 1.08,
+ "epoch": 11.02,
+ "learning_rate": 6.150568181818183e-05,
+ "loss": 0.4333,
"step": 975
},
{
- "epoch": 19.75,
- "learning_rate": 7.551020408163266e-05,
- "loss": 1.0402,
+ "epoch": 11.03,
+ "learning_rate": 6.136363636363636e-05,
+ "loss": 0.3936,
"step": 976
},
{
- "epoch": 19.77,
- "learning_rate": 7.53826530612245e-05,
- "loss": 1.0567,
+ "epoch": 11.04,
+ "learning_rate": 6.122159090909091e-05,
+ "loss": 0.3933,
"step": 977
},
{
- "epoch": 19.79,
- "learning_rate": 7.525510204081633e-05,
- "loss": 1.0169,
+ "epoch": 11.05,
+ "learning_rate": 6.107954545454547e-05,
+ "loss": 0.4161,
"step": 978
},
{
- "epoch": 19.81,
- "learning_rate": 7.512755102040818e-05,
- "loss": 0.9881,
+ "epoch": 11.06,
+ "learning_rate": 6.0937500000000004e-05,
+ "loss": 0.4097,
"step": 979
},
{
- "epoch": 19.83,
- "learning_rate": 7.500000000000001e-05,
- "loss": 1.0677,
+ "epoch": 11.07,
+ "learning_rate": 6.079545454545454e-05,
+ "loss": 0.412,
"step": 980
},
{
- "epoch": 19.85,
- "learning_rate": 7.487244897959184e-05,
- "loss": 1.1026,
+ "epoch": 11.08,
+ "learning_rate": 6.0653409090909094e-05,
+ "loss": 0.4104,
"step": 981
},
{
- "epoch": 19.87,
- "learning_rate": 7.474489795918368e-05,
- "loss": 1.0101,
+ "epoch": 11.09,
+ "learning_rate": 6.051136363636364e-05,
+ "loss": 0.4152,
"step": 982
},
{
- "epoch": 19.89,
- "learning_rate": 7.461734693877551e-05,
- "loss": 1.069,
+ "epoch": 11.11,
+ "learning_rate": 6.036931818181818e-05,
+ "loss": 0.4037,
"step": 983
},
{
- "epoch": 19.91,
- "learning_rate": 7.448979591836736e-05,
- "loss": 1.0493,
+ "epoch": 11.12,
+ "learning_rate": 6.022727272727273e-05,
+ "loss": 0.413,
"step": 984
},
{
- "epoch": 19.93,
- "learning_rate": 7.436224489795919e-05,
- "loss": 1.0858,
+ "epoch": 11.13,
+ "learning_rate": 6.0085227272727274e-05,
+ "loss": 0.4413,
"step": 985
},
{
- "epoch": 19.95,
- "learning_rate": 7.423469387755102e-05,
- "loss": 1.0734,
+ "epoch": 11.14,
+ "learning_rate": 5.9943181818181826e-05,
+ "loss": 0.3908,
"step": 986
},
{
- "epoch": 19.97,
- "learning_rate": 7.410714285714286e-05,
- "loss": 1.0203,
+ "epoch": 11.15,
+ "learning_rate": 5.9801136363636365e-05,
+ "loss": 0.3982,
"step": 987
},
{
- "epoch": 19.99,
- "learning_rate": 7.39795918367347e-05,
- "loss": 1.0285,
+ "epoch": 11.16,
+ "learning_rate": 5.965909090909091e-05,
+ "loss": 0.4109,
"step": 988
},
{
- "epoch": 20.01,
- "learning_rate": 7.385204081632653e-05,
- "loss": 0.9446,
+ "epoch": 11.17,
+ "learning_rate": 5.951704545454546e-05,
+ "loss": 0.3923,
"step": 989
},
{
- "epoch": 20.03,
- "learning_rate": 7.372448979591837e-05,
- "loss": 0.9915,
+ "epoch": 11.18,
+ "learning_rate": 5.9375e-05,
+ "loss": 0.4107,
"step": 990
},
{
- "epoch": 20.05,
- "learning_rate": 7.35969387755102e-05,
- "loss": 0.9882,
+ "epoch": 11.2,
+ "learning_rate": 5.9232954545454545e-05,
+ "loss": 0.4099,
"step": 991
},
{
- "epoch": 20.07,
- "learning_rate": 7.346938775510205e-05,
- "loss": 0.9338,
+ "epoch": 11.21,
+ "learning_rate": 5.90909090909091e-05,
+ "loss": 0.4163,
"step": 992
},
{
- "epoch": 20.09,
- "learning_rate": 7.334183673469388e-05,
- "loss": 0.942,
+ "epoch": 11.22,
+ "learning_rate": 5.8948863636363635e-05,
+ "loss": 0.4189,
"step": 993
},
{
- "epoch": 20.11,
- "learning_rate": 7.321428571428571e-05,
- "loss": 0.9725,
+ "epoch": 11.23,
+ "learning_rate": 5.880681818181818e-05,
+ "loss": 0.3889,
"step": 994
},
{
- "epoch": 20.13,
- "learning_rate": 7.308673469387755e-05,
- "loss": 1.027,
+ "epoch": 11.24,
+ "learning_rate": 5.866477272727273e-05,
+ "loss": 0.3988,
"step": 995
},
{
- "epoch": 20.15,
- "learning_rate": 7.29591836734694e-05,
- "loss": 1.0081,
+ "epoch": 11.25,
+ "learning_rate": 5.852272727272727e-05,
+ "loss": 0.4215,
"step": 996
},
{
- "epoch": 20.17,
- "learning_rate": 7.283163265306123e-05,
- "loss": 1.0117,
+ "epoch": 11.26,
+ "learning_rate": 5.838068181818183e-05,
+ "loss": 0.4207,
"step": 997
},
{
- "epoch": 20.19,
- "learning_rate": 7.270408163265307e-05,
- "loss": 0.969,
+ "epoch": 11.27,
+ "learning_rate": 5.823863636363637e-05,
+ "loss": 0.413,
"step": 998
},
{
- "epoch": 20.21,
- "learning_rate": 7.25765306122449e-05,
- "loss": 1.0024,
+ "epoch": 11.29,
+ "learning_rate": 5.8096590909090906e-05,
+ "loss": 0.4057,
"step": 999
},
{
- "epoch": 20.23,
- "learning_rate": 7.244897959183675e-05,
- "loss": 0.994,
+ "epoch": 11.3,
+ "learning_rate": 5.7954545454545464e-05,
+ "loss": 0.3939,
"step": 1000
},
{
- "epoch": 20.25,
- "learning_rate": 7.232142857142858e-05,
- "loss": 1.0248,
+ "epoch": 11.31,
+ "learning_rate": 5.78125e-05,
+ "loss": 0.4199,
"step": 1001
},
{
- "epoch": 20.27,
- "learning_rate": 7.219387755102042e-05,
- "loss": 1.0493,
+ "epoch": 11.32,
+ "learning_rate": 5.767045454545454e-05,
+ "loss": 0.4076,
"step": 1002
},
{
- "epoch": 20.29,
- "learning_rate": 7.206632653061225e-05,
- "loss": 1.0011,
+ "epoch": 11.33,
+ "learning_rate": 5.75284090909091e-05,
+ "loss": 0.4079,
"step": 1003
},
{
- "epoch": 20.31,
- "learning_rate": 7.193877551020408e-05,
- "loss": 0.9874,
+ "epoch": 11.34,
+ "learning_rate": 5.738636363636364e-05,
+ "loss": 0.4002,
"step": 1004
},
{
- "epoch": 20.34,
- "learning_rate": 7.181122448979593e-05,
- "loss": 1.0049,
+ "epoch": 11.35,
+ "learning_rate": 5.724431818181818e-05,
+ "loss": 0.3801,
"step": 1005
},
{
- "epoch": 20.36,
- "learning_rate": 7.168367346938776e-05,
- "loss": 1.0314,
+ "epoch": 11.37,
+ "learning_rate": 5.7102272727272735e-05,
+ "loss": 0.3939,
"step": 1006
},
{
- "epoch": 20.38,
- "learning_rate": 7.155612244897959e-05,
- "loss": 0.9742,
+ "epoch": 11.38,
+ "learning_rate": 5.696022727272727e-05,
+ "loss": 0.3904,
"step": 1007
},
{
- "epoch": 20.4,
- "learning_rate": 7.142857142857143e-05,
- "loss": 1.0621,
+ "epoch": 11.39,
+ "learning_rate": 5.6818181818181825e-05,
+ "loss": 0.406,
"step": 1008
},
{
- "epoch": 20.42,
- "learning_rate": 7.130102040816326e-05,
- "loss": 0.9672,
+ "epoch": 11.4,
+ "learning_rate": 5.667613636363637e-05,
+ "loss": 0.4185,
"step": 1009
},
{
- "epoch": 20.44,
- "learning_rate": 7.117346938775511e-05,
- "loss": 1.0018,
+ "epoch": 11.41,
+ "learning_rate": 5.653409090909091e-05,
+ "loss": 0.3976,
"step": 1010
},
{
- "epoch": 20.46,
- "learning_rate": 7.104591836734694e-05,
- "loss": 1.0045,
+ "epoch": 11.42,
+ "learning_rate": 5.639204545454546e-05,
+ "loss": 0.3907,
"step": 1011
},
{
- "epoch": 20.48,
- "learning_rate": 7.091836734693877e-05,
- "loss": 0.9675,
+ "epoch": 11.43,
+ "learning_rate": 5.6250000000000005e-05,
+ "loss": 0.4065,
"step": 1012
},
{
- "epoch": 20.5,
- "learning_rate": 7.079081632653062e-05,
- "loss": 0.976,
+ "epoch": 11.44,
+ "learning_rate": 5.6107954545454544e-05,
+ "loss": 0.4069,
"step": 1013
},
{
- "epoch": 20.52,
- "learning_rate": 7.066326530612245e-05,
- "loss": 1.0523,
+ "epoch": 11.46,
+ "learning_rate": 5.5965909090909095e-05,
+ "loss": 0.3964,
"step": 1014
},
{
- "epoch": 20.54,
- "learning_rate": 7.053571428571429e-05,
- "loss": 1.052,
+ "epoch": 11.47,
+ "learning_rate": 5.582386363636364e-05,
+ "loss": 0.3912,
"step": 1015
},
{
- "epoch": 20.56,
- "learning_rate": 7.040816326530612e-05,
- "loss": 0.9903,
+ "epoch": 11.48,
+ "learning_rate": 5.568181818181818e-05,
+ "loss": 0.3944,
"step": 1016
},
{
- "epoch": 20.58,
- "learning_rate": 7.028061224489795e-05,
- "loss": 1.0337,
+ "epoch": 11.49,
+ "learning_rate": 5.553977272727273e-05,
+ "loss": 0.4197,
"step": 1017
},
{
- "epoch": 20.6,
- "learning_rate": 7.01530612244898e-05,
- "loss": 1.1122,
+ "epoch": 11.5,
+ "learning_rate": 5.5397727272727276e-05,
+ "loss": 0.4064,
"step": 1018
},
{
- "epoch": 20.62,
- "learning_rate": 7.002551020408164e-05,
- "loss": 1.0133,
+ "epoch": 11.51,
+ "learning_rate": 5.525568181818183e-05,
+ "loss": 0.4054,
"step": 1019
},
{
- "epoch": 20.64,
- "learning_rate": 6.989795918367347e-05,
- "loss": 0.9588,
+ "epoch": 11.52,
+ "learning_rate": 5.5113636363636366e-05,
+ "loss": 0.4128,
"step": 1020
},
{
- "epoch": 20.66,
- "learning_rate": 6.977040816326532e-05,
- "loss": 0.9892,
+ "epoch": 11.53,
+ "learning_rate": 5.497159090909091e-05,
+ "loss": 0.3976,
"step": 1021
},
{
- "epoch": 20.68,
- "learning_rate": 6.964285714285715e-05,
- "loss": 1.025,
+ "epoch": 11.55,
+ "learning_rate": 5.482954545454546e-05,
+ "loss": 0.3863,
"step": 1022
},
{
- "epoch": 20.7,
- "learning_rate": 6.951530612244899e-05,
- "loss": 1.0196,
+ "epoch": 11.56,
+ "learning_rate": 5.46875e-05,
+ "loss": 0.3994,
"step": 1023
},
{
- "epoch": 20.72,
- "learning_rate": 6.938775510204082e-05,
- "loss": 1.0146,
+ "epoch": 11.57,
+ "learning_rate": 5.4545454545454546e-05,
+ "loss": 0.401,
"step": 1024
},
{
- "epoch": 20.74,
- "learning_rate": 6.926020408163265e-05,
- "loss": 1.0656,
+ "epoch": 11.58,
+ "learning_rate": 5.44034090909091e-05,
+ "loss": 0.3948,
"step": 1025
},
{
- "epoch": 20.76,
- "learning_rate": 6.91326530612245e-05,
- "loss": 0.9584,
+ "epoch": 11.59,
+ "learning_rate": 5.4261363636363636e-05,
+ "loss": 0.3967,
"step": 1026
},
{
- "epoch": 20.78,
- "learning_rate": 6.900510204081633e-05,
- "loss": 0.9877,
+ "epoch": 11.6,
+ "learning_rate": 5.411931818181818e-05,
+ "loss": 0.413,
"step": 1027
},
{
- "epoch": 20.8,
- "learning_rate": 6.887755102040817e-05,
- "loss": 1.0607,
+ "epoch": 11.61,
+ "learning_rate": 5.397727272727273e-05,
+ "loss": 0.4032,
"step": 1028
},
{
- "epoch": 20.82,
- "learning_rate": 6.875e-05,
- "loss": 0.9969,
+ "epoch": 11.63,
+ "learning_rate": 5.383522727272727e-05,
+ "loss": 0.3905,
"step": 1029
},
{
- "epoch": 20.84,
- "learning_rate": 6.862244897959184e-05,
- "loss": 0.9506,
+ "epoch": 11.64,
+ "learning_rate": 5.3693181818181823e-05,
+ "loss": 0.4041,
"step": 1030
},
{
- "epoch": 20.86,
- "learning_rate": 6.849489795918368e-05,
- "loss": 1.0576,
+ "epoch": 11.65,
+ "learning_rate": 5.355113636363637e-05,
+ "loss": 0.392,
"step": 1031
},
{
- "epoch": 20.88,
- "learning_rate": 6.836734693877551e-05,
- "loss": 1.0094,
+ "epoch": 11.66,
+ "learning_rate": 5.340909090909091e-05,
+ "loss": 0.3942,
"step": 1032
},
{
- "epoch": 20.9,
- "learning_rate": 6.823979591836735e-05,
- "loss": 0.9872,
+ "epoch": 11.67,
+ "learning_rate": 5.326704545454546e-05,
+ "loss": 0.3946,
"step": 1033
},
{
- "epoch": 20.92,
- "learning_rate": 6.811224489795919e-05,
- "loss": 1.0544,
+ "epoch": 11.68,
+ "learning_rate": 5.3125000000000004e-05,
+ "loss": 0.3989,
"step": 1034
},
{
- "epoch": 20.94,
- "learning_rate": 6.798469387755102e-05,
- "loss": 1.0194,
+ "epoch": 11.69,
+ "learning_rate": 5.298295454545454e-05,
+ "loss": 0.4101,
"step": 1035
},
{
- "epoch": 20.96,
- "learning_rate": 6.785714285714286e-05,
- "loss": 1.0009,
+ "epoch": 11.7,
+ "learning_rate": 5.2840909090909094e-05,
+ "loss": 0.4033,
"step": 1036
},
{
- "epoch": 20.98,
- "learning_rate": 6.772959183673469e-05,
- "loss": 0.9727,
+ "epoch": 11.72,
+ "learning_rate": 5.269886363636364e-05,
+ "loss": 0.3937,
"step": 1037
},
{
- "epoch": 21.0,
- "learning_rate": 6.760204081632652e-05,
- "loss": 0.9754,
+ "epoch": 11.73,
+ "learning_rate": 5.255681818181818e-05,
+ "loss": 0.3873,
"step": 1038
},
{
- "epoch": 21.02,
- "learning_rate": 6.747448979591837e-05,
- "loss": 0.9953,
+ "epoch": 11.74,
+ "learning_rate": 5.241477272727273e-05,
+ "loss": 0.3922,
"step": 1039
},
{
- "epoch": 21.04,
- "learning_rate": 6.73469387755102e-05,
- "loss": 0.9307,
+ "epoch": 11.75,
+ "learning_rate": 5.2272727272727274e-05,
+ "loss": 0.4016,
"step": 1040
},
{
- "epoch": 21.06,
- "learning_rate": 6.721938775510204e-05,
- "loss": 0.9151,
+ "epoch": 11.76,
+ "learning_rate": 5.2130681818181826e-05,
+ "loss": 0.3892,
"step": 1041
},
{
- "epoch": 21.08,
- "learning_rate": 6.709183673469389e-05,
- "loss": 0.9474,
+ "epoch": 11.77,
+ "learning_rate": 5.1988636363636364e-05,
+ "loss": 0.3974,
"step": 1042
},
{
- "epoch": 21.1,
- "learning_rate": 6.696428571428572e-05,
- "loss": 0.9697,
+ "epoch": 11.78,
+ "learning_rate": 5.184659090909091e-05,
+ "loss": 0.4024,
"step": 1043
},
{
- "epoch": 21.12,
- "learning_rate": 6.683673469387756e-05,
- "loss": 0.9423,
+ "epoch": 11.79,
+ "learning_rate": 5.170454545454546e-05,
+ "loss": 0.3889,
"step": 1044
},
{
- "epoch": 21.14,
- "learning_rate": 6.670918367346939e-05,
- "loss": 0.9797,
+ "epoch": 11.81,
+ "learning_rate": 5.15625e-05,
+ "loss": 0.4097,
"step": 1045
},
{
- "epoch": 21.16,
- "learning_rate": 6.658163265306124e-05,
- "loss": 0.919,
+ "epoch": 11.82,
+ "learning_rate": 5.1420454545454545e-05,
+ "loss": 0.4047,
"step": 1046
},
{
- "epoch": 21.18,
- "learning_rate": 6.645408163265307e-05,
- "loss": 0.9743,
+ "epoch": 11.83,
+ "learning_rate": 5.12784090909091e-05,
+ "loss": 0.4033,
"step": 1047
},
{
- "epoch": 21.21,
- "learning_rate": 6.63265306122449e-05,
- "loss": 0.9575,
+ "epoch": 11.84,
+ "learning_rate": 5.1136363636363635e-05,
+ "loss": 0.3774,
"step": 1048
},
{
- "epoch": 21.23,
- "learning_rate": 6.619897959183674e-05,
- "loss": 0.9861,
+ "epoch": 11.85,
+ "learning_rate": 5.099431818181818e-05,
+ "loss": 0.405,
"step": 1049
},
{
- "epoch": 21.25,
- "learning_rate": 6.607142857142857e-05,
- "loss": 0.9103,
+ "epoch": 11.86,
+ "learning_rate": 5.085227272727273e-05,
+ "loss": 0.3996,
"step": 1050
},
{
- "epoch": 21.27,
- "learning_rate": 6.594387755102042e-05,
- "loss": 0.993,
+ "epoch": 11.87,
+ "learning_rate": 5.071022727272727e-05,
+ "loss": 0.3885,
"step": 1051
},
{
- "epoch": 21.29,
- "learning_rate": 6.581632653061225e-05,
- "loss": 0.9668,
+ "epoch": 11.88,
+ "learning_rate": 5.056818181818183e-05,
+ "loss": 0.3914,
"step": 1052
},
{
- "epoch": 21.31,
- "learning_rate": 6.568877551020408e-05,
- "loss": 1.0008,
+ "epoch": 11.9,
+ "learning_rate": 5.042613636363637e-05,
+ "loss": 0.3908,
"step": 1053
},
{
- "epoch": 21.33,
- "learning_rate": 6.556122448979592e-05,
- "loss": 0.9825,
+ "epoch": 11.91,
+ "learning_rate": 5.0284090909090905e-05,
+ "loss": 0.3921,
"step": 1054
},
{
- "epoch": 21.35,
- "learning_rate": 6.543367346938776e-05,
- "loss": 1.0174,
+ "epoch": 11.92,
+ "learning_rate": 5.0142045454545464e-05,
+ "loss": 0.4077,
"step": 1055
},
{
- "epoch": 21.37,
- "learning_rate": 6.530612244897959e-05,
- "loss": 0.9685,
+ "epoch": 11.93,
+ "learning_rate": 5e-05,
+ "loss": 0.3973,
"step": 1056
},
{
- "epoch": 21.39,
- "learning_rate": 6.517857142857143e-05,
- "loss": 0.9265,
+ "epoch": 11.94,
+ "learning_rate": 4.985795454545455e-05,
+ "loss": 0.3986,
"step": 1057
},
{
- "epoch": 21.41,
- "learning_rate": 6.505102040816326e-05,
- "loss": 0.9495,
+ "epoch": 11.95,
+ "learning_rate": 4.971590909090909e-05,
+ "loss": 0.3938,
"step": 1058
},
{
- "epoch": 21.43,
- "learning_rate": 6.49234693877551e-05,
- "loss": 0.9541,
+ "epoch": 11.96,
+ "learning_rate": 4.957386363636364e-05,
+ "loss": 0.3897,
"step": 1059
},
{
- "epoch": 21.45,
- "learning_rate": 6.479591836734694e-05,
- "loss": 0.9299,
+ "epoch": 11.98,
+ "learning_rate": 4.943181818181818e-05,
+ "loss": 0.3965,
"step": 1060
},
{
- "epoch": 21.47,
- "learning_rate": 6.466836734693877e-05,
- "loss": 0.9625,
+ "epoch": 11.99,
+ "learning_rate": 4.9289772727272735e-05,
+ "loss": 0.3999,
"step": 1061
},
{
- "epoch": 21.49,
- "learning_rate": 6.454081632653061e-05,
- "loss": 1.0054,
+ "epoch": 12.0,
+ "learning_rate": 4.914772727272727e-05,
+ "loss": 0.3814,
"step": 1062
},
{
- "epoch": 21.51,
- "learning_rate": 6.441326530612244e-05,
- "loss": 0.9893,
+ "epoch": 12.01,
+ "learning_rate": 4.900568181818182e-05,
+ "loss": 0.3879,
"step": 1063
},
{
- "epoch": 21.53,
- "learning_rate": 6.428571428571429e-05,
- "loss": 0.9906,
+ "epoch": 12.02,
+ "learning_rate": 4.886363636363637e-05,
+ "loss": 0.3768,
"step": 1064
},
{
- "epoch": 21.55,
- "learning_rate": 6.415816326530613e-05,
- "loss": 0.9487,
+ "epoch": 12.03,
+ "learning_rate": 4.8721590909090915e-05,
+ "loss": 0.3813,
"step": 1065
},
{
- "epoch": 21.57,
- "learning_rate": 6.403061224489796e-05,
- "loss": 0.9728,
+ "epoch": 12.04,
+ "learning_rate": 4.857954545454545e-05,
+ "loss": 0.3759,
"step": 1066
},
{
- "epoch": 21.59,
- "learning_rate": 6.390306122448981e-05,
- "loss": 0.9883,
+ "epoch": 12.05,
+ "learning_rate": 4.8437500000000005e-05,
+ "loss": 0.3817,
"step": 1067
},
{
- "epoch": 21.61,
- "learning_rate": 6.377551020408164e-05,
- "loss": 1.053,
+ "epoch": 12.07,
+ "learning_rate": 4.829545454545455e-05,
+ "loss": 0.3773,
"step": 1068
},
{
- "epoch": 21.63,
- "learning_rate": 6.364795918367348e-05,
- "loss": 1.012,
+ "epoch": 12.08,
+ "learning_rate": 4.815340909090909e-05,
+ "loss": 0.3807,
"step": 1069
},
{
- "epoch": 21.65,
- "learning_rate": 6.352040816326531e-05,
- "loss": 0.962,
+ "epoch": 12.09,
+ "learning_rate": 4.801136363636364e-05,
+ "loss": 0.3757,
"step": 1070
},
{
- "epoch": 21.67,
- "learning_rate": 6.339285714285714e-05,
- "loss": 0.9955,
+ "epoch": 12.1,
+ "learning_rate": 4.7869318181818185e-05,
+ "loss": 0.3819,
"step": 1071
},
{
- "epoch": 21.69,
- "learning_rate": 6.326530612244899e-05,
- "loss": 0.9908,
+ "epoch": 12.11,
+ "learning_rate": 4.772727272727273e-05,
+ "loss": 0.3731,
"step": 1072
},
{
- "epoch": 21.71,
- "learning_rate": 6.313775510204082e-05,
- "loss": 1.0327,
+ "epoch": 12.12,
+ "learning_rate": 4.7585227272727276e-05,
+ "loss": 0.3706,
"step": 1073
},
{
- "epoch": 21.73,
- "learning_rate": 6.301020408163265e-05,
- "loss": 0.9255,
+ "epoch": 12.13,
+ "learning_rate": 4.744318181818182e-05,
+ "loss": 0.3762,
"step": 1074
},
{
- "epoch": 21.75,
- "learning_rate": 6.28826530612245e-05,
- "loss": 0.9268,
+ "epoch": 12.14,
+ "learning_rate": 4.7301136363636366e-05,
+ "loss": 0.3749,
"step": 1075
},
{
- "epoch": 21.77,
- "learning_rate": 6.275510204081633e-05,
- "loss": 0.9204,
+ "epoch": 12.16,
+ "learning_rate": 4.715909090909091e-05,
+ "loss": 0.3884,
"step": 1076
},
{
- "epoch": 21.79,
- "learning_rate": 6.262755102040817e-05,
- "loss": 0.9838,
+ "epoch": 12.17,
+ "learning_rate": 4.7017045454545456e-05,
+ "loss": 0.373,
"step": 1077
},
{
- "epoch": 21.81,
- "learning_rate": 6.25e-05,
- "loss": 0.954,
+ "epoch": 12.18,
+ "learning_rate": 4.6875e-05,
+ "loss": 0.374,
"step": 1078
},
{
- "epoch": 21.83,
- "learning_rate": 6.237244897959183e-05,
- "loss": 1.0102,
+ "epoch": 12.19,
+ "learning_rate": 4.6732954545454546e-05,
+ "loss": 0.3813,
"step": 1079
},
{
- "epoch": 21.85,
- "learning_rate": 6.224489795918368e-05,
- "loss": 0.916,
+ "epoch": 12.2,
+ "learning_rate": 4.659090909090909e-05,
+ "loss": 0.3745,
"step": 1080
},
{
- "epoch": 21.87,
- "learning_rate": 6.211734693877551e-05,
- "loss": 0.9939,
+ "epoch": 12.21,
+ "learning_rate": 4.6448863636363636e-05,
+ "loss": 0.3646,
"step": 1081
},
{
- "epoch": 21.89,
- "learning_rate": 6.198979591836735e-05,
- "loss": 0.9675,
+ "epoch": 12.22,
+ "learning_rate": 4.630681818181818e-05,
+ "loss": 0.3729,
"step": 1082
},
{
- "epoch": 21.91,
- "learning_rate": 6.186224489795918e-05,
- "loss": 0.9666,
+ "epoch": 12.24,
+ "learning_rate": 4.616477272727273e-05,
+ "loss": 0.3701,
"step": 1083
},
{
- "epoch": 21.93,
- "learning_rate": 6.173469387755101e-05,
- "loss": 0.9919,
+ "epoch": 12.25,
+ "learning_rate": 4.602272727272727e-05,
+ "loss": 0.3655,
"step": 1084
},
{
- "epoch": 21.95,
- "learning_rate": 6.160714285714286e-05,
- "loss": 1.0106,
+ "epoch": 12.26,
+ "learning_rate": 4.5880681818181817e-05,
+ "loss": 0.3758,
"step": 1085
},
{
- "epoch": 21.97,
- "learning_rate": 6.14795918367347e-05,
- "loss": 0.9982,
+ "epoch": 12.27,
+ "learning_rate": 4.573863636363637e-05,
+ "loss": 0.3682,
"step": 1086
},
{
- "epoch": 21.99,
- "learning_rate": 6.135204081632653e-05,
- "loss": 1.0137,
+ "epoch": 12.28,
+ "learning_rate": 4.5596590909090913e-05,
+ "loss": 0.3865,
"step": 1087
},
{
- "epoch": 22.01,
- "learning_rate": 6.122448979591838e-05,
- "loss": 0.9331,
+ "epoch": 12.29,
+ "learning_rate": 4.545454545454546e-05,
+ "loss": 0.363,
"step": 1088
},
{
- "epoch": 22.03,
- "learning_rate": 6.109693877551021e-05,
- "loss": 0.8834,
+ "epoch": 12.3,
+ "learning_rate": 4.5312500000000004e-05,
+ "loss": 0.3727,
"step": 1089
},
{
- "epoch": 22.06,
- "learning_rate": 6.0969387755102046e-05,
- "loss": 0.9757,
+ "epoch": 12.31,
+ "learning_rate": 4.517045454545455e-05,
+ "loss": 0.3827,
"step": 1090
},
{
- "epoch": 22.08,
- "learning_rate": 6.084183673469388e-05,
- "loss": 0.9038,
+ "epoch": 12.33,
+ "learning_rate": 4.5028409090909094e-05,
+ "loss": 0.3658,
"step": 1091
},
{
- "epoch": 22.1,
- "learning_rate": 6.0714285714285715e-05,
- "loss": 0.9097,
+ "epoch": 12.34,
+ "learning_rate": 4.488636363636364e-05,
+ "loss": 0.3844,
"step": 1092
},
{
- "epoch": 22.12,
- "learning_rate": 6.058673469387756e-05,
- "loss": 0.8972,
+ "epoch": 12.35,
+ "learning_rate": 4.4744318181818184e-05,
+ "loss": 0.3731,
"step": 1093
},
{
- "epoch": 22.14,
- "learning_rate": 6.045918367346939e-05,
- "loss": 0.8825,
+ "epoch": 12.36,
+ "learning_rate": 4.460227272727273e-05,
+ "loss": 0.3767,
"step": 1094
},
{
- "epoch": 22.16,
- "learning_rate": 6.0331632653061234e-05,
- "loss": 0.9814,
+ "epoch": 12.37,
+ "learning_rate": 4.4460227272727274e-05,
+ "loss": 0.3751,
"step": 1095
},
{
- "epoch": 22.18,
- "learning_rate": 6.0204081632653065e-05,
- "loss": 0.9874,
+ "epoch": 12.38,
+ "learning_rate": 4.431818181818182e-05,
+ "loss": 0.3718,
"step": 1096
},
{
- "epoch": 22.2,
- "learning_rate": 6.0076530612244896e-05,
- "loss": 0.912,
+ "epoch": 12.39,
+ "learning_rate": 4.4176136363636364e-05,
+ "loss": 0.3833,
"step": 1097
},
{
- "epoch": 22.22,
- "learning_rate": 5.994897959183674e-05,
- "loss": 0.9206,
+ "epoch": 12.4,
+ "learning_rate": 4.4034090909090916e-05,
+ "loss": 0.3673,
"step": 1098
},
{
- "epoch": 22.24,
- "learning_rate": 5.982142857142857e-05,
- "loss": 0.9497,
+ "epoch": 12.42,
+ "learning_rate": 4.3892045454545454e-05,
+ "loss": 0.3799,
"step": 1099
},
{
- "epoch": 22.26,
- "learning_rate": 5.9693877551020416e-05,
- "loss": 0.9269,
+ "epoch": 12.43,
+ "learning_rate": 4.375e-05,
+ "loss": 0.3661,
"step": 1100
},
{
- "epoch": 22.28,
- "learning_rate": 5.956632653061225e-05,
- "loss": 0.9452,
+ "epoch": 12.44,
+ "learning_rate": 4.360795454545455e-05,
+ "loss": 0.3554,
"step": 1101
},
{
- "epoch": 22.3,
- "learning_rate": 5.9438775510204084e-05,
- "loss": 0.9548,
+ "epoch": 12.45,
+ "learning_rate": 4.346590909090909e-05,
+ "loss": 0.3787,
"step": 1102
},
{
- "epoch": 22.32,
- "learning_rate": 5.931122448979592e-05,
- "loss": 0.9689,
+ "epoch": 12.46,
+ "learning_rate": 4.3323863636363635e-05,
+ "loss": 0.3695,
"step": 1103
},
{
- "epoch": 22.34,
- "learning_rate": 5.918367346938776e-05,
- "loss": 0.9455,
+ "epoch": 12.47,
+ "learning_rate": 4.318181818181819e-05,
+ "loss": 0.3777,
"step": 1104
},
{
- "epoch": 22.36,
- "learning_rate": 5.905612244897959e-05,
- "loss": 0.9409,
+ "epoch": 12.48,
+ "learning_rate": 4.303977272727273e-05,
+ "loss": 0.3693,
"step": 1105
},
{
- "epoch": 22.38,
- "learning_rate": 5.8928571428571435e-05,
- "loss": 0.9093,
+ "epoch": 12.49,
+ "learning_rate": 4.289772727272727e-05,
+ "loss": 0.3731,
"step": 1106
},
{
- "epoch": 22.4,
- "learning_rate": 5.8801020408163266e-05,
- "loss": 0.921,
+ "epoch": 12.51,
+ "learning_rate": 4.275568181818182e-05,
+ "loss": 0.3659,
"step": 1107
},
{
- "epoch": 22.42,
- "learning_rate": 5.867346938775511e-05,
- "loss": 0.9368,
+ "epoch": 12.52,
+ "learning_rate": 4.261363636363637e-05,
+ "loss": 0.3689,
"step": 1108
},
{
- "epoch": 22.44,
- "learning_rate": 5.854591836734694e-05,
- "loss": 0.907,
+ "epoch": 12.53,
+ "learning_rate": 4.247159090909091e-05,
+ "loss": 0.3625,
"step": 1109
},
{
- "epoch": 22.46,
- "learning_rate": 5.841836734693877e-05,
- "loss": 0.9126,
+ "epoch": 12.54,
+ "learning_rate": 4.232954545454546e-05,
+ "loss": 0.3874,
"step": 1110
},
{
- "epoch": 22.48,
- "learning_rate": 5.8290816326530616e-05,
- "loss": 0.9161,
+ "epoch": 12.55,
+ "learning_rate": 4.21875e-05,
+ "loss": 0.3651,
"step": 1111
},
{
- "epoch": 22.5,
- "learning_rate": 5.816326530612245e-05,
- "loss": 0.9542,
+ "epoch": 12.56,
+ "learning_rate": 4.204545454545455e-05,
+ "loss": 0.3639,
"step": 1112
},
{
- "epoch": 22.52,
- "learning_rate": 5.803571428571429e-05,
- "loss": 0.9775,
+ "epoch": 12.57,
+ "learning_rate": 4.190340909090909e-05,
+ "loss": 0.378,
"step": 1113
},
{
- "epoch": 22.54,
- "learning_rate": 5.790816326530612e-05,
- "loss": 1.0006,
+ "epoch": 12.59,
+ "learning_rate": 4.176136363636364e-05,
+ "loss": 0.3726,
"step": 1114
},
{
- "epoch": 22.56,
- "learning_rate": 5.778061224489796e-05,
- "loss": 0.8965,
+ "epoch": 12.6,
+ "learning_rate": 4.161931818181818e-05,
+ "loss": 0.3732,
"step": 1115
},
{
- "epoch": 22.58,
- "learning_rate": 5.7653061224489805e-05,
- "loss": 0.944,
+ "epoch": 12.61,
+ "learning_rate": 4.1477272727272734e-05,
+ "loss": 0.3673,
"step": 1116
},
{
- "epoch": 22.6,
- "learning_rate": 5.7525510204081636e-05,
- "loss": 0.9162,
+ "epoch": 12.62,
+ "learning_rate": 4.133522727272727e-05,
+ "loss": 0.3566,
"step": 1117
},
{
- "epoch": 22.62,
- "learning_rate": 5.739795918367348e-05,
- "loss": 0.9325,
+ "epoch": 12.63,
+ "learning_rate": 4.119318181818182e-05,
+ "loss": 0.3757,
"step": 1118
},
{
- "epoch": 22.64,
- "learning_rate": 5.727040816326531e-05,
- "loss": 0.8998,
+ "epoch": 12.64,
+ "learning_rate": 4.105113636363637e-05,
+ "loss": 0.3739,
"step": 1119
},
{
- "epoch": 22.66,
- "learning_rate": 5.714285714285714e-05,
- "loss": 0.9362,
+ "epoch": 12.65,
+ "learning_rate": 4.0909090909090915e-05,
+ "loss": 0.3768,
"step": 1120
},
{
- "epoch": 22.68,
- "learning_rate": 5.7015306122448986e-05,
- "loss": 0.9969,
+ "epoch": 12.66,
+ "learning_rate": 4.076704545454545e-05,
+ "loss": 0.3758,
"step": 1121
},
{
- "epoch": 22.7,
- "learning_rate": 5.688775510204082e-05,
- "loss": 0.9104,
+ "epoch": 12.68,
+ "learning_rate": 4.0625000000000005e-05,
+ "loss": 0.3655,
"step": 1122
},
{
- "epoch": 22.72,
- "learning_rate": 5.676020408163265e-05,
- "loss": 0.9746,
+ "epoch": 12.69,
+ "learning_rate": 4.048295454545455e-05,
+ "loss": 0.3673,
"step": 1123
},
{
- "epoch": 22.74,
- "learning_rate": 5.663265306122449e-05,
- "loss": 0.9821,
+ "epoch": 12.7,
+ "learning_rate": 4.034090909090909e-05,
+ "loss": 0.3683,
"step": 1124
},
{
- "epoch": 22.76,
- "learning_rate": 5.650510204081633e-05,
- "loss": 0.9526,
+ "epoch": 12.71,
+ "learning_rate": 4.019886363636364e-05,
+ "loss": 0.3569,
"step": 1125
},
{
- "epoch": 22.78,
- "learning_rate": 5.637755102040817e-05,
- "loss": 0.871,
+ "epoch": 12.72,
+ "learning_rate": 4.0056818181818185e-05,
+ "loss": 0.3741,
"step": 1126
},
{
- "epoch": 22.8,
- "learning_rate": 5.6250000000000005e-05,
- "loss": 0.9534,
+ "epoch": 12.73,
+ "learning_rate": 3.991477272727273e-05,
+ "loss": 0.3817,
"step": 1127
},
{
- "epoch": 22.82,
- "learning_rate": 5.6122448979591836e-05,
- "loss": 0.9616,
+ "epoch": 12.74,
+ "learning_rate": 3.9772727272727275e-05,
+ "loss": 0.3748,
"step": 1128
},
{
- "epoch": 22.84,
- "learning_rate": 5.599489795918368e-05,
- "loss": 0.9627,
+ "epoch": 12.75,
+ "learning_rate": 3.963068181818182e-05,
+ "loss": 0.3625,
"step": 1129
},
{
- "epoch": 22.86,
- "learning_rate": 5.586734693877551e-05,
- "loss": 0.9704,
+ "epoch": 12.77,
+ "learning_rate": 3.9488636363636366e-05,
+ "loss": 0.3656,
"step": 1130
},
{
- "epoch": 22.88,
- "learning_rate": 5.5739795918367356e-05,
- "loss": 0.9506,
+ "epoch": 12.78,
+ "learning_rate": 3.934659090909091e-05,
+ "loss": 0.3564,
"step": 1131
},
{
- "epoch": 22.9,
- "learning_rate": 5.561224489795919e-05,
- "loss": 0.9553,
+ "epoch": 12.79,
+ "learning_rate": 3.9204545454545456e-05,
+ "loss": 0.3737,
"step": 1132
},
{
- "epoch": 22.93,
- "learning_rate": 5.548469387755102e-05,
- "loss": 0.9294,
+ "epoch": 12.8,
+ "learning_rate": 3.90625e-05,
+ "loss": 0.3649,
"step": 1133
},
{
- "epoch": 22.95,
- "learning_rate": 5.535714285714286e-05,
- "loss": 0.8979,
+ "epoch": 12.81,
+ "learning_rate": 3.8920454545454546e-05,
+ "loss": 0.3728,
"step": 1134
},
{
- "epoch": 22.97,
- "learning_rate": 5.522959183673469e-05,
- "loss": 1.0004,
+ "epoch": 12.82,
+ "learning_rate": 3.877840909090909e-05,
+ "loss": 0.3865,
"step": 1135
},
{
- "epoch": 22.99,
- "learning_rate": 5.510204081632653e-05,
- "loss": 0.9821,
+ "epoch": 12.83,
+ "learning_rate": 3.8636363636363636e-05,
+ "loss": 0.3866,
"step": 1136
},
{
- "epoch": 23.01,
- "learning_rate": 5.497448979591837e-05,
- "loss": 0.9607,
+ "epoch": 12.85,
+ "learning_rate": 3.849431818181818e-05,
+ "loss": 0.3725,
"step": 1137
},
{
- "epoch": 23.03,
- "learning_rate": 5.4846938775510206e-05,
- "loss": 0.9757,
+ "epoch": 12.86,
+ "learning_rate": 3.835227272727273e-05,
+ "loss": 0.3662,
"step": 1138
},
{
- "epoch": 23.05,
- "learning_rate": 5.471938775510205e-05,
- "loss": 0.9096,
+ "epoch": 12.87,
+ "learning_rate": 3.821022727272727e-05,
+ "loss": 0.3742,
"step": 1139
},
{
- "epoch": 23.07,
- "learning_rate": 5.459183673469388e-05,
- "loss": 0.9144,
+ "epoch": 12.88,
+ "learning_rate": 3.8068181818181816e-05,
+ "loss": 0.3727,
"step": 1140
},
{
- "epoch": 23.09,
- "learning_rate": 5.446428571428571e-05,
- "loss": 0.8667,
+ "epoch": 12.89,
+ "learning_rate": 3.792613636363637e-05,
+ "loss": 0.3653,
"step": 1141
},
{
- "epoch": 23.11,
- "learning_rate": 5.4336734693877556e-05,
- "loss": 0.8993,
+ "epoch": 12.9,
+ "learning_rate": 3.778409090909091e-05,
+ "loss": 0.3631,
"step": 1142
},
{
- "epoch": 23.13,
- "learning_rate": 5.420918367346939e-05,
- "loss": 0.8964,
+ "epoch": 12.91,
+ "learning_rate": 3.764204545454545e-05,
+ "loss": 0.3674,
"step": 1143
},
{
- "epoch": 23.15,
- "learning_rate": 5.408163265306123e-05,
- "loss": 0.9173,
+ "epoch": 12.92,
+ "learning_rate": 3.7500000000000003e-05,
+ "loss": 0.3598,
"step": 1144
},
{
- "epoch": 23.17,
- "learning_rate": 5.395408163265306e-05,
- "loss": 0.9019,
+ "epoch": 12.94,
+ "learning_rate": 3.735795454545455e-05,
+ "loss": 0.3697,
"step": 1145
},
{
- "epoch": 23.19,
- "learning_rate": 5.382653061224489e-05,
- "loss": 0.9303,
+ "epoch": 12.95,
+ "learning_rate": 3.721590909090909e-05,
+ "loss": 0.3639,
"step": 1146
},
{
- "epoch": 23.21,
- "learning_rate": 5.369897959183674e-05,
- "loss": 0.9268,
+ "epoch": 12.96,
+ "learning_rate": 3.707386363636364e-05,
+ "loss": 0.3597,
"step": 1147
},
{
- "epoch": 23.23,
- "learning_rate": 5.3571428571428575e-05,
- "loss": 0.8803,
+ "epoch": 12.97,
+ "learning_rate": 3.6931818181818184e-05,
+ "loss": 0.3815,
"step": 1148
},
{
- "epoch": 23.25,
- "learning_rate": 5.344387755102041e-05,
- "loss": 0.9197,
+ "epoch": 12.98,
+ "learning_rate": 3.678977272727273e-05,
+ "loss": 0.3477,
"step": 1149
},
{
- "epoch": 23.27,
- "learning_rate": 5.331632653061225e-05,
- "loss": 0.9204,
+ "epoch": 12.99,
+ "learning_rate": 3.6647727272727274e-05,
+ "loss": 0.3631,
"step": 1150
},
{
- "epoch": 23.29,
- "learning_rate": 5.318877551020408e-05,
- "loss": 0.8802,
+ "epoch": 13.0,
+ "learning_rate": 3.650568181818182e-05,
+ "loss": 0.3569,
"step": 1151
},
{
- "epoch": 23.31,
- "learning_rate": 5.3061224489795926e-05,
- "loss": 0.9044,
+ "epoch": 13.01,
+ "learning_rate": 3.6363636363636364e-05,
+ "loss": 0.3435,
"step": 1152
},
{
- "epoch": 23.33,
- "learning_rate": 5.293367346938776e-05,
- "loss": 0.8893,
+ "epoch": 13.03,
+ "learning_rate": 3.6221590909090916e-05,
+ "loss": 0.3504,
"step": 1153
},
{
- "epoch": 23.35,
- "learning_rate": 5.280612244897959e-05,
- "loss": 0.8928,
+ "epoch": 13.04,
+ "learning_rate": 3.6079545454545454e-05,
+ "loss": 0.3582,
"step": 1154
},
{
- "epoch": 23.37,
- "learning_rate": 5.267857142857143e-05,
- "loss": 0.9353,
+ "epoch": 13.05,
+ "learning_rate": 3.59375e-05,
+ "loss": 0.356,
"step": 1155
},
{
- "epoch": 23.39,
- "learning_rate": 5.255102040816326e-05,
- "loss": 0.9345,
+ "epoch": 13.06,
+ "learning_rate": 3.579545454545455e-05,
+ "loss": 0.3506,
"step": 1156
},
{
- "epoch": 23.41,
- "learning_rate": 5.242346938775511e-05,
- "loss": 0.9372,
+ "epoch": 13.07,
+ "learning_rate": 3.565340909090909e-05,
+ "loss": 0.3628,
"step": 1157
},
{
- "epoch": 23.43,
- "learning_rate": 5.229591836734694e-05,
- "loss": 0.9234,
+ "epoch": 13.08,
+ "learning_rate": 3.5511363636363635e-05,
+ "loss": 0.3494,
"step": 1158
},
{
- "epoch": 23.45,
- "learning_rate": 5.2168367346938776e-05,
- "loss": 0.9177,
+ "epoch": 13.09,
+ "learning_rate": 3.5369318181818186e-05,
+ "loss": 0.3653,
"step": 1159
},
{
- "epoch": 23.47,
- "learning_rate": 5.2040816326530614e-05,
- "loss": 0.8757,
+ "epoch": 13.11,
+ "learning_rate": 3.522727272727273e-05,
+ "loss": 0.3515,
"step": 1160
},
{
- "epoch": 23.49,
- "learning_rate": 5.191326530612245e-05,
- "loss": 0.9048,
+ "epoch": 13.12,
+ "learning_rate": 3.508522727272727e-05,
+ "loss": 0.3474,
"step": 1161
},
{
- "epoch": 23.51,
- "learning_rate": 5.1785714285714296e-05,
- "loss": 0.9248,
+ "epoch": 13.13,
+ "learning_rate": 3.494318181818182e-05,
+ "loss": 0.3469,
"step": 1162
},
{
- "epoch": 23.53,
- "learning_rate": 5.1658163265306127e-05,
- "loss": 0.9379,
+ "epoch": 13.14,
+ "learning_rate": 3.480113636363637e-05,
+ "loss": 0.3471,
"step": 1163
},
{
- "epoch": 23.55,
- "learning_rate": 5.153061224489796e-05,
- "loss": 0.8596,
+ "epoch": 13.15,
+ "learning_rate": 3.465909090909091e-05,
+ "loss": 0.355,
"step": 1164
},
{
- "epoch": 23.57,
- "learning_rate": 5.14030612244898e-05,
- "loss": 0.9751,
+ "epoch": 13.16,
+ "learning_rate": 3.451704545454546e-05,
+ "loss": 0.3532,
"step": 1165
},
{
- "epoch": 23.59,
- "learning_rate": 5.127551020408163e-05,
- "loss": 0.8842,
+ "epoch": 13.17,
+ "learning_rate": 3.4375e-05,
+ "loss": 0.3533,
"step": 1166
},
{
- "epoch": 23.61,
- "learning_rate": 5.114795918367348e-05,
- "loss": 0.8765,
+ "epoch": 13.18,
+ "learning_rate": 3.423295454545455e-05,
+ "loss": 0.3571,
"step": 1167
},
{
- "epoch": 23.63,
- "learning_rate": 5.102040816326531e-05,
- "loss": 0.8942,
+ "epoch": 13.2,
+ "learning_rate": 3.409090909090909e-05,
+ "loss": 0.3435,
"step": 1168
},
{
- "epoch": 23.65,
- "learning_rate": 5.089285714285714e-05,
- "loss": 0.938,
+ "epoch": 13.21,
+ "learning_rate": 3.394886363636364e-05,
+ "loss": 0.348,
"step": 1169
},
{
- "epoch": 23.67,
- "learning_rate": 5.076530612244898e-05,
- "loss": 0.8993,
+ "epoch": 13.22,
+ "learning_rate": 3.380681818181818e-05,
+ "loss": 0.3505,
"step": 1170
},
{
- "epoch": 23.69,
- "learning_rate": 5.063775510204082e-05,
- "loss": 0.9362,
+ "epoch": 13.23,
+ "learning_rate": 3.3664772727272734e-05,
+ "loss": 0.346,
"step": 1171
},
{
- "epoch": 23.71,
- "learning_rate": 5.051020408163265e-05,
- "loss": 0.9249,
+ "epoch": 13.24,
+ "learning_rate": 3.352272727272727e-05,
+ "loss": 0.3568,
"step": 1172
},
{
- "epoch": 23.73,
- "learning_rate": 5.0382653061224496e-05,
- "loss": 0.9055,
+ "epoch": 13.25,
+ "learning_rate": 3.338068181818182e-05,
+ "loss": 0.3548,
"step": 1173
},
{
- "epoch": 23.75,
- "learning_rate": 5.025510204081633e-05,
- "loss": 0.8967,
+ "epoch": 13.26,
+ "learning_rate": 3.323863636363637e-05,
+ "loss": 0.352,
"step": 1174
},
{
- "epoch": 23.77,
- "learning_rate": 5.012755102040817e-05,
- "loss": 0.8795,
+ "epoch": 13.27,
+ "learning_rate": 3.3096590909090915e-05,
+ "loss": 0.3561,
"step": 1175
},
{
- "epoch": 23.8,
- "learning_rate": 5e-05,
- "loss": 0.9452,
+ "epoch": 13.29,
+ "learning_rate": 3.295454545454545e-05,
+ "loss": 0.3424,
"step": 1176
},
{
- "epoch": 23.82,
- "learning_rate": 4.987244897959184e-05,
- "loss": 0.926,
+ "epoch": 13.3,
+ "learning_rate": 3.2812500000000005e-05,
+ "loss": 0.3453,
"step": 1177
},
{
- "epoch": 23.84,
- "learning_rate": 4.974489795918368e-05,
- "loss": 0.8948,
+ "epoch": 13.31,
+ "learning_rate": 3.267045454545455e-05,
+ "loss": 0.347,
"step": 1178
},
{
- "epoch": 23.86,
- "learning_rate": 4.961734693877551e-05,
- "loss": 0.8926,
+ "epoch": 13.32,
+ "learning_rate": 3.252840909090909e-05,
+ "loss": 0.3526,
"step": 1179
},
{
- "epoch": 23.88,
- "learning_rate": 4.9489795918367346e-05,
- "loss": 0.8949,
+ "epoch": 13.33,
+ "learning_rate": 3.238636363636364e-05,
+ "loss": 0.3634,
"step": 1180
},
{
- "epoch": 23.9,
- "learning_rate": 4.9362244897959184e-05,
- "loss": 0.9648,
+ "epoch": 13.34,
+ "learning_rate": 3.2244318181818185e-05,
+ "loss": 0.3591,
"step": 1181
},
{
- "epoch": 23.92,
- "learning_rate": 4.923469387755102e-05,
- "loss": 0.9599,
+ "epoch": 13.35,
+ "learning_rate": 3.210227272727273e-05,
+ "loss": 0.3449,
"step": 1182
},
{
- "epoch": 23.94,
- "learning_rate": 4.910714285714286e-05,
- "loss": 0.9603,
+ "epoch": 13.36,
+ "learning_rate": 3.1960227272727275e-05,
+ "loss": 0.3362,
"step": 1183
},
{
- "epoch": 23.96,
- "learning_rate": 4.89795918367347e-05,
- "loss": 0.9302,
+ "epoch": 13.38,
+ "learning_rate": 3.181818181818182e-05,
+ "loss": 0.3613,
"step": 1184
},
{
- "epoch": 23.98,
- "learning_rate": 4.8852040816326534e-05,
- "loss": 0.9261,
+ "epoch": 13.39,
+ "learning_rate": 3.1676136363636365e-05,
+ "loss": 0.3509,
"step": 1185
},
{
- "epoch": 24.0,
- "learning_rate": 4.872448979591837e-05,
- "loss": 0.9257,
+ "epoch": 13.4,
+ "learning_rate": 3.153409090909091e-05,
+ "loss": 0.3534,
"step": 1186
},
{
- "epoch": 24.02,
- "learning_rate": 4.859693877551021e-05,
- "loss": 0.8725,
+ "epoch": 13.41,
+ "learning_rate": 3.1392045454545456e-05,
+ "loss": 0.3452,
"step": 1187
},
{
- "epoch": 24.04,
- "learning_rate": 4.846938775510204e-05,
- "loss": 0.8486,
+ "epoch": 13.42,
+ "learning_rate": 3.125e-05,
+ "loss": 0.3659,
"step": 1188
},
{
- "epoch": 24.06,
- "learning_rate": 4.834183673469388e-05,
- "loss": 0.8457,
+ "epoch": 13.43,
+ "learning_rate": 3.1107954545454546e-05,
+ "loss": 0.3445,
"step": 1189
},
{
- "epoch": 24.08,
- "learning_rate": 4.8214285714285716e-05,
- "loss": 0.7848,
+ "epoch": 13.44,
+ "learning_rate": 3.096590909090909e-05,
+ "loss": 0.3536,
"step": 1190
},
{
- "epoch": 24.1,
- "learning_rate": 4.8086734693877554e-05,
- "loss": 0.8885,
+ "epoch": 13.46,
+ "learning_rate": 3.0823863636363636e-05,
+ "loss": 0.3588,
"step": 1191
},
{
- "epoch": 24.12,
- "learning_rate": 4.795918367346939e-05,
- "loss": 0.9099,
+ "epoch": 13.47,
+ "learning_rate": 3.068181818181818e-05,
+ "loss": 0.347,
"step": 1192
},
{
- "epoch": 24.14,
- "learning_rate": 4.783163265306123e-05,
- "loss": 0.9147,
+ "epoch": 13.48,
+ "learning_rate": 3.053977272727273e-05,
+ "loss": 0.3537,
"step": 1193
},
{
- "epoch": 24.16,
- "learning_rate": 4.7704081632653066e-05,
- "loss": 0.8781,
+ "epoch": 13.49,
+ "learning_rate": 3.039772727272727e-05,
+ "loss": 0.3516,
"step": 1194
},
{
- "epoch": 24.18,
- "learning_rate": 4.7576530612244904e-05,
- "loss": 0.8847,
+ "epoch": 13.5,
+ "learning_rate": 3.025568181818182e-05,
+ "loss": 0.3587,
"step": 1195
},
{
- "epoch": 24.2,
- "learning_rate": 4.744897959183674e-05,
- "loss": 0.9041,
+ "epoch": 13.51,
+ "learning_rate": 3.0113636363636365e-05,
+ "loss": 0.3494,
"step": 1196
},
{
- "epoch": 24.22,
- "learning_rate": 4.732142857142857e-05,
- "loss": 0.8639,
+ "epoch": 13.52,
+ "learning_rate": 2.9971590909090913e-05,
+ "loss": 0.3341,
"step": 1197
},
{
- "epoch": 24.24,
- "learning_rate": 4.719387755102041e-05,
- "loss": 0.8831,
+ "epoch": 13.53,
+ "learning_rate": 2.9829545454545455e-05,
+ "loss": 0.3563,
"step": 1198
},
{
- "epoch": 24.26,
- "learning_rate": 4.706632653061225e-05,
- "loss": 0.9063,
+ "epoch": 13.55,
+ "learning_rate": 2.96875e-05,
+ "loss": 0.3534,
"step": 1199
},
{
- "epoch": 24.28,
- "learning_rate": 4.6938775510204086e-05,
- "loss": 0.8753,
+ "epoch": 13.56,
+ "learning_rate": 2.954545454545455e-05,
+ "loss": 0.3632,
"step": 1200
},
{
- "epoch": 24.3,
- "learning_rate": 4.6811224489795916e-05,
- "loss": 0.8977,
+ "epoch": 13.57,
+ "learning_rate": 2.940340909090909e-05,
+ "loss": 0.3523,
"step": 1201
},
{
- "epoch": 24.32,
- "learning_rate": 4.6683673469387754e-05,
- "loss": 0.8729,
+ "epoch": 13.58,
+ "learning_rate": 2.9261363636363635e-05,
+ "loss": 0.3587,
"step": 1202
},
{
- "epoch": 24.34,
- "learning_rate": 4.655612244897959e-05,
- "loss": 0.898,
+ "epoch": 13.59,
+ "learning_rate": 2.9119318181818184e-05,
+ "loss": 0.3523,
"step": 1203
},
{
- "epoch": 24.36,
- "learning_rate": 4.642857142857143e-05,
- "loss": 0.8521,
+ "epoch": 13.6,
+ "learning_rate": 2.8977272727272732e-05,
+ "loss": 0.3418,
"step": 1204
},
{
- "epoch": 24.38,
- "learning_rate": 4.630102040816327e-05,
- "loss": 0.8563,
+ "epoch": 13.61,
+ "learning_rate": 2.883522727272727e-05,
+ "loss": 0.3515,
"step": 1205
},
{
- "epoch": 24.4,
- "learning_rate": 4.6173469387755105e-05,
- "loss": 0.8462,
+ "epoch": 13.62,
+ "learning_rate": 2.869318181818182e-05,
+ "loss": 0.3362,
"step": 1206
},
{
- "epoch": 24.42,
- "learning_rate": 4.604591836734694e-05,
- "loss": 0.8929,
+ "epoch": 13.64,
+ "learning_rate": 2.8551136363636367e-05,
+ "loss": 0.3393,
"step": 1207
},
{
- "epoch": 24.44,
- "learning_rate": 4.591836734693878e-05,
- "loss": 0.9154,
+ "epoch": 13.65,
+ "learning_rate": 2.8409090909090912e-05,
+ "loss": 0.3395,
"step": 1208
},
{
- "epoch": 24.46,
- "learning_rate": 4.579081632653062e-05,
- "loss": 0.811,
+ "epoch": 13.66,
+ "learning_rate": 2.8267045454545454e-05,
+ "loss": 0.3434,
"step": 1209
},
{
- "epoch": 24.48,
- "learning_rate": 4.566326530612245e-05,
- "loss": 0.8667,
+ "epoch": 13.67,
+ "learning_rate": 2.8125000000000003e-05,
+ "loss": 0.3536,
"step": 1210
},
{
- "epoch": 24.5,
- "learning_rate": 4.5535714285714286e-05,
- "loss": 0.9179,
+ "epoch": 13.68,
+ "learning_rate": 2.7982954545454548e-05,
+ "loss": 0.3482,
"step": 1211
},
{
- "epoch": 24.52,
- "learning_rate": 4.5408163265306124e-05,
- "loss": 0.8757,
+ "epoch": 13.69,
+ "learning_rate": 2.784090909090909e-05,
+ "loss": 0.3383,
"step": 1212
},
{
- "epoch": 24.54,
- "learning_rate": 4.528061224489796e-05,
- "loss": 0.8519,
+ "epoch": 13.7,
+ "learning_rate": 2.7698863636363638e-05,
+ "loss": 0.3582,
"step": 1213
},
{
- "epoch": 24.56,
- "learning_rate": 4.515306122448979e-05,
- "loss": 0.9335,
+ "epoch": 13.72,
+ "learning_rate": 2.7556818181818183e-05,
+ "loss": 0.3469,
"step": 1214
},
{
- "epoch": 24.58,
- "learning_rate": 4.502551020408164e-05,
- "loss": 0.8785,
+ "epoch": 13.73,
+ "learning_rate": 2.741477272727273e-05,
+ "loss": 0.351,
"step": 1215
},
{
- "epoch": 24.6,
- "learning_rate": 4.4897959183673474e-05,
- "loss": 0.9022,
+ "epoch": 13.74,
+ "learning_rate": 2.7272727272727273e-05,
+ "loss": 0.3461,
"step": 1216
},
{
- "epoch": 24.62,
- "learning_rate": 4.477040816326531e-05,
- "loss": 0.9532,
+ "epoch": 13.75,
+ "learning_rate": 2.7130681818181818e-05,
+ "loss": 0.3497,
"step": 1217
},
{
- "epoch": 24.64,
- "learning_rate": 4.464285714285715e-05,
- "loss": 0.8956,
+ "epoch": 13.76,
+ "learning_rate": 2.6988636363636367e-05,
+ "loss": 0.3503,
"step": 1218
},
{
- "epoch": 24.67,
- "learning_rate": 4.451530612244898e-05,
- "loss": 0.8739,
+ "epoch": 13.77,
+ "learning_rate": 2.6846590909090912e-05,
+ "loss": 0.3499,
"step": 1219
},
{
- "epoch": 24.69,
- "learning_rate": 4.438775510204082e-05,
- "loss": 0.9312,
+ "epoch": 13.78,
+ "learning_rate": 2.6704545454545453e-05,
+ "loss": 0.3529,
"step": 1220
},
{
- "epoch": 24.71,
- "learning_rate": 4.4260204081632656e-05,
- "loss": 0.8536,
+ "epoch": 13.79,
+ "learning_rate": 2.6562500000000002e-05,
+ "loss": 0.3516,
"step": 1221
},
{
- "epoch": 24.73,
- "learning_rate": 4.4132653061224493e-05,
- "loss": 0.8984,
+ "epoch": 13.81,
+ "learning_rate": 2.6420454545454547e-05,
+ "loss": 0.3457,
"step": 1222
},
{
- "epoch": 24.75,
- "learning_rate": 4.4005102040816324e-05,
- "loss": 0.8949,
+ "epoch": 13.82,
+ "learning_rate": 2.627840909090909e-05,
+ "loss": 0.3482,
"step": 1223
},
{
- "epoch": 24.77,
- "learning_rate": 4.387755102040816e-05,
- "loss": 0.9389,
+ "epoch": 13.83,
+ "learning_rate": 2.6136363636363637e-05,
+ "loss": 0.3458,
"step": 1224
},
{
- "epoch": 24.79,
- "learning_rate": 4.375e-05,
- "loss": 0.8703,
+ "epoch": 13.84,
+ "learning_rate": 2.5994318181818182e-05,
+ "loss": 0.3442,
"step": 1225
},
{
- "epoch": 24.81,
- "learning_rate": 4.362244897959184e-05,
- "loss": 0.9407,
+ "epoch": 13.85,
+ "learning_rate": 2.585227272727273e-05,
+ "loss": 0.3717,
"step": 1226
},
{
- "epoch": 24.83,
- "learning_rate": 4.3494897959183675e-05,
- "loss": 0.9016,
+ "epoch": 13.86,
+ "learning_rate": 2.5710227272727272e-05,
+ "loss": 0.3404,
"step": 1227
},
{
- "epoch": 24.85,
- "learning_rate": 4.336734693877551e-05,
- "loss": 0.9025,
+ "epoch": 13.87,
+ "learning_rate": 2.5568181818181817e-05,
+ "loss": 0.34,
"step": 1228
},
{
- "epoch": 24.87,
- "learning_rate": 4.323979591836735e-05,
- "loss": 0.9415,
+ "epoch": 13.88,
+ "learning_rate": 2.5426136363636366e-05,
+ "loss": 0.3615,
"step": 1229
},
{
- "epoch": 24.89,
- "learning_rate": 4.311224489795919e-05,
- "loss": 0.9146,
+ "epoch": 13.9,
+ "learning_rate": 2.5284090909090914e-05,
+ "loss": 0.3473,
"step": 1230
},
{
- "epoch": 24.91,
- "learning_rate": 4.2984693877551025e-05,
- "loss": 0.9144,
+ "epoch": 13.91,
+ "learning_rate": 2.5142045454545453e-05,
+ "loss": 0.3532,
"step": 1231
},
{
- "epoch": 24.93,
- "learning_rate": 4.2857142857142856e-05,
- "loss": 0.9138,
+ "epoch": 13.92,
+ "learning_rate": 2.5e-05,
+ "loss": 0.3524,
"step": 1232
},
{
- "epoch": 24.95,
- "learning_rate": 4.2729591836734694e-05,
- "loss": 0.9372,
+ "epoch": 13.93,
+ "learning_rate": 2.4857954545454546e-05,
+ "loss": 0.3681,
"step": 1233
},
{
- "epoch": 24.97,
- "learning_rate": 4.260204081632653e-05,
- "loss": 0.8701,
+ "epoch": 13.94,
+ "learning_rate": 2.471590909090909e-05,
+ "loss": 0.3432,
"step": 1234
},
{
- "epoch": 24.99,
- "learning_rate": 4.247448979591837e-05,
- "loss": 0.9278,
+ "epoch": 13.95,
+ "learning_rate": 2.4573863636363636e-05,
+ "loss": 0.3507,
"step": 1235
},
{
- "epoch": 25.01,
- "learning_rate": 4.234693877551021e-05,
- "loss": 0.9157,
+ "epoch": 13.96,
+ "learning_rate": 2.4431818181818185e-05,
+ "loss": 0.3448,
"step": 1236
},
{
- "epoch": 25.03,
- "learning_rate": 4.2219387755102045e-05,
- "loss": 0.8852,
+ "epoch": 13.97,
+ "learning_rate": 2.4289772727272727e-05,
+ "loss": 0.3501,
"step": 1237
},
{
- "epoch": 25.05,
- "learning_rate": 4.209183673469388e-05,
- "loss": 0.855,
+ "epoch": 13.99,
+ "learning_rate": 2.4147727272727275e-05,
+ "loss": 0.3624,
"step": 1238
},
{
- "epoch": 25.07,
- "learning_rate": 4.196428571428572e-05,
- "loss": 0.8547,
+ "epoch": 14.0,
+ "learning_rate": 2.400568181818182e-05,
+ "loss": 0.3446,
"step": 1239
},
{
- "epoch": 25.09,
- "learning_rate": 4.183673469387756e-05,
- "loss": 0.8691,
+ "epoch": 14.01,
+ "learning_rate": 2.3863636363636365e-05,
+ "loss": 0.3463,
"step": 1240
},
{
- "epoch": 25.11,
- "learning_rate": 4.170918367346939e-05,
- "loss": 0.9101,
+ "epoch": 14.02,
+ "learning_rate": 2.372159090909091e-05,
+ "loss": 0.3492,
"step": 1241
},
{
- "epoch": 25.13,
- "learning_rate": 4.1581632653061226e-05,
- "loss": 0.8408,
+ "epoch": 14.03,
+ "learning_rate": 2.3579545454545455e-05,
+ "loss": 0.3352,
"step": 1242
},
{
- "epoch": 25.15,
- "learning_rate": 4.1454081632653064e-05,
- "loss": 0.9008,
+ "epoch": 14.04,
+ "learning_rate": 2.34375e-05,
+ "loss": 0.3368,
"step": 1243
},
{
- "epoch": 25.17,
- "learning_rate": 4.13265306122449e-05,
- "loss": 0.859,
+ "epoch": 14.05,
+ "learning_rate": 2.3295454545454546e-05,
+ "loss": 0.3295,
"step": 1244
},
{
- "epoch": 25.19,
- "learning_rate": 4.119897959183674e-05,
- "loss": 0.8525,
+ "epoch": 14.07,
+ "learning_rate": 2.315340909090909e-05,
+ "loss": 0.3426,
"step": 1245
},
{
- "epoch": 25.21,
- "learning_rate": 4.107142857142857e-05,
- "loss": 0.8682,
+ "epoch": 14.08,
+ "learning_rate": 2.3011363636363636e-05,
+ "loss": 0.3284,
"step": 1246
},
{
- "epoch": 25.23,
- "learning_rate": 4.094387755102041e-05,
- "loss": 0.8426,
+ "epoch": 14.09,
+ "learning_rate": 2.2869318181818184e-05,
+ "loss": 0.3305,
"step": 1247
},
{
- "epoch": 25.25,
- "learning_rate": 4.0816326530612245e-05,
- "loss": 0.8948,
+ "epoch": 14.1,
+ "learning_rate": 2.272727272727273e-05,
+ "loss": 0.3447,
"step": 1248
},
{
- "epoch": 25.27,
- "learning_rate": 4.068877551020408e-05,
- "loss": 0.8333,
+ "epoch": 14.11,
+ "learning_rate": 2.2585227272727274e-05,
+ "loss": 0.344,
"step": 1249
},
{
- "epoch": 25.29,
- "learning_rate": 4.056122448979592e-05,
- "loss": 0.87,
+ "epoch": 14.12,
+ "learning_rate": 2.244318181818182e-05,
+ "loss": 0.3516,
"step": 1250
},
{
- "epoch": 25.31,
- "learning_rate": 4.043367346938776e-05,
- "loss": 0.8215,
+ "epoch": 14.13,
+ "learning_rate": 2.2301136363636365e-05,
+ "loss": 0.3417,
"step": 1251
},
{
- "epoch": 25.33,
- "learning_rate": 4.0306122448979596e-05,
- "loss": 0.862,
+ "epoch": 14.14,
+ "learning_rate": 2.215909090909091e-05,
+ "loss": 0.3353,
"step": 1252
},
{
- "epoch": 25.35,
- "learning_rate": 4.017857142857143e-05,
- "loss": 0.8607,
+ "epoch": 14.16,
+ "learning_rate": 2.2017045454545458e-05,
+ "loss": 0.3363,
"step": 1253
},
{
- "epoch": 25.37,
- "learning_rate": 4.0051020408163264e-05,
- "loss": 0.8218,
+ "epoch": 14.17,
+ "learning_rate": 2.1875e-05,
+ "loss": 0.3342,
"step": 1254
},
{
- "epoch": 25.39,
- "learning_rate": 3.99234693877551e-05,
- "loss": 0.806,
+ "epoch": 14.18,
+ "learning_rate": 2.1732954545454545e-05,
+ "loss": 0.3366,
"step": 1255
},
{
- "epoch": 25.41,
- "learning_rate": 3.979591836734694e-05,
- "loss": 0.8929,
+ "epoch": 14.19,
+ "learning_rate": 2.1590909090909093e-05,
+ "loss": 0.3333,
"step": 1256
},
{
- "epoch": 25.43,
- "learning_rate": 3.966836734693878e-05,
- "loss": 0.8551,
+ "epoch": 14.2,
+ "learning_rate": 2.1448863636363635e-05,
+ "loss": 0.3425,
"step": 1257
},
{
- "epoch": 25.45,
- "learning_rate": 3.9540816326530615e-05,
- "loss": 0.8408,
+ "epoch": 14.21,
+ "learning_rate": 2.1306818181818183e-05,
+ "loss": 0.3366,
"step": 1258
},
{
- "epoch": 25.47,
- "learning_rate": 3.9413265306122446e-05,
- "loss": 0.8819,
+ "epoch": 14.22,
+ "learning_rate": 2.116477272727273e-05,
+ "loss": 0.3324,
"step": 1259
},
{
- "epoch": 25.49,
- "learning_rate": 3.928571428571429e-05,
- "loss": 0.8757,
+ "epoch": 14.23,
+ "learning_rate": 2.1022727272727274e-05,
+ "loss": 0.3527,
"step": 1260
},
{
- "epoch": 25.52,
- "learning_rate": 3.915816326530613e-05,
- "loss": 0.8778,
+ "epoch": 14.25,
+ "learning_rate": 2.088068181818182e-05,
+ "loss": 0.3399,
"step": 1261
},
{
- "epoch": 25.54,
- "learning_rate": 3.9030612244897965e-05,
- "loss": 0.8524,
+ "epoch": 14.26,
+ "learning_rate": 2.0738636363636367e-05,
+ "loss": 0.3651,
"step": 1262
},
{
- "epoch": 25.56,
- "learning_rate": 3.8903061224489796e-05,
- "loss": 0.846,
+ "epoch": 14.27,
+ "learning_rate": 2.059659090909091e-05,
+ "loss": 0.3381,
"step": 1263
},
{
- "epoch": 25.58,
- "learning_rate": 3.8775510204081634e-05,
- "loss": 0.8757,
+ "epoch": 14.28,
+ "learning_rate": 2.0454545454545457e-05,
+ "loss": 0.3408,
"step": 1264
},
{
- "epoch": 25.6,
- "learning_rate": 3.864795918367347e-05,
- "loss": 0.9084,
+ "epoch": 14.29,
+ "learning_rate": 2.0312500000000002e-05,
+ "loss": 0.3237,
"step": 1265
},
{
- "epoch": 25.62,
- "learning_rate": 3.852040816326531e-05,
- "loss": 0.8826,
+ "epoch": 14.3,
+ "learning_rate": 2.0170454545454544e-05,
+ "loss": 0.3421,
"step": 1266
},
{
- "epoch": 25.64,
- "learning_rate": 3.839285714285715e-05,
- "loss": 0.8619,
+ "epoch": 14.31,
+ "learning_rate": 2.0028409090909093e-05,
+ "loss": 0.3361,
"step": 1267
},
{
- "epoch": 25.66,
- "learning_rate": 3.826530612244898e-05,
- "loss": 0.8942,
+ "epoch": 14.33,
+ "learning_rate": 1.9886363636363638e-05,
+ "loss": 0.3475,
"step": 1268
},
{
- "epoch": 25.68,
- "learning_rate": 3.8137755102040815e-05,
- "loss": 0.8342,
+ "epoch": 14.34,
+ "learning_rate": 1.9744318181818183e-05,
+ "loss": 0.3337,
"step": 1269
},
{
- "epoch": 25.7,
- "learning_rate": 3.801020408163265e-05,
- "loss": 0.8512,
+ "epoch": 14.35,
+ "learning_rate": 1.9602272727272728e-05,
+ "loss": 0.3384,
"step": 1270
},
{
- "epoch": 25.72,
- "learning_rate": 3.788265306122449e-05,
- "loss": 0.8393,
+ "epoch": 14.36,
+ "learning_rate": 1.9460227272727273e-05,
+ "loss": 0.3255,
"step": 1271
},
{
- "epoch": 25.74,
- "learning_rate": 3.775510204081633e-05,
- "loss": 0.8508,
+ "epoch": 14.37,
+ "learning_rate": 1.9318181818181818e-05,
+ "loss": 0.3568,
"step": 1272
},
{
- "epoch": 25.76,
- "learning_rate": 3.7627551020408166e-05,
- "loss": 0.9094,
+ "epoch": 14.38,
+ "learning_rate": 1.9176136363636366e-05,
+ "loss": 0.3427,
"step": 1273
},
{
- "epoch": 25.78,
- "learning_rate": 3.7500000000000003e-05,
- "loss": 0.9175,
+ "epoch": 14.39,
+ "learning_rate": 1.9034090909090908e-05,
+ "loss": 0.3468,
"step": 1274
},
{
- "epoch": 25.8,
- "learning_rate": 3.737244897959184e-05,
- "loss": 0.9179,
+ "epoch": 14.4,
+ "learning_rate": 1.8892045454545457e-05,
+ "loss": 0.3312,
"step": 1275
},
{
- "epoch": 25.82,
- "learning_rate": 3.724489795918368e-05,
- "loss": 0.869,
+ "epoch": 14.42,
+ "learning_rate": 1.8750000000000002e-05,
+ "loss": 0.3376,
"step": 1276
},
{
- "epoch": 25.84,
- "learning_rate": 3.711734693877551e-05,
- "loss": 0.8568,
+ "epoch": 14.43,
+ "learning_rate": 1.8607954545454543e-05,
+ "loss": 0.3284,
"step": 1277
},
{
- "epoch": 25.86,
- "learning_rate": 3.698979591836735e-05,
- "loss": 0.9104,
+ "epoch": 14.44,
+ "learning_rate": 1.8465909090909092e-05,
+ "loss": 0.3378,
"step": 1278
},
{
- "epoch": 25.88,
- "learning_rate": 3.6862244897959185e-05,
- "loss": 0.8912,
+ "epoch": 14.45,
+ "learning_rate": 1.8323863636363637e-05,
+ "loss": 0.3331,
"step": 1279
},
{
- "epoch": 25.9,
- "learning_rate": 3.673469387755102e-05,
- "loss": 0.878,
+ "epoch": 14.46,
+ "learning_rate": 1.8181818181818182e-05,
+ "loss": 0.3297,
"step": 1280
},
{
- "epoch": 25.92,
- "learning_rate": 3.6607142857142853e-05,
- "loss": 0.8711,
+ "epoch": 14.47,
+ "learning_rate": 1.8039772727272727e-05,
+ "loss": 0.3491,
"step": 1281
},
{
- "epoch": 25.94,
- "learning_rate": 3.64795918367347e-05,
- "loss": 0.9404,
+ "epoch": 14.48,
+ "learning_rate": 1.7897727272727276e-05,
+ "loss": 0.3354,
"step": 1282
},
{
- "epoch": 25.96,
- "learning_rate": 3.6352040816326536e-05,
- "loss": 0.9302,
+ "epoch": 14.49,
+ "learning_rate": 1.7755681818181817e-05,
+ "loss": 0.3292,
"step": 1283
},
{
- "epoch": 25.98,
- "learning_rate": 3.622448979591837e-05,
- "loss": 0.8907,
+ "epoch": 14.51,
+ "learning_rate": 1.7613636363636366e-05,
+ "loss": 0.3419,
"step": 1284
},
{
- "epoch": 26.0,
- "learning_rate": 3.609693877551021e-05,
- "loss": 0.8473,
+ "epoch": 14.52,
+ "learning_rate": 1.747159090909091e-05,
+ "loss": 0.329,
"step": 1285
},
{
- "epoch": 26.02,
- "learning_rate": 3.596938775510204e-05,
- "loss": 0.8482,
+ "epoch": 14.53,
+ "learning_rate": 1.7329545454545456e-05,
+ "loss": 0.345,
"step": 1286
},
{
- "epoch": 26.04,
- "learning_rate": 3.584183673469388e-05,
- "loss": 0.8683,
+ "epoch": 14.54,
+ "learning_rate": 1.71875e-05,
+ "loss": 0.3369,
"step": 1287
},
{
- "epoch": 26.06,
- "learning_rate": 3.571428571428572e-05,
- "loss": 0.8443,
+ "epoch": 14.55,
+ "learning_rate": 1.7045454545454546e-05,
+ "loss": 0.3537,
"step": 1288
},
{
- "epoch": 26.08,
- "learning_rate": 3.5586734693877555e-05,
- "loss": 0.8462,
+ "epoch": 14.56,
+ "learning_rate": 1.690340909090909e-05,
+ "loss": 0.3418,
"step": 1289
},
{
- "epoch": 26.1,
- "learning_rate": 3.5459183673469385e-05,
- "loss": 0.8204,
+ "epoch": 14.57,
+ "learning_rate": 1.6761363636363636e-05,
+ "loss": 0.3514,
"step": 1290
},
{
- "epoch": 26.12,
- "learning_rate": 3.533163265306122e-05,
- "loss": 0.8632,
+ "epoch": 14.58,
+ "learning_rate": 1.6619318181818185e-05,
+ "loss": 0.3325,
"step": 1291
},
{
- "epoch": 26.14,
- "learning_rate": 3.520408163265306e-05,
- "loss": 0.8883,
+ "epoch": 14.6,
+ "learning_rate": 1.6477272727272726e-05,
+ "loss": 0.3492,
"step": 1292
},
{
- "epoch": 26.16,
- "learning_rate": 3.50765306122449e-05,
- "loss": 0.8369,
+ "epoch": 14.61,
+ "learning_rate": 1.6335227272727275e-05,
+ "loss": 0.3439,
"step": 1293
},
{
- "epoch": 26.18,
- "learning_rate": 3.4948979591836736e-05,
- "loss": 0.8369,
+ "epoch": 14.62,
+ "learning_rate": 1.619318181818182e-05,
+ "loss": 0.3401,
"step": 1294
},
{
- "epoch": 26.2,
- "learning_rate": 3.4821428571428574e-05,
- "loss": 0.8506,
+ "epoch": 14.63,
+ "learning_rate": 1.6051136363636365e-05,
+ "loss": 0.3373,
"step": 1295
},
{
- "epoch": 26.22,
- "learning_rate": 3.469387755102041e-05,
- "loss": 0.839,
+ "epoch": 14.64,
+ "learning_rate": 1.590909090909091e-05,
+ "loss": 0.339,
"step": 1296
},
{
- "epoch": 26.24,
- "learning_rate": 3.456632653061225e-05,
- "loss": 0.8421,
+ "epoch": 14.65,
+ "learning_rate": 1.5767045454545455e-05,
+ "loss": 0.3229,
"step": 1297
},
{
- "epoch": 26.26,
- "learning_rate": 3.443877551020409e-05,
- "loss": 0.8292,
+ "epoch": 14.66,
+ "learning_rate": 1.5625e-05,
+ "loss": 0.3369,
"step": 1298
},
{
- "epoch": 26.28,
- "learning_rate": 3.431122448979592e-05,
- "loss": 0.8412,
+ "epoch": 14.68,
+ "learning_rate": 1.5482954545454545e-05,
+ "loss": 0.3295,
"step": 1299
},
{
- "epoch": 26.3,
- "learning_rate": 3.4183673469387755e-05,
- "loss": 0.8305,
+ "epoch": 14.69,
+ "learning_rate": 1.534090909090909e-05,
+ "loss": 0.3333,
"step": 1300
},
{
- "epoch": 26.32,
- "learning_rate": 3.405612244897959e-05,
- "loss": 0.8181,
+ "epoch": 14.7,
+ "learning_rate": 1.5198863636363636e-05,
+ "loss": 0.3455,
"step": 1301
},
{
- "epoch": 26.34,
- "learning_rate": 3.392857142857143e-05,
- "loss": 0.8588,
+ "epoch": 14.71,
+ "learning_rate": 1.5056818181818182e-05,
+ "loss": 0.3331,
"step": 1302
},
{
- "epoch": 26.36,
- "learning_rate": 3.380102040816326e-05,
- "loss": 0.8528,
+ "epoch": 14.72,
+ "learning_rate": 1.4914772727272727e-05,
+ "loss": 0.3281,
"step": 1303
},
{
- "epoch": 26.39,
- "learning_rate": 3.36734693877551e-05,
- "loss": 0.9055,
+ "epoch": 14.73,
+ "learning_rate": 1.4772727272727274e-05,
+ "loss": 0.3222,
"step": 1304
},
{
- "epoch": 26.41,
- "learning_rate": 3.354591836734694e-05,
- "loss": 0.8762,
+ "epoch": 14.74,
+ "learning_rate": 1.4630681818181818e-05,
+ "loss": 0.3265,
"step": 1305
},
{
- "epoch": 26.43,
- "learning_rate": 3.341836734693878e-05,
- "loss": 0.8507,
+ "epoch": 14.75,
+ "learning_rate": 1.4488636363636366e-05,
+ "loss": 0.3312,
"step": 1306
},
{
- "epoch": 26.45,
- "learning_rate": 3.329081632653062e-05,
- "loss": 0.8541,
+ "epoch": 14.77,
+ "learning_rate": 1.434659090909091e-05,
+ "loss": 0.3406,
"step": 1307
},
{
- "epoch": 26.47,
- "learning_rate": 3.316326530612245e-05,
- "loss": 0.8205,
+ "epoch": 14.78,
+ "learning_rate": 1.4204545454545456e-05,
+ "loss": 0.3404,
"step": 1308
},
{
- "epoch": 26.49,
- "learning_rate": 3.303571428571429e-05,
- "loss": 0.8133,
+ "epoch": 14.79,
+ "learning_rate": 1.4062500000000001e-05,
+ "loss": 0.3293,
"step": 1309
},
{
- "epoch": 26.51,
- "learning_rate": 3.2908163265306125e-05,
- "loss": 0.8854,
+ "epoch": 14.8,
+ "learning_rate": 1.3920454545454545e-05,
+ "loss": 0.3317,
"step": 1310
},
{
- "epoch": 26.53,
- "learning_rate": 3.278061224489796e-05,
- "loss": 0.9397,
+ "epoch": 14.81,
+ "learning_rate": 1.3778409090909091e-05,
+ "loss": 0.3334,
"step": 1311
},
{
- "epoch": 26.55,
- "learning_rate": 3.265306122448979e-05,
- "loss": 0.854,
+ "epoch": 14.82,
+ "learning_rate": 1.3636363636363637e-05,
+ "loss": 0.332,
"step": 1312
},
{
- "epoch": 26.57,
- "learning_rate": 3.252551020408163e-05,
- "loss": 0.8617,
+ "epoch": 14.83,
+ "learning_rate": 1.3494318181818183e-05,
+ "loss": 0.3313,
"step": 1313
},
{
- "epoch": 26.59,
- "learning_rate": 3.239795918367347e-05,
- "loss": 0.8739,
+ "epoch": 14.84,
+ "learning_rate": 1.3352272727272727e-05,
+ "loss": 0.3374,
"step": 1314
},
{
- "epoch": 26.61,
- "learning_rate": 3.2270408163265306e-05,
- "loss": 0.8139,
+ "epoch": 14.86,
+ "learning_rate": 1.3210227272727273e-05,
+ "loss": 0.3238,
"step": 1315
},
{
- "epoch": 26.63,
- "learning_rate": 3.2142857142857144e-05,
- "loss": 0.7575,
+ "epoch": 14.87,
+ "learning_rate": 1.3068181818181819e-05,
+ "loss": 0.3391,
"step": 1316
},
{
- "epoch": 26.65,
- "learning_rate": 3.201530612244898e-05,
- "loss": 0.846,
+ "epoch": 14.88,
+ "learning_rate": 1.2926136363636365e-05,
+ "loss": 0.3329,
"step": 1317
},
{
- "epoch": 26.67,
- "learning_rate": 3.188775510204082e-05,
- "loss": 0.8797,
+ "epoch": 14.89,
+ "learning_rate": 1.2784090909090909e-05,
+ "loss": 0.3312,
"step": 1318
},
{
- "epoch": 26.69,
- "learning_rate": 3.176020408163266e-05,
- "loss": 0.8525,
+ "epoch": 14.9,
+ "learning_rate": 1.2642045454545457e-05,
+ "loss": 0.3405,
"step": 1319
},
{
- "epoch": 26.71,
- "learning_rate": 3.1632653061224494e-05,
- "loss": 0.8276,
+ "epoch": 14.91,
+ "learning_rate": 1.25e-05,
+ "loss": 0.3253,
"step": 1320
},
{
- "epoch": 26.73,
- "learning_rate": 3.1505102040816325e-05,
- "loss": 0.8734,
+ "epoch": 14.92,
+ "learning_rate": 1.2357954545454546e-05,
+ "loss": 0.3335,
"step": 1321
},
{
- "epoch": 26.75,
- "learning_rate": 3.137755102040816e-05,
- "loss": 0.8663,
+ "epoch": 14.94,
+ "learning_rate": 1.2215909090909092e-05,
+ "loss": 0.34,
"step": 1322
},
{
- "epoch": 26.77,
- "learning_rate": 3.125e-05,
- "loss": 0.8354,
+ "epoch": 14.95,
+ "learning_rate": 1.2073863636363638e-05,
+ "loss": 0.3293,
"step": 1323
},
{
- "epoch": 26.79,
- "learning_rate": 3.112244897959184e-05,
- "loss": 0.8374,
+ "epoch": 14.96,
+ "learning_rate": 1.1931818181818183e-05,
+ "loss": 0.3315,
"step": 1324
},
{
- "epoch": 26.81,
- "learning_rate": 3.0994897959183676e-05,
- "loss": 0.9025,
+ "epoch": 14.97,
+ "learning_rate": 1.1789772727272728e-05,
+ "loss": 0.3338,
"step": 1325
},
{
- "epoch": 26.83,
- "learning_rate": 3.086734693877551e-05,
- "loss": 0.8618,
+ "epoch": 14.98,
+ "learning_rate": 1.1647727272727273e-05,
+ "loss": 0.3427,
"step": 1326
},
{
- "epoch": 26.85,
- "learning_rate": 3.073979591836735e-05,
- "loss": 0.8867,
+ "epoch": 14.99,
+ "learning_rate": 1.1505681818181818e-05,
+ "loss": 0.337,
"step": 1327
},
{
- "epoch": 26.87,
- "learning_rate": 3.061224489795919e-05,
- "loss": 0.7864,
+ "epoch": 15.0,
+ "learning_rate": 1.1363636363636365e-05,
+ "loss": 0.3317,
"step": 1328
},
{
- "epoch": 26.89,
- "learning_rate": 3.0484693877551023e-05,
- "loss": 0.7706,
+ "epoch": 15.01,
+ "learning_rate": 1.122159090909091e-05,
+ "loss": 0.3259,
"step": 1329
},
{
- "epoch": 26.91,
- "learning_rate": 3.0357142857142857e-05,
- "loss": 0.8677,
+ "epoch": 15.03,
+ "learning_rate": 1.1079545454545455e-05,
+ "loss": 0.3323,
"step": 1330
},
{
- "epoch": 26.93,
- "learning_rate": 3.0229591836734695e-05,
- "loss": 0.8619,
+ "epoch": 15.04,
+ "learning_rate": 1.09375e-05,
+ "loss": 0.3267,
"step": 1331
},
{
- "epoch": 26.95,
- "learning_rate": 3.0102040816326533e-05,
- "loss": 0.8487,
+ "epoch": 15.05,
+ "learning_rate": 1.0795454545454547e-05,
+ "loss": 0.3296,
"step": 1332
},
{
- "epoch": 26.97,
- "learning_rate": 2.997448979591837e-05,
- "loss": 0.8644,
+ "epoch": 15.06,
+ "learning_rate": 1.0653409090909092e-05,
+ "loss": 0.3169,
"step": 1333
},
{
- "epoch": 26.99,
- "learning_rate": 2.9846938775510208e-05,
- "loss": 0.8779,
+ "epoch": 15.07,
+ "learning_rate": 1.0511363636363637e-05,
+ "loss": 0.3228,
"step": 1334
},
{
- "epoch": 27.01,
- "learning_rate": 2.9719387755102042e-05,
- "loss": 0.8589,
+ "epoch": 15.08,
+ "learning_rate": 1.0369318181818184e-05,
+ "loss": 0.3382,
"step": 1335
},
{
- "epoch": 27.03,
- "learning_rate": 2.959183673469388e-05,
- "loss": 0.8214,
+ "epoch": 15.09,
+ "learning_rate": 1.0227272727272729e-05,
+ "loss": 0.3271,
"step": 1336
},
{
- "epoch": 27.05,
- "learning_rate": 2.9464285714285718e-05,
- "loss": 0.7907,
+ "epoch": 15.1,
+ "learning_rate": 1.0085227272727272e-05,
+ "loss": 0.3388,
"step": 1337
},
{
- "epoch": 27.07,
- "learning_rate": 2.9336734693877555e-05,
- "loss": 0.8493,
+ "epoch": 15.12,
+ "learning_rate": 9.943181818181819e-06,
+ "loss": 0.3242,
"step": 1338
},
{
- "epoch": 27.09,
- "learning_rate": 2.9209183673469386e-05,
- "loss": 0.8423,
+ "epoch": 15.13,
+ "learning_rate": 9.801136363636364e-06,
+ "loss": 0.3373,
"step": 1339
},
{
- "epoch": 27.11,
- "learning_rate": 2.9081632653061224e-05,
- "loss": 0.7737,
+ "epoch": 15.14,
+ "learning_rate": 9.659090909090909e-06,
+ "loss": 0.325,
"step": 1340
},
{
- "epoch": 27.13,
- "learning_rate": 2.895408163265306e-05,
- "loss": 0.792,
+ "epoch": 15.15,
+ "learning_rate": 9.517045454545454e-06,
+ "loss": 0.3304,
"step": 1341
},
{
- "epoch": 27.15,
- "learning_rate": 2.8826530612244902e-05,
- "loss": 0.8145,
+ "epoch": 15.16,
+ "learning_rate": 9.375000000000001e-06,
+ "loss": 0.3291,
"step": 1342
},
{
- "epoch": 27.17,
- "learning_rate": 2.869897959183674e-05,
- "loss": 0.8356,
+ "epoch": 15.17,
+ "learning_rate": 9.232954545454546e-06,
+ "loss": 0.322,
"step": 1343
},
{
- "epoch": 27.19,
- "learning_rate": 2.857142857142857e-05,
- "loss": 0.815,
+ "epoch": 15.18,
+ "learning_rate": 9.090909090909091e-06,
+ "loss": 0.3499,
"step": 1344
},
{
- "epoch": 27.21,
- "learning_rate": 2.844387755102041e-05,
- "loss": 0.7806,
+ "epoch": 15.2,
+ "learning_rate": 8.948863636363638e-06,
+ "loss": 0.3307,
"step": 1345
},
{
- "epoch": 27.23,
- "learning_rate": 2.8316326530612246e-05,
- "loss": 0.835,
+ "epoch": 15.21,
+ "learning_rate": 8.806818181818183e-06,
+ "loss": 0.3527,
"step": 1346
},
{
- "epoch": 27.26,
- "learning_rate": 2.8188775510204084e-05,
- "loss": 0.8514,
+ "epoch": 15.22,
+ "learning_rate": 8.664772727272728e-06,
+ "loss": 0.325,
"step": 1347
},
{
- "epoch": 27.28,
- "learning_rate": 2.8061224489795918e-05,
- "loss": 0.8251,
+ "epoch": 15.23,
+ "learning_rate": 8.522727272727273e-06,
+ "loss": 0.3353,
"step": 1348
},
{
- "epoch": 27.3,
- "learning_rate": 2.7933673469387756e-05,
- "loss": 0.8456,
+ "epoch": 15.24,
+ "learning_rate": 8.380681818181818e-06,
+ "loss": 0.3316,
"step": 1349
},
{
- "epoch": 27.32,
- "learning_rate": 2.7806122448979593e-05,
- "loss": 0.8925,
+ "epoch": 15.25,
+ "learning_rate": 8.238636363636363e-06,
+ "loss": 0.3347,
"step": 1350
},
{
- "epoch": 27.34,
- "learning_rate": 2.767857142857143e-05,
- "loss": 0.8284,
+ "epoch": 15.26,
+ "learning_rate": 8.09659090909091e-06,
+ "loss": 0.3275,
"step": 1351
},
{
- "epoch": 27.36,
- "learning_rate": 2.7551020408163265e-05,
- "loss": 0.8471,
+ "epoch": 15.27,
+ "learning_rate": 7.954545454545455e-06,
+ "loss": 0.3288,
"step": 1352
},
{
- "epoch": 27.38,
- "learning_rate": 2.7423469387755103e-05,
- "loss": 0.819,
+ "epoch": 15.29,
+ "learning_rate": 7.8125e-06,
+ "loss": 0.3293,
"step": 1353
},
{
- "epoch": 27.4,
- "learning_rate": 2.729591836734694e-05,
- "loss": 0.8474,
+ "epoch": 15.3,
+ "learning_rate": 7.670454545454545e-06,
+ "loss": 0.3324,
"step": 1354
},
{
- "epoch": 27.42,
- "learning_rate": 2.7168367346938778e-05,
- "loss": 0.8378,
+ "epoch": 15.31,
+ "learning_rate": 7.528409090909091e-06,
+ "loss": 0.3286,
"step": 1355
},
{
- "epoch": 27.44,
- "learning_rate": 2.7040816326530616e-05,
- "loss": 0.8383,
+ "epoch": 15.32,
+ "learning_rate": 7.386363636363637e-06,
+ "loss": 0.3355,
"step": 1356
},
{
- "epoch": 27.46,
- "learning_rate": 2.6913265306122447e-05,
- "loss": 0.8534,
+ "epoch": 15.33,
+ "learning_rate": 7.244318181818183e-06,
+ "loss": 0.3353,
"step": 1357
},
{
- "epoch": 27.48,
- "learning_rate": 2.6785714285714288e-05,
- "loss": 0.8243,
+ "epoch": 15.34,
+ "learning_rate": 7.102272727272728e-06,
+ "loss": 0.3291,
"step": 1358
},
{
- "epoch": 27.5,
- "learning_rate": 2.6658163265306125e-05,
- "loss": 0.8467,
+ "epoch": 15.35,
+ "learning_rate": 6.960227272727272e-06,
+ "loss": 0.3358,
"step": 1359
},
{
- "epoch": 27.52,
- "learning_rate": 2.6530612244897963e-05,
- "loss": 0.8503,
+ "epoch": 15.36,
+ "learning_rate": 6.818181818181818e-06,
+ "loss": 0.3289,
"step": 1360
},
{
- "epoch": 27.54,
- "learning_rate": 2.6403061224489794e-05,
- "loss": 0.7655,
+ "epoch": 15.38,
+ "learning_rate": 6.676136363636363e-06,
+ "loss": 0.3253,
"step": 1361
},
{
- "epoch": 27.56,
- "learning_rate": 2.627551020408163e-05,
- "loss": 0.854,
+ "epoch": 15.39,
+ "learning_rate": 6.534090909090909e-06,
+ "loss": 0.3172,
"step": 1362
},
{
- "epoch": 27.58,
- "learning_rate": 2.614795918367347e-05,
- "loss": 0.838,
+ "epoch": 15.4,
+ "learning_rate": 6.392045454545454e-06,
+ "loss": 0.3192,
"step": 1363
},
{
- "epoch": 27.6,
- "learning_rate": 2.6020408163265307e-05,
- "loss": 0.8275,
+ "epoch": 15.41,
+ "learning_rate": 6.25e-06,
+ "loss": 0.3228,
"step": 1364
},
{
- "epoch": 27.62,
- "learning_rate": 2.5892857142857148e-05,
- "loss": 0.8494,
+ "epoch": 15.42,
+ "learning_rate": 6.107954545454546e-06,
+ "loss": 0.3269,
"step": 1365
},
{
- "epoch": 27.64,
- "learning_rate": 2.576530612244898e-05,
- "loss": 0.842,
+ "epoch": 15.43,
+ "learning_rate": 5.965909090909091e-06,
+ "loss": 0.3222,
"step": 1366
},
{
- "epoch": 27.66,
- "learning_rate": 2.5637755102040816e-05,
- "loss": 0.8176,
+ "epoch": 15.44,
+ "learning_rate": 5.823863636363636e-06,
+ "loss": 0.3382,
"step": 1367
},
{
- "epoch": 27.68,
- "learning_rate": 2.5510204081632654e-05,
- "loss": 0.8301,
+ "epoch": 15.45,
+ "learning_rate": 5.681818181818182e-06,
+ "loss": 0.3259,
"step": 1368
},
{
- "epoch": 27.7,
- "learning_rate": 2.538265306122449e-05,
- "loss": 0.8182,
+ "epoch": 15.47,
+ "learning_rate": 5.539772727272727e-06,
+ "loss": 0.3187,
"step": 1369
},
{
- "epoch": 27.72,
- "learning_rate": 2.5255102040816326e-05,
- "loss": 0.8067,
+ "epoch": 15.48,
+ "learning_rate": 5.397727272727273e-06,
+ "loss": 0.3283,
"step": 1370
},
{
- "epoch": 27.74,
- "learning_rate": 2.5127551020408164e-05,
- "loss": 0.8322,
+ "epoch": 15.49,
+ "learning_rate": 5.255681818181818e-06,
+ "loss": 0.3197,
"step": 1371
},
{
- "epoch": 27.76,
- "learning_rate": 2.5e-05,
- "loss": 0.828,
+ "epoch": 15.5,
+ "learning_rate": 5.113636363636364e-06,
+ "loss": 0.3508,
"step": 1372
},
{
- "epoch": 27.78,
- "learning_rate": 2.487244897959184e-05,
- "loss": 0.8583,
+ "epoch": 15.51,
+ "learning_rate": 4.9715909090909094e-06,
+ "loss": 0.3429,
"step": 1373
},
{
- "epoch": 27.8,
- "learning_rate": 2.4744897959183673e-05,
- "loss": 0.8273,
+ "epoch": 15.52,
+ "learning_rate": 4.8295454545454545e-06,
+ "loss": 0.3444,
"step": 1374
},
{
- "epoch": 27.82,
- "learning_rate": 2.461734693877551e-05,
- "loss": 0.8292,
+ "epoch": 15.53,
+ "learning_rate": 4.6875000000000004e-06,
+ "loss": 0.3289,
"step": 1375
},
{
- "epoch": 27.84,
- "learning_rate": 2.448979591836735e-05,
- "loss": 0.9004,
+ "epoch": 15.55,
+ "learning_rate": 4.5454545454545455e-06,
+ "loss": 0.3307,
"step": 1376
},
{
- "epoch": 27.86,
- "learning_rate": 2.4362244897959186e-05,
- "loss": 0.8589,
+ "epoch": 15.56,
+ "learning_rate": 4.4034090909090914e-06,
+ "loss": 0.3295,
"step": 1377
},
{
- "epoch": 27.88,
- "learning_rate": 2.423469387755102e-05,
- "loss": 0.8559,
+ "epoch": 15.57,
+ "learning_rate": 4.2613636363636365e-06,
+ "loss": 0.3241,
"step": 1378
},
{
- "epoch": 27.9,
- "learning_rate": 2.4107142857142858e-05,
- "loss": 0.8224,
+ "epoch": 15.58,
+ "learning_rate": 4.119318181818182e-06,
+ "loss": 0.3213,
"step": 1379
},
{
- "epoch": 27.92,
- "learning_rate": 2.3979591836734696e-05,
- "loss": 0.8438,
+ "epoch": 15.59,
+ "learning_rate": 3.9772727272727275e-06,
+ "loss": 0.3289,
"step": 1380
},
{
- "epoch": 27.94,
- "learning_rate": 2.3852040816326533e-05,
- "loss": 0.8267,
+ "epoch": 15.6,
+ "learning_rate": 3.835227272727273e-06,
+ "loss": 0.3272,
"step": 1381
},
{
- "epoch": 27.96,
- "learning_rate": 2.372448979591837e-05,
- "loss": 0.8472,
+ "epoch": 15.61,
+ "learning_rate": 3.6931818181818186e-06,
+ "loss": 0.3257,
"step": 1382
},
{
- "epoch": 27.98,
- "learning_rate": 2.3596938775510205e-05,
- "loss": 0.835,
+ "epoch": 15.62,
+ "learning_rate": 3.551136363636364e-06,
+ "loss": 0.3396,
"step": 1383
},
{
- "epoch": 28.0,
- "learning_rate": 2.3469387755102043e-05,
- "loss": 0.847,
+ "epoch": 15.64,
+ "learning_rate": 3.409090909090909e-06,
+ "loss": 0.3163,
"step": 1384
},
{
- "epoch": 28.02,
- "learning_rate": 2.3341836734693877e-05,
- "loss": 0.865,
+ "epoch": 15.65,
+ "learning_rate": 3.2670454545454546e-06,
+ "loss": 0.3268,
"step": 1385
},
{
- "epoch": 28.04,
- "learning_rate": 2.3214285714285715e-05,
- "loss": 0.807,
+ "epoch": 15.66,
+ "learning_rate": 3.125e-06,
+ "loss": 0.3203,
"step": 1386
},
{
- "epoch": 28.06,
- "learning_rate": 2.3086734693877552e-05,
- "loss": 0.8133,
+ "epoch": 15.67,
+ "learning_rate": 2.9829545454545457e-06,
+ "loss": 0.338,
"step": 1387
},
{
- "epoch": 28.08,
- "learning_rate": 2.295918367346939e-05,
- "loss": 0.8242,
+ "epoch": 15.68,
+ "learning_rate": 2.840909090909091e-06,
+ "loss": 0.325,
"step": 1388
},
{
- "epoch": 28.1,
- "learning_rate": 2.2831632653061224e-05,
- "loss": 0.8142,
+ "epoch": 15.69,
+ "learning_rate": 2.6988636363636367e-06,
+ "loss": 0.3236,
"step": 1389
},
{
- "epoch": 28.13,
- "learning_rate": 2.2704081632653062e-05,
- "loss": 0.7772,
+ "epoch": 15.7,
+ "learning_rate": 2.556818181818182e-06,
+ "loss": 0.3247,
"step": 1390
},
{
- "epoch": 28.15,
- "learning_rate": 2.2576530612244896e-05,
- "loss": 0.7885,
+ "epoch": 15.71,
+ "learning_rate": 2.4147727272727273e-06,
+ "loss": 0.3312,
"step": 1391
},
{
- "epoch": 28.17,
- "learning_rate": 2.2448979591836737e-05,
- "loss": 0.8096,
+ "epoch": 15.73,
+ "learning_rate": 2.2727272727272728e-06,
+ "loss": 0.3431,
"step": 1392
},
{
- "epoch": 28.19,
- "learning_rate": 2.2321428571428575e-05,
- "loss": 0.8497,
+ "epoch": 15.74,
+ "learning_rate": 2.1306818181818183e-06,
+ "loss": 0.3205,
"step": 1393
},
{
- "epoch": 28.21,
- "learning_rate": 2.219387755102041e-05,
- "loss": 0.8814,
+ "epoch": 15.75,
+ "learning_rate": 1.9886363636363638e-06,
+ "loss": 0.3273,
"step": 1394
},
{
- "epoch": 28.23,
- "learning_rate": 2.2066326530612247e-05,
- "loss": 0.8634,
+ "epoch": 15.76,
+ "learning_rate": 1.8465909090909093e-06,
+ "loss": 0.3253,
"step": 1395
},
{
- "epoch": 28.25,
- "learning_rate": 2.193877551020408e-05,
- "loss": 0.8084,
+ "epoch": 15.77,
+ "learning_rate": 1.7045454545454546e-06,
+ "loss": 0.3279,
"step": 1396
},
{
- "epoch": 28.27,
- "learning_rate": 2.181122448979592e-05,
- "loss": 0.7792,
+ "epoch": 15.78,
+ "learning_rate": 1.5625e-06,
+ "loss": 0.3338,
"step": 1397
},
{
- "epoch": 28.29,
- "learning_rate": 2.1683673469387756e-05,
- "loss": 0.7998,
+ "epoch": 15.79,
+ "learning_rate": 1.4204545454545456e-06,
+ "loss": 0.3292,
"step": 1398
},
{
- "epoch": 28.31,
- "learning_rate": 2.1556122448979594e-05,
- "loss": 0.7963,
+ "epoch": 15.81,
+ "learning_rate": 1.278409090909091e-06,
+ "loss": 0.324,
"step": 1399
},
{
- "epoch": 28.33,
- "learning_rate": 2.1428571428571428e-05,
- "loss": 0.8058,
+ "epoch": 15.82,
+ "learning_rate": 1.1363636363636364e-06,
+ "loss": 0.31,
"step": 1400
}
],
"logging_steps": 1,
- "max_steps": 1568,
- "num_train_epochs": 32,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
"save_steps": 100,
- "total_flos": 2.0726121875201434e+18,
+ "total_flos": 1.9109229260683162e+18,
"trial_name": null,
"trial_params": null
}
diff --git a/checkpoint-1400/training_args.bin b/checkpoint-1400/training_args.bin
index db23e07d097c18532e52f58a70eb72d22e39c8c1..ee7ddb867f05d9a969f71467a8eb88994865cf51 100644
--- a/checkpoint-1400/training_args.bin
+++ b/checkpoint-1400/training_args.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
size 4155
diff --git a/checkpoint-500/README.md b/checkpoint-500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..08371015f02382e6fcba318f4aaea54ae52cd3c4
--- /dev/null
+++ b/checkpoint-500/README.md
@@ -0,0 +1,34 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+- PEFT 0.6.0.dev0
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-500/adapter_config.json b/checkpoint-500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..751d838ac0c1ae5ca71ca448b25d7a8a0173f01b
--- /dev/null
+++ b/checkpoint-500/adapter_config.json
@@ -0,0 +1,23 @@
+{
+ "auto_mapping": null,
+ "base_model_name_or_path": "bigscience/bloomz-3b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "lora_alpha": 16,
+ "lora_dropout": 0.0,
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "revision": null,
+ "target_modules": [
+ "dense_4h_to_h",
+ "dense",
+ "dense_h_to_4h",
+ "query_key_value"
+ ],
+ "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-500/adapter_model.bin b/checkpoint-500/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..29fa2903b59a1caaeb699cae9c531c16898a763c
--- /dev/null
+++ b/checkpoint-500/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:297ef8417e7df986ce834d9b0c8ebd28197873ea409686414f04e91b74281978
+size 39409357
diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4e94c574163d8d7559e98a1529bd1fb5f3f661fc
--- /dev/null
+++ b/checkpoint-500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8afe492977b67949412a751b16cf3c9e70d22ef10182d710a235c40cb1a4ac
+size 78844421
diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..52c3c528216530c307d1385ed9ffbc3fc18fe283
--- /dev/null
+++ b/checkpoint-500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6162bb9db25c89c41e126a7a00a5d0695219447bff9b18d08731531620758440
+size 14575
diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cf19db9ba23ce9daa53e3253bf2841a2fd659a36
--- /dev/null
+++ b/checkpoint-500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5434e83c78ab052927972350ed56fbd84392b488b1d09a11bdb87201790659f
+size 627
diff --git a/checkpoint-500/special_tokens_map.json b/checkpoint-500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..fdafe480f024ff444c7492147536765ce5d55a2d
--- /dev/null
+++ b/checkpoint-500/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+ "bos_token": "",
+ "eos_token": "",
+ "pad_token": "",
+ "unk_token": ""
+}
diff --git a/checkpoint-500/tokenizer.json b/checkpoint-500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..dbf002cafbd4818dcff2abc9156c088d681b4533
--- /dev/null
+++ b/checkpoint-500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
+size 14500471
diff --git a/checkpoint-500/tokenizer_config.json b/checkpoint-500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b56cc9c2965c07132c35df3e2972e93d98c82c3
--- /dev/null
+++ b/checkpoint-500/tokenizer_config.json
@@ -0,0 +1,10 @@
+{
+ "add_prefix_space": false,
+ "bos_token": "",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "",
+ "tokenizer_class": "BloomTokenizer",
+ "unk_token": ""
+}
diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9a1fb94e52a3f74ba72094e87380c24b49a9bf44
--- /dev/null
+++ b/checkpoint-500/trainer_state.json
@@ -0,0 +1,3019 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 5.648720211827008,
+ "eval_steps": 500,
+ "global_step": 500,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
+ "step": 1
+ },
+ {
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
+ "step": 2
+ },
+ {
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
+ "step": 3
+ },
+ {
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
+ "step": 4
+ },
+ {
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
+ "step": 5
+ },
+ {
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
+ "step": 6
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
+ "step": 7
+ },
+ {
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
+ "step": 8
+ },
+ {
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
+ "step": 9
+ },
+ {
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
+ "step": 10
+ },
+ {
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
+ "step": 11
+ },
+ {
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
+ "step": 12
+ },
+ {
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
+ "step": 13
+ },
+ {
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
+ "step": 14
+ },
+ {
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
+ "step": 15
+ },
+ {
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
+ "step": 16
+ },
+ {
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
+ "step": 17
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
+ "step": 18
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
+ "step": 19
+ },
+ {
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
+ "step": 20
+ },
+ {
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
+ "step": 21
+ },
+ {
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
+ "step": 22
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
+ "step": 23
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
+ "step": 24
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
+ "step": 25
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
+ "step": 26
+ },
+ {
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
+ "step": 27
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
+ "step": 28
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
+ "step": 29
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
+ "step": 30
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
+ "step": 31
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
+ "step": 32
+ },
+ {
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
+ "step": 33
+ },
+ {
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
+ "step": 34
+ },
+ {
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
+ "step": 35
+ },
+ {
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
+ "step": 36
+ },
+ {
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
+ "step": 37
+ },
+ {
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
+ "step": 38
+ },
+ {
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
+ "step": 39
+ },
+ {
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
+ "step": 40
+ },
+ {
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
+ "step": 41
+ },
+ {
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
+ "step": 42
+ },
+ {
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
+ "step": 43
+ },
+ {
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
+ "step": 44
+ },
+ {
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
+ "step": 45
+ },
+ {
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
+ "step": 46
+ },
+ {
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
+ "step": 47
+ },
+ {
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
+ "step": 48
+ },
+ {
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
+ "step": 49
+ },
+ {
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
+ "step": 50
+ },
+ {
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
+ "step": 51
+ },
+ {
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
+ "step": 52
+ },
+ {
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
+ "step": 53
+ },
+ {
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
+ "step": 54
+ },
+ {
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
+ "step": 55
+ },
+ {
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
+ "step": 56
+ },
+ {
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
+ "step": 57
+ },
+ {
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
+ "step": 58
+ },
+ {
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
+ "step": 59
+ },
+ {
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
+ "step": 60
+ },
+ {
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
+ "step": 61
+ },
+ {
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
+ "step": 62
+ },
+ {
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
+ "step": 63
+ },
+ {
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
+ "step": 64
+ },
+ {
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
+ "step": 65
+ },
+ {
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
+ "step": 66
+ },
+ {
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
+ "step": 67
+ },
+ {
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
+ "step": 68
+ },
+ {
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
+ "step": 69
+ },
+ {
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
+ "step": 70
+ },
+ {
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
+ "step": 71
+ },
+ {
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
+ "step": 72
+ },
+ {
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
+ "step": 73
+ },
+ {
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
+ "step": 74
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
+ "step": 75
+ },
+ {
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
+ "step": 76
+ },
+ {
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
+ "step": 77
+ },
+ {
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
+ "step": 78
+ },
+ {
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
+ "step": 79
+ },
+ {
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
+ "step": 80
+ },
+ {
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
+ "step": 81
+ },
+ {
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
+ "step": 82
+ },
+ {
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
+ "step": 83
+ },
+ {
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
+ "step": 84
+ },
+ {
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
+ "step": 85
+ },
+ {
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
+ "step": 86
+ },
+ {
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
+ "step": 87
+ },
+ {
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
+ "step": 88
+ },
+ {
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
+ "step": 89
+ },
+ {
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
+ "step": 90
+ },
+ {
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
+ "step": 91
+ },
+ {
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
+ "step": 92
+ },
+ {
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
+ "step": 93
+ },
+ {
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
+ "step": 94
+ },
+ {
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
+ "step": 95
+ },
+ {
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
+ "step": 96
+ },
+ {
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
+ "step": 97
+ },
+ {
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
+ "step": 98
+ },
+ {
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
+ "step": 99
+ },
+ {
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
+ "step": 100
+ },
+ {
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
+ "step": 101
+ },
+ {
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
+ "step": 102
+ },
+ {
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
+ "step": 103
+ },
+ {
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
+ "step": 104
+ },
+ {
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
+ "step": 105
+ },
+ {
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
+ "step": 106
+ },
+ {
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
+ "step": 107
+ },
+ {
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
+ "step": 108
+ },
+ {
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
+ "step": 109
+ },
+ {
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
+ "step": 110
+ },
+ {
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
+ "step": 111
+ },
+ {
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
+ "step": 112
+ },
+ {
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
+ "step": 113
+ },
+ {
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
+ "step": 114
+ },
+ {
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
+ "step": 115
+ },
+ {
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
+ "step": 116
+ },
+ {
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
+ "step": 117
+ },
+ {
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
+ "step": 118
+ },
+ {
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
+ "step": 119
+ },
+ {
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
+ "step": 120
+ },
+ {
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
+ "step": 121
+ },
+ {
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
+ "step": 122
+ },
+ {
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
+ "step": 123
+ },
+ {
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
+ "step": 124
+ },
+ {
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
+ "step": 125
+ },
+ {
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
+ "step": 126
+ },
+ {
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
+ "step": 127
+ },
+ {
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
+ "step": 128
+ },
+ {
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
+ "step": 129
+ },
+ {
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
+ "step": 130
+ },
+ {
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
+ "step": 131
+ },
+ {
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
+ "step": 132
+ },
+ {
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
+ "step": 133
+ },
+ {
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
+ "step": 134
+ },
+ {
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
+ "step": 135
+ },
+ {
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
+ "step": 136
+ },
+ {
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
+ "step": 137
+ },
+ {
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
+ "step": 138
+ },
+ {
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
+ "step": 139
+ },
+ {
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
+ "step": 140
+ },
+ {
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
+ "step": 141
+ },
+ {
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
+ "step": 142
+ },
+ {
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
+ "step": 143
+ },
+ {
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
+ "step": 144
+ },
+ {
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
+ "step": 145
+ },
+ {
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
+ "step": 146
+ },
+ {
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
+ "step": 147
+ },
+ {
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
+ "step": 148
+ },
+ {
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
+ "step": 149
+ },
+ {
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
+ "step": 150
+ },
+ {
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
+ "step": 151
+ },
+ {
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
+ "step": 152
+ },
+ {
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
+ "step": 153
+ },
+ {
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
+ "step": 154
+ },
+ {
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
+ "step": 155
+ },
+ {
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
+ "step": 156
+ },
+ {
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
+ "step": 157
+ },
+ {
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
+ "step": 158
+ },
+ {
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
+ "step": 159
+ },
+ {
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
+ "step": 160
+ },
+ {
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
+ "step": 161
+ },
+ {
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
+ "step": 162
+ },
+ {
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
+ "step": 163
+ },
+ {
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
+ "step": 164
+ },
+ {
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
+ "step": 165
+ },
+ {
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
+ "step": 166
+ },
+ {
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
+ "step": 167
+ },
+ {
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
+ "step": 168
+ },
+ {
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
+ "step": 169
+ },
+ {
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
+ "step": 170
+ },
+ {
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
+ "step": 171
+ },
+ {
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
+ "step": 172
+ },
+ {
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
+ "step": 173
+ },
+ {
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
+ "step": 174
+ },
+ {
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
+ "step": 175
+ },
+ {
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
+ "step": 176
+ },
+ {
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
+ "step": 177
+ },
+ {
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
+ "step": 178
+ },
+ {
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
+ "step": 179
+ },
+ {
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
+ "step": 180
+ },
+ {
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
+ "step": 181
+ },
+ {
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
+ "step": 182
+ },
+ {
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
+ "step": 183
+ },
+ {
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
+ "step": 184
+ },
+ {
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
+ "step": 185
+ },
+ {
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
+ "step": 186
+ },
+ {
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
+ "step": 187
+ },
+ {
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
+ "step": 188
+ },
+ {
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
+ "step": 189
+ },
+ {
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
+ "step": 190
+ },
+ {
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
+ "step": 191
+ },
+ {
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
+ "step": 192
+ },
+ {
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
+ "step": 193
+ },
+ {
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
+ "step": 194
+ },
+ {
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
+ "step": 195
+ },
+ {
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
+ "step": 196
+ },
+ {
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
+ "step": 197
+ },
+ {
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
+ "step": 198
+ },
+ {
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
+ "step": 199
+ },
+ {
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
+ "step": 200
+ },
+ {
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
+ "step": 201
+ },
+ {
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
+ "step": 202
+ },
+ {
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
+ "step": 203
+ },
+ {
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
+ "step": 204
+ },
+ {
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
+ "step": 205
+ },
+ {
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
+ "step": 206
+ },
+ {
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
+ "step": 207
+ },
+ {
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
+ "step": 208
+ },
+ {
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
+ "step": 209
+ },
+ {
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
+ "step": 210
+ },
+ {
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
+ "step": 211
+ },
+ {
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
+ "step": 212
+ },
+ {
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
+ "step": 213
+ },
+ {
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
+ "step": 214
+ },
+ {
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
+ "step": 215
+ },
+ {
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
+ "step": 216
+ },
+ {
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
+ "step": 217
+ },
+ {
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
+ "step": 218
+ },
+ {
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
+ "step": 219
+ },
+ {
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
+ "step": 220
+ },
+ {
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
+ "step": 221
+ },
+ {
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
+ "step": 222
+ },
+ {
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
+ "step": 223
+ },
+ {
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
+ "step": 224
+ },
+ {
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
+ "step": 225
+ },
+ {
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
+ "step": 226
+ },
+ {
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
+ "step": 227
+ },
+ {
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
+ "step": 228
+ },
+ {
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
+ "step": 229
+ },
+ {
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
+ "step": 230
+ },
+ {
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
+ "step": 231
+ },
+ {
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
+ "step": 232
+ },
+ {
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
+ "step": 233
+ },
+ {
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
+ "step": 234
+ },
+ {
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
+ "step": 235
+ },
+ {
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
+ "step": 236
+ },
+ {
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
+ "step": 237
+ },
+ {
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
+ "step": 238
+ },
+ {
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
+ "step": 239
+ },
+ {
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
+ "step": 240
+ },
+ {
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
+ "step": 241
+ },
+ {
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
+ "step": 242
+ },
+ {
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
+ "step": 243
+ },
+ {
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
+ "step": 244
+ },
+ {
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
+ "step": 245
+ },
+ {
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
+ "step": 246
+ },
+ {
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
+ "step": 247
+ },
+ {
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
+ "step": 248
+ },
+ {
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
+ "step": 249
+ },
+ {
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
+ "step": 250
+ },
+ {
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
+ "step": 251
+ },
+ {
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
+ "step": 252
+ },
+ {
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
+ "step": 253
+ },
+ {
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
+ "step": 254
+ },
+ {
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
+ "step": 255
+ },
+ {
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
+ "step": 256
+ },
+ {
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
+ "step": 257
+ },
+ {
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
+ "step": 258
+ },
+ {
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
+ "step": 259
+ },
+ {
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
+ "step": 260
+ },
+ {
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
+ "step": 261
+ },
+ {
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
+ "step": 262
+ },
+ {
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
+ "step": 263
+ },
+ {
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
+ "step": 264
+ },
+ {
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
+ "step": 265
+ },
+ {
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
+ "step": 266
+ },
+ {
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
+ "step": 267
+ },
+ {
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
+ "step": 268
+ },
+ {
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
+ "step": 269
+ },
+ {
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
+ "step": 270
+ },
+ {
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
+ "step": 271
+ },
+ {
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
+ "step": 272
+ },
+ {
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
+ "step": 273
+ },
+ {
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
+ "step": 274
+ },
+ {
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
+ "step": 275
+ },
+ {
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
+ "step": 276
+ },
+ {
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
+ "step": 277
+ },
+ {
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
+ "step": 278
+ },
+ {
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
+ "step": 279
+ },
+ {
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
+ "step": 280
+ },
+ {
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
+ "step": 281
+ },
+ {
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
+ "step": 282
+ },
+ {
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
+ "step": 283
+ },
+ {
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
+ "step": 284
+ },
+ {
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
+ "step": 285
+ },
+ {
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
+ "step": 286
+ },
+ {
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
+ "step": 287
+ },
+ {
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
+ "step": 288
+ },
+ {
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
+ "step": 289
+ },
+ {
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
+ "step": 290
+ },
+ {
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
+ "step": 291
+ },
+ {
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
+ "step": 292
+ },
+ {
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
+ "step": 293
+ },
+ {
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
+ "step": 294
+ },
+ {
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
+ "step": 295
+ },
+ {
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
+ "step": 296
+ },
+ {
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
+ "step": 297
+ },
+ {
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
+ "step": 298
+ },
+ {
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
+ "step": 299
+ },
+ {
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
+ "step": 300
+ },
+ {
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
+ "step": 301
+ },
+ {
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
+ "step": 302
+ },
+ {
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
+ "step": 303
+ },
+ {
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
+ "step": 304
+ },
+ {
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
+ "step": 305
+ },
+ {
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
+ "step": 306
+ },
+ {
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
+ "step": 307
+ },
+ {
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
+ "step": 308
+ },
+ {
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
+ "step": 309
+ },
+ {
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
+ "step": 310
+ },
+ {
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
+ "step": 311
+ },
+ {
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
+ "step": 312
+ },
+ {
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
+ "step": 313
+ },
+ {
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
+ "step": 314
+ },
+ {
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
+ "step": 315
+ },
+ {
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
+ "step": 316
+ },
+ {
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
+ "step": 317
+ },
+ {
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
+ "step": 318
+ },
+ {
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
+ "step": 319
+ },
+ {
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
+ "step": 320
+ },
+ {
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
+ "step": 321
+ },
+ {
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
+ "step": 322
+ },
+ {
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
+ "step": 323
+ },
+ {
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
+ "step": 324
+ },
+ {
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
+ "step": 325
+ },
+ {
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
+ "step": 326
+ },
+ {
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
+ "step": 327
+ },
+ {
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
+ "step": 328
+ },
+ {
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
+ "step": 329
+ },
+ {
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
+ "step": 330
+ },
+ {
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
+ "step": 331
+ },
+ {
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
+ "step": 332
+ },
+ {
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
+ "step": 333
+ },
+ {
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
+ "step": 334
+ },
+ {
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
+ "step": 335
+ },
+ {
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
+ "step": 336
+ },
+ {
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
+ "step": 337
+ },
+ {
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
+ "step": 338
+ },
+ {
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
+ "step": 339
+ },
+ {
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
+ "step": 340
+ },
+ {
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
+ "step": 341
+ },
+ {
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
+ "step": 342
+ },
+ {
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
+ "step": 343
+ },
+ {
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
+ "step": 344
+ },
+ {
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
+ "step": 345
+ },
+ {
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
+ "step": 346
+ },
+ {
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
+ "step": 347
+ },
+ {
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
+ "step": 348
+ },
+ {
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
+ "step": 349
+ },
+ {
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
+ "step": 350
+ },
+ {
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
+ "step": 351
+ },
+ {
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
+ "step": 352
+ },
+ {
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
+ "step": 353
+ },
+ {
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
+ "step": 354
+ },
+ {
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
+ "step": 355
+ },
+ {
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
+ "step": 356
+ },
+ {
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
+ "step": 357
+ },
+ {
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
+ "step": 358
+ },
+ {
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
+ "step": 359
+ },
+ {
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
+ "step": 360
+ },
+ {
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
+ "step": 361
+ },
+ {
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
+ "step": 362
+ },
+ {
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
+ "step": 363
+ },
+ {
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
+ "step": 364
+ },
+ {
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
+ "step": 365
+ },
+ {
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
+ "step": 366
+ },
+ {
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
+ "step": 367
+ },
+ {
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
+ "step": 368
+ },
+ {
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
+ "step": 369
+ },
+ {
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
+ "step": 370
+ },
+ {
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
+ "step": 371
+ },
+ {
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
+ "step": 372
+ },
+ {
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
+ "step": 373
+ },
+ {
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
+ "step": 374
+ },
+ {
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
+ "step": 375
+ },
+ {
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
+ "step": 376
+ },
+ {
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
+ "step": 377
+ },
+ {
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
+ "step": 378
+ },
+ {
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
+ "step": 379
+ },
+ {
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
+ "step": 380
+ },
+ {
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
+ "step": 381
+ },
+ {
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
+ "step": 382
+ },
+ {
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
+ "step": 383
+ },
+ {
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
+ "step": 384
+ },
+ {
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
+ "step": 385
+ },
+ {
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
+ "step": 386
+ },
+ {
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
+ "step": 387
+ },
+ {
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
+ "step": 388
+ },
+ {
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
+ "step": 389
+ },
+ {
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
+ "step": 390
+ },
+ {
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
+ "step": 391
+ },
+ {
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
+ "step": 392
+ },
+ {
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
+ "step": 393
+ },
+ {
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
+ "step": 394
+ },
+ {
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
+ "step": 395
+ },
+ {
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
+ "step": 396
+ },
+ {
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
+ "step": 397
+ },
+ {
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
+ "step": 398
+ },
+ {
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
+ "step": 399
+ },
+ {
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
+ "step": 400
+ },
+ {
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
+ "step": 401
+ },
+ {
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
+ "step": 402
+ },
+ {
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
+ "step": 403
+ },
+ {
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
+ "step": 404
+ },
+ {
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
+ "step": 405
+ },
+ {
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
+ "step": 406
+ },
+ {
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
+ "step": 407
+ },
+ {
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
+ "step": 408
+ },
+ {
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
+ "step": 409
+ },
+ {
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
+ "step": 410
+ },
+ {
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
+ "step": 411
+ },
+ {
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
+ "step": 412
+ },
+ {
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
+ "step": 413
+ },
+ {
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
+ "step": 414
+ },
+ {
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
+ "step": 415
+ },
+ {
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
+ "step": 416
+ },
+ {
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
+ "step": 417
+ },
+ {
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
+ "step": 418
+ },
+ {
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
+ "step": 419
+ },
+ {
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
+ "step": 420
+ },
+ {
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
+ "step": 421
+ },
+ {
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
+ "step": 422
+ },
+ {
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
+ "step": 423
+ },
+ {
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
+ "step": 424
+ },
+ {
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
+ "step": 425
+ },
+ {
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
+ "step": 426
+ },
+ {
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
+ "step": 427
+ },
+ {
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
+ "step": 428
+ },
+ {
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
+ "step": 429
+ },
+ {
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
+ "step": 430
+ },
+ {
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
+ "step": 431
+ },
+ {
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
+ "step": 432
+ },
+ {
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
+ "step": 433
+ },
+ {
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
+ "step": 434
+ },
+ {
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
+ "step": 435
+ },
+ {
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
+ "step": 436
+ },
+ {
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
+ "step": 437
+ },
+ {
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
+ "step": 438
+ },
+ {
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
+ "step": 439
+ },
+ {
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
+ "step": 440
+ },
+ {
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
+ "step": 441
+ },
+ {
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
+ "step": 442
+ },
+ {
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
+ "step": 443
+ },
+ {
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
+ "step": 444
+ },
+ {
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
+ "step": 445
+ },
+ {
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
+ "step": 446
+ },
+ {
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
+ "step": 447
+ },
+ {
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
+ "step": 448
+ },
+ {
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
+ "step": 449
+ },
+ {
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
+ "step": 450
+ },
+ {
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
+ "step": 451
+ },
+ {
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
+ "step": 452
+ },
+ {
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
+ "step": 453
+ },
+ {
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
+ "step": 454
+ },
+ {
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
+ "step": 455
+ },
+ {
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
+ "step": 456
+ },
+ {
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
+ "step": 457
+ },
+ {
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
+ "step": 458
+ },
+ {
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
+ "step": 459
+ },
+ {
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
+ "step": 460
+ },
+ {
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
+ "step": 461
+ },
+ {
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
+ "step": 462
+ },
+ {
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
+ "step": 463
+ },
+ {
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
+ "step": 464
+ },
+ {
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
+ "step": 465
+ },
+ {
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
+ "step": 466
+ },
+ {
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
+ "step": 467
+ },
+ {
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
+ "step": 468
+ },
+ {
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
+ "step": 469
+ },
+ {
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
+ "step": 470
+ },
+ {
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
+ "step": 471
+ },
+ {
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
+ "step": 472
+ },
+ {
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
+ "step": 473
+ },
+ {
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
+ "step": 474
+ },
+ {
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
+ "step": 475
+ },
+ {
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
+ "step": 476
+ },
+ {
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
+ "step": 477
+ },
+ {
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
+ "step": 478
+ },
+ {
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
+ "step": 479
+ },
+ {
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
+ "step": 480
+ },
+ {
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
+ "step": 481
+ },
+ {
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
+ "step": 482
+ },
+ {
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
+ "step": 483
+ },
+ {
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
+ "step": 484
+ },
+ {
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
+ "step": 485
+ },
+ {
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
+ "step": 486
+ },
+ {
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
+ "step": 487
+ },
+ {
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
+ "step": 488
+ },
+ {
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
+ "step": 489
+ },
+ {
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
+ "step": 490
+ },
+ {
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
+ "step": 491
+ },
+ {
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
+ "step": 492
+ },
+ {
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
+ "step": 493
+ },
+ {
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
+ "step": 494
+ },
+ {
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
+ "step": 495
+ },
+ {
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
+ "step": 496
+ },
+ {
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
+ "step": 497
+ },
+ {
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
+ "step": 498
+ },
+ {
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
+ "step": 499
+ },
+ {
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
+ "step": 500
+ }
+ ],
+ "logging_steps": 1,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
+ "save_steps": 100,
+ "total_flos": 6.820509352598323e+17,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ee7ddb867f05d9a969f71467a8eb88994865cf51
--- /dev/null
+++ b/checkpoint-500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
+size 4155
diff --git a/checkpoint-600/adapter_model.bin b/checkpoint-600/adapter_model.bin
index 9187ebbdb23fe0566e9b1bc80bf61091168bec53..0e3b6260f833a8a28a216ce8e666b9d210229def 100644
--- a/checkpoint-600/adapter_model.bin
+++ b/checkpoint-600/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:8bdafbf712a13caac2eff2baadedfa7d69fb1ba1a1618c0652bba7fda3e99d02
+oid sha256:646401c6da34042eb7268456ed4813b4e011d0c30427bf0cfec0315f0a6549d6
size 39409357
diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt
index ff5066c6b6e3961344dee396ea0cf019fe2c8008..b4226db73d63627941c147462501ca003003e066 100644
--- a/checkpoint-600/optimizer.pt
+++ b/checkpoint-600/optimizer.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:2e98eee29adfb5b0c5dfcad4773c74d2234215ec17cf81e21ff40b5dcdd0980f
+oid sha256:a5291a1a2741ff5eba566c03897395a429b391eef776c13e39cae513e36c8f0e
size 78844421
diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth
index 961069ec281e351c01eb6735b97b75dd3d8d33b7..2d80ea84c5f73d441972e03ddda3329bcd15dedb 100644
--- a/checkpoint-600/rng_state.pth
+++ b/checkpoint-600/rng_state.pth
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:696b4cef517e79a03215d5c5fccde0c73d2d962fe70ebab1e472f650136142b2
+oid sha256:1dd247f5d8a4bdaa46e9a22dea4b3ff7e3cc6bbd0eca5a0dcd56fe15ceba641a
size 14575
diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt
index 85ac73474f178c78555b00fc82c696e29cc9f8ca..50a8b9b4add9e50970ea37329af2b0293ef923f0 100644
--- a/checkpoint-600/scheduler.pt
+++ b/checkpoint-600/scheduler.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b6ec2d50f574aac2aa9116fabbb4b97fdb31897bc783b4e235f34f9907d573b9
+oid sha256:0b4fc3b8a57d0b742fbb1df682ae607287e3cc698015cd0bd91af21e4797b7f6
size 627
diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json
index ceb031af3f1beb812ee9cf0893a1d35d18d1d2fc..5ee7ad0a9b4b24fcd3e7e047f14121061f9548ab 100644
--- a/checkpoint-600/trainer_state.json
+++ b/checkpoint-600/trainer_state.json
@@ -1,7 +1,7 @@
{
"best_metric": null,
"best_model_checkpoint": null,
- "epoch": 12.140373063547266,
+ "epoch": 6.77846425419241,
"eval_steps": 500,
"global_step": 600,
"is_hyper_param_search": false,
@@ -9,3611 +9,3611 @@
"is_world_process_zero": true,
"log_history": [
{
- "epoch": 0.02,
- "learning_rate": 0.00019987244897959184,
- "loss": 3.2215,
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
"step": 1
},
{
- "epoch": 0.04,
- "learning_rate": 0.00019974489795918367,
- "loss": 2.8365,
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
"step": 2
},
{
- "epoch": 0.06,
- "learning_rate": 0.00019961734693877553,
- "loss": 2.602,
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
"step": 3
},
{
- "epoch": 0.08,
- "learning_rate": 0.00019948979591836736,
- "loss": 2.4196,
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
"step": 4
},
{
- "epoch": 0.1,
- "learning_rate": 0.0001993622448979592,
- "loss": 2.2574,
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
"step": 5
},
{
- "epoch": 0.12,
- "learning_rate": 0.00019923469387755102,
- "loss": 2.2239,
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
"step": 6
},
{
- "epoch": 0.14,
- "learning_rate": 0.00019910714285714288,
- "loss": 2.1661,
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
"step": 7
},
{
- "epoch": 0.16,
- "learning_rate": 0.0001989795918367347,
- "loss": 2.0987,
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
"step": 8
},
{
- "epoch": 0.18,
- "learning_rate": 0.00019885204081632654,
- "loss": 2.015,
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
"step": 9
},
{
- "epoch": 0.2,
- "learning_rate": 0.00019872448979591837,
- "loss": 1.9771,
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
"step": 10
},
{
- "epoch": 0.22,
- "learning_rate": 0.00019859693877551023,
- "loss": 2.0271,
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
"step": 11
},
{
- "epoch": 0.24,
- "learning_rate": 0.00019846938775510203,
- "loss": 1.9812,
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
"step": 12
},
{
- "epoch": 0.26,
- "learning_rate": 0.0001983418367346939,
- "loss": 2.0834,
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
"step": 13
},
{
- "epoch": 0.28,
- "learning_rate": 0.00019821428571428572,
- "loss": 1.9174,
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
"step": 14
},
{
- "epoch": 0.3,
- "learning_rate": 0.00019808673469387755,
- "loss": 1.8409,
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
"step": 15
},
{
- "epoch": 0.32,
- "learning_rate": 0.00019795918367346938,
- "loss": 1.929,
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
"step": 16
},
{
- "epoch": 0.34,
- "learning_rate": 0.00019783163265306124,
- "loss": 2.0041,
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
"step": 17
},
{
- "epoch": 0.36,
- "learning_rate": 0.00019770408163265305,
- "loss": 1.9385,
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
"step": 18
},
{
- "epoch": 0.38,
- "learning_rate": 0.0001975765306122449,
- "loss": 1.9592,
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
"step": 19
},
{
- "epoch": 0.4,
- "learning_rate": 0.00019744897959183674,
- "loss": 1.9701,
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
"step": 20
},
{
- "epoch": 0.42,
- "learning_rate": 0.0001973214285714286,
- "loss": 1.9277,
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
"step": 21
},
{
- "epoch": 0.45,
- "learning_rate": 0.00019719387755102042,
- "loss": 1.8394,
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
"step": 22
},
{
- "epoch": 0.47,
- "learning_rate": 0.00019706632653061226,
- "loss": 1.8666,
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
"step": 23
},
{
- "epoch": 0.49,
- "learning_rate": 0.00019693877551020409,
- "loss": 1.8997,
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
"step": 24
},
{
- "epoch": 0.51,
- "learning_rate": 0.00019681122448979592,
- "loss": 1.9432,
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
"step": 25
},
{
- "epoch": 0.53,
- "learning_rate": 0.00019668367346938777,
- "loss": 1.9137,
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
"step": 26
},
{
- "epoch": 0.55,
- "learning_rate": 0.0001965561224489796,
- "loss": 1.905,
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
"step": 27
},
{
- "epoch": 0.57,
- "learning_rate": 0.00019642857142857144,
- "loss": 1.8708,
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
"step": 28
},
{
- "epoch": 0.59,
- "learning_rate": 0.00019630102040816327,
- "loss": 1.9097,
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
"step": 29
},
{
- "epoch": 0.61,
- "learning_rate": 0.00019617346938775513,
- "loss": 1.896,
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
"step": 30
},
{
- "epoch": 0.63,
- "learning_rate": 0.00019604591836734696,
- "loss": 1.8834,
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
"step": 31
},
{
- "epoch": 0.65,
- "learning_rate": 0.0001959183673469388,
- "loss": 1.8323,
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
"step": 32
},
{
- "epoch": 0.67,
- "learning_rate": 0.00019579081632653062,
- "loss": 1.804,
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
"step": 33
},
{
- "epoch": 0.69,
- "learning_rate": 0.00019566326530612248,
- "loss": 1.8906,
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
"step": 34
},
{
- "epoch": 0.71,
- "learning_rate": 0.00019553571428571428,
- "loss": 1.8693,
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
"step": 35
},
{
- "epoch": 0.73,
- "learning_rate": 0.00019540816326530614,
- "loss": 1.9308,
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
"step": 36
},
{
- "epoch": 0.75,
- "learning_rate": 0.00019528061224489797,
- "loss": 1.8082,
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
"step": 37
},
{
- "epoch": 0.77,
- "learning_rate": 0.0001951530612244898,
- "loss": 1.848,
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
"step": 38
},
{
- "epoch": 0.79,
- "learning_rate": 0.00019502551020408163,
- "loss": 1.8866,
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
"step": 39
},
{
- "epoch": 0.81,
- "learning_rate": 0.0001948979591836735,
- "loss": 1.7844,
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
"step": 40
},
{
- "epoch": 0.83,
- "learning_rate": 0.0001947704081632653,
- "loss": 1.8485,
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
"step": 41
},
{
- "epoch": 0.85,
- "learning_rate": 0.00019464285714285715,
- "loss": 1.7917,
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
"step": 42
},
{
- "epoch": 0.87,
- "learning_rate": 0.00019451530612244898,
- "loss": 1.7342,
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
"step": 43
},
{
- "epoch": 0.89,
- "learning_rate": 0.00019438775510204084,
- "loss": 1.8479,
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
"step": 44
},
{
- "epoch": 0.91,
- "learning_rate": 0.00019426020408163267,
- "loss": 1.8639,
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
"step": 45
},
{
- "epoch": 0.93,
- "learning_rate": 0.0001941326530612245,
- "loss": 1.8166,
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
"step": 46
},
{
- "epoch": 0.95,
- "learning_rate": 0.00019400510204081633,
- "loss": 1.7566,
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
"step": 47
},
{
- "epoch": 0.97,
- "learning_rate": 0.00019387755102040816,
- "loss": 1.8071,
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
"step": 48
},
{
- "epoch": 0.99,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.8612,
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
"step": 49
},
{
- "epoch": 1.01,
- "learning_rate": 0.00019362244897959185,
- "loss": 1.7819,
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
"step": 50
},
{
- "epoch": 1.03,
- "learning_rate": 0.00019349489795918368,
- "loss": 1.8647,
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
"step": 51
},
{
- "epoch": 1.05,
- "learning_rate": 0.0001933673469387755,
- "loss": 1.8196,
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
"step": 52
},
{
- "epoch": 1.07,
- "learning_rate": 0.00019323979591836737,
- "loss": 1.8027,
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
"step": 53
},
{
- "epoch": 1.09,
- "learning_rate": 0.00019311224489795917,
- "loss": 1.8927,
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
"step": 54
},
{
- "epoch": 1.11,
- "learning_rate": 0.00019298469387755103,
- "loss": 1.8481,
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
"step": 55
},
{
- "epoch": 1.13,
- "learning_rate": 0.00019285714285714286,
- "loss": 1.7781,
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
"step": 56
},
{
- "epoch": 1.15,
- "learning_rate": 0.00019272959183673472,
- "loss": 1.8101,
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
"step": 57
},
{
- "epoch": 1.17,
- "learning_rate": 0.00019260204081632653,
- "loss": 1.7257,
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
"step": 58
},
{
- "epoch": 1.19,
- "learning_rate": 0.00019247448979591838,
- "loss": 1.8185,
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
"step": 59
},
{
- "epoch": 1.21,
- "learning_rate": 0.00019234693877551021,
- "loss": 1.8557,
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
"step": 60
},
{
- "epoch": 1.23,
- "learning_rate": 0.00019221938775510204,
- "loss": 1.7418,
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
"step": 61
},
{
- "epoch": 1.25,
- "learning_rate": 0.00019209183673469388,
- "loss": 1.6879,
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
"step": 62
},
{
- "epoch": 1.27,
- "learning_rate": 0.00019196428571428573,
- "loss": 1.7651,
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
"step": 63
},
{
- "epoch": 1.29,
- "learning_rate": 0.00019183673469387756,
- "loss": 1.7759,
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
"step": 64
},
{
- "epoch": 1.32,
- "learning_rate": 0.0001917091836734694,
- "loss": 1.7691,
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
"step": 65
},
{
- "epoch": 1.34,
- "learning_rate": 0.00019158163265306123,
- "loss": 1.7794,
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
"step": 66
},
{
- "epoch": 1.36,
- "learning_rate": 0.00019145408163265306,
- "loss": 1.8152,
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
"step": 67
},
{
- "epoch": 1.38,
- "learning_rate": 0.00019132653061224492,
- "loss": 1.8052,
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
"step": 68
},
{
- "epoch": 1.4,
- "learning_rate": 0.00019119897959183675,
- "loss": 1.8054,
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
"step": 69
},
{
- "epoch": 1.42,
- "learning_rate": 0.00019107142857142858,
- "loss": 1.8114,
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
"step": 70
},
{
- "epoch": 1.44,
- "learning_rate": 0.0001909438775510204,
- "loss": 1.7749,
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
"step": 71
},
{
- "epoch": 1.46,
- "learning_rate": 0.00019081632653061227,
- "loss": 1.777,
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
"step": 72
},
{
- "epoch": 1.48,
- "learning_rate": 0.0001906887755102041,
- "loss": 1.7896,
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
"step": 73
},
{
- "epoch": 1.5,
- "learning_rate": 0.00019056122448979593,
- "loss": 1.8335,
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
"step": 74
},
{
- "epoch": 1.52,
- "learning_rate": 0.00019043367346938776,
- "loss": 1.8155,
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
"step": 75
},
{
- "epoch": 1.54,
- "learning_rate": 0.00019030612244897962,
- "loss": 1.8224,
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
"step": 76
},
{
- "epoch": 1.56,
- "learning_rate": 0.00019017857142857142,
- "loss": 1.7889,
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
"step": 77
},
{
- "epoch": 1.58,
- "learning_rate": 0.00019005102040816328,
- "loss": 1.8866,
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
"step": 78
},
{
- "epoch": 1.6,
- "learning_rate": 0.0001899234693877551,
- "loss": 1.8439,
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
"step": 79
},
{
- "epoch": 1.62,
- "learning_rate": 0.00018979591836734697,
- "loss": 1.7906,
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
"step": 80
},
{
- "epoch": 1.64,
- "learning_rate": 0.00018966836734693877,
- "loss": 1.8627,
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
"step": 81
},
{
- "epoch": 1.66,
- "learning_rate": 0.00018954081632653063,
- "loss": 1.7497,
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
"step": 82
},
{
- "epoch": 1.68,
- "learning_rate": 0.00018941326530612246,
- "loss": 1.7936,
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
"step": 83
},
{
- "epoch": 1.7,
- "learning_rate": 0.0001892857142857143,
- "loss": 1.8341,
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
"step": 84
},
{
- "epoch": 1.72,
- "learning_rate": 0.00018915816326530612,
- "loss": 1.7868,
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
"step": 85
},
{
- "epoch": 1.74,
- "learning_rate": 0.00018903061224489798,
- "loss": 1.7493,
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
"step": 86
},
{
- "epoch": 1.76,
- "learning_rate": 0.0001889030612244898,
- "loss": 1.7926,
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
"step": 87
},
{
- "epoch": 1.78,
- "learning_rate": 0.00018877551020408164,
- "loss": 1.8278,
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
"step": 88
},
{
- "epoch": 1.8,
- "learning_rate": 0.00018864795918367347,
- "loss": 1.7387,
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
"step": 89
},
{
- "epoch": 1.82,
- "learning_rate": 0.0001885204081632653,
- "loss": 1.7669,
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
"step": 90
},
{
- "epoch": 1.84,
- "learning_rate": 0.00018839285714285716,
- "loss": 1.7686,
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
"step": 91
},
{
- "epoch": 1.86,
- "learning_rate": 0.000188265306122449,
- "loss": 1.7759,
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
"step": 92
},
{
- "epoch": 1.88,
- "learning_rate": 0.00018813775510204082,
- "loss": 1.7016,
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
"step": 93
},
{
- "epoch": 1.9,
- "learning_rate": 0.00018801020408163265,
- "loss": 1.8123,
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
"step": 94
},
{
- "epoch": 1.92,
- "learning_rate": 0.0001878826530612245,
- "loss": 1.8315,
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
"step": 95
},
{
- "epoch": 1.94,
- "learning_rate": 0.00018775510204081634,
- "loss": 1.7679,
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
"step": 96
},
{
- "epoch": 1.96,
- "learning_rate": 0.00018762755102040817,
- "loss": 1.7874,
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
"step": 97
},
{
- "epoch": 1.98,
- "learning_rate": 0.0001875,
- "loss": 1.8008,
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
"step": 98
},
{
- "epoch": 2.0,
- "learning_rate": 0.00018737244897959186,
- "loss": 1.7177,
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
"step": 99
},
{
- "epoch": 2.02,
- "learning_rate": 0.00018724489795918367,
- "loss": 1.7272,
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
"step": 100
},
{
- "epoch": 2.04,
- "learning_rate": 0.00018711734693877552,
- "loss": 1.7848,
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
"step": 101
},
{
- "epoch": 2.06,
- "learning_rate": 0.00018698979591836735,
- "loss": 1.744,
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
"step": 102
},
{
- "epoch": 2.08,
- "learning_rate": 0.00018686224489795919,
- "loss": 1.7005,
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
"step": 103
},
{
- "epoch": 2.1,
- "learning_rate": 0.00018673469387755102,
- "loss": 1.8247,
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
"step": 104
},
{
- "epoch": 2.12,
- "learning_rate": 0.00018660714285714287,
- "loss": 1.6855,
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
"step": 105
},
{
- "epoch": 2.14,
- "learning_rate": 0.0001864795918367347,
- "loss": 1.7627,
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
"step": 106
},
{
- "epoch": 2.17,
- "learning_rate": 0.00018635204081632654,
- "loss": 1.7564,
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
"step": 107
},
{
- "epoch": 2.19,
- "learning_rate": 0.00018622448979591837,
- "loss": 1.8237,
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
"step": 108
},
{
- "epoch": 2.21,
- "learning_rate": 0.00018609693877551022,
- "loss": 1.7421,
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
"step": 109
},
{
- "epoch": 2.23,
- "learning_rate": 0.00018596938775510206,
- "loss": 1.7517,
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
"step": 110
},
{
- "epoch": 2.25,
- "learning_rate": 0.0001858418367346939,
- "loss": 1.7515,
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
"step": 111
},
{
- "epoch": 2.27,
- "learning_rate": 0.00018571428571428572,
- "loss": 1.7842,
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
"step": 112
},
{
- "epoch": 2.29,
- "learning_rate": 0.00018558673469387755,
- "loss": 1.8001,
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
"step": 113
},
{
- "epoch": 2.31,
- "learning_rate": 0.0001854591836734694,
- "loss": 1.7653,
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
"step": 114
},
{
- "epoch": 2.33,
- "learning_rate": 0.00018533163265306124,
- "loss": 1.694,
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
"step": 115
},
{
- "epoch": 2.35,
- "learning_rate": 0.00018520408163265307,
- "loss": 1.7457,
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
"step": 116
},
{
- "epoch": 2.37,
- "learning_rate": 0.0001850765306122449,
- "loss": 1.7899,
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
"step": 117
},
{
- "epoch": 2.39,
- "learning_rate": 0.00018494897959183676,
- "loss": 1.7473,
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
"step": 118
},
{
- "epoch": 2.41,
- "learning_rate": 0.0001848214285714286,
- "loss": 1.6639,
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
"step": 119
},
{
- "epoch": 2.43,
- "learning_rate": 0.00018469387755102042,
- "loss": 1.762,
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
"step": 120
},
{
- "epoch": 2.45,
- "learning_rate": 0.00018456632653061225,
- "loss": 1.7378,
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
"step": 121
},
{
- "epoch": 2.47,
- "learning_rate": 0.0001844387755102041,
- "loss": 1.672,
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
"step": 122
},
{
- "epoch": 2.49,
- "learning_rate": 0.0001843112244897959,
- "loss": 1.7267,
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
"step": 123
},
{
- "epoch": 2.51,
- "learning_rate": 0.00018418367346938777,
- "loss": 1.7825,
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
"step": 124
},
{
- "epoch": 2.53,
- "learning_rate": 0.0001840561224489796,
- "loss": 1.7566,
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
"step": 125
},
{
- "epoch": 2.55,
- "learning_rate": 0.00018392857142857143,
- "loss": 1.8169,
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
"step": 126
},
{
- "epoch": 2.57,
- "learning_rate": 0.00018380102040816326,
- "loss": 1.6801,
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
"step": 127
},
{
- "epoch": 2.59,
- "learning_rate": 0.00018367346938775512,
- "loss": 1.7292,
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
"step": 128
},
{
- "epoch": 2.61,
- "learning_rate": 0.00018354591836734695,
- "loss": 1.737,
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
"step": 129
},
{
- "epoch": 2.63,
- "learning_rate": 0.00018341836734693878,
- "loss": 1.7696,
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
"step": 130
},
{
- "epoch": 2.65,
- "learning_rate": 0.0001832908163265306,
- "loss": 1.7239,
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
"step": 131
},
{
- "epoch": 2.67,
- "learning_rate": 0.00018316326530612247,
- "loss": 1.7441,
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
"step": 132
},
{
- "epoch": 2.69,
- "learning_rate": 0.0001830357142857143,
- "loss": 1.7825,
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
"step": 133
},
{
- "epoch": 2.71,
- "learning_rate": 0.00018290816326530613,
- "loss": 1.7411,
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
"step": 134
},
{
- "epoch": 2.73,
- "learning_rate": 0.00018278061224489796,
- "loss": 1.7119,
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
"step": 135
},
{
- "epoch": 2.75,
- "learning_rate": 0.0001826530612244898,
- "loss": 1.7443,
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
"step": 136
},
{
- "epoch": 2.77,
- "learning_rate": 0.00018252551020408165,
- "loss": 1.7197,
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
"step": 137
},
{
- "epoch": 2.79,
- "learning_rate": 0.00018239795918367348,
- "loss": 1.7273,
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
"step": 138
},
{
- "epoch": 2.81,
- "learning_rate": 0.0001822704081632653,
- "loss": 1.7681,
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
"step": 139
},
{
- "epoch": 2.83,
- "learning_rate": 0.00018214285714285714,
- "loss": 1.8088,
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
"step": 140
},
{
- "epoch": 2.85,
- "learning_rate": 0.000182015306122449,
- "loss": 1.7301,
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
"step": 141
},
{
- "epoch": 2.87,
- "learning_rate": 0.00018188775510204083,
- "loss": 1.6853,
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
"step": 142
},
{
- "epoch": 2.89,
- "learning_rate": 0.00018176020408163266,
- "loss": 1.6966,
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
"step": 143
},
{
- "epoch": 2.91,
- "learning_rate": 0.0001816326530612245,
- "loss": 1.7938,
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
"step": 144
},
{
- "epoch": 2.93,
- "learning_rate": 0.00018150510204081635,
- "loss": 1.7639,
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
"step": 145
},
{
- "epoch": 2.95,
- "learning_rate": 0.00018137755102040816,
- "loss": 1.7527,
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
"step": 146
},
{
- "epoch": 2.97,
- "learning_rate": 0.00018125000000000001,
- "loss": 1.7386,
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
"step": 147
},
{
- "epoch": 2.99,
- "learning_rate": 0.00018112244897959185,
- "loss": 1.7223,
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
"step": 148
},
{
- "epoch": 3.01,
- "learning_rate": 0.00018099489795918368,
- "loss": 1.7571,
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
"step": 149
},
{
- "epoch": 3.04,
- "learning_rate": 0.0001808673469387755,
- "loss": 1.7054,
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
"step": 150
},
{
- "epoch": 3.06,
- "learning_rate": 0.00018073979591836737,
- "loss": 1.6581,
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
"step": 151
},
{
- "epoch": 3.08,
- "learning_rate": 0.00018061224489795917,
- "loss": 1.681,
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
"step": 152
},
{
- "epoch": 3.1,
- "learning_rate": 0.00018048469387755103,
- "loss": 1.7425,
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
"step": 153
},
{
- "epoch": 3.12,
- "learning_rate": 0.00018035714285714286,
- "loss": 1.7108,
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
"step": 154
},
{
- "epoch": 3.14,
- "learning_rate": 0.00018022959183673472,
- "loss": 1.7194,
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
"step": 155
},
{
- "epoch": 3.16,
- "learning_rate": 0.00018010204081632655,
- "loss": 1.6953,
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
"step": 156
},
{
- "epoch": 3.18,
- "learning_rate": 0.00017997448979591838,
- "loss": 1.669,
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
"step": 157
},
{
- "epoch": 3.2,
- "learning_rate": 0.0001798469387755102,
- "loss": 1.744,
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
"step": 158
},
{
- "epoch": 3.22,
- "learning_rate": 0.00017971938775510204,
- "loss": 1.6467,
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
"step": 159
},
{
- "epoch": 3.24,
- "learning_rate": 0.0001795918367346939,
- "loss": 1.7103,
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
"step": 160
},
{
- "epoch": 3.26,
- "learning_rate": 0.00017946428571428573,
- "loss": 1.6662,
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
"step": 161
},
{
- "epoch": 3.28,
- "learning_rate": 0.00017933673469387756,
- "loss": 1.6657,
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
"step": 162
},
{
- "epoch": 3.3,
- "learning_rate": 0.0001792091836734694,
- "loss": 1.791,
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
"step": 163
},
{
- "epoch": 3.32,
- "learning_rate": 0.00017908163265306125,
- "loss": 1.7704,
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
"step": 164
},
{
- "epoch": 3.34,
- "learning_rate": 0.00017895408163265305,
- "loss": 1.7229,
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
"step": 165
},
{
- "epoch": 3.36,
- "learning_rate": 0.0001788265306122449,
- "loss": 1.76,
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
"step": 166
},
{
- "epoch": 3.38,
- "learning_rate": 0.00017869897959183674,
- "loss": 1.6482,
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
"step": 167
},
{
- "epoch": 3.4,
- "learning_rate": 0.0001785714285714286,
- "loss": 1.8076,
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
"step": 168
},
{
- "epoch": 3.42,
- "learning_rate": 0.0001784438775510204,
- "loss": 1.7368,
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
"step": 169
},
{
- "epoch": 3.44,
- "learning_rate": 0.00017831632653061226,
- "loss": 1.6264,
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
"step": 170
},
{
- "epoch": 3.46,
- "learning_rate": 0.0001781887755102041,
- "loss": 1.6289,
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
"step": 171
},
{
- "epoch": 3.48,
- "learning_rate": 0.00017806122448979592,
- "loss": 1.7913,
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
"step": 172
},
{
- "epoch": 3.5,
- "learning_rate": 0.00017793367346938775,
- "loss": 1.6985,
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
"step": 173
},
{
- "epoch": 3.52,
- "learning_rate": 0.0001778061224489796,
- "loss": 1.6936,
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
"step": 174
},
{
- "epoch": 3.54,
- "learning_rate": 0.00017767857142857141,
- "loss": 1.8068,
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
"step": 175
},
{
- "epoch": 3.56,
- "learning_rate": 0.00017755102040816327,
- "loss": 1.7243,
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
"step": 176
},
{
- "epoch": 3.58,
- "learning_rate": 0.0001774234693877551,
- "loss": 1.6893,
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
"step": 177
},
{
- "epoch": 3.6,
- "learning_rate": 0.00017729591836734696,
- "loss": 1.8122,
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
"step": 178
},
{
- "epoch": 3.62,
- "learning_rate": 0.0001771683673469388,
- "loss": 1.6562,
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
"step": 179
},
{
- "epoch": 3.64,
- "learning_rate": 0.00017704081632653062,
- "loss": 1.6999,
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
"step": 180
},
{
- "epoch": 3.66,
- "learning_rate": 0.00017691326530612245,
- "loss": 1.7229,
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
"step": 181
},
{
- "epoch": 3.68,
- "learning_rate": 0.00017678571428571428,
- "loss": 1.6764,
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
"step": 182
},
{
- "epoch": 3.7,
- "learning_rate": 0.00017665816326530614,
- "loss": 1.6982,
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
"step": 183
},
{
- "epoch": 3.72,
- "learning_rate": 0.00017653061224489797,
- "loss": 1.696,
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
"step": 184
},
{
- "epoch": 3.74,
- "learning_rate": 0.0001764030612244898,
- "loss": 1.6797,
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
"step": 185
},
{
- "epoch": 3.76,
- "learning_rate": 0.00017627551020408164,
- "loss": 1.637,
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
"step": 186
},
{
- "epoch": 3.78,
- "learning_rate": 0.0001761479591836735,
- "loss": 1.7074,
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
"step": 187
},
{
- "epoch": 3.8,
- "learning_rate": 0.0001760204081632653,
- "loss": 1.705,
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
"step": 188
},
{
- "epoch": 3.82,
- "learning_rate": 0.00017589285714285716,
- "loss": 1.6153,
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
"step": 189
},
{
- "epoch": 3.84,
- "learning_rate": 0.00017576530612244899,
- "loss": 1.7354,
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
"step": 190
},
{
- "epoch": 3.86,
- "learning_rate": 0.00017563775510204084,
- "loss": 1.6941,
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
"step": 191
},
{
- "epoch": 3.88,
- "learning_rate": 0.00017551020408163265,
- "loss": 1.7231,
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
"step": 192
},
{
- "epoch": 3.91,
- "learning_rate": 0.0001753826530612245,
- "loss": 1.7663,
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
"step": 193
},
{
- "epoch": 3.93,
- "learning_rate": 0.00017525510204081634,
- "loss": 1.6532,
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
"step": 194
},
{
- "epoch": 3.95,
- "learning_rate": 0.00017512755102040817,
- "loss": 1.7115,
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
"step": 195
},
{
- "epoch": 3.97,
- "learning_rate": 0.000175,
- "loss": 1.6955,
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
"step": 196
},
{
- "epoch": 3.99,
- "learning_rate": 0.00017487244897959186,
- "loss": 1.6863,
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
"step": 197
},
{
- "epoch": 4.01,
- "learning_rate": 0.00017474489795918366,
- "loss": 1.7012,
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
"step": 198
},
{
- "epoch": 4.03,
- "learning_rate": 0.00017461734693877552,
- "loss": 1.5927,
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
"step": 199
},
{
- "epoch": 4.05,
- "learning_rate": 0.00017448979591836735,
- "loss": 1.6272,
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
"step": 200
},
{
- "epoch": 4.07,
- "learning_rate": 0.00017436224489795918,
- "loss": 1.5994,
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
"step": 201
},
{
- "epoch": 4.09,
- "learning_rate": 0.00017423469387755104,
- "loss": 1.7141,
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
"step": 202
},
{
- "epoch": 4.11,
- "learning_rate": 0.00017410714285714287,
- "loss": 1.7547,
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
"step": 203
},
{
- "epoch": 4.13,
- "learning_rate": 0.0001739795918367347,
- "loss": 1.6254,
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
"step": 204
},
{
- "epoch": 4.15,
- "learning_rate": 0.00017385204081632653,
- "loss": 1.6686,
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
"step": 205
},
{
- "epoch": 4.17,
- "learning_rate": 0.0001737244897959184,
- "loss": 1.6684,
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
"step": 206
},
{
- "epoch": 4.19,
- "learning_rate": 0.00017359693877551022,
- "loss": 1.6724,
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
"step": 207
},
{
- "epoch": 4.21,
- "learning_rate": 0.00017346938775510205,
- "loss": 1.7361,
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
"step": 208
},
{
- "epoch": 4.23,
- "learning_rate": 0.00017334183673469388,
- "loss": 1.7167,
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
"step": 209
},
{
- "epoch": 4.25,
- "learning_rate": 0.00017321428571428574,
- "loss": 1.7226,
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
"step": 210
},
{
- "epoch": 4.27,
- "learning_rate": 0.00017308673469387754,
- "loss": 1.7133,
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
"step": 211
},
{
- "epoch": 4.29,
- "learning_rate": 0.0001729591836734694,
- "loss": 1.649,
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
"step": 212
},
{
- "epoch": 4.31,
- "learning_rate": 0.00017283163265306123,
- "loss": 1.7104,
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
"step": 213
},
{
- "epoch": 4.33,
- "learning_rate": 0.00017270408163265306,
- "loss": 1.6861,
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
"step": 214
},
{
- "epoch": 4.35,
- "learning_rate": 0.0001725765306122449,
- "loss": 1.648,
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
"step": 215
},
{
- "epoch": 4.37,
- "learning_rate": 0.00017244897959183675,
- "loss": 1.6215,
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
"step": 216
},
{
- "epoch": 4.39,
- "learning_rate": 0.00017232142857142858,
- "loss": 1.6334,
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
"step": 217
},
{
- "epoch": 4.41,
- "learning_rate": 0.0001721938775510204,
- "loss": 1.6283,
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
"step": 218
},
{
- "epoch": 4.43,
- "learning_rate": 0.00017206632653061224,
- "loss": 1.6462,
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
"step": 219
},
{
- "epoch": 4.45,
- "learning_rate": 0.0001719387755102041,
- "loss": 1.7233,
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
"step": 220
},
{
- "epoch": 4.47,
- "learning_rate": 0.0001718112244897959,
- "loss": 1.7839,
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
"step": 221
},
{
- "epoch": 4.49,
- "learning_rate": 0.00017168367346938776,
- "loss": 1.7204,
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
"step": 222
},
{
- "epoch": 4.51,
- "learning_rate": 0.0001715561224489796,
- "loss": 1.7671,
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
"step": 223
},
{
- "epoch": 4.53,
- "learning_rate": 0.00017142857142857143,
- "loss": 1.6824,
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
"step": 224
},
{
- "epoch": 4.55,
- "learning_rate": 0.00017130102040816328,
- "loss": 1.7068,
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
"step": 225
},
{
- "epoch": 4.57,
- "learning_rate": 0.00017117346938775511,
- "loss": 1.6515,
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
"step": 226
},
{
- "epoch": 4.59,
- "learning_rate": 0.00017104591836734694,
- "loss": 1.6586,
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
"step": 227
},
{
- "epoch": 4.61,
- "learning_rate": 0.00017091836734693878,
- "loss": 1.6355,
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
"step": 228
},
{
- "epoch": 4.63,
- "learning_rate": 0.00017079081632653063,
- "loss": 1.7173,
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
"step": 229
},
{
- "epoch": 4.65,
- "learning_rate": 0.00017066326530612246,
- "loss": 1.6585,
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
"step": 230
},
{
- "epoch": 4.67,
- "learning_rate": 0.0001705357142857143,
- "loss": 1.5856,
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
"step": 231
},
{
- "epoch": 4.69,
- "learning_rate": 0.00017040816326530613,
- "loss": 1.5923,
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
"step": 232
},
{
- "epoch": 4.71,
- "learning_rate": 0.00017028061224489798,
- "loss": 1.7128,
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
"step": 233
},
{
- "epoch": 4.73,
- "learning_rate": 0.0001701530612244898,
- "loss": 1.6971,
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
"step": 234
},
{
- "epoch": 4.75,
- "learning_rate": 0.00017002551020408165,
- "loss": 1.6416,
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
"step": 235
},
{
- "epoch": 4.78,
- "learning_rate": 0.00016989795918367348,
- "loss": 1.645,
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
"step": 236
},
{
- "epoch": 4.8,
- "learning_rate": 0.0001697704081632653,
- "loss": 1.6792,
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
"step": 237
},
{
- "epoch": 4.82,
- "learning_rate": 0.00016964285714285714,
- "loss": 1.6522,
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
"step": 238
},
{
- "epoch": 4.84,
- "learning_rate": 0.000169515306122449,
- "loss": 1.6315,
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
"step": 239
},
{
- "epoch": 4.86,
- "learning_rate": 0.00016938775510204083,
- "loss": 1.6622,
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
"step": 240
},
{
- "epoch": 4.88,
- "learning_rate": 0.00016926020408163266,
- "loss": 1.6566,
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
"step": 241
},
{
- "epoch": 4.9,
- "learning_rate": 0.0001691326530612245,
- "loss": 1.7141,
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
"step": 242
},
{
- "epoch": 4.92,
- "learning_rate": 0.00016900510204081635,
- "loss": 1.5873,
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
"step": 243
},
{
- "epoch": 4.94,
- "learning_rate": 0.00016887755102040818,
- "loss": 1.6571,
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
"step": 244
},
{
- "epoch": 4.96,
- "learning_rate": 0.00016875,
- "loss": 1.6829,
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
"step": 245
},
{
- "epoch": 4.98,
- "learning_rate": 0.00016862244897959184,
- "loss": 1.6935,
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
"step": 246
},
{
- "epoch": 5.0,
- "learning_rate": 0.00016849489795918367,
- "loss": 1.6782,
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
"step": 247
},
{
- "epoch": 5.02,
- "learning_rate": 0.00016836734693877553,
- "loss": 1.622,
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
"step": 248
},
{
- "epoch": 5.04,
- "learning_rate": 0.00016823979591836736,
- "loss": 1.6596,
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
"step": 249
},
{
- "epoch": 5.06,
- "learning_rate": 0.0001681122448979592,
- "loss": 1.5821,
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
"step": 250
},
{
- "epoch": 5.08,
- "learning_rate": 0.00016798469387755102,
- "loss": 1.7292,
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
"step": 251
},
{
- "epoch": 5.1,
- "learning_rate": 0.00016785714285714288,
- "loss": 1.646,
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
"step": 252
},
{
- "epoch": 5.12,
- "learning_rate": 0.0001677295918367347,
- "loss": 1.6969,
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
"step": 253
},
{
- "epoch": 5.14,
- "learning_rate": 0.00016760204081632654,
- "loss": 1.6082,
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
"step": 254
},
{
- "epoch": 5.16,
- "learning_rate": 0.00016747448979591837,
- "loss": 1.5843,
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
"step": 255
},
{
- "epoch": 5.18,
- "learning_rate": 0.00016734693877551023,
- "loss": 1.6827,
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
"step": 256
},
{
- "epoch": 5.2,
- "learning_rate": 0.00016721938775510203,
- "loss": 1.5824,
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
"step": 257
},
{
- "epoch": 5.22,
- "learning_rate": 0.0001670918367346939,
- "loss": 1.6795,
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
"step": 258
},
{
- "epoch": 5.24,
- "learning_rate": 0.00016696428571428572,
- "loss": 1.5639,
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
"step": 259
},
{
- "epoch": 5.26,
- "learning_rate": 0.00016683673469387755,
- "loss": 1.592,
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
"step": 260
},
{
- "epoch": 5.28,
- "learning_rate": 0.00016670918367346938,
- "loss": 1.65,
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
"step": 261
},
{
- "epoch": 5.3,
- "learning_rate": 0.00016658163265306124,
- "loss": 1.5592,
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
"step": 262
},
{
- "epoch": 5.32,
- "learning_rate": 0.00016645408163265305,
- "loss": 1.5091,
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
"step": 263
},
{
- "epoch": 5.34,
- "learning_rate": 0.0001663265306122449,
- "loss": 1.6138,
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
"step": 264
},
{
- "epoch": 5.36,
- "learning_rate": 0.00016619897959183673,
- "loss": 1.625,
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
"step": 265
},
{
- "epoch": 5.38,
- "learning_rate": 0.0001660714285714286,
- "loss": 1.5757,
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
"step": 266
},
{
- "epoch": 5.4,
- "learning_rate": 0.00016594387755102042,
- "loss": 1.6372,
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
"step": 267
},
{
- "epoch": 5.42,
- "learning_rate": 0.00016581632653061225,
- "loss": 1.5891,
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
"step": 268
},
{
- "epoch": 5.44,
- "learning_rate": 0.00016568877551020409,
- "loss": 1.6893,
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
"step": 269
},
{
- "epoch": 5.46,
- "learning_rate": 0.00016556122448979592,
- "loss": 1.6662,
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
"step": 270
},
{
- "epoch": 5.48,
- "learning_rate": 0.00016543367346938777,
- "loss": 1.7132,
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
"step": 271
},
{
- "epoch": 5.5,
- "learning_rate": 0.0001653061224489796,
- "loss": 1.5835,
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
"step": 272
},
{
- "epoch": 5.52,
- "learning_rate": 0.00016517857142857144,
- "loss": 1.6342,
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
"step": 273
},
{
- "epoch": 5.54,
- "learning_rate": 0.00016505102040816327,
- "loss": 1.6717,
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
"step": 274
},
{
- "epoch": 5.56,
- "learning_rate": 0.00016492346938775512,
- "loss": 1.6248,
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
"step": 275
},
{
- "epoch": 5.58,
- "learning_rate": 0.00016479591836734696,
- "loss": 1.6117,
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
"step": 276
},
{
- "epoch": 5.6,
- "learning_rate": 0.0001646683673469388,
- "loss": 1.6798,
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
"step": 277
},
{
- "epoch": 5.63,
- "learning_rate": 0.00016454081632653062,
- "loss": 1.6406,
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
"step": 278
},
{
- "epoch": 5.65,
- "learning_rate": 0.00016441326530612248,
- "loss": 1.6512,
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
"step": 279
},
{
- "epoch": 5.67,
- "learning_rate": 0.00016428571428571428,
- "loss": 1.6102,
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
"step": 280
},
{
- "epoch": 5.69,
- "learning_rate": 0.00016415816326530614,
- "loss": 1.6113,
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
"step": 281
},
{
- "epoch": 5.71,
- "learning_rate": 0.00016403061224489797,
- "loss": 1.7116,
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
"step": 282
},
{
- "epoch": 5.73,
- "learning_rate": 0.0001639030612244898,
- "loss": 1.6846,
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
"step": 283
},
{
- "epoch": 5.75,
- "learning_rate": 0.00016377551020408163,
- "loss": 1.6911,
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
"step": 284
},
{
- "epoch": 5.77,
- "learning_rate": 0.0001636479591836735,
- "loss": 1.6202,
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
"step": 285
},
{
- "epoch": 5.79,
- "learning_rate": 0.0001635204081632653,
- "loss": 1.5715,
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
"step": 286
},
{
- "epoch": 5.81,
- "learning_rate": 0.00016339285714285715,
- "loss": 1.6461,
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
"step": 287
},
{
- "epoch": 5.83,
- "learning_rate": 0.00016326530612244898,
- "loss": 1.6624,
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
"step": 288
},
{
- "epoch": 5.85,
- "learning_rate": 0.00016313775510204084,
- "loss": 1.6535,
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
"step": 289
},
{
- "epoch": 5.87,
- "learning_rate": 0.00016301020408163267,
- "loss": 1.6275,
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
"step": 290
},
{
- "epoch": 5.89,
- "learning_rate": 0.0001628826530612245,
- "loss": 1.6636,
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
"step": 291
},
{
- "epoch": 5.91,
- "learning_rate": 0.00016275510204081633,
- "loss": 1.6546,
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
"step": 292
},
{
- "epoch": 5.93,
- "learning_rate": 0.00016262755102040816,
- "loss": 1.7274,
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
"step": 293
},
{
- "epoch": 5.95,
- "learning_rate": 0.00016250000000000002,
- "loss": 1.5901,
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
"step": 294
},
{
- "epoch": 5.97,
- "learning_rate": 0.00016237244897959185,
- "loss": 1.6046,
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
"step": 295
},
{
- "epoch": 5.99,
- "learning_rate": 0.00016224489795918368,
- "loss": 1.5828,
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
"step": 296
},
{
- "epoch": 6.01,
- "learning_rate": 0.0001621173469387755,
- "loss": 1.6435,
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
"step": 297
},
{
- "epoch": 6.03,
- "learning_rate": 0.00016198979591836737,
- "loss": 1.6263,
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
"step": 298
},
{
- "epoch": 6.05,
- "learning_rate": 0.00016186224489795917,
- "loss": 1.4944,
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
"step": 299
},
{
- "epoch": 6.07,
- "learning_rate": 0.00016173469387755103,
- "loss": 1.6286,
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
"step": 300
},
{
- "epoch": 6.09,
- "learning_rate": 0.00016160714285714286,
- "loss": 1.694,
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
"step": 301
},
{
- "epoch": 6.11,
- "learning_rate": 0.00016147959183673472,
- "loss": 1.6197,
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
"step": 302
},
{
- "epoch": 6.13,
- "learning_rate": 0.00016135204081632652,
- "loss": 1.5597,
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
"step": 303
},
{
- "epoch": 6.15,
- "learning_rate": 0.00016122448979591838,
- "loss": 1.5487,
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
"step": 304
},
{
- "epoch": 6.17,
- "learning_rate": 0.0001610969387755102,
- "loss": 1.5769,
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
"step": 305
},
{
- "epoch": 6.19,
- "learning_rate": 0.00016096938775510204,
- "loss": 1.6367,
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
"step": 306
},
{
- "epoch": 6.21,
- "learning_rate": 0.00016084183673469388,
- "loss": 1.583,
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
"step": 307
},
{
- "epoch": 6.23,
- "learning_rate": 0.00016071428571428573,
- "loss": 1.6201,
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
"step": 308
},
{
- "epoch": 6.25,
- "learning_rate": 0.00016058673469387754,
- "loss": 1.6586,
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
"step": 309
},
{
- "epoch": 6.27,
- "learning_rate": 0.0001604591836734694,
- "loss": 1.6711,
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
"step": 310
},
{
- "epoch": 6.29,
- "learning_rate": 0.00016033163265306123,
- "loss": 1.6402,
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
"step": 311
},
{
- "epoch": 6.31,
- "learning_rate": 0.00016020408163265306,
- "loss": 1.5247,
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
"step": 312
},
{
- "epoch": 6.33,
- "learning_rate": 0.00016007653061224491,
- "loss": 1.5356,
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
"step": 313
},
{
- "epoch": 6.35,
- "learning_rate": 0.00015994897959183675,
- "loss": 1.564,
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
"step": 314
},
{
- "epoch": 6.37,
- "learning_rate": 0.00015982142857142858,
- "loss": 1.563,
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
"step": 315
},
{
- "epoch": 6.39,
- "learning_rate": 0.0001596938775510204,
- "loss": 1.5198,
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
"step": 316
},
{
- "epoch": 6.41,
- "learning_rate": 0.00015956632653061227,
- "loss": 1.6558,
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
"step": 317
},
{
- "epoch": 6.43,
- "learning_rate": 0.0001594387755102041,
- "loss": 1.5534,
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
"step": 318
},
{
- "epoch": 6.45,
- "learning_rate": 0.00015931122448979593,
- "loss": 1.6239,
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
"step": 319
},
{
- "epoch": 6.47,
- "learning_rate": 0.00015918367346938776,
- "loss": 1.5645,
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
"step": 320
},
{
- "epoch": 6.5,
- "learning_rate": 0.00015905612244897962,
- "loss": 1.5713,
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
"step": 321
},
{
- "epoch": 6.52,
- "learning_rate": 0.00015892857142857142,
- "loss": 1.6176,
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
"step": 322
},
{
- "epoch": 6.54,
- "learning_rate": 0.00015880102040816328,
- "loss": 1.502,
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
"step": 323
},
{
- "epoch": 6.56,
- "learning_rate": 0.0001586734693877551,
- "loss": 1.645,
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
"step": 324
},
{
- "epoch": 6.58,
- "learning_rate": 0.00015854591836734697,
- "loss": 1.5904,
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
"step": 325
},
{
- "epoch": 6.6,
- "learning_rate": 0.00015841836734693877,
- "loss": 1.6149,
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
"step": 326
},
{
- "epoch": 6.62,
- "learning_rate": 0.00015829081632653063,
- "loss": 1.6757,
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
"step": 327
},
{
- "epoch": 6.64,
- "learning_rate": 0.00015816326530612246,
- "loss": 1.541,
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
"step": 328
},
{
- "epoch": 6.66,
- "learning_rate": 0.0001580357142857143,
- "loss": 1.5898,
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
"step": 329
},
{
- "epoch": 6.68,
- "learning_rate": 0.00015790816326530612,
- "loss": 1.5441,
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
"step": 330
},
{
- "epoch": 6.7,
- "learning_rate": 0.00015778061224489798,
- "loss": 1.61,
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
"step": 331
},
{
- "epoch": 6.72,
- "learning_rate": 0.00015765306122448978,
- "loss": 1.615,
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
"step": 332
},
{
- "epoch": 6.74,
- "learning_rate": 0.00015752551020408164,
- "loss": 1.6575,
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
"step": 333
},
{
- "epoch": 6.76,
- "learning_rate": 0.00015739795918367347,
- "loss": 1.6702,
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
"step": 334
},
{
- "epoch": 6.78,
- "learning_rate": 0.0001572704081632653,
- "loss": 1.6009,
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
"step": 335
},
{
- "epoch": 6.8,
- "learning_rate": 0.00015714285714285716,
- "loss": 1.5568,
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
"step": 336
},
{
- "epoch": 6.82,
- "learning_rate": 0.000157015306122449,
- "loss": 1.619,
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
"step": 337
},
{
- "epoch": 6.84,
- "learning_rate": 0.00015688775510204082,
- "loss": 1.5563,
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
"step": 338
},
{
- "epoch": 6.86,
- "learning_rate": 0.00015676020408163265,
- "loss": 1.6328,
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
"step": 339
},
{
- "epoch": 6.88,
- "learning_rate": 0.0001566326530612245,
- "loss": 1.5726,
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
"step": 340
},
{
- "epoch": 6.9,
- "learning_rate": 0.00015650510204081634,
- "loss": 1.6199,
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
"step": 341
},
{
- "epoch": 6.92,
- "learning_rate": 0.00015637755102040817,
- "loss": 1.5722,
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
"step": 342
},
{
- "epoch": 6.94,
- "learning_rate": 0.00015625,
- "loss": 1.5685,
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
"step": 343
},
{
- "epoch": 6.96,
- "learning_rate": 0.00015612244897959186,
- "loss": 1.5615,
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
"step": 344
},
{
- "epoch": 6.98,
- "learning_rate": 0.00015599489795918366,
- "loss": 1.5994,
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
"step": 345
},
{
- "epoch": 7.0,
- "learning_rate": 0.00015586734693877552,
- "loss": 1.5579,
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
"step": 346
},
{
- "epoch": 7.02,
- "learning_rate": 0.00015573979591836735,
- "loss": 1.547,
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
"step": 347
},
{
- "epoch": 7.04,
- "learning_rate": 0.00015561224489795918,
- "loss": 1.5292,
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
"step": 348
},
{
- "epoch": 7.06,
- "learning_rate": 0.00015548469387755102,
- "loss": 1.6032,
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
"step": 349
},
{
- "epoch": 7.08,
- "learning_rate": 0.00015535714285714287,
- "loss": 1.5149,
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
"step": 350
},
{
- "epoch": 7.1,
- "learning_rate": 0.0001552295918367347,
- "loss": 1.6093,
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
"step": 351
},
{
- "epoch": 7.12,
- "learning_rate": 0.00015510204081632654,
- "loss": 1.5421,
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
"step": 352
},
{
- "epoch": 7.14,
- "learning_rate": 0.00015497448979591837,
- "loss": 1.5733,
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
"step": 353
},
{
- "epoch": 7.16,
- "learning_rate": 0.00015484693877551022,
- "loss": 1.5703,
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
"step": 354
},
{
- "epoch": 7.18,
- "learning_rate": 0.00015471938775510203,
- "loss": 1.6141,
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
"step": 355
},
{
- "epoch": 7.2,
- "learning_rate": 0.00015459183673469389,
- "loss": 1.5526,
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
"step": 356
},
{
- "epoch": 7.22,
- "learning_rate": 0.00015446428571428572,
- "loss": 1.5347,
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
"step": 357
},
{
- "epoch": 7.24,
- "learning_rate": 0.00015433673469387755,
- "loss": 1.5682,
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
"step": 358
},
{
- "epoch": 7.26,
- "learning_rate": 0.0001542091836734694,
- "loss": 1.5292,
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
"step": 359
},
{
- "epoch": 7.28,
- "learning_rate": 0.00015408163265306124,
- "loss": 1.499,
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
"step": 360
},
{
- "epoch": 7.3,
- "learning_rate": 0.00015395408163265307,
- "loss": 1.5624,
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
"step": 361
},
{
- "epoch": 7.32,
- "learning_rate": 0.0001538265306122449,
- "loss": 1.627,
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
"step": 362
},
{
- "epoch": 7.34,
- "learning_rate": 0.00015369897959183676,
- "loss": 1.5327,
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
"step": 363
},
{
- "epoch": 7.37,
- "learning_rate": 0.0001535714285714286,
- "loss": 1.5622,
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
"step": 364
},
{
- "epoch": 7.39,
- "learning_rate": 0.00015344387755102042,
- "loss": 1.5659,
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
"step": 365
},
{
- "epoch": 7.41,
- "learning_rate": 0.00015331632653061225,
- "loss": 1.5019,
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
"step": 366
},
{
- "epoch": 7.43,
- "learning_rate": 0.0001531887755102041,
- "loss": 1.5921,
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
"step": 367
},
{
- "epoch": 7.45,
- "learning_rate": 0.0001530612244897959,
- "loss": 1.5914,
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
"step": 368
},
{
- "epoch": 7.47,
- "learning_rate": 0.00015293367346938777,
- "loss": 1.5045,
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
"step": 369
},
{
- "epoch": 7.49,
- "learning_rate": 0.0001528061224489796,
- "loss": 1.6209,
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
"step": 370
},
{
- "epoch": 7.51,
- "learning_rate": 0.00015267857142857143,
- "loss": 1.5198,
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
"step": 371
},
{
- "epoch": 7.53,
- "learning_rate": 0.00015255102040816326,
- "loss": 1.5363,
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
"step": 372
},
{
- "epoch": 7.55,
- "learning_rate": 0.00015242346938775512,
- "loss": 1.5391,
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
"step": 373
},
{
- "epoch": 7.57,
- "learning_rate": 0.00015229591836734695,
- "loss": 1.4546,
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
"step": 374
},
{
- "epoch": 7.59,
- "learning_rate": 0.00015216836734693878,
- "loss": 1.5546,
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
"step": 375
},
{
- "epoch": 7.61,
- "learning_rate": 0.0001520408163265306,
- "loss": 1.5629,
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
"step": 376
},
{
- "epoch": 7.63,
- "learning_rate": 0.00015191326530612247,
- "loss": 1.6002,
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
"step": 377
},
{
- "epoch": 7.65,
- "learning_rate": 0.00015178571428571427,
- "loss": 1.5543,
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
"step": 378
},
{
- "epoch": 7.67,
- "learning_rate": 0.00015165816326530613,
- "loss": 1.5925,
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
"step": 379
},
{
- "epoch": 7.69,
- "learning_rate": 0.00015153061224489796,
- "loss": 1.5631,
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
"step": 380
},
{
- "epoch": 7.71,
- "learning_rate": 0.0001514030612244898,
- "loss": 1.5677,
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
"step": 381
},
{
- "epoch": 7.73,
- "learning_rate": 0.00015127551020408165,
- "loss": 1.5828,
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
"step": 382
},
{
- "epoch": 7.75,
- "learning_rate": 0.00015114795918367348,
- "loss": 1.6494,
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
"step": 383
},
{
- "epoch": 7.77,
- "learning_rate": 0.0001510204081632653,
- "loss": 1.553,
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
"step": 384
},
{
- "epoch": 7.79,
- "learning_rate": 0.00015089285714285714,
- "loss": 1.6156,
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
"step": 385
},
{
- "epoch": 7.81,
- "learning_rate": 0.000150765306122449,
- "loss": 1.5001,
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
"step": 386
},
{
- "epoch": 7.83,
- "learning_rate": 0.00015063775510204083,
- "loss": 1.5321,
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
"step": 387
},
{
- "epoch": 7.85,
- "learning_rate": 0.00015051020408163266,
- "loss": 1.5307,
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
"step": 388
},
{
- "epoch": 7.87,
- "learning_rate": 0.0001503826530612245,
- "loss": 1.5639,
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
"step": 389
},
{
- "epoch": 7.89,
- "learning_rate": 0.00015025510204081635,
- "loss": 1.517,
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
"step": 390
},
{
- "epoch": 7.91,
- "learning_rate": 0.00015012755102040816,
- "loss": 1.4776,
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
"step": 391
},
{
- "epoch": 7.93,
- "learning_rate": 0.00015000000000000001,
- "loss": 1.5368,
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
"step": 392
},
{
- "epoch": 7.95,
- "learning_rate": 0.00014987244897959184,
- "loss": 1.5636,
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
"step": 393
},
{
- "epoch": 7.97,
- "learning_rate": 0.00014974489795918368,
- "loss": 1.6004,
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
"step": 394
},
{
- "epoch": 7.99,
- "learning_rate": 0.0001496173469387755,
- "loss": 1.5524,
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
"step": 395
},
{
- "epoch": 8.01,
- "learning_rate": 0.00014948979591836736,
- "loss": 1.5307,
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
"step": 396
},
{
- "epoch": 8.03,
- "learning_rate": 0.00014936224489795917,
- "loss": 1.5123,
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
"step": 397
},
{
- "epoch": 8.05,
- "learning_rate": 0.00014923469387755103,
- "loss": 1.5132,
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
"step": 398
},
{
- "epoch": 8.07,
- "learning_rate": 0.00014910714285714286,
- "loss": 1.5109,
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
"step": 399
},
{
- "epoch": 8.09,
- "learning_rate": 0.00014897959183673472,
- "loss": 1.5302,
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
"step": 400
},
{
- "epoch": 8.11,
- "learning_rate": 0.00014885204081632652,
- "loss": 1.5238,
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
"step": 401
},
{
- "epoch": 8.13,
- "learning_rate": 0.00014872448979591838,
- "loss": 1.4781,
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
"step": 402
},
{
- "epoch": 8.15,
- "learning_rate": 0.0001485969387755102,
- "loss": 1.5446,
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
"step": 403
},
{
- "epoch": 8.17,
- "learning_rate": 0.00014846938775510204,
- "loss": 1.5,
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
"step": 404
},
{
- "epoch": 8.19,
- "learning_rate": 0.0001483418367346939,
- "loss": 1.5458,
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
"step": 405
},
{
- "epoch": 8.21,
- "learning_rate": 0.00014821428571428573,
- "loss": 1.5257,
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
"step": 406
},
{
- "epoch": 8.24,
- "learning_rate": 0.00014808673469387756,
- "loss": 1.4607,
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
"step": 407
},
{
- "epoch": 8.26,
- "learning_rate": 0.0001479591836734694,
- "loss": 1.4282,
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
"step": 408
},
{
- "epoch": 8.28,
- "learning_rate": 0.00014783163265306125,
- "loss": 1.4519,
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
"step": 409
},
{
- "epoch": 8.3,
- "learning_rate": 0.00014770408163265305,
- "loss": 1.475,
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
"step": 410
},
{
- "epoch": 8.32,
- "learning_rate": 0.0001475765306122449,
- "loss": 1.5425,
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
"step": 411
},
{
- "epoch": 8.34,
- "learning_rate": 0.00014744897959183674,
- "loss": 1.5407,
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
"step": 412
},
{
- "epoch": 8.36,
- "learning_rate": 0.0001473214285714286,
- "loss": 1.5698,
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
"step": 413
},
{
- "epoch": 8.38,
- "learning_rate": 0.0001471938775510204,
- "loss": 1.4282,
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
"step": 414
},
{
- "epoch": 8.4,
- "learning_rate": 0.00014706632653061226,
- "loss": 1.5301,
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
"step": 415
},
{
- "epoch": 8.42,
- "learning_rate": 0.0001469387755102041,
- "loss": 1.5083,
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
"step": 416
},
{
- "epoch": 8.44,
- "learning_rate": 0.00014681122448979592,
- "loss": 1.5712,
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
"step": 417
},
{
- "epoch": 8.46,
- "learning_rate": 0.00014668367346938775,
- "loss": 1.4363,
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
"step": 418
},
{
- "epoch": 8.48,
- "learning_rate": 0.0001465561224489796,
- "loss": 1.4463,
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
"step": 419
},
{
- "epoch": 8.5,
- "learning_rate": 0.00014642857142857141,
- "loss": 1.4738,
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
"step": 420
},
{
- "epoch": 8.52,
- "learning_rate": 0.00014630102040816327,
- "loss": 1.5396,
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
"step": 421
},
{
- "epoch": 8.54,
- "learning_rate": 0.0001461734693877551,
- "loss": 1.4384,
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
"step": 422
},
{
- "epoch": 8.56,
- "learning_rate": 0.00014604591836734696,
- "loss": 1.5345,
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
"step": 423
},
{
- "epoch": 8.58,
- "learning_rate": 0.0001459183673469388,
- "loss": 1.5355,
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
"step": 424
},
{
- "epoch": 8.6,
- "learning_rate": 0.00014579081632653062,
- "loss": 1.5188,
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
"step": 425
},
{
- "epoch": 8.62,
- "learning_rate": 0.00014566326530612245,
- "loss": 1.5575,
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
"step": 426
},
{
- "epoch": 8.64,
- "learning_rate": 0.00014553571428571428,
- "loss": 1.5279,
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
"step": 427
},
{
- "epoch": 8.66,
- "learning_rate": 0.00014540816326530614,
- "loss": 1.5484,
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
"step": 428
},
{
- "epoch": 8.68,
- "learning_rate": 0.00014528061224489797,
- "loss": 1.4878,
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
"step": 429
},
{
- "epoch": 8.7,
- "learning_rate": 0.0001451530612244898,
- "loss": 1.503,
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
"step": 430
},
{
- "epoch": 8.72,
- "learning_rate": 0.00014502551020408163,
- "loss": 1.4723,
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
"step": 431
},
{
- "epoch": 8.74,
- "learning_rate": 0.0001448979591836735,
- "loss": 1.5579,
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
"step": 432
},
{
- "epoch": 8.76,
- "learning_rate": 0.0001447704081632653,
- "loss": 1.4789,
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
"step": 433
},
{
- "epoch": 8.78,
- "learning_rate": 0.00014464285714285715,
- "loss": 1.5501,
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
"step": 434
},
{
- "epoch": 8.8,
- "learning_rate": 0.00014451530612244899,
- "loss": 1.5204,
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
"step": 435
},
{
- "epoch": 8.82,
- "learning_rate": 0.00014438775510204084,
- "loss": 1.5489,
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
"step": 436
},
{
- "epoch": 8.84,
- "learning_rate": 0.00014426020408163265,
- "loss": 1.5464,
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
"step": 437
},
{
- "epoch": 8.86,
- "learning_rate": 0.0001441326530612245,
- "loss": 1.5896,
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
"step": 438
},
{
- "epoch": 8.88,
- "learning_rate": 0.00014400510204081634,
- "loss": 1.5465,
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
"step": 439
},
{
- "epoch": 8.9,
- "learning_rate": 0.00014387755102040817,
- "loss": 1.5094,
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
"step": 440
},
{
- "epoch": 8.92,
- "learning_rate": 0.00014375,
- "loss": 1.5144,
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
"step": 441
},
{
- "epoch": 8.94,
- "learning_rate": 0.00014362244897959186,
- "loss": 1.4919,
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
"step": 442
},
{
- "epoch": 8.96,
- "learning_rate": 0.00014349489795918366,
- "loss": 1.4702,
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
"step": 443
},
{
- "epoch": 8.98,
- "learning_rate": 0.00014336734693877552,
- "loss": 1.4996,
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
"step": 444
},
{
- "epoch": 9.0,
- "learning_rate": 0.00014323979591836735,
- "loss": 1.5503,
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
"step": 445
},
{
- "epoch": 9.02,
- "learning_rate": 0.00014311224489795918,
- "loss": 1.4125,
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
"step": 446
},
{
- "epoch": 9.04,
- "learning_rate": 0.00014298469387755104,
- "loss": 1.4722,
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
"step": 447
},
{
- "epoch": 9.06,
- "learning_rate": 0.00014285714285714287,
- "loss": 1.5199,
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
"step": 448
},
{
- "epoch": 9.09,
- "learning_rate": 0.0001427295918367347,
- "loss": 1.4571,
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
"step": 449
},
{
- "epoch": 9.11,
- "learning_rate": 0.00014260204081632653,
- "loss": 1.4996,
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
"step": 450
},
{
- "epoch": 9.13,
- "learning_rate": 0.0001424744897959184,
- "loss": 1.4092,
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
"step": 451
},
{
- "epoch": 9.15,
- "learning_rate": 0.00014234693877551022,
- "loss": 1.4198,
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
"step": 452
},
{
- "epoch": 9.17,
- "learning_rate": 0.00014221938775510205,
- "loss": 1.4916,
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
"step": 453
},
{
- "epoch": 9.19,
- "learning_rate": 0.00014209183673469388,
- "loss": 1.5051,
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
"step": 454
},
{
- "epoch": 9.21,
- "learning_rate": 0.00014196428571428574,
- "loss": 1.4321,
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
"step": 455
},
{
- "epoch": 9.23,
- "learning_rate": 0.00014183673469387754,
- "loss": 1.4097,
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
"step": 456
},
{
- "epoch": 9.25,
- "learning_rate": 0.0001417091836734694,
- "loss": 1.4853,
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
"step": 457
},
{
- "epoch": 9.27,
- "learning_rate": 0.00014158163265306123,
- "loss": 1.4593,
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
"step": 458
},
{
- "epoch": 9.29,
- "learning_rate": 0.00014145408163265306,
- "loss": 1.3729,
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
"step": 459
},
{
- "epoch": 9.31,
- "learning_rate": 0.0001413265306122449,
- "loss": 1.4467,
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
"step": 460
},
{
- "epoch": 9.33,
- "learning_rate": 0.00014119897959183675,
- "loss": 1.4467,
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
"step": 461
},
{
- "epoch": 9.35,
- "learning_rate": 0.00014107142857142858,
- "loss": 1.4785,
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
"step": 462
},
{
- "epoch": 9.37,
- "learning_rate": 0.0001409438775510204,
- "loss": 1.4089,
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
"step": 463
},
{
- "epoch": 9.39,
- "learning_rate": 0.00014081632653061224,
- "loss": 1.5026,
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
"step": 464
},
{
- "epoch": 9.41,
- "learning_rate": 0.0001406887755102041,
- "loss": 1.4857,
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
"step": 465
},
{
- "epoch": 9.43,
- "learning_rate": 0.0001405612244897959,
- "loss": 1.3745,
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
"step": 466
},
{
- "epoch": 9.45,
- "learning_rate": 0.00014043367346938776,
- "loss": 1.4733,
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
"step": 467
},
{
- "epoch": 9.47,
- "learning_rate": 0.0001403061224489796,
- "loss": 1.5212,
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
"step": 468
},
{
- "epoch": 9.49,
- "learning_rate": 0.00014017857142857142,
- "loss": 1.5398,
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
"step": 469
},
{
- "epoch": 9.51,
- "learning_rate": 0.00014005102040816328,
- "loss": 1.478,
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
"step": 470
},
{
- "epoch": 9.53,
- "learning_rate": 0.0001399234693877551,
- "loss": 1.496,
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
"step": 471
},
{
- "epoch": 9.55,
- "learning_rate": 0.00013979591836734694,
- "loss": 1.4837,
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
"step": 472
},
{
- "epoch": 9.57,
- "learning_rate": 0.00013966836734693878,
- "loss": 1.4724,
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
"step": 473
},
{
- "epoch": 9.59,
- "learning_rate": 0.00013954081632653063,
- "loss": 1.4828,
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
"step": 474
},
{
- "epoch": 9.61,
- "learning_rate": 0.00013941326530612246,
- "loss": 1.5012,
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
"step": 475
},
{
- "epoch": 9.63,
- "learning_rate": 0.0001392857142857143,
- "loss": 1.4879,
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
"step": 476
},
{
- "epoch": 9.65,
- "learning_rate": 0.00013915816326530613,
- "loss": 1.4196,
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
"step": 477
},
{
- "epoch": 9.67,
- "learning_rate": 0.00013903061224489798,
- "loss": 1.4915,
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
"step": 478
},
{
- "epoch": 9.69,
- "learning_rate": 0.0001389030612244898,
- "loss": 1.3878,
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
"step": 479
},
{
- "epoch": 9.71,
- "learning_rate": 0.00013877551020408165,
- "loss": 1.466,
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
"step": 480
},
{
- "epoch": 9.73,
- "learning_rate": 0.00013864795918367348,
- "loss": 1.4582,
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
"step": 481
},
{
- "epoch": 9.75,
- "learning_rate": 0.0001385204081632653,
- "loss": 1.533,
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
"step": 482
},
{
- "epoch": 9.77,
- "learning_rate": 0.00013839285714285714,
- "loss": 1.4697,
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
"step": 483
},
{
- "epoch": 9.79,
- "learning_rate": 0.000138265306122449,
- "loss": 1.3989,
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
"step": 484
},
{
- "epoch": 9.81,
- "learning_rate": 0.00013813775510204083,
- "loss": 1.4361,
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
"step": 485
},
{
- "epoch": 9.83,
- "learning_rate": 0.00013801020408163266,
- "loss": 1.5271,
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
"step": 486
},
{
- "epoch": 9.85,
- "learning_rate": 0.0001378826530612245,
- "loss": 1.4905,
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
"step": 487
},
{
- "epoch": 9.87,
- "learning_rate": 0.00013775510204081635,
- "loss": 1.4757,
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
"step": 488
},
{
- "epoch": 9.89,
- "learning_rate": 0.00013762755102040815,
- "loss": 1.5485,
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
"step": 489
},
{
- "epoch": 9.91,
- "learning_rate": 0.0001375,
- "loss": 1.4783,
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
"step": 490
},
{
- "epoch": 9.93,
- "learning_rate": 0.00013737244897959184,
- "loss": 1.4849,
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
"step": 491
},
{
- "epoch": 9.96,
- "learning_rate": 0.00013724489795918367,
- "loss": 1.5382,
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
"step": 492
},
{
- "epoch": 9.98,
- "learning_rate": 0.00013711734693877553,
- "loss": 1.4902,
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
"step": 493
},
{
- "epoch": 10.0,
- "learning_rate": 0.00013698979591836736,
- "loss": 1.4865,
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
"step": 494
},
{
- "epoch": 10.02,
- "learning_rate": 0.0001368622448979592,
- "loss": 1.4436,
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
"step": 495
},
{
- "epoch": 10.04,
- "learning_rate": 0.00013673469387755102,
- "loss": 1.408,
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
"step": 496
},
{
- "epoch": 10.06,
- "learning_rate": 0.00013660714285714288,
- "loss": 1.4764,
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
"step": 497
},
{
- "epoch": 10.08,
- "learning_rate": 0.0001364795918367347,
- "loss": 1.4646,
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
"step": 498
},
{
- "epoch": 10.1,
- "learning_rate": 0.00013635204081632654,
- "loss": 1.406,
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
"step": 499
},
{
- "epoch": 10.12,
- "learning_rate": 0.00013622448979591837,
- "loss": 1.4785,
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
"step": 500
},
{
- "epoch": 10.14,
- "learning_rate": 0.00013609693877551023,
- "loss": 1.4117,
+ "epoch": 5.66,
+ "learning_rate": 0.00012883522727272727,
+ "loss": 1.0755,
"step": 501
},
{
- "epoch": 10.16,
- "learning_rate": 0.00013596938775510203,
- "loss": 1.4108,
+ "epoch": 5.67,
+ "learning_rate": 0.00012869318181818183,
+ "loss": 1.0755,
"step": 502
},
{
- "epoch": 10.18,
- "learning_rate": 0.0001358418367346939,
- "loss": 1.4155,
+ "epoch": 5.68,
+ "learning_rate": 0.00012855113636363636,
+ "loss": 1.0869,
"step": 503
},
{
- "epoch": 10.2,
- "learning_rate": 0.00013571428571428572,
- "loss": 1.4021,
+ "epoch": 5.69,
+ "learning_rate": 0.00012840909090909092,
+ "loss": 1.0673,
"step": 504
},
{
- "epoch": 10.22,
- "learning_rate": 0.00013558673469387755,
- "loss": 1.411,
+ "epoch": 5.71,
+ "learning_rate": 0.00012826704545454545,
+ "loss": 1.0692,
"step": 505
},
{
- "epoch": 10.24,
- "learning_rate": 0.00013545918367346938,
- "loss": 1.3851,
+ "epoch": 5.72,
+ "learning_rate": 0.000128125,
+ "loss": 1.0474,
"step": 506
},
{
- "epoch": 10.26,
- "learning_rate": 0.00013533163265306124,
- "loss": 1.387,
+ "epoch": 5.73,
+ "learning_rate": 0.00012798295454545454,
+ "loss": 1.0749,
"step": 507
},
{
- "epoch": 10.28,
- "learning_rate": 0.00013520408163265305,
- "loss": 1.4163,
+ "epoch": 5.74,
+ "learning_rate": 0.0001278409090909091,
+ "loss": 1.0519,
"step": 508
},
{
- "epoch": 10.3,
- "learning_rate": 0.0001350765306122449,
- "loss": 1.3343,
+ "epoch": 5.75,
+ "learning_rate": 0.00012769886363636366,
+ "loss": 1.0566,
"step": 509
},
{
- "epoch": 10.32,
- "learning_rate": 0.00013494897959183673,
- "loss": 1.4811,
+ "epoch": 5.76,
+ "learning_rate": 0.0001275568181818182,
+ "loss": 1.06,
"step": 510
},
{
- "epoch": 10.34,
- "learning_rate": 0.0001348214285714286,
- "loss": 1.4086,
+ "epoch": 5.77,
+ "learning_rate": 0.00012741477272727272,
+ "loss": 1.0618,
"step": 511
},
{
- "epoch": 10.36,
- "learning_rate": 0.0001346938775510204,
- "loss": 1.3879,
+ "epoch": 5.78,
+ "learning_rate": 0.00012727272727272728,
+ "loss": 1.0643,
"step": 512
},
{
- "epoch": 10.38,
- "learning_rate": 0.00013456632653061225,
- "loss": 1.4204,
+ "epoch": 5.8,
+ "learning_rate": 0.0001271306818181818,
+ "loss": 1.026,
"step": 513
},
{
- "epoch": 10.4,
- "learning_rate": 0.00013443877551020408,
- "loss": 1.4158,
+ "epoch": 5.81,
+ "learning_rate": 0.00012698863636363637,
+ "loss": 1.0335,
"step": 514
},
{
- "epoch": 10.42,
- "learning_rate": 0.00013431122448979592,
- "loss": 1.4521,
+ "epoch": 5.82,
+ "learning_rate": 0.00012684659090909093,
+ "loss": 1.0205,
"step": 515
},
{
- "epoch": 10.44,
- "learning_rate": 0.00013418367346938777,
- "loss": 1.4196,
+ "epoch": 5.83,
+ "learning_rate": 0.00012670454545454546,
+ "loss": 1.0594,
"step": 516
},
{
- "epoch": 10.46,
- "learning_rate": 0.0001340561224489796,
- "loss": 1.4361,
+ "epoch": 5.84,
+ "learning_rate": 0.0001265625,
+ "loss": 1.0136,
"step": 517
},
{
- "epoch": 10.48,
- "learning_rate": 0.00013392857142857144,
- "loss": 1.4482,
+ "epoch": 5.85,
+ "learning_rate": 0.00012642045454545455,
+ "loss": 1.0244,
"step": 518
},
{
- "epoch": 10.5,
- "learning_rate": 0.00013380102040816327,
- "loss": 1.4801,
+ "epoch": 5.86,
+ "learning_rate": 0.00012627840909090908,
+ "loss": 1.0569,
"step": 519
},
{
- "epoch": 10.52,
- "learning_rate": 0.00013367346938775512,
- "loss": 1.4556,
+ "epoch": 5.87,
+ "learning_rate": 0.00012613636363636364,
+ "loss": 1.0416,
"step": 520
},
{
- "epoch": 10.54,
- "learning_rate": 0.00013354591836734695,
- "loss": 1.3902,
+ "epoch": 5.89,
+ "learning_rate": 0.0001259943181818182,
+ "loss": 0.9884,
"step": 521
},
{
- "epoch": 10.56,
- "learning_rate": 0.00013341836734693879,
- "loss": 1.4269,
+ "epoch": 5.9,
+ "learning_rate": 0.00012585227272727273,
+ "loss": 1.0351,
"step": 522
},
{
- "epoch": 10.58,
- "learning_rate": 0.00013329081632653062,
- "loss": 1.4899,
+ "epoch": 5.91,
+ "learning_rate": 0.00012571022727272726,
+ "loss": 1.0037,
"step": 523
},
{
- "epoch": 10.6,
- "learning_rate": 0.00013316326530612247,
- "loss": 1.3952,
+ "epoch": 5.92,
+ "learning_rate": 0.00012556818181818182,
+ "loss": 1.0219,
"step": 524
},
{
- "epoch": 10.62,
- "learning_rate": 0.00013303571428571428,
- "loss": 1.4116,
+ "epoch": 5.93,
+ "learning_rate": 0.00012542613636363635,
+ "loss": 1.0533,
"step": 525
},
{
- "epoch": 10.64,
- "learning_rate": 0.00013290816326530614,
- "loss": 1.4583,
+ "epoch": 5.94,
+ "learning_rate": 0.0001252840909090909,
+ "loss": 1.0031,
"step": 526
},
{
- "epoch": 10.66,
- "learning_rate": 0.00013278061224489797,
- "loss": 1.4466,
+ "epoch": 5.95,
+ "learning_rate": 0.00012514204545454547,
+ "loss": 1.0454,
"step": 527
},
{
- "epoch": 10.68,
- "learning_rate": 0.0001326530612244898,
- "loss": 1.4242,
+ "epoch": 5.97,
+ "learning_rate": 0.000125,
+ "loss": 1.0195,
"step": 528
},
{
- "epoch": 10.7,
- "learning_rate": 0.00013252551020408163,
- "loss": 1.3717,
+ "epoch": 5.98,
+ "learning_rate": 0.00012485795454545453,
+ "loss": 1.0076,
"step": 529
},
{
- "epoch": 10.72,
- "learning_rate": 0.0001323979591836735,
- "loss": 1.4583,
+ "epoch": 5.99,
+ "learning_rate": 0.0001247159090909091,
+ "loss": 1.0378,
"step": 530
},
{
- "epoch": 10.74,
- "learning_rate": 0.0001322704081632653,
- "loss": 1.4185,
+ "epoch": 6.0,
+ "learning_rate": 0.00012457386363636365,
+ "loss": 0.9795,
"step": 531
},
{
- "epoch": 10.76,
- "learning_rate": 0.00013214285714285715,
- "loss": 1.4287,
+ "epoch": 6.01,
+ "learning_rate": 0.00012443181818181818,
+ "loss": 0.9405,
"step": 532
},
{
- "epoch": 10.78,
- "learning_rate": 0.00013201530612244898,
- "loss": 1.4385,
+ "epoch": 6.02,
+ "learning_rate": 0.00012428977272727274,
+ "loss": 0.9503,
"step": 533
},
{
- "epoch": 10.8,
- "learning_rate": 0.00013188775510204084,
- "loss": 1.453,
+ "epoch": 6.03,
+ "learning_rate": 0.00012414772727272727,
+ "loss": 0.9456,
"step": 534
},
{
- "epoch": 10.83,
- "learning_rate": 0.00013176020408163264,
- "loss": 1.4161,
+ "epoch": 6.04,
+ "learning_rate": 0.0001240056818181818,
+ "loss": 0.9536,
"step": 535
},
{
- "epoch": 10.85,
- "learning_rate": 0.0001316326530612245,
- "loss": 1.457,
+ "epoch": 6.06,
+ "learning_rate": 0.00012386363636363636,
+ "loss": 0.9412,
"step": 536
},
{
- "epoch": 10.87,
- "learning_rate": 0.00013150510204081633,
- "loss": 1.4367,
+ "epoch": 6.07,
+ "learning_rate": 0.00012372159090909092,
+ "loss": 0.9315,
"step": 537
},
{
- "epoch": 10.89,
- "learning_rate": 0.00013137755102040816,
- "loss": 1.4256,
+ "epoch": 6.08,
+ "learning_rate": 0.00012357954545454545,
+ "loss": 0.9486,
"step": 538
},
{
- "epoch": 10.91,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.424,
+ "epoch": 6.09,
+ "learning_rate": 0.0001234375,
+ "loss": 0.9405,
"step": 539
},
{
- "epoch": 10.93,
- "learning_rate": 0.00013112244897959185,
- "loss": 1.3923,
+ "epoch": 6.1,
+ "learning_rate": 0.00012329545454545454,
+ "loss": 0.9269,
"step": 540
},
{
- "epoch": 10.95,
- "learning_rate": 0.00013099489795918368,
- "loss": 1.4225,
+ "epoch": 6.11,
+ "learning_rate": 0.0001231534090909091,
+ "loss": 0.9378,
"step": 541
},
{
- "epoch": 10.97,
- "learning_rate": 0.0001308673469387755,
- "loss": 1.3969,
+ "epoch": 6.12,
+ "learning_rate": 0.00012301136363636366,
+ "loss": 0.9431,
"step": 542
},
{
- "epoch": 10.99,
- "learning_rate": 0.00013073979591836737,
- "loss": 1.4446,
+ "epoch": 6.13,
+ "learning_rate": 0.0001228693181818182,
+ "loss": 0.9256,
"step": 543
},
{
- "epoch": 11.01,
- "learning_rate": 0.00013061224489795917,
- "loss": 1.4375,
+ "epoch": 6.15,
+ "learning_rate": 0.00012272727272727272,
+ "loss": 0.919,
"step": 544
},
{
- "epoch": 11.03,
- "learning_rate": 0.00013048469387755103,
- "loss": 1.4064,
+ "epoch": 6.16,
+ "learning_rate": 0.00012258522727272728,
+ "loss": 0.9188,
"step": 545
},
{
- "epoch": 11.05,
- "learning_rate": 0.00013035714285714286,
- "loss": 1.3454,
+ "epoch": 6.17,
+ "learning_rate": 0.00012244318181818181,
+ "loss": 0.9447,
"step": 546
},
{
- "epoch": 11.07,
- "learning_rate": 0.00013022959183673472,
- "loss": 1.3234,
+ "epoch": 6.18,
+ "learning_rate": 0.00012230113636363637,
+ "loss": 0.9261,
"step": 547
},
{
- "epoch": 11.09,
- "learning_rate": 0.00013010204081632652,
- "loss": 1.3759,
+ "epoch": 6.19,
+ "learning_rate": 0.00012215909090909093,
+ "loss": 0.9302,
"step": 548
},
{
- "epoch": 11.11,
- "learning_rate": 0.00012997448979591838,
- "loss": 1.4221,
+ "epoch": 6.2,
+ "learning_rate": 0.00012201704545454546,
+ "loss": 0.9161,
"step": 549
},
{
- "epoch": 11.13,
- "learning_rate": 0.0001298469387755102,
- "loss": 1.4261,
+ "epoch": 6.21,
+ "learning_rate": 0.00012187500000000001,
+ "loss": 0.9521,
"step": 550
},
{
- "epoch": 11.15,
- "learning_rate": 0.00012971938775510204,
- "loss": 1.3341,
+ "epoch": 6.22,
+ "learning_rate": 0.00012173295454545455,
+ "loss": 0.9026,
"step": 551
},
{
- "epoch": 11.17,
- "learning_rate": 0.00012959183673469387,
- "loss": 1.3994,
+ "epoch": 6.24,
+ "learning_rate": 0.00012159090909090908,
+ "loss": 0.9361,
"step": 552
},
{
- "epoch": 11.19,
- "learning_rate": 0.00012946428571428573,
- "loss": 1.3894,
+ "epoch": 6.25,
+ "learning_rate": 0.00012144886363636366,
+ "loss": 0.8944,
"step": 553
},
{
- "epoch": 11.21,
- "learning_rate": 0.00012933673469387754,
- "loss": 1.3585,
+ "epoch": 6.26,
+ "learning_rate": 0.00012130681818181819,
+ "loss": 0.895,
"step": 554
},
{
- "epoch": 11.23,
- "learning_rate": 0.0001292091836734694,
- "loss": 1.3763,
+ "epoch": 6.27,
+ "learning_rate": 0.00012116477272727273,
+ "loss": 0.8956,
"step": 555
},
{
- "epoch": 11.25,
- "learning_rate": 0.00012908163265306123,
- "loss": 1.3623,
+ "epoch": 6.28,
+ "learning_rate": 0.00012102272727272728,
+ "loss": 0.8998,
"step": 556
},
{
- "epoch": 11.27,
- "learning_rate": 0.00012895408163265306,
- "loss": 1.3907,
+ "epoch": 6.29,
+ "learning_rate": 0.00012088068181818182,
+ "loss": 0.915,
"step": 557
},
{
- "epoch": 11.29,
- "learning_rate": 0.0001288265306122449,
- "loss": 1.3807,
+ "epoch": 6.3,
+ "learning_rate": 0.00012073863636363636,
+ "loss": 0.9282,
"step": 558
},
{
- "epoch": 11.31,
- "learning_rate": 0.00012869897959183674,
- "loss": 1.4045,
+ "epoch": 6.32,
+ "learning_rate": 0.00012059659090909093,
+ "loss": 0.8938,
"step": 559
},
{
- "epoch": 11.33,
- "learning_rate": 0.00012857142857142858,
- "loss": 1.4038,
+ "epoch": 6.33,
+ "learning_rate": 0.00012045454545454546,
+ "loss": 0.8886,
"step": 560
},
{
- "epoch": 11.35,
- "learning_rate": 0.0001284438775510204,
- "loss": 1.3466,
+ "epoch": 6.34,
+ "learning_rate": 0.0001203125,
+ "loss": 0.8988,
"step": 561
},
{
- "epoch": 11.37,
- "learning_rate": 0.00012831632653061226,
- "loss": 1.3449,
+ "epoch": 6.35,
+ "learning_rate": 0.00012017045454545455,
+ "loss": 0.8852,
"step": 562
},
{
- "epoch": 11.39,
- "learning_rate": 0.0001281887755102041,
- "loss": 1.3866,
+ "epoch": 6.36,
+ "learning_rate": 0.0001200284090909091,
+ "loss": 0.8818,
"step": 563
},
{
- "epoch": 11.41,
- "learning_rate": 0.00012806122448979593,
- "loss": 1.3106,
+ "epoch": 6.37,
+ "learning_rate": 0.00011988636363636365,
+ "loss": 0.8881,
"step": 564
},
{
- "epoch": 11.43,
- "learning_rate": 0.00012793367346938776,
- "loss": 1.4414,
+ "epoch": 6.38,
+ "learning_rate": 0.0001197443181818182,
+ "loss": 0.9226,
"step": 565
},
{
- "epoch": 11.45,
- "learning_rate": 0.00012780612244897962,
- "loss": 1.3737,
+ "epoch": 6.39,
+ "learning_rate": 0.00011960227272727273,
+ "loss": 0.8849,
"step": 566
},
{
- "epoch": 11.47,
- "learning_rate": 0.00012767857142857142,
- "loss": 1.4053,
+ "epoch": 6.41,
+ "learning_rate": 0.00011946022727272727,
+ "loss": 0.8894,
"step": 567
},
{
- "epoch": 11.49,
- "learning_rate": 0.00012755102040816328,
- "loss": 1.4561,
+ "epoch": 6.42,
+ "learning_rate": 0.00011931818181818182,
+ "loss": 0.9207,
"step": 568
},
{
- "epoch": 11.51,
- "learning_rate": 0.0001274234693877551,
- "loss": 1.3684,
+ "epoch": 6.43,
+ "learning_rate": 0.00011917613636363636,
+ "loss": 0.9105,
"step": 569
},
{
- "epoch": 11.53,
- "learning_rate": 0.00012729591836734697,
- "loss": 1.3117,
+ "epoch": 6.44,
+ "learning_rate": 0.00011903409090909092,
+ "loss": 0.8762,
"step": 570
},
{
- "epoch": 11.55,
- "learning_rate": 0.00012716836734693877,
- "loss": 1.3474,
+ "epoch": 6.45,
+ "learning_rate": 0.00011889204545454547,
+ "loss": 0.8926,
"step": 571
},
{
- "epoch": 11.57,
- "learning_rate": 0.00012704081632653063,
- "loss": 1.3804,
+ "epoch": 6.46,
+ "learning_rate": 0.00011875,
+ "loss": 0.8719,
"step": 572
},
{
- "epoch": 11.59,
- "learning_rate": 0.00012691326530612246,
- "loss": 1.3656,
+ "epoch": 6.47,
+ "learning_rate": 0.00011860795454545454,
+ "loss": 0.9198,
"step": 573
},
{
- "epoch": 11.61,
- "learning_rate": 0.0001267857142857143,
- "loss": 1.3133,
+ "epoch": 6.48,
+ "learning_rate": 0.00011846590909090909,
+ "loss": 0.8846,
"step": 574
},
{
- "epoch": 11.63,
- "learning_rate": 0.00012665816326530612,
- "loss": 1.4077,
+ "epoch": 6.5,
+ "learning_rate": 0.00011832386363636365,
+ "loss": 0.8495,
"step": 575
},
{
- "epoch": 11.65,
- "learning_rate": 0.00012653061224489798,
- "loss": 1.4087,
+ "epoch": 6.51,
+ "learning_rate": 0.0001181818181818182,
+ "loss": 0.8953,
"step": 576
},
{
- "epoch": 11.67,
- "learning_rate": 0.00012640306122448978,
- "loss": 1.3524,
+ "epoch": 6.52,
+ "learning_rate": 0.00011803977272727274,
+ "loss": 0.8686,
"step": 577
},
{
- "epoch": 11.7,
- "learning_rate": 0.00012627551020408164,
- "loss": 1.3481,
+ "epoch": 6.53,
+ "learning_rate": 0.00011789772727272727,
+ "loss": 0.8841,
"step": 578
},
{
- "epoch": 11.72,
- "learning_rate": 0.00012614795918367347,
- "loss": 1.4497,
+ "epoch": 6.54,
+ "learning_rate": 0.00011775568181818182,
+ "loss": 0.8681,
"step": 579
},
{
- "epoch": 11.74,
- "learning_rate": 0.0001260204081632653,
- "loss": 1.3866,
+ "epoch": 6.55,
+ "learning_rate": 0.00011761363636363636,
+ "loss": 0.8732,
"step": 580
},
{
- "epoch": 11.76,
- "learning_rate": 0.00012589285714285713,
- "loss": 1.42,
+ "epoch": 6.56,
+ "learning_rate": 0.00011747159090909092,
+ "loss": 0.8582,
"step": 581
},
{
- "epoch": 11.78,
- "learning_rate": 0.000125765306122449,
- "loss": 1.3562,
+ "epoch": 6.58,
+ "learning_rate": 0.00011732954545454546,
+ "loss": 0.8744,
"step": 582
},
{
- "epoch": 11.8,
- "learning_rate": 0.00012563775510204082,
- "loss": 1.3249,
+ "epoch": 6.59,
+ "learning_rate": 0.00011718750000000001,
+ "loss": 0.8694,
"step": 583
},
{
- "epoch": 11.82,
- "learning_rate": 0.00012551020408163265,
- "loss": 1.4277,
+ "epoch": 6.6,
+ "learning_rate": 0.00011704545454545454,
+ "loss": 0.8565,
"step": 584
},
{
- "epoch": 11.84,
- "learning_rate": 0.0001253826530612245,
- "loss": 1.3734,
+ "epoch": 6.61,
+ "learning_rate": 0.00011690340909090909,
+ "loss": 0.8584,
"step": 585
},
{
- "epoch": 11.86,
- "learning_rate": 0.00012525510204081634,
- "loss": 1.3765,
+ "epoch": 6.62,
+ "learning_rate": 0.00011676136363636366,
+ "loss": 0.8859,
"step": 586
},
{
- "epoch": 11.88,
- "learning_rate": 0.00012512755102040817,
- "loss": 1.4153,
+ "epoch": 6.63,
+ "learning_rate": 0.00011661931818181819,
+ "loss": 0.8452,
"step": 587
},
{
- "epoch": 11.9,
- "learning_rate": 0.000125,
- "loss": 1.3847,
+ "epoch": 6.64,
+ "learning_rate": 0.00011647727272727273,
+ "loss": 0.8323,
"step": 588
},
{
- "epoch": 11.92,
- "learning_rate": 0.00012487244897959186,
- "loss": 1.3824,
+ "epoch": 6.65,
+ "learning_rate": 0.00011633522727272728,
+ "loss": 0.8548,
"step": 589
},
{
- "epoch": 11.94,
- "learning_rate": 0.00012474489795918366,
- "loss": 1.3938,
+ "epoch": 6.67,
+ "learning_rate": 0.00011619318181818181,
+ "loss": 0.8506,
"step": 590
},
{
- "epoch": 11.96,
- "learning_rate": 0.00012461734693877552,
- "loss": 1.4143,
+ "epoch": 6.68,
+ "learning_rate": 0.00011605113636363636,
+ "loss": 0.8556,
"step": 591
},
{
- "epoch": 11.98,
- "learning_rate": 0.00012448979591836735,
- "loss": 1.3794,
+ "epoch": 6.69,
+ "learning_rate": 0.00011590909090909093,
+ "loss": 0.8459,
"step": 592
},
{
- "epoch": 12.0,
- "learning_rate": 0.00012436224489795918,
- "loss": 1.3755,
+ "epoch": 6.7,
+ "learning_rate": 0.00011576704545454546,
+ "loss": 0.8432,
"step": 593
},
{
- "epoch": 12.02,
- "learning_rate": 0.00012423469387755101,
- "loss": 1.3736,
+ "epoch": 6.71,
+ "learning_rate": 0.000115625,
+ "loss": 0.8645,
"step": 594
},
{
- "epoch": 12.04,
- "learning_rate": 0.00012410714285714287,
- "loss": 1.2957,
+ "epoch": 6.72,
+ "learning_rate": 0.00011548295454545455,
+ "loss": 0.86,
"step": 595
},
{
- "epoch": 12.06,
- "learning_rate": 0.0001239795918367347,
- "loss": 1.2996,
+ "epoch": 6.73,
+ "learning_rate": 0.00011534090909090908,
+ "loss": 0.8161,
"step": 596
},
{
- "epoch": 12.08,
- "learning_rate": 0.00012385204081632653,
- "loss": 1.3648,
+ "epoch": 6.74,
+ "learning_rate": 0.00011519886363636365,
+ "loss": 0.8133,
"step": 597
},
{
- "epoch": 12.1,
- "learning_rate": 0.00012372448979591837,
- "loss": 1.3031,
+ "epoch": 6.76,
+ "learning_rate": 0.0001150568181818182,
+ "loss": 0.8372,
"step": 598
},
{
- "epoch": 12.12,
- "learning_rate": 0.00012359693877551022,
- "loss": 1.2933,
+ "epoch": 6.77,
+ "learning_rate": 0.00011491477272727273,
+ "loss": 0.8222,
"step": 599
},
{
- "epoch": 12.14,
- "learning_rate": 0.00012346938775510203,
- "loss": 1.322,
+ "epoch": 6.78,
+ "learning_rate": 0.00011477272727272728,
+ "loss": 0.8372,
"step": 600
}
],
"logging_steps": 1,
- "max_steps": 1568,
- "num_train_epochs": 32,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
"save_steps": 100,
- "total_flos": 8.877519690112819e+17,
+ "total_flos": 8.186165472352358e+17,
"trial_name": null,
"trial_params": null
}
diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin
index db23e07d097c18532e52f58a70eb72d22e39c8c1..ee7ddb867f05d9a969f71467a8eb88994865cf51 100644
--- a/checkpoint-600/training_args.bin
+++ b/checkpoint-600/training_args.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
size 4155
diff --git a/checkpoint-700/adapter_model.bin b/checkpoint-700/adapter_model.bin
index 555b872534b3769fecafaf9320509b206eaa9ba2..47edcdade531f430a4841b8c75a8994cccc6886e 100644
--- a/checkpoint-700/adapter_model.bin
+++ b/checkpoint-700/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:6fe79826e26fa903fa64560c79bd0221d35aa416cc9a8d5ec9e09e149435dfbb
+oid sha256:83a2bd54ab68a3dcad8fe0e5a630e45f5342750c381fd29ab4100c5db3d4e0e9
size 39409357
diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt
index 6422dd33c8fe76b4f9fbf53da14138518675e40c..a62e3aec1fb00d3f76e73f1aefbfc3d9d39e10aa 100644
--- a/checkpoint-700/optimizer.pt
+++ b/checkpoint-700/optimizer.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:829988f0b71481d26c8b54a86768543c7c14a48d695552f6933481d5709420c1
+oid sha256:81ef498b8b8b31a2a5c36ffe3529e1378029eb4c3e4ba4770de0c248e4c62950
size 78844421
diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth
index c1c4c79fcb2148e5de373db02c3ee2987200a3a9..a0e229d77fa9bb9693355411d7e7ba7367c65223 100644
--- a/checkpoint-700/rng_state.pth
+++ b/checkpoint-700/rng_state.pth
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:3e46ce4eb16240da9f3a8b3066acb6f59a234249ee2a3052f3323786da479838
+oid sha256:36fc71bd44bd7f04f2599c5dface64c517de1a7ab7bac3600f3f6470c6c72673
size 14575
diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt
index 4543a318cb958b4b426e7561985db7ab82a9d34b..5bf1dd76a9cb3ad1e89ec2bcd4d8085e0d94a8e9 100644
--- a/checkpoint-700/scheduler.pt
+++ b/checkpoint-700/scheduler.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:091c20f4c5e244fe8f3c4fd8851e0e20a9e6123652dcfb2277f8793845f1eb70
+oid sha256:7c6badaa6737fa9306a1f25b19c54f91672e90aa94d505b95ab467e7d08dd541
size 627
diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json
index 2aeb564b0e254822ffc5698a6594bddc49348229..c2d19f019ed3319a4afbcd2d2827df146950c4f2 100644
--- a/checkpoint-700/trainer_state.json
+++ b/checkpoint-700/trainer_state.json
@@ -1,7 +1,7 @@
{
"best_metric": null,
"best_model_checkpoint": null,
- "epoch": 14.163768574138476,
+ "epoch": 7.908208296557811,
"eval_steps": 500,
"global_step": 700,
"is_hyper_param_search": false,
@@ -9,4211 +9,4211 @@
"is_world_process_zero": true,
"log_history": [
{
- "epoch": 0.02,
- "learning_rate": 0.00019987244897959184,
- "loss": 3.2215,
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
"step": 1
},
{
- "epoch": 0.04,
- "learning_rate": 0.00019974489795918367,
- "loss": 2.8365,
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
"step": 2
},
{
- "epoch": 0.06,
- "learning_rate": 0.00019961734693877553,
- "loss": 2.602,
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
"step": 3
},
{
- "epoch": 0.08,
- "learning_rate": 0.00019948979591836736,
- "loss": 2.4196,
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
"step": 4
},
{
- "epoch": 0.1,
- "learning_rate": 0.0001993622448979592,
- "loss": 2.2574,
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
"step": 5
},
{
- "epoch": 0.12,
- "learning_rate": 0.00019923469387755102,
- "loss": 2.2239,
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
"step": 6
},
{
- "epoch": 0.14,
- "learning_rate": 0.00019910714285714288,
- "loss": 2.1661,
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
"step": 7
},
{
- "epoch": 0.16,
- "learning_rate": 0.0001989795918367347,
- "loss": 2.0987,
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
"step": 8
},
{
- "epoch": 0.18,
- "learning_rate": 0.00019885204081632654,
- "loss": 2.015,
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
"step": 9
},
{
- "epoch": 0.2,
- "learning_rate": 0.00019872448979591837,
- "loss": 1.9771,
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
"step": 10
},
{
- "epoch": 0.22,
- "learning_rate": 0.00019859693877551023,
- "loss": 2.0271,
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
"step": 11
},
{
- "epoch": 0.24,
- "learning_rate": 0.00019846938775510203,
- "loss": 1.9812,
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
"step": 12
},
{
- "epoch": 0.26,
- "learning_rate": 0.0001983418367346939,
- "loss": 2.0834,
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
"step": 13
},
{
- "epoch": 0.28,
- "learning_rate": 0.00019821428571428572,
- "loss": 1.9174,
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
"step": 14
},
{
- "epoch": 0.3,
- "learning_rate": 0.00019808673469387755,
- "loss": 1.8409,
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
"step": 15
},
{
- "epoch": 0.32,
- "learning_rate": 0.00019795918367346938,
- "loss": 1.929,
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
"step": 16
},
{
- "epoch": 0.34,
- "learning_rate": 0.00019783163265306124,
- "loss": 2.0041,
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
"step": 17
},
{
- "epoch": 0.36,
- "learning_rate": 0.00019770408163265305,
- "loss": 1.9385,
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
"step": 18
},
{
- "epoch": 0.38,
- "learning_rate": 0.0001975765306122449,
- "loss": 1.9592,
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
"step": 19
},
{
- "epoch": 0.4,
- "learning_rate": 0.00019744897959183674,
- "loss": 1.9701,
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
"step": 20
},
{
- "epoch": 0.42,
- "learning_rate": 0.0001973214285714286,
- "loss": 1.9277,
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
"step": 21
},
{
- "epoch": 0.45,
- "learning_rate": 0.00019719387755102042,
- "loss": 1.8394,
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
"step": 22
},
{
- "epoch": 0.47,
- "learning_rate": 0.00019706632653061226,
- "loss": 1.8666,
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
"step": 23
},
{
- "epoch": 0.49,
- "learning_rate": 0.00019693877551020409,
- "loss": 1.8997,
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
"step": 24
},
{
- "epoch": 0.51,
- "learning_rate": 0.00019681122448979592,
- "loss": 1.9432,
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
"step": 25
},
{
- "epoch": 0.53,
- "learning_rate": 0.00019668367346938777,
- "loss": 1.9137,
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
"step": 26
},
{
- "epoch": 0.55,
- "learning_rate": 0.0001965561224489796,
- "loss": 1.905,
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
"step": 27
},
{
- "epoch": 0.57,
- "learning_rate": 0.00019642857142857144,
- "loss": 1.8708,
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
"step": 28
},
{
- "epoch": 0.59,
- "learning_rate": 0.00019630102040816327,
- "loss": 1.9097,
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
"step": 29
},
{
- "epoch": 0.61,
- "learning_rate": 0.00019617346938775513,
- "loss": 1.896,
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
"step": 30
},
{
- "epoch": 0.63,
- "learning_rate": 0.00019604591836734696,
- "loss": 1.8834,
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
"step": 31
},
{
- "epoch": 0.65,
- "learning_rate": 0.0001959183673469388,
- "loss": 1.8323,
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
"step": 32
},
{
- "epoch": 0.67,
- "learning_rate": 0.00019579081632653062,
- "loss": 1.804,
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
"step": 33
},
{
- "epoch": 0.69,
- "learning_rate": 0.00019566326530612248,
- "loss": 1.8906,
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
"step": 34
},
{
- "epoch": 0.71,
- "learning_rate": 0.00019553571428571428,
- "loss": 1.8693,
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
"step": 35
},
{
- "epoch": 0.73,
- "learning_rate": 0.00019540816326530614,
- "loss": 1.9308,
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
"step": 36
},
{
- "epoch": 0.75,
- "learning_rate": 0.00019528061224489797,
- "loss": 1.8082,
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
"step": 37
},
{
- "epoch": 0.77,
- "learning_rate": 0.0001951530612244898,
- "loss": 1.848,
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
"step": 38
},
{
- "epoch": 0.79,
- "learning_rate": 0.00019502551020408163,
- "loss": 1.8866,
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
"step": 39
},
{
- "epoch": 0.81,
- "learning_rate": 0.0001948979591836735,
- "loss": 1.7844,
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
"step": 40
},
{
- "epoch": 0.83,
- "learning_rate": 0.0001947704081632653,
- "loss": 1.8485,
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
"step": 41
},
{
- "epoch": 0.85,
- "learning_rate": 0.00019464285714285715,
- "loss": 1.7917,
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
"step": 42
},
{
- "epoch": 0.87,
- "learning_rate": 0.00019451530612244898,
- "loss": 1.7342,
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
"step": 43
},
{
- "epoch": 0.89,
- "learning_rate": 0.00019438775510204084,
- "loss": 1.8479,
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
"step": 44
},
{
- "epoch": 0.91,
- "learning_rate": 0.00019426020408163267,
- "loss": 1.8639,
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
"step": 45
},
{
- "epoch": 0.93,
- "learning_rate": 0.0001941326530612245,
- "loss": 1.8166,
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
"step": 46
},
{
- "epoch": 0.95,
- "learning_rate": 0.00019400510204081633,
- "loss": 1.7566,
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
"step": 47
},
{
- "epoch": 0.97,
- "learning_rate": 0.00019387755102040816,
- "loss": 1.8071,
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
"step": 48
},
{
- "epoch": 0.99,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.8612,
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
"step": 49
},
{
- "epoch": 1.01,
- "learning_rate": 0.00019362244897959185,
- "loss": 1.7819,
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
"step": 50
},
{
- "epoch": 1.03,
- "learning_rate": 0.00019349489795918368,
- "loss": 1.8647,
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
"step": 51
},
{
- "epoch": 1.05,
- "learning_rate": 0.0001933673469387755,
- "loss": 1.8196,
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
"step": 52
},
{
- "epoch": 1.07,
- "learning_rate": 0.00019323979591836737,
- "loss": 1.8027,
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
"step": 53
},
{
- "epoch": 1.09,
- "learning_rate": 0.00019311224489795917,
- "loss": 1.8927,
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
"step": 54
},
{
- "epoch": 1.11,
- "learning_rate": 0.00019298469387755103,
- "loss": 1.8481,
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
"step": 55
},
{
- "epoch": 1.13,
- "learning_rate": 0.00019285714285714286,
- "loss": 1.7781,
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
"step": 56
},
{
- "epoch": 1.15,
- "learning_rate": 0.00019272959183673472,
- "loss": 1.8101,
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
"step": 57
},
{
- "epoch": 1.17,
- "learning_rate": 0.00019260204081632653,
- "loss": 1.7257,
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
"step": 58
},
{
- "epoch": 1.19,
- "learning_rate": 0.00019247448979591838,
- "loss": 1.8185,
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
"step": 59
},
{
- "epoch": 1.21,
- "learning_rate": 0.00019234693877551021,
- "loss": 1.8557,
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
"step": 60
},
{
- "epoch": 1.23,
- "learning_rate": 0.00019221938775510204,
- "loss": 1.7418,
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
"step": 61
},
{
- "epoch": 1.25,
- "learning_rate": 0.00019209183673469388,
- "loss": 1.6879,
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
"step": 62
},
{
- "epoch": 1.27,
- "learning_rate": 0.00019196428571428573,
- "loss": 1.7651,
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
"step": 63
},
{
- "epoch": 1.29,
- "learning_rate": 0.00019183673469387756,
- "loss": 1.7759,
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
"step": 64
},
{
- "epoch": 1.32,
- "learning_rate": 0.0001917091836734694,
- "loss": 1.7691,
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
"step": 65
},
{
- "epoch": 1.34,
- "learning_rate": 0.00019158163265306123,
- "loss": 1.7794,
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
"step": 66
},
{
- "epoch": 1.36,
- "learning_rate": 0.00019145408163265306,
- "loss": 1.8152,
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
"step": 67
},
{
- "epoch": 1.38,
- "learning_rate": 0.00019132653061224492,
- "loss": 1.8052,
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
"step": 68
},
{
- "epoch": 1.4,
- "learning_rate": 0.00019119897959183675,
- "loss": 1.8054,
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
"step": 69
},
{
- "epoch": 1.42,
- "learning_rate": 0.00019107142857142858,
- "loss": 1.8114,
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
"step": 70
},
{
- "epoch": 1.44,
- "learning_rate": 0.0001909438775510204,
- "loss": 1.7749,
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
"step": 71
},
{
- "epoch": 1.46,
- "learning_rate": 0.00019081632653061227,
- "loss": 1.777,
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
"step": 72
},
{
- "epoch": 1.48,
- "learning_rate": 0.0001906887755102041,
- "loss": 1.7896,
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
"step": 73
},
{
- "epoch": 1.5,
- "learning_rate": 0.00019056122448979593,
- "loss": 1.8335,
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
"step": 74
},
{
- "epoch": 1.52,
- "learning_rate": 0.00019043367346938776,
- "loss": 1.8155,
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
"step": 75
},
{
- "epoch": 1.54,
- "learning_rate": 0.00019030612244897962,
- "loss": 1.8224,
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
"step": 76
},
{
- "epoch": 1.56,
- "learning_rate": 0.00019017857142857142,
- "loss": 1.7889,
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
"step": 77
},
{
- "epoch": 1.58,
- "learning_rate": 0.00019005102040816328,
- "loss": 1.8866,
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
"step": 78
},
{
- "epoch": 1.6,
- "learning_rate": 0.0001899234693877551,
- "loss": 1.8439,
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
"step": 79
},
{
- "epoch": 1.62,
- "learning_rate": 0.00018979591836734697,
- "loss": 1.7906,
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
"step": 80
},
{
- "epoch": 1.64,
- "learning_rate": 0.00018966836734693877,
- "loss": 1.8627,
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
"step": 81
},
{
- "epoch": 1.66,
- "learning_rate": 0.00018954081632653063,
- "loss": 1.7497,
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
"step": 82
},
{
- "epoch": 1.68,
- "learning_rate": 0.00018941326530612246,
- "loss": 1.7936,
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
"step": 83
},
{
- "epoch": 1.7,
- "learning_rate": 0.0001892857142857143,
- "loss": 1.8341,
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
"step": 84
},
{
- "epoch": 1.72,
- "learning_rate": 0.00018915816326530612,
- "loss": 1.7868,
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
"step": 85
},
{
- "epoch": 1.74,
- "learning_rate": 0.00018903061224489798,
- "loss": 1.7493,
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
"step": 86
},
{
- "epoch": 1.76,
- "learning_rate": 0.0001889030612244898,
- "loss": 1.7926,
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
"step": 87
},
{
- "epoch": 1.78,
- "learning_rate": 0.00018877551020408164,
- "loss": 1.8278,
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
"step": 88
},
{
- "epoch": 1.8,
- "learning_rate": 0.00018864795918367347,
- "loss": 1.7387,
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
"step": 89
},
{
- "epoch": 1.82,
- "learning_rate": 0.0001885204081632653,
- "loss": 1.7669,
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
"step": 90
},
{
- "epoch": 1.84,
- "learning_rate": 0.00018839285714285716,
- "loss": 1.7686,
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
"step": 91
},
{
- "epoch": 1.86,
- "learning_rate": 0.000188265306122449,
- "loss": 1.7759,
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
"step": 92
},
{
- "epoch": 1.88,
- "learning_rate": 0.00018813775510204082,
- "loss": 1.7016,
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
"step": 93
},
{
- "epoch": 1.9,
- "learning_rate": 0.00018801020408163265,
- "loss": 1.8123,
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
"step": 94
},
{
- "epoch": 1.92,
- "learning_rate": 0.0001878826530612245,
- "loss": 1.8315,
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
"step": 95
},
{
- "epoch": 1.94,
- "learning_rate": 0.00018775510204081634,
- "loss": 1.7679,
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
"step": 96
},
{
- "epoch": 1.96,
- "learning_rate": 0.00018762755102040817,
- "loss": 1.7874,
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
"step": 97
},
{
- "epoch": 1.98,
- "learning_rate": 0.0001875,
- "loss": 1.8008,
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
"step": 98
},
{
- "epoch": 2.0,
- "learning_rate": 0.00018737244897959186,
- "loss": 1.7177,
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
"step": 99
},
{
- "epoch": 2.02,
- "learning_rate": 0.00018724489795918367,
- "loss": 1.7272,
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
"step": 100
},
{
- "epoch": 2.04,
- "learning_rate": 0.00018711734693877552,
- "loss": 1.7848,
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
"step": 101
},
{
- "epoch": 2.06,
- "learning_rate": 0.00018698979591836735,
- "loss": 1.744,
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
"step": 102
},
{
- "epoch": 2.08,
- "learning_rate": 0.00018686224489795919,
- "loss": 1.7005,
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
"step": 103
},
{
- "epoch": 2.1,
- "learning_rate": 0.00018673469387755102,
- "loss": 1.8247,
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
"step": 104
},
{
- "epoch": 2.12,
- "learning_rate": 0.00018660714285714287,
- "loss": 1.6855,
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
"step": 105
},
{
- "epoch": 2.14,
- "learning_rate": 0.0001864795918367347,
- "loss": 1.7627,
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
"step": 106
},
{
- "epoch": 2.17,
- "learning_rate": 0.00018635204081632654,
- "loss": 1.7564,
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
"step": 107
},
{
- "epoch": 2.19,
- "learning_rate": 0.00018622448979591837,
- "loss": 1.8237,
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
"step": 108
},
{
- "epoch": 2.21,
- "learning_rate": 0.00018609693877551022,
- "loss": 1.7421,
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
"step": 109
},
{
- "epoch": 2.23,
- "learning_rate": 0.00018596938775510206,
- "loss": 1.7517,
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
"step": 110
},
{
- "epoch": 2.25,
- "learning_rate": 0.0001858418367346939,
- "loss": 1.7515,
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
"step": 111
},
{
- "epoch": 2.27,
- "learning_rate": 0.00018571428571428572,
- "loss": 1.7842,
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
"step": 112
},
{
- "epoch": 2.29,
- "learning_rate": 0.00018558673469387755,
- "loss": 1.8001,
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
"step": 113
},
{
- "epoch": 2.31,
- "learning_rate": 0.0001854591836734694,
- "loss": 1.7653,
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
"step": 114
},
{
- "epoch": 2.33,
- "learning_rate": 0.00018533163265306124,
- "loss": 1.694,
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
"step": 115
},
{
- "epoch": 2.35,
- "learning_rate": 0.00018520408163265307,
- "loss": 1.7457,
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
"step": 116
},
{
- "epoch": 2.37,
- "learning_rate": 0.0001850765306122449,
- "loss": 1.7899,
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
"step": 117
},
{
- "epoch": 2.39,
- "learning_rate": 0.00018494897959183676,
- "loss": 1.7473,
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
"step": 118
},
{
- "epoch": 2.41,
- "learning_rate": 0.0001848214285714286,
- "loss": 1.6639,
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
"step": 119
},
{
- "epoch": 2.43,
- "learning_rate": 0.00018469387755102042,
- "loss": 1.762,
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
"step": 120
},
{
- "epoch": 2.45,
- "learning_rate": 0.00018456632653061225,
- "loss": 1.7378,
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
"step": 121
},
{
- "epoch": 2.47,
- "learning_rate": 0.0001844387755102041,
- "loss": 1.672,
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
"step": 122
},
{
- "epoch": 2.49,
- "learning_rate": 0.0001843112244897959,
- "loss": 1.7267,
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
"step": 123
},
{
- "epoch": 2.51,
- "learning_rate": 0.00018418367346938777,
- "loss": 1.7825,
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
"step": 124
},
{
- "epoch": 2.53,
- "learning_rate": 0.0001840561224489796,
- "loss": 1.7566,
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
"step": 125
},
{
- "epoch": 2.55,
- "learning_rate": 0.00018392857142857143,
- "loss": 1.8169,
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
"step": 126
},
{
- "epoch": 2.57,
- "learning_rate": 0.00018380102040816326,
- "loss": 1.6801,
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
"step": 127
},
{
- "epoch": 2.59,
- "learning_rate": 0.00018367346938775512,
- "loss": 1.7292,
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
"step": 128
},
{
- "epoch": 2.61,
- "learning_rate": 0.00018354591836734695,
- "loss": 1.737,
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
"step": 129
},
{
- "epoch": 2.63,
- "learning_rate": 0.00018341836734693878,
- "loss": 1.7696,
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
"step": 130
},
{
- "epoch": 2.65,
- "learning_rate": 0.0001832908163265306,
- "loss": 1.7239,
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
"step": 131
},
{
- "epoch": 2.67,
- "learning_rate": 0.00018316326530612247,
- "loss": 1.7441,
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
"step": 132
},
{
- "epoch": 2.69,
- "learning_rate": 0.0001830357142857143,
- "loss": 1.7825,
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
"step": 133
},
{
- "epoch": 2.71,
- "learning_rate": 0.00018290816326530613,
- "loss": 1.7411,
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
"step": 134
},
{
- "epoch": 2.73,
- "learning_rate": 0.00018278061224489796,
- "loss": 1.7119,
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
"step": 135
},
{
- "epoch": 2.75,
- "learning_rate": 0.0001826530612244898,
- "loss": 1.7443,
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
"step": 136
},
{
- "epoch": 2.77,
- "learning_rate": 0.00018252551020408165,
- "loss": 1.7197,
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
"step": 137
},
{
- "epoch": 2.79,
- "learning_rate": 0.00018239795918367348,
- "loss": 1.7273,
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
"step": 138
},
{
- "epoch": 2.81,
- "learning_rate": 0.0001822704081632653,
- "loss": 1.7681,
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
"step": 139
},
{
- "epoch": 2.83,
- "learning_rate": 0.00018214285714285714,
- "loss": 1.8088,
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
"step": 140
},
{
- "epoch": 2.85,
- "learning_rate": 0.000182015306122449,
- "loss": 1.7301,
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
"step": 141
},
{
- "epoch": 2.87,
- "learning_rate": 0.00018188775510204083,
- "loss": 1.6853,
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
"step": 142
},
{
- "epoch": 2.89,
- "learning_rate": 0.00018176020408163266,
- "loss": 1.6966,
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
"step": 143
},
{
- "epoch": 2.91,
- "learning_rate": 0.0001816326530612245,
- "loss": 1.7938,
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
"step": 144
},
{
- "epoch": 2.93,
- "learning_rate": 0.00018150510204081635,
- "loss": 1.7639,
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
"step": 145
},
{
- "epoch": 2.95,
- "learning_rate": 0.00018137755102040816,
- "loss": 1.7527,
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
"step": 146
},
{
- "epoch": 2.97,
- "learning_rate": 0.00018125000000000001,
- "loss": 1.7386,
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
"step": 147
},
{
- "epoch": 2.99,
- "learning_rate": 0.00018112244897959185,
- "loss": 1.7223,
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
"step": 148
},
{
- "epoch": 3.01,
- "learning_rate": 0.00018099489795918368,
- "loss": 1.7571,
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
"step": 149
},
{
- "epoch": 3.04,
- "learning_rate": 0.0001808673469387755,
- "loss": 1.7054,
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
"step": 150
},
{
- "epoch": 3.06,
- "learning_rate": 0.00018073979591836737,
- "loss": 1.6581,
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
"step": 151
},
{
- "epoch": 3.08,
- "learning_rate": 0.00018061224489795917,
- "loss": 1.681,
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
"step": 152
},
{
- "epoch": 3.1,
- "learning_rate": 0.00018048469387755103,
- "loss": 1.7425,
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
"step": 153
},
{
- "epoch": 3.12,
- "learning_rate": 0.00018035714285714286,
- "loss": 1.7108,
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
"step": 154
},
{
- "epoch": 3.14,
- "learning_rate": 0.00018022959183673472,
- "loss": 1.7194,
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
"step": 155
},
{
- "epoch": 3.16,
- "learning_rate": 0.00018010204081632655,
- "loss": 1.6953,
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
"step": 156
},
{
- "epoch": 3.18,
- "learning_rate": 0.00017997448979591838,
- "loss": 1.669,
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
"step": 157
},
{
- "epoch": 3.2,
- "learning_rate": 0.0001798469387755102,
- "loss": 1.744,
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
"step": 158
},
{
- "epoch": 3.22,
- "learning_rate": 0.00017971938775510204,
- "loss": 1.6467,
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
"step": 159
},
{
- "epoch": 3.24,
- "learning_rate": 0.0001795918367346939,
- "loss": 1.7103,
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
"step": 160
},
{
- "epoch": 3.26,
- "learning_rate": 0.00017946428571428573,
- "loss": 1.6662,
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
"step": 161
},
{
- "epoch": 3.28,
- "learning_rate": 0.00017933673469387756,
- "loss": 1.6657,
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
"step": 162
},
{
- "epoch": 3.3,
- "learning_rate": 0.0001792091836734694,
- "loss": 1.791,
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
"step": 163
},
{
- "epoch": 3.32,
- "learning_rate": 0.00017908163265306125,
- "loss": 1.7704,
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
"step": 164
},
{
- "epoch": 3.34,
- "learning_rate": 0.00017895408163265305,
- "loss": 1.7229,
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
"step": 165
},
{
- "epoch": 3.36,
- "learning_rate": 0.0001788265306122449,
- "loss": 1.76,
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
"step": 166
},
{
- "epoch": 3.38,
- "learning_rate": 0.00017869897959183674,
- "loss": 1.6482,
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
"step": 167
},
{
- "epoch": 3.4,
- "learning_rate": 0.0001785714285714286,
- "loss": 1.8076,
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
"step": 168
},
{
- "epoch": 3.42,
- "learning_rate": 0.0001784438775510204,
- "loss": 1.7368,
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
"step": 169
},
{
- "epoch": 3.44,
- "learning_rate": 0.00017831632653061226,
- "loss": 1.6264,
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
"step": 170
},
{
- "epoch": 3.46,
- "learning_rate": 0.0001781887755102041,
- "loss": 1.6289,
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
"step": 171
},
{
- "epoch": 3.48,
- "learning_rate": 0.00017806122448979592,
- "loss": 1.7913,
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
"step": 172
},
{
- "epoch": 3.5,
- "learning_rate": 0.00017793367346938775,
- "loss": 1.6985,
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
"step": 173
},
{
- "epoch": 3.52,
- "learning_rate": 0.0001778061224489796,
- "loss": 1.6936,
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
"step": 174
},
{
- "epoch": 3.54,
- "learning_rate": 0.00017767857142857141,
- "loss": 1.8068,
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
"step": 175
},
{
- "epoch": 3.56,
- "learning_rate": 0.00017755102040816327,
- "loss": 1.7243,
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
"step": 176
},
{
- "epoch": 3.58,
- "learning_rate": 0.0001774234693877551,
- "loss": 1.6893,
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
"step": 177
},
{
- "epoch": 3.6,
- "learning_rate": 0.00017729591836734696,
- "loss": 1.8122,
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
"step": 178
},
{
- "epoch": 3.62,
- "learning_rate": 0.0001771683673469388,
- "loss": 1.6562,
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
"step": 179
},
{
- "epoch": 3.64,
- "learning_rate": 0.00017704081632653062,
- "loss": 1.6999,
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
"step": 180
},
{
- "epoch": 3.66,
- "learning_rate": 0.00017691326530612245,
- "loss": 1.7229,
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
"step": 181
},
{
- "epoch": 3.68,
- "learning_rate": 0.00017678571428571428,
- "loss": 1.6764,
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
"step": 182
},
{
- "epoch": 3.7,
- "learning_rate": 0.00017665816326530614,
- "loss": 1.6982,
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
"step": 183
},
{
- "epoch": 3.72,
- "learning_rate": 0.00017653061224489797,
- "loss": 1.696,
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
"step": 184
},
{
- "epoch": 3.74,
- "learning_rate": 0.0001764030612244898,
- "loss": 1.6797,
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
"step": 185
},
{
- "epoch": 3.76,
- "learning_rate": 0.00017627551020408164,
- "loss": 1.637,
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
"step": 186
},
{
- "epoch": 3.78,
- "learning_rate": 0.0001761479591836735,
- "loss": 1.7074,
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
"step": 187
},
{
- "epoch": 3.8,
- "learning_rate": 0.0001760204081632653,
- "loss": 1.705,
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
"step": 188
},
{
- "epoch": 3.82,
- "learning_rate": 0.00017589285714285716,
- "loss": 1.6153,
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
"step": 189
},
{
- "epoch": 3.84,
- "learning_rate": 0.00017576530612244899,
- "loss": 1.7354,
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
"step": 190
},
{
- "epoch": 3.86,
- "learning_rate": 0.00017563775510204084,
- "loss": 1.6941,
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
"step": 191
},
{
- "epoch": 3.88,
- "learning_rate": 0.00017551020408163265,
- "loss": 1.7231,
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
"step": 192
},
{
- "epoch": 3.91,
- "learning_rate": 0.0001753826530612245,
- "loss": 1.7663,
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
"step": 193
},
{
- "epoch": 3.93,
- "learning_rate": 0.00017525510204081634,
- "loss": 1.6532,
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
"step": 194
},
{
- "epoch": 3.95,
- "learning_rate": 0.00017512755102040817,
- "loss": 1.7115,
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
"step": 195
},
{
- "epoch": 3.97,
- "learning_rate": 0.000175,
- "loss": 1.6955,
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
"step": 196
},
{
- "epoch": 3.99,
- "learning_rate": 0.00017487244897959186,
- "loss": 1.6863,
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
"step": 197
},
{
- "epoch": 4.01,
- "learning_rate": 0.00017474489795918366,
- "loss": 1.7012,
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
"step": 198
},
{
- "epoch": 4.03,
- "learning_rate": 0.00017461734693877552,
- "loss": 1.5927,
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
"step": 199
},
{
- "epoch": 4.05,
- "learning_rate": 0.00017448979591836735,
- "loss": 1.6272,
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
"step": 200
},
{
- "epoch": 4.07,
- "learning_rate": 0.00017436224489795918,
- "loss": 1.5994,
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
"step": 201
},
{
- "epoch": 4.09,
- "learning_rate": 0.00017423469387755104,
- "loss": 1.7141,
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
"step": 202
},
{
- "epoch": 4.11,
- "learning_rate": 0.00017410714285714287,
- "loss": 1.7547,
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
"step": 203
},
{
- "epoch": 4.13,
- "learning_rate": 0.0001739795918367347,
- "loss": 1.6254,
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
"step": 204
},
{
- "epoch": 4.15,
- "learning_rate": 0.00017385204081632653,
- "loss": 1.6686,
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
"step": 205
},
{
- "epoch": 4.17,
- "learning_rate": 0.0001737244897959184,
- "loss": 1.6684,
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
"step": 206
},
{
- "epoch": 4.19,
- "learning_rate": 0.00017359693877551022,
- "loss": 1.6724,
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
"step": 207
},
{
- "epoch": 4.21,
- "learning_rate": 0.00017346938775510205,
- "loss": 1.7361,
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
"step": 208
},
{
- "epoch": 4.23,
- "learning_rate": 0.00017334183673469388,
- "loss": 1.7167,
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
"step": 209
},
{
- "epoch": 4.25,
- "learning_rate": 0.00017321428571428574,
- "loss": 1.7226,
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
"step": 210
},
{
- "epoch": 4.27,
- "learning_rate": 0.00017308673469387754,
- "loss": 1.7133,
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
"step": 211
},
{
- "epoch": 4.29,
- "learning_rate": 0.0001729591836734694,
- "loss": 1.649,
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
"step": 212
},
{
- "epoch": 4.31,
- "learning_rate": 0.00017283163265306123,
- "loss": 1.7104,
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
"step": 213
},
{
- "epoch": 4.33,
- "learning_rate": 0.00017270408163265306,
- "loss": 1.6861,
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
"step": 214
},
{
- "epoch": 4.35,
- "learning_rate": 0.0001725765306122449,
- "loss": 1.648,
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
"step": 215
},
{
- "epoch": 4.37,
- "learning_rate": 0.00017244897959183675,
- "loss": 1.6215,
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
"step": 216
},
{
- "epoch": 4.39,
- "learning_rate": 0.00017232142857142858,
- "loss": 1.6334,
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
"step": 217
},
{
- "epoch": 4.41,
- "learning_rate": 0.0001721938775510204,
- "loss": 1.6283,
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
"step": 218
},
{
- "epoch": 4.43,
- "learning_rate": 0.00017206632653061224,
- "loss": 1.6462,
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
"step": 219
},
{
- "epoch": 4.45,
- "learning_rate": 0.0001719387755102041,
- "loss": 1.7233,
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
"step": 220
},
{
- "epoch": 4.47,
- "learning_rate": 0.0001718112244897959,
- "loss": 1.7839,
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
"step": 221
},
{
- "epoch": 4.49,
- "learning_rate": 0.00017168367346938776,
- "loss": 1.7204,
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
"step": 222
},
{
- "epoch": 4.51,
- "learning_rate": 0.0001715561224489796,
- "loss": 1.7671,
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
"step": 223
},
{
- "epoch": 4.53,
- "learning_rate": 0.00017142857142857143,
- "loss": 1.6824,
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
"step": 224
},
{
- "epoch": 4.55,
- "learning_rate": 0.00017130102040816328,
- "loss": 1.7068,
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
"step": 225
},
{
- "epoch": 4.57,
- "learning_rate": 0.00017117346938775511,
- "loss": 1.6515,
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
"step": 226
},
{
- "epoch": 4.59,
- "learning_rate": 0.00017104591836734694,
- "loss": 1.6586,
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
"step": 227
},
{
- "epoch": 4.61,
- "learning_rate": 0.00017091836734693878,
- "loss": 1.6355,
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
"step": 228
},
{
- "epoch": 4.63,
- "learning_rate": 0.00017079081632653063,
- "loss": 1.7173,
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
"step": 229
},
{
- "epoch": 4.65,
- "learning_rate": 0.00017066326530612246,
- "loss": 1.6585,
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
"step": 230
},
{
- "epoch": 4.67,
- "learning_rate": 0.0001705357142857143,
- "loss": 1.5856,
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
"step": 231
},
{
- "epoch": 4.69,
- "learning_rate": 0.00017040816326530613,
- "loss": 1.5923,
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
"step": 232
},
{
- "epoch": 4.71,
- "learning_rate": 0.00017028061224489798,
- "loss": 1.7128,
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
"step": 233
},
{
- "epoch": 4.73,
- "learning_rate": 0.0001701530612244898,
- "loss": 1.6971,
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
"step": 234
},
{
- "epoch": 4.75,
- "learning_rate": 0.00017002551020408165,
- "loss": 1.6416,
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
"step": 235
},
{
- "epoch": 4.78,
- "learning_rate": 0.00016989795918367348,
- "loss": 1.645,
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
"step": 236
},
{
- "epoch": 4.8,
- "learning_rate": 0.0001697704081632653,
- "loss": 1.6792,
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
"step": 237
},
{
- "epoch": 4.82,
- "learning_rate": 0.00016964285714285714,
- "loss": 1.6522,
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
"step": 238
},
{
- "epoch": 4.84,
- "learning_rate": 0.000169515306122449,
- "loss": 1.6315,
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
"step": 239
},
{
- "epoch": 4.86,
- "learning_rate": 0.00016938775510204083,
- "loss": 1.6622,
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
"step": 240
},
{
- "epoch": 4.88,
- "learning_rate": 0.00016926020408163266,
- "loss": 1.6566,
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
"step": 241
},
{
- "epoch": 4.9,
- "learning_rate": 0.0001691326530612245,
- "loss": 1.7141,
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
"step": 242
},
{
- "epoch": 4.92,
- "learning_rate": 0.00016900510204081635,
- "loss": 1.5873,
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
"step": 243
},
{
- "epoch": 4.94,
- "learning_rate": 0.00016887755102040818,
- "loss": 1.6571,
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
"step": 244
},
{
- "epoch": 4.96,
- "learning_rate": 0.00016875,
- "loss": 1.6829,
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
"step": 245
},
{
- "epoch": 4.98,
- "learning_rate": 0.00016862244897959184,
- "loss": 1.6935,
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
"step": 246
},
{
- "epoch": 5.0,
- "learning_rate": 0.00016849489795918367,
- "loss": 1.6782,
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
"step": 247
},
{
- "epoch": 5.02,
- "learning_rate": 0.00016836734693877553,
- "loss": 1.622,
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
"step": 248
},
{
- "epoch": 5.04,
- "learning_rate": 0.00016823979591836736,
- "loss": 1.6596,
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
"step": 249
},
{
- "epoch": 5.06,
- "learning_rate": 0.0001681122448979592,
- "loss": 1.5821,
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
"step": 250
},
{
- "epoch": 5.08,
- "learning_rate": 0.00016798469387755102,
- "loss": 1.7292,
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
"step": 251
},
{
- "epoch": 5.1,
- "learning_rate": 0.00016785714285714288,
- "loss": 1.646,
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
"step": 252
},
{
- "epoch": 5.12,
- "learning_rate": 0.0001677295918367347,
- "loss": 1.6969,
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
"step": 253
},
{
- "epoch": 5.14,
- "learning_rate": 0.00016760204081632654,
- "loss": 1.6082,
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
"step": 254
},
{
- "epoch": 5.16,
- "learning_rate": 0.00016747448979591837,
- "loss": 1.5843,
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
"step": 255
},
{
- "epoch": 5.18,
- "learning_rate": 0.00016734693877551023,
- "loss": 1.6827,
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
"step": 256
},
{
- "epoch": 5.2,
- "learning_rate": 0.00016721938775510203,
- "loss": 1.5824,
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
"step": 257
},
{
- "epoch": 5.22,
- "learning_rate": 0.0001670918367346939,
- "loss": 1.6795,
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
"step": 258
},
{
- "epoch": 5.24,
- "learning_rate": 0.00016696428571428572,
- "loss": 1.5639,
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
"step": 259
},
{
- "epoch": 5.26,
- "learning_rate": 0.00016683673469387755,
- "loss": 1.592,
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
"step": 260
},
{
- "epoch": 5.28,
- "learning_rate": 0.00016670918367346938,
- "loss": 1.65,
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
"step": 261
},
{
- "epoch": 5.3,
- "learning_rate": 0.00016658163265306124,
- "loss": 1.5592,
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
"step": 262
},
{
- "epoch": 5.32,
- "learning_rate": 0.00016645408163265305,
- "loss": 1.5091,
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
"step": 263
},
{
- "epoch": 5.34,
- "learning_rate": 0.0001663265306122449,
- "loss": 1.6138,
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
"step": 264
},
{
- "epoch": 5.36,
- "learning_rate": 0.00016619897959183673,
- "loss": 1.625,
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
"step": 265
},
{
- "epoch": 5.38,
- "learning_rate": 0.0001660714285714286,
- "loss": 1.5757,
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
"step": 266
},
{
- "epoch": 5.4,
- "learning_rate": 0.00016594387755102042,
- "loss": 1.6372,
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
"step": 267
},
{
- "epoch": 5.42,
- "learning_rate": 0.00016581632653061225,
- "loss": 1.5891,
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
"step": 268
},
{
- "epoch": 5.44,
- "learning_rate": 0.00016568877551020409,
- "loss": 1.6893,
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
"step": 269
},
{
- "epoch": 5.46,
- "learning_rate": 0.00016556122448979592,
- "loss": 1.6662,
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
"step": 270
},
{
- "epoch": 5.48,
- "learning_rate": 0.00016543367346938777,
- "loss": 1.7132,
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
"step": 271
},
{
- "epoch": 5.5,
- "learning_rate": 0.0001653061224489796,
- "loss": 1.5835,
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
"step": 272
},
{
- "epoch": 5.52,
- "learning_rate": 0.00016517857142857144,
- "loss": 1.6342,
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
"step": 273
},
{
- "epoch": 5.54,
- "learning_rate": 0.00016505102040816327,
- "loss": 1.6717,
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
"step": 274
},
{
- "epoch": 5.56,
- "learning_rate": 0.00016492346938775512,
- "loss": 1.6248,
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
"step": 275
},
{
- "epoch": 5.58,
- "learning_rate": 0.00016479591836734696,
- "loss": 1.6117,
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
"step": 276
},
{
- "epoch": 5.6,
- "learning_rate": 0.0001646683673469388,
- "loss": 1.6798,
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
"step": 277
},
{
- "epoch": 5.63,
- "learning_rate": 0.00016454081632653062,
- "loss": 1.6406,
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
"step": 278
},
{
- "epoch": 5.65,
- "learning_rate": 0.00016441326530612248,
- "loss": 1.6512,
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
"step": 279
},
{
- "epoch": 5.67,
- "learning_rate": 0.00016428571428571428,
- "loss": 1.6102,
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
"step": 280
},
{
- "epoch": 5.69,
- "learning_rate": 0.00016415816326530614,
- "loss": 1.6113,
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
"step": 281
},
{
- "epoch": 5.71,
- "learning_rate": 0.00016403061224489797,
- "loss": 1.7116,
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
"step": 282
},
{
- "epoch": 5.73,
- "learning_rate": 0.0001639030612244898,
- "loss": 1.6846,
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
"step": 283
},
{
- "epoch": 5.75,
- "learning_rate": 0.00016377551020408163,
- "loss": 1.6911,
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
"step": 284
},
{
- "epoch": 5.77,
- "learning_rate": 0.0001636479591836735,
- "loss": 1.6202,
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
"step": 285
},
{
- "epoch": 5.79,
- "learning_rate": 0.0001635204081632653,
- "loss": 1.5715,
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
"step": 286
},
{
- "epoch": 5.81,
- "learning_rate": 0.00016339285714285715,
- "loss": 1.6461,
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
"step": 287
},
{
- "epoch": 5.83,
- "learning_rate": 0.00016326530612244898,
- "loss": 1.6624,
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
"step": 288
},
{
- "epoch": 5.85,
- "learning_rate": 0.00016313775510204084,
- "loss": 1.6535,
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
"step": 289
},
{
- "epoch": 5.87,
- "learning_rate": 0.00016301020408163267,
- "loss": 1.6275,
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
"step": 290
},
{
- "epoch": 5.89,
- "learning_rate": 0.0001628826530612245,
- "loss": 1.6636,
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
"step": 291
},
{
- "epoch": 5.91,
- "learning_rate": 0.00016275510204081633,
- "loss": 1.6546,
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
"step": 292
},
{
- "epoch": 5.93,
- "learning_rate": 0.00016262755102040816,
- "loss": 1.7274,
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
"step": 293
},
{
- "epoch": 5.95,
- "learning_rate": 0.00016250000000000002,
- "loss": 1.5901,
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
"step": 294
},
{
- "epoch": 5.97,
- "learning_rate": 0.00016237244897959185,
- "loss": 1.6046,
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
"step": 295
},
{
- "epoch": 5.99,
- "learning_rate": 0.00016224489795918368,
- "loss": 1.5828,
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
"step": 296
},
{
- "epoch": 6.01,
- "learning_rate": 0.0001621173469387755,
- "loss": 1.6435,
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
"step": 297
},
{
- "epoch": 6.03,
- "learning_rate": 0.00016198979591836737,
- "loss": 1.6263,
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
"step": 298
},
{
- "epoch": 6.05,
- "learning_rate": 0.00016186224489795917,
- "loss": 1.4944,
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
"step": 299
},
{
- "epoch": 6.07,
- "learning_rate": 0.00016173469387755103,
- "loss": 1.6286,
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
"step": 300
},
{
- "epoch": 6.09,
- "learning_rate": 0.00016160714285714286,
- "loss": 1.694,
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
"step": 301
},
{
- "epoch": 6.11,
- "learning_rate": 0.00016147959183673472,
- "loss": 1.6197,
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
"step": 302
},
{
- "epoch": 6.13,
- "learning_rate": 0.00016135204081632652,
- "loss": 1.5597,
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
"step": 303
},
{
- "epoch": 6.15,
- "learning_rate": 0.00016122448979591838,
- "loss": 1.5487,
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
"step": 304
},
{
- "epoch": 6.17,
- "learning_rate": 0.0001610969387755102,
- "loss": 1.5769,
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
"step": 305
},
{
- "epoch": 6.19,
- "learning_rate": 0.00016096938775510204,
- "loss": 1.6367,
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
"step": 306
},
{
- "epoch": 6.21,
- "learning_rate": 0.00016084183673469388,
- "loss": 1.583,
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
"step": 307
},
{
- "epoch": 6.23,
- "learning_rate": 0.00016071428571428573,
- "loss": 1.6201,
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
"step": 308
},
{
- "epoch": 6.25,
- "learning_rate": 0.00016058673469387754,
- "loss": 1.6586,
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
"step": 309
},
{
- "epoch": 6.27,
- "learning_rate": 0.0001604591836734694,
- "loss": 1.6711,
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
"step": 310
},
{
- "epoch": 6.29,
- "learning_rate": 0.00016033163265306123,
- "loss": 1.6402,
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
"step": 311
},
{
- "epoch": 6.31,
- "learning_rate": 0.00016020408163265306,
- "loss": 1.5247,
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
"step": 312
},
{
- "epoch": 6.33,
- "learning_rate": 0.00016007653061224491,
- "loss": 1.5356,
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
"step": 313
},
{
- "epoch": 6.35,
- "learning_rate": 0.00015994897959183675,
- "loss": 1.564,
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
"step": 314
},
{
- "epoch": 6.37,
- "learning_rate": 0.00015982142857142858,
- "loss": 1.563,
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
"step": 315
},
{
- "epoch": 6.39,
- "learning_rate": 0.0001596938775510204,
- "loss": 1.5198,
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
"step": 316
},
{
- "epoch": 6.41,
- "learning_rate": 0.00015956632653061227,
- "loss": 1.6558,
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
"step": 317
},
{
- "epoch": 6.43,
- "learning_rate": 0.0001594387755102041,
- "loss": 1.5534,
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
"step": 318
},
{
- "epoch": 6.45,
- "learning_rate": 0.00015931122448979593,
- "loss": 1.6239,
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
"step": 319
},
{
- "epoch": 6.47,
- "learning_rate": 0.00015918367346938776,
- "loss": 1.5645,
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
"step": 320
},
{
- "epoch": 6.5,
- "learning_rate": 0.00015905612244897962,
- "loss": 1.5713,
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
"step": 321
},
{
- "epoch": 6.52,
- "learning_rate": 0.00015892857142857142,
- "loss": 1.6176,
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
"step": 322
},
{
- "epoch": 6.54,
- "learning_rate": 0.00015880102040816328,
- "loss": 1.502,
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
"step": 323
},
{
- "epoch": 6.56,
- "learning_rate": 0.0001586734693877551,
- "loss": 1.645,
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
"step": 324
},
{
- "epoch": 6.58,
- "learning_rate": 0.00015854591836734697,
- "loss": 1.5904,
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
"step": 325
},
{
- "epoch": 6.6,
- "learning_rate": 0.00015841836734693877,
- "loss": 1.6149,
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
"step": 326
},
{
- "epoch": 6.62,
- "learning_rate": 0.00015829081632653063,
- "loss": 1.6757,
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
"step": 327
},
{
- "epoch": 6.64,
- "learning_rate": 0.00015816326530612246,
- "loss": 1.541,
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
"step": 328
},
{
- "epoch": 6.66,
- "learning_rate": 0.0001580357142857143,
- "loss": 1.5898,
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
"step": 329
},
{
- "epoch": 6.68,
- "learning_rate": 0.00015790816326530612,
- "loss": 1.5441,
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
"step": 330
},
{
- "epoch": 6.7,
- "learning_rate": 0.00015778061224489798,
- "loss": 1.61,
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
"step": 331
},
{
- "epoch": 6.72,
- "learning_rate": 0.00015765306122448978,
- "loss": 1.615,
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
"step": 332
},
{
- "epoch": 6.74,
- "learning_rate": 0.00015752551020408164,
- "loss": 1.6575,
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
"step": 333
},
{
- "epoch": 6.76,
- "learning_rate": 0.00015739795918367347,
- "loss": 1.6702,
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
"step": 334
},
{
- "epoch": 6.78,
- "learning_rate": 0.0001572704081632653,
- "loss": 1.6009,
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
"step": 335
},
{
- "epoch": 6.8,
- "learning_rate": 0.00015714285714285716,
- "loss": 1.5568,
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
"step": 336
},
{
- "epoch": 6.82,
- "learning_rate": 0.000157015306122449,
- "loss": 1.619,
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
"step": 337
},
{
- "epoch": 6.84,
- "learning_rate": 0.00015688775510204082,
- "loss": 1.5563,
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
"step": 338
},
{
- "epoch": 6.86,
- "learning_rate": 0.00015676020408163265,
- "loss": 1.6328,
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
"step": 339
},
{
- "epoch": 6.88,
- "learning_rate": 0.0001566326530612245,
- "loss": 1.5726,
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
"step": 340
},
{
- "epoch": 6.9,
- "learning_rate": 0.00015650510204081634,
- "loss": 1.6199,
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
"step": 341
},
{
- "epoch": 6.92,
- "learning_rate": 0.00015637755102040817,
- "loss": 1.5722,
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
"step": 342
},
{
- "epoch": 6.94,
- "learning_rate": 0.00015625,
- "loss": 1.5685,
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
"step": 343
},
{
- "epoch": 6.96,
- "learning_rate": 0.00015612244897959186,
- "loss": 1.5615,
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
"step": 344
},
{
- "epoch": 6.98,
- "learning_rate": 0.00015599489795918366,
- "loss": 1.5994,
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
"step": 345
},
{
- "epoch": 7.0,
- "learning_rate": 0.00015586734693877552,
- "loss": 1.5579,
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
"step": 346
},
{
- "epoch": 7.02,
- "learning_rate": 0.00015573979591836735,
- "loss": 1.547,
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
"step": 347
},
{
- "epoch": 7.04,
- "learning_rate": 0.00015561224489795918,
- "loss": 1.5292,
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
"step": 348
},
{
- "epoch": 7.06,
- "learning_rate": 0.00015548469387755102,
- "loss": 1.6032,
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
"step": 349
},
{
- "epoch": 7.08,
- "learning_rate": 0.00015535714285714287,
- "loss": 1.5149,
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
"step": 350
},
{
- "epoch": 7.1,
- "learning_rate": 0.0001552295918367347,
- "loss": 1.6093,
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
"step": 351
},
{
- "epoch": 7.12,
- "learning_rate": 0.00015510204081632654,
- "loss": 1.5421,
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
"step": 352
},
{
- "epoch": 7.14,
- "learning_rate": 0.00015497448979591837,
- "loss": 1.5733,
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
"step": 353
},
{
- "epoch": 7.16,
- "learning_rate": 0.00015484693877551022,
- "loss": 1.5703,
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
"step": 354
},
{
- "epoch": 7.18,
- "learning_rate": 0.00015471938775510203,
- "loss": 1.6141,
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
"step": 355
},
{
- "epoch": 7.2,
- "learning_rate": 0.00015459183673469389,
- "loss": 1.5526,
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
"step": 356
},
{
- "epoch": 7.22,
- "learning_rate": 0.00015446428571428572,
- "loss": 1.5347,
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
"step": 357
},
{
- "epoch": 7.24,
- "learning_rate": 0.00015433673469387755,
- "loss": 1.5682,
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
"step": 358
},
{
- "epoch": 7.26,
- "learning_rate": 0.0001542091836734694,
- "loss": 1.5292,
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
"step": 359
},
{
- "epoch": 7.28,
- "learning_rate": 0.00015408163265306124,
- "loss": 1.499,
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
"step": 360
},
{
- "epoch": 7.3,
- "learning_rate": 0.00015395408163265307,
- "loss": 1.5624,
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
"step": 361
},
{
- "epoch": 7.32,
- "learning_rate": 0.0001538265306122449,
- "loss": 1.627,
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
"step": 362
},
{
- "epoch": 7.34,
- "learning_rate": 0.00015369897959183676,
- "loss": 1.5327,
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
"step": 363
},
{
- "epoch": 7.37,
- "learning_rate": 0.0001535714285714286,
- "loss": 1.5622,
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
"step": 364
},
{
- "epoch": 7.39,
- "learning_rate": 0.00015344387755102042,
- "loss": 1.5659,
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
"step": 365
},
{
- "epoch": 7.41,
- "learning_rate": 0.00015331632653061225,
- "loss": 1.5019,
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
"step": 366
},
{
- "epoch": 7.43,
- "learning_rate": 0.0001531887755102041,
- "loss": 1.5921,
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
"step": 367
},
{
- "epoch": 7.45,
- "learning_rate": 0.0001530612244897959,
- "loss": 1.5914,
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
"step": 368
},
{
- "epoch": 7.47,
- "learning_rate": 0.00015293367346938777,
- "loss": 1.5045,
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
"step": 369
},
{
- "epoch": 7.49,
- "learning_rate": 0.0001528061224489796,
- "loss": 1.6209,
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
"step": 370
},
{
- "epoch": 7.51,
- "learning_rate": 0.00015267857142857143,
- "loss": 1.5198,
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
"step": 371
},
{
- "epoch": 7.53,
- "learning_rate": 0.00015255102040816326,
- "loss": 1.5363,
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
"step": 372
},
{
- "epoch": 7.55,
- "learning_rate": 0.00015242346938775512,
- "loss": 1.5391,
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
"step": 373
},
{
- "epoch": 7.57,
- "learning_rate": 0.00015229591836734695,
- "loss": 1.4546,
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
"step": 374
},
{
- "epoch": 7.59,
- "learning_rate": 0.00015216836734693878,
- "loss": 1.5546,
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
"step": 375
},
{
- "epoch": 7.61,
- "learning_rate": 0.0001520408163265306,
- "loss": 1.5629,
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
"step": 376
},
{
- "epoch": 7.63,
- "learning_rate": 0.00015191326530612247,
- "loss": 1.6002,
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
"step": 377
},
{
- "epoch": 7.65,
- "learning_rate": 0.00015178571428571427,
- "loss": 1.5543,
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
"step": 378
},
{
- "epoch": 7.67,
- "learning_rate": 0.00015165816326530613,
- "loss": 1.5925,
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
"step": 379
},
{
- "epoch": 7.69,
- "learning_rate": 0.00015153061224489796,
- "loss": 1.5631,
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
"step": 380
},
{
- "epoch": 7.71,
- "learning_rate": 0.0001514030612244898,
- "loss": 1.5677,
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
"step": 381
},
{
- "epoch": 7.73,
- "learning_rate": 0.00015127551020408165,
- "loss": 1.5828,
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
"step": 382
},
{
- "epoch": 7.75,
- "learning_rate": 0.00015114795918367348,
- "loss": 1.6494,
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
"step": 383
},
{
- "epoch": 7.77,
- "learning_rate": 0.0001510204081632653,
- "loss": 1.553,
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
"step": 384
},
{
- "epoch": 7.79,
- "learning_rate": 0.00015089285714285714,
- "loss": 1.6156,
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
"step": 385
},
{
- "epoch": 7.81,
- "learning_rate": 0.000150765306122449,
- "loss": 1.5001,
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
"step": 386
},
{
- "epoch": 7.83,
- "learning_rate": 0.00015063775510204083,
- "loss": 1.5321,
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
"step": 387
},
{
- "epoch": 7.85,
- "learning_rate": 0.00015051020408163266,
- "loss": 1.5307,
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
"step": 388
},
{
- "epoch": 7.87,
- "learning_rate": 0.0001503826530612245,
- "loss": 1.5639,
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
"step": 389
},
{
- "epoch": 7.89,
- "learning_rate": 0.00015025510204081635,
- "loss": 1.517,
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
"step": 390
},
{
- "epoch": 7.91,
- "learning_rate": 0.00015012755102040816,
- "loss": 1.4776,
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
"step": 391
},
{
- "epoch": 7.93,
- "learning_rate": 0.00015000000000000001,
- "loss": 1.5368,
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
"step": 392
},
{
- "epoch": 7.95,
- "learning_rate": 0.00014987244897959184,
- "loss": 1.5636,
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
"step": 393
},
{
- "epoch": 7.97,
- "learning_rate": 0.00014974489795918368,
- "loss": 1.6004,
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
"step": 394
},
{
- "epoch": 7.99,
- "learning_rate": 0.0001496173469387755,
- "loss": 1.5524,
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
"step": 395
},
{
- "epoch": 8.01,
- "learning_rate": 0.00014948979591836736,
- "loss": 1.5307,
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
"step": 396
},
{
- "epoch": 8.03,
- "learning_rate": 0.00014936224489795917,
- "loss": 1.5123,
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
"step": 397
},
{
- "epoch": 8.05,
- "learning_rate": 0.00014923469387755103,
- "loss": 1.5132,
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
"step": 398
},
{
- "epoch": 8.07,
- "learning_rate": 0.00014910714285714286,
- "loss": 1.5109,
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
"step": 399
},
{
- "epoch": 8.09,
- "learning_rate": 0.00014897959183673472,
- "loss": 1.5302,
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
"step": 400
},
{
- "epoch": 8.11,
- "learning_rate": 0.00014885204081632652,
- "loss": 1.5238,
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
"step": 401
},
{
- "epoch": 8.13,
- "learning_rate": 0.00014872448979591838,
- "loss": 1.4781,
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
"step": 402
},
{
- "epoch": 8.15,
- "learning_rate": 0.0001485969387755102,
- "loss": 1.5446,
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
"step": 403
},
{
- "epoch": 8.17,
- "learning_rate": 0.00014846938775510204,
- "loss": 1.5,
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
"step": 404
},
{
- "epoch": 8.19,
- "learning_rate": 0.0001483418367346939,
- "loss": 1.5458,
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
"step": 405
},
{
- "epoch": 8.21,
- "learning_rate": 0.00014821428571428573,
- "loss": 1.5257,
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
"step": 406
},
{
- "epoch": 8.24,
- "learning_rate": 0.00014808673469387756,
- "loss": 1.4607,
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
"step": 407
},
{
- "epoch": 8.26,
- "learning_rate": 0.0001479591836734694,
- "loss": 1.4282,
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
"step": 408
},
{
- "epoch": 8.28,
- "learning_rate": 0.00014783163265306125,
- "loss": 1.4519,
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
"step": 409
},
{
- "epoch": 8.3,
- "learning_rate": 0.00014770408163265305,
- "loss": 1.475,
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
"step": 410
},
{
- "epoch": 8.32,
- "learning_rate": 0.0001475765306122449,
- "loss": 1.5425,
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
"step": 411
},
{
- "epoch": 8.34,
- "learning_rate": 0.00014744897959183674,
- "loss": 1.5407,
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
"step": 412
},
{
- "epoch": 8.36,
- "learning_rate": 0.0001473214285714286,
- "loss": 1.5698,
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
"step": 413
},
{
- "epoch": 8.38,
- "learning_rate": 0.0001471938775510204,
- "loss": 1.4282,
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
"step": 414
},
{
- "epoch": 8.4,
- "learning_rate": 0.00014706632653061226,
- "loss": 1.5301,
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
"step": 415
},
{
- "epoch": 8.42,
- "learning_rate": 0.0001469387755102041,
- "loss": 1.5083,
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
"step": 416
},
{
- "epoch": 8.44,
- "learning_rate": 0.00014681122448979592,
- "loss": 1.5712,
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
"step": 417
},
{
- "epoch": 8.46,
- "learning_rate": 0.00014668367346938775,
- "loss": 1.4363,
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
"step": 418
},
{
- "epoch": 8.48,
- "learning_rate": 0.0001465561224489796,
- "loss": 1.4463,
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
"step": 419
},
{
- "epoch": 8.5,
- "learning_rate": 0.00014642857142857141,
- "loss": 1.4738,
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
"step": 420
},
{
- "epoch": 8.52,
- "learning_rate": 0.00014630102040816327,
- "loss": 1.5396,
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
"step": 421
},
{
- "epoch": 8.54,
- "learning_rate": 0.0001461734693877551,
- "loss": 1.4384,
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
"step": 422
},
{
- "epoch": 8.56,
- "learning_rate": 0.00014604591836734696,
- "loss": 1.5345,
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
"step": 423
},
{
- "epoch": 8.58,
- "learning_rate": 0.0001459183673469388,
- "loss": 1.5355,
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
"step": 424
},
{
- "epoch": 8.6,
- "learning_rate": 0.00014579081632653062,
- "loss": 1.5188,
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
"step": 425
},
{
- "epoch": 8.62,
- "learning_rate": 0.00014566326530612245,
- "loss": 1.5575,
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
"step": 426
},
{
- "epoch": 8.64,
- "learning_rate": 0.00014553571428571428,
- "loss": 1.5279,
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
"step": 427
},
{
- "epoch": 8.66,
- "learning_rate": 0.00014540816326530614,
- "loss": 1.5484,
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
"step": 428
},
{
- "epoch": 8.68,
- "learning_rate": 0.00014528061224489797,
- "loss": 1.4878,
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
"step": 429
},
{
- "epoch": 8.7,
- "learning_rate": 0.0001451530612244898,
- "loss": 1.503,
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
"step": 430
},
{
- "epoch": 8.72,
- "learning_rate": 0.00014502551020408163,
- "loss": 1.4723,
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
"step": 431
},
{
- "epoch": 8.74,
- "learning_rate": 0.0001448979591836735,
- "loss": 1.5579,
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
"step": 432
},
{
- "epoch": 8.76,
- "learning_rate": 0.0001447704081632653,
- "loss": 1.4789,
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
"step": 433
},
{
- "epoch": 8.78,
- "learning_rate": 0.00014464285714285715,
- "loss": 1.5501,
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
"step": 434
},
{
- "epoch": 8.8,
- "learning_rate": 0.00014451530612244899,
- "loss": 1.5204,
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
"step": 435
},
{
- "epoch": 8.82,
- "learning_rate": 0.00014438775510204084,
- "loss": 1.5489,
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
"step": 436
},
{
- "epoch": 8.84,
- "learning_rate": 0.00014426020408163265,
- "loss": 1.5464,
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
"step": 437
},
{
- "epoch": 8.86,
- "learning_rate": 0.0001441326530612245,
- "loss": 1.5896,
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
"step": 438
},
{
- "epoch": 8.88,
- "learning_rate": 0.00014400510204081634,
- "loss": 1.5465,
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
"step": 439
},
{
- "epoch": 8.9,
- "learning_rate": 0.00014387755102040817,
- "loss": 1.5094,
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
"step": 440
},
{
- "epoch": 8.92,
- "learning_rate": 0.00014375,
- "loss": 1.5144,
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
"step": 441
},
{
- "epoch": 8.94,
- "learning_rate": 0.00014362244897959186,
- "loss": 1.4919,
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
"step": 442
},
{
- "epoch": 8.96,
- "learning_rate": 0.00014349489795918366,
- "loss": 1.4702,
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
"step": 443
},
{
- "epoch": 8.98,
- "learning_rate": 0.00014336734693877552,
- "loss": 1.4996,
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
"step": 444
},
{
- "epoch": 9.0,
- "learning_rate": 0.00014323979591836735,
- "loss": 1.5503,
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
"step": 445
},
{
- "epoch": 9.02,
- "learning_rate": 0.00014311224489795918,
- "loss": 1.4125,
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
"step": 446
},
{
- "epoch": 9.04,
- "learning_rate": 0.00014298469387755104,
- "loss": 1.4722,
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
"step": 447
},
{
- "epoch": 9.06,
- "learning_rate": 0.00014285714285714287,
- "loss": 1.5199,
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
"step": 448
},
{
- "epoch": 9.09,
- "learning_rate": 0.0001427295918367347,
- "loss": 1.4571,
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
"step": 449
},
{
- "epoch": 9.11,
- "learning_rate": 0.00014260204081632653,
- "loss": 1.4996,
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
"step": 450
},
{
- "epoch": 9.13,
- "learning_rate": 0.0001424744897959184,
- "loss": 1.4092,
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
"step": 451
},
{
- "epoch": 9.15,
- "learning_rate": 0.00014234693877551022,
- "loss": 1.4198,
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
"step": 452
},
{
- "epoch": 9.17,
- "learning_rate": 0.00014221938775510205,
- "loss": 1.4916,
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
"step": 453
},
{
- "epoch": 9.19,
- "learning_rate": 0.00014209183673469388,
- "loss": 1.5051,
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
"step": 454
},
{
- "epoch": 9.21,
- "learning_rate": 0.00014196428571428574,
- "loss": 1.4321,
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
"step": 455
},
{
- "epoch": 9.23,
- "learning_rate": 0.00014183673469387754,
- "loss": 1.4097,
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
"step": 456
},
{
- "epoch": 9.25,
- "learning_rate": 0.0001417091836734694,
- "loss": 1.4853,
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
"step": 457
},
{
- "epoch": 9.27,
- "learning_rate": 0.00014158163265306123,
- "loss": 1.4593,
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
"step": 458
},
{
- "epoch": 9.29,
- "learning_rate": 0.00014145408163265306,
- "loss": 1.3729,
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
"step": 459
},
{
- "epoch": 9.31,
- "learning_rate": 0.0001413265306122449,
- "loss": 1.4467,
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
"step": 460
},
{
- "epoch": 9.33,
- "learning_rate": 0.00014119897959183675,
- "loss": 1.4467,
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
"step": 461
},
{
- "epoch": 9.35,
- "learning_rate": 0.00014107142857142858,
- "loss": 1.4785,
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
"step": 462
},
{
- "epoch": 9.37,
- "learning_rate": 0.0001409438775510204,
- "loss": 1.4089,
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
"step": 463
},
{
- "epoch": 9.39,
- "learning_rate": 0.00014081632653061224,
- "loss": 1.5026,
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
"step": 464
},
{
- "epoch": 9.41,
- "learning_rate": 0.0001406887755102041,
- "loss": 1.4857,
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
"step": 465
},
{
- "epoch": 9.43,
- "learning_rate": 0.0001405612244897959,
- "loss": 1.3745,
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
"step": 466
},
{
- "epoch": 9.45,
- "learning_rate": 0.00014043367346938776,
- "loss": 1.4733,
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
"step": 467
},
{
- "epoch": 9.47,
- "learning_rate": 0.0001403061224489796,
- "loss": 1.5212,
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
"step": 468
},
{
- "epoch": 9.49,
- "learning_rate": 0.00014017857142857142,
- "loss": 1.5398,
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
"step": 469
},
{
- "epoch": 9.51,
- "learning_rate": 0.00014005102040816328,
- "loss": 1.478,
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
"step": 470
},
{
- "epoch": 9.53,
- "learning_rate": 0.0001399234693877551,
- "loss": 1.496,
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
"step": 471
},
{
- "epoch": 9.55,
- "learning_rate": 0.00013979591836734694,
- "loss": 1.4837,
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
"step": 472
},
{
- "epoch": 9.57,
- "learning_rate": 0.00013966836734693878,
- "loss": 1.4724,
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
"step": 473
},
{
- "epoch": 9.59,
- "learning_rate": 0.00013954081632653063,
- "loss": 1.4828,
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
"step": 474
},
{
- "epoch": 9.61,
- "learning_rate": 0.00013941326530612246,
- "loss": 1.5012,
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
"step": 475
},
{
- "epoch": 9.63,
- "learning_rate": 0.0001392857142857143,
- "loss": 1.4879,
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
"step": 476
},
{
- "epoch": 9.65,
- "learning_rate": 0.00013915816326530613,
- "loss": 1.4196,
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
"step": 477
},
{
- "epoch": 9.67,
- "learning_rate": 0.00013903061224489798,
- "loss": 1.4915,
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
"step": 478
},
{
- "epoch": 9.69,
- "learning_rate": 0.0001389030612244898,
- "loss": 1.3878,
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
"step": 479
},
{
- "epoch": 9.71,
- "learning_rate": 0.00013877551020408165,
- "loss": 1.466,
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
"step": 480
},
{
- "epoch": 9.73,
- "learning_rate": 0.00013864795918367348,
- "loss": 1.4582,
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
"step": 481
},
{
- "epoch": 9.75,
- "learning_rate": 0.0001385204081632653,
- "loss": 1.533,
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
"step": 482
},
{
- "epoch": 9.77,
- "learning_rate": 0.00013839285714285714,
- "loss": 1.4697,
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
"step": 483
},
{
- "epoch": 9.79,
- "learning_rate": 0.000138265306122449,
- "loss": 1.3989,
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
"step": 484
},
{
- "epoch": 9.81,
- "learning_rate": 0.00013813775510204083,
- "loss": 1.4361,
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
"step": 485
},
{
- "epoch": 9.83,
- "learning_rate": 0.00013801020408163266,
- "loss": 1.5271,
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
"step": 486
},
{
- "epoch": 9.85,
- "learning_rate": 0.0001378826530612245,
- "loss": 1.4905,
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
"step": 487
},
{
- "epoch": 9.87,
- "learning_rate": 0.00013775510204081635,
- "loss": 1.4757,
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
"step": 488
},
{
- "epoch": 9.89,
- "learning_rate": 0.00013762755102040815,
- "loss": 1.5485,
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
"step": 489
},
{
- "epoch": 9.91,
- "learning_rate": 0.0001375,
- "loss": 1.4783,
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
"step": 490
},
{
- "epoch": 9.93,
- "learning_rate": 0.00013737244897959184,
- "loss": 1.4849,
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
"step": 491
},
{
- "epoch": 9.96,
- "learning_rate": 0.00013724489795918367,
- "loss": 1.5382,
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
"step": 492
},
{
- "epoch": 9.98,
- "learning_rate": 0.00013711734693877553,
- "loss": 1.4902,
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
"step": 493
},
{
- "epoch": 10.0,
- "learning_rate": 0.00013698979591836736,
- "loss": 1.4865,
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
"step": 494
},
{
- "epoch": 10.02,
- "learning_rate": 0.0001368622448979592,
- "loss": 1.4436,
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
"step": 495
},
{
- "epoch": 10.04,
- "learning_rate": 0.00013673469387755102,
- "loss": 1.408,
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
"step": 496
},
{
- "epoch": 10.06,
- "learning_rate": 0.00013660714285714288,
- "loss": 1.4764,
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
"step": 497
},
{
- "epoch": 10.08,
- "learning_rate": 0.0001364795918367347,
- "loss": 1.4646,
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
"step": 498
},
{
- "epoch": 10.1,
- "learning_rate": 0.00013635204081632654,
- "loss": 1.406,
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
"step": 499
},
{
- "epoch": 10.12,
- "learning_rate": 0.00013622448979591837,
- "loss": 1.4785,
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
"step": 500
},
{
- "epoch": 10.14,
- "learning_rate": 0.00013609693877551023,
- "loss": 1.4117,
+ "epoch": 5.66,
+ "learning_rate": 0.00012883522727272727,
+ "loss": 1.0755,
"step": 501
},
{
- "epoch": 10.16,
- "learning_rate": 0.00013596938775510203,
- "loss": 1.4108,
+ "epoch": 5.67,
+ "learning_rate": 0.00012869318181818183,
+ "loss": 1.0755,
"step": 502
},
{
- "epoch": 10.18,
- "learning_rate": 0.0001358418367346939,
- "loss": 1.4155,
+ "epoch": 5.68,
+ "learning_rate": 0.00012855113636363636,
+ "loss": 1.0869,
"step": 503
},
{
- "epoch": 10.2,
- "learning_rate": 0.00013571428571428572,
- "loss": 1.4021,
+ "epoch": 5.69,
+ "learning_rate": 0.00012840909090909092,
+ "loss": 1.0673,
"step": 504
},
{
- "epoch": 10.22,
- "learning_rate": 0.00013558673469387755,
- "loss": 1.411,
+ "epoch": 5.71,
+ "learning_rate": 0.00012826704545454545,
+ "loss": 1.0692,
"step": 505
},
{
- "epoch": 10.24,
- "learning_rate": 0.00013545918367346938,
- "loss": 1.3851,
+ "epoch": 5.72,
+ "learning_rate": 0.000128125,
+ "loss": 1.0474,
"step": 506
},
{
- "epoch": 10.26,
- "learning_rate": 0.00013533163265306124,
- "loss": 1.387,
+ "epoch": 5.73,
+ "learning_rate": 0.00012798295454545454,
+ "loss": 1.0749,
"step": 507
},
{
- "epoch": 10.28,
- "learning_rate": 0.00013520408163265305,
- "loss": 1.4163,
+ "epoch": 5.74,
+ "learning_rate": 0.0001278409090909091,
+ "loss": 1.0519,
"step": 508
},
{
- "epoch": 10.3,
- "learning_rate": 0.0001350765306122449,
- "loss": 1.3343,
+ "epoch": 5.75,
+ "learning_rate": 0.00012769886363636366,
+ "loss": 1.0566,
"step": 509
},
{
- "epoch": 10.32,
- "learning_rate": 0.00013494897959183673,
- "loss": 1.4811,
+ "epoch": 5.76,
+ "learning_rate": 0.0001275568181818182,
+ "loss": 1.06,
"step": 510
},
{
- "epoch": 10.34,
- "learning_rate": 0.0001348214285714286,
- "loss": 1.4086,
+ "epoch": 5.77,
+ "learning_rate": 0.00012741477272727272,
+ "loss": 1.0618,
"step": 511
},
{
- "epoch": 10.36,
- "learning_rate": 0.0001346938775510204,
- "loss": 1.3879,
+ "epoch": 5.78,
+ "learning_rate": 0.00012727272727272728,
+ "loss": 1.0643,
"step": 512
},
{
- "epoch": 10.38,
- "learning_rate": 0.00013456632653061225,
- "loss": 1.4204,
+ "epoch": 5.8,
+ "learning_rate": 0.0001271306818181818,
+ "loss": 1.026,
"step": 513
},
{
- "epoch": 10.4,
- "learning_rate": 0.00013443877551020408,
- "loss": 1.4158,
+ "epoch": 5.81,
+ "learning_rate": 0.00012698863636363637,
+ "loss": 1.0335,
"step": 514
},
{
- "epoch": 10.42,
- "learning_rate": 0.00013431122448979592,
- "loss": 1.4521,
+ "epoch": 5.82,
+ "learning_rate": 0.00012684659090909093,
+ "loss": 1.0205,
"step": 515
},
{
- "epoch": 10.44,
- "learning_rate": 0.00013418367346938777,
- "loss": 1.4196,
+ "epoch": 5.83,
+ "learning_rate": 0.00012670454545454546,
+ "loss": 1.0594,
"step": 516
},
{
- "epoch": 10.46,
- "learning_rate": 0.0001340561224489796,
- "loss": 1.4361,
+ "epoch": 5.84,
+ "learning_rate": 0.0001265625,
+ "loss": 1.0136,
"step": 517
},
{
- "epoch": 10.48,
- "learning_rate": 0.00013392857142857144,
- "loss": 1.4482,
+ "epoch": 5.85,
+ "learning_rate": 0.00012642045454545455,
+ "loss": 1.0244,
"step": 518
},
{
- "epoch": 10.5,
- "learning_rate": 0.00013380102040816327,
- "loss": 1.4801,
+ "epoch": 5.86,
+ "learning_rate": 0.00012627840909090908,
+ "loss": 1.0569,
"step": 519
},
{
- "epoch": 10.52,
- "learning_rate": 0.00013367346938775512,
- "loss": 1.4556,
+ "epoch": 5.87,
+ "learning_rate": 0.00012613636363636364,
+ "loss": 1.0416,
"step": 520
},
{
- "epoch": 10.54,
- "learning_rate": 0.00013354591836734695,
- "loss": 1.3902,
+ "epoch": 5.89,
+ "learning_rate": 0.0001259943181818182,
+ "loss": 0.9884,
"step": 521
},
{
- "epoch": 10.56,
- "learning_rate": 0.00013341836734693879,
- "loss": 1.4269,
+ "epoch": 5.9,
+ "learning_rate": 0.00012585227272727273,
+ "loss": 1.0351,
"step": 522
},
{
- "epoch": 10.58,
- "learning_rate": 0.00013329081632653062,
- "loss": 1.4899,
+ "epoch": 5.91,
+ "learning_rate": 0.00012571022727272726,
+ "loss": 1.0037,
"step": 523
},
{
- "epoch": 10.6,
- "learning_rate": 0.00013316326530612247,
- "loss": 1.3952,
+ "epoch": 5.92,
+ "learning_rate": 0.00012556818181818182,
+ "loss": 1.0219,
"step": 524
},
{
- "epoch": 10.62,
- "learning_rate": 0.00013303571428571428,
- "loss": 1.4116,
+ "epoch": 5.93,
+ "learning_rate": 0.00012542613636363635,
+ "loss": 1.0533,
"step": 525
},
{
- "epoch": 10.64,
- "learning_rate": 0.00013290816326530614,
- "loss": 1.4583,
+ "epoch": 5.94,
+ "learning_rate": 0.0001252840909090909,
+ "loss": 1.0031,
"step": 526
},
{
- "epoch": 10.66,
- "learning_rate": 0.00013278061224489797,
- "loss": 1.4466,
+ "epoch": 5.95,
+ "learning_rate": 0.00012514204545454547,
+ "loss": 1.0454,
"step": 527
},
{
- "epoch": 10.68,
- "learning_rate": 0.0001326530612244898,
- "loss": 1.4242,
+ "epoch": 5.97,
+ "learning_rate": 0.000125,
+ "loss": 1.0195,
"step": 528
},
{
- "epoch": 10.7,
- "learning_rate": 0.00013252551020408163,
- "loss": 1.3717,
+ "epoch": 5.98,
+ "learning_rate": 0.00012485795454545453,
+ "loss": 1.0076,
"step": 529
},
{
- "epoch": 10.72,
- "learning_rate": 0.0001323979591836735,
- "loss": 1.4583,
+ "epoch": 5.99,
+ "learning_rate": 0.0001247159090909091,
+ "loss": 1.0378,
"step": 530
},
{
- "epoch": 10.74,
- "learning_rate": 0.0001322704081632653,
- "loss": 1.4185,
+ "epoch": 6.0,
+ "learning_rate": 0.00012457386363636365,
+ "loss": 0.9795,
"step": 531
},
{
- "epoch": 10.76,
- "learning_rate": 0.00013214285714285715,
- "loss": 1.4287,
+ "epoch": 6.01,
+ "learning_rate": 0.00012443181818181818,
+ "loss": 0.9405,
"step": 532
},
{
- "epoch": 10.78,
- "learning_rate": 0.00013201530612244898,
- "loss": 1.4385,
+ "epoch": 6.02,
+ "learning_rate": 0.00012428977272727274,
+ "loss": 0.9503,
"step": 533
},
{
- "epoch": 10.8,
- "learning_rate": 0.00013188775510204084,
- "loss": 1.453,
+ "epoch": 6.03,
+ "learning_rate": 0.00012414772727272727,
+ "loss": 0.9456,
"step": 534
},
{
- "epoch": 10.83,
- "learning_rate": 0.00013176020408163264,
- "loss": 1.4161,
+ "epoch": 6.04,
+ "learning_rate": 0.0001240056818181818,
+ "loss": 0.9536,
"step": 535
},
{
- "epoch": 10.85,
- "learning_rate": 0.0001316326530612245,
- "loss": 1.457,
+ "epoch": 6.06,
+ "learning_rate": 0.00012386363636363636,
+ "loss": 0.9412,
"step": 536
},
{
- "epoch": 10.87,
- "learning_rate": 0.00013150510204081633,
- "loss": 1.4367,
+ "epoch": 6.07,
+ "learning_rate": 0.00012372159090909092,
+ "loss": 0.9315,
"step": 537
},
{
- "epoch": 10.89,
- "learning_rate": 0.00013137755102040816,
- "loss": 1.4256,
+ "epoch": 6.08,
+ "learning_rate": 0.00012357954545454545,
+ "loss": 0.9486,
"step": 538
},
{
- "epoch": 10.91,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.424,
+ "epoch": 6.09,
+ "learning_rate": 0.0001234375,
+ "loss": 0.9405,
"step": 539
},
{
- "epoch": 10.93,
- "learning_rate": 0.00013112244897959185,
- "loss": 1.3923,
+ "epoch": 6.1,
+ "learning_rate": 0.00012329545454545454,
+ "loss": 0.9269,
"step": 540
},
{
- "epoch": 10.95,
- "learning_rate": 0.00013099489795918368,
- "loss": 1.4225,
+ "epoch": 6.11,
+ "learning_rate": 0.0001231534090909091,
+ "loss": 0.9378,
"step": 541
},
{
- "epoch": 10.97,
- "learning_rate": 0.0001308673469387755,
- "loss": 1.3969,
+ "epoch": 6.12,
+ "learning_rate": 0.00012301136363636366,
+ "loss": 0.9431,
"step": 542
},
{
- "epoch": 10.99,
- "learning_rate": 0.00013073979591836737,
- "loss": 1.4446,
+ "epoch": 6.13,
+ "learning_rate": 0.0001228693181818182,
+ "loss": 0.9256,
"step": 543
},
{
- "epoch": 11.01,
- "learning_rate": 0.00013061224489795917,
- "loss": 1.4375,
+ "epoch": 6.15,
+ "learning_rate": 0.00012272727272727272,
+ "loss": 0.919,
"step": 544
},
{
- "epoch": 11.03,
- "learning_rate": 0.00013048469387755103,
- "loss": 1.4064,
+ "epoch": 6.16,
+ "learning_rate": 0.00012258522727272728,
+ "loss": 0.9188,
"step": 545
},
{
- "epoch": 11.05,
- "learning_rate": 0.00013035714285714286,
- "loss": 1.3454,
+ "epoch": 6.17,
+ "learning_rate": 0.00012244318181818181,
+ "loss": 0.9447,
"step": 546
},
{
- "epoch": 11.07,
- "learning_rate": 0.00013022959183673472,
- "loss": 1.3234,
+ "epoch": 6.18,
+ "learning_rate": 0.00012230113636363637,
+ "loss": 0.9261,
"step": 547
},
{
- "epoch": 11.09,
- "learning_rate": 0.00013010204081632652,
- "loss": 1.3759,
+ "epoch": 6.19,
+ "learning_rate": 0.00012215909090909093,
+ "loss": 0.9302,
"step": 548
},
{
- "epoch": 11.11,
- "learning_rate": 0.00012997448979591838,
- "loss": 1.4221,
+ "epoch": 6.2,
+ "learning_rate": 0.00012201704545454546,
+ "loss": 0.9161,
"step": 549
},
{
- "epoch": 11.13,
- "learning_rate": 0.0001298469387755102,
- "loss": 1.4261,
+ "epoch": 6.21,
+ "learning_rate": 0.00012187500000000001,
+ "loss": 0.9521,
"step": 550
},
{
- "epoch": 11.15,
- "learning_rate": 0.00012971938775510204,
- "loss": 1.3341,
+ "epoch": 6.22,
+ "learning_rate": 0.00012173295454545455,
+ "loss": 0.9026,
"step": 551
},
{
- "epoch": 11.17,
- "learning_rate": 0.00012959183673469387,
- "loss": 1.3994,
+ "epoch": 6.24,
+ "learning_rate": 0.00012159090909090908,
+ "loss": 0.9361,
"step": 552
},
{
- "epoch": 11.19,
- "learning_rate": 0.00012946428571428573,
- "loss": 1.3894,
+ "epoch": 6.25,
+ "learning_rate": 0.00012144886363636366,
+ "loss": 0.8944,
"step": 553
},
{
- "epoch": 11.21,
- "learning_rate": 0.00012933673469387754,
- "loss": 1.3585,
+ "epoch": 6.26,
+ "learning_rate": 0.00012130681818181819,
+ "loss": 0.895,
"step": 554
},
{
- "epoch": 11.23,
- "learning_rate": 0.0001292091836734694,
- "loss": 1.3763,
+ "epoch": 6.27,
+ "learning_rate": 0.00012116477272727273,
+ "loss": 0.8956,
"step": 555
},
{
- "epoch": 11.25,
- "learning_rate": 0.00012908163265306123,
- "loss": 1.3623,
+ "epoch": 6.28,
+ "learning_rate": 0.00012102272727272728,
+ "loss": 0.8998,
"step": 556
},
{
- "epoch": 11.27,
- "learning_rate": 0.00012895408163265306,
- "loss": 1.3907,
+ "epoch": 6.29,
+ "learning_rate": 0.00012088068181818182,
+ "loss": 0.915,
"step": 557
},
{
- "epoch": 11.29,
- "learning_rate": 0.0001288265306122449,
- "loss": 1.3807,
+ "epoch": 6.3,
+ "learning_rate": 0.00012073863636363636,
+ "loss": 0.9282,
"step": 558
},
{
- "epoch": 11.31,
- "learning_rate": 0.00012869897959183674,
- "loss": 1.4045,
+ "epoch": 6.32,
+ "learning_rate": 0.00012059659090909093,
+ "loss": 0.8938,
"step": 559
},
{
- "epoch": 11.33,
- "learning_rate": 0.00012857142857142858,
- "loss": 1.4038,
+ "epoch": 6.33,
+ "learning_rate": 0.00012045454545454546,
+ "loss": 0.8886,
"step": 560
},
{
- "epoch": 11.35,
- "learning_rate": 0.0001284438775510204,
- "loss": 1.3466,
+ "epoch": 6.34,
+ "learning_rate": 0.0001203125,
+ "loss": 0.8988,
"step": 561
},
{
- "epoch": 11.37,
- "learning_rate": 0.00012831632653061226,
- "loss": 1.3449,
+ "epoch": 6.35,
+ "learning_rate": 0.00012017045454545455,
+ "loss": 0.8852,
"step": 562
},
{
- "epoch": 11.39,
- "learning_rate": 0.0001281887755102041,
- "loss": 1.3866,
+ "epoch": 6.36,
+ "learning_rate": 0.0001200284090909091,
+ "loss": 0.8818,
"step": 563
},
{
- "epoch": 11.41,
- "learning_rate": 0.00012806122448979593,
- "loss": 1.3106,
+ "epoch": 6.37,
+ "learning_rate": 0.00011988636363636365,
+ "loss": 0.8881,
"step": 564
},
{
- "epoch": 11.43,
- "learning_rate": 0.00012793367346938776,
- "loss": 1.4414,
+ "epoch": 6.38,
+ "learning_rate": 0.0001197443181818182,
+ "loss": 0.9226,
"step": 565
},
{
- "epoch": 11.45,
- "learning_rate": 0.00012780612244897962,
- "loss": 1.3737,
+ "epoch": 6.39,
+ "learning_rate": 0.00011960227272727273,
+ "loss": 0.8849,
"step": 566
},
{
- "epoch": 11.47,
- "learning_rate": 0.00012767857142857142,
- "loss": 1.4053,
+ "epoch": 6.41,
+ "learning_rate": 0.00011946022727272727,
+ "loss": 0.8894,
"step": 567
},
{
- "epoch": 11.49,
- "learning_rate": 0.00012755102040816328,
- "loss": 1.4561,
+ "epoch": 6.42,
+ "learning_rate": 0.00011931818181818182,
+ "loss": 0.9207,
"step": 568
},
{
- "epoch": 11.51,
- "learning_rate": 0.0001274234693877551,
- "loss": 1.3684,
+ "epoch": 6.43,
+ "learning_rate": 0.00011917613636363636,
+ "loss": 0.9105,
"step": 569
},
{
- "epoch": 11.53,
- "learning_rate": 0.00012729591836734697,
- "loss": 1.3117,
+ "epoch": 6.44,
+ "learning_rate": 0.00011903409090909092,
+ "loss": 0.8762,
"step": 570
},
{
- "epoch": 11.55,
- "learning_rate": 0.00012716836734693877,
- "loss": 1.3474,
+ "epoch": 6.45,
+ "learning_rate": 0.00011889204545454547,
+ "loss": 0.8926,
"step": 571
},
{
- "epoch": 11.57,
- "learning_rate": 0.00012704081632653063,
- "loss": 1.3804,
+ "epoch": 6.46,
+ "learning_rate": 0.00011875,
+ "loss": 0.8719,
"step": 572
},
{
- "epoch": 11.59,
- "learning_rate": 0.00012691326530612246,
- "loss": 1.3656,
+ "epoch": 6.47,
+ "learning_rate": 0.00011860795454545454,
+ "loss": 0.9198,
"step": 573
},
{
- "epoch": 11.61,
- "learning_rate": 0.0001267857142857143,
- "loss": 1.3133,
+ "epoch": 6.48,
+ "learning_rate": 0.00011846590909090909,
+ "loss": 0.8846,
"step": 574
},
{
- "epoch": 11.63,
- "learning_rate": 0.00012665816326530612,
- "loss": 1.4077,
+ "epoch": 6.5,
+ "learning_rate": 0.00011832386363636365,
+ "loss": 0.8495,
"step": 575
},
{
- "epoch": 11.65,
- "learning_rate": 0.00012653061224489798,
- "loss": 1.4087,
+ "epoch": 6.51,
+ "learning_rate": 0.0001181818181818182,
+ "loss": 0.8953,
"step": 576
},
{
- "epoch": 11.67,
- "learning_rate": 0.00012640306122448978,
- "loss": 1.3524,
+ "epoch": 6.52,
+ "learning_rate": 0.00011803977272727274,
+ "loss": 0.8686,
"step": 577
},
{
- "epoch": 11.7,
- "learning_rate": 0.00012627551020408164,
- "loss": 1.3481,
+ "epoch": 6.53,
+ "learning_rate": 0.00011789772727272727,
+ "loss": 0.8841,
"step": 578
},
{
- "epoch": 11.72,
- "learning_rate": 0.00012614795918367347,
- "loss": 1.4497,
+ "epoch": 6.54,
+ "learning_rate": 0.00011775568181818182,
+ "loss": 0.8681,
"step": 579
},
{
- "epoch": 11.74,
- "learning_rate": 0.0001260204081632653,
- "loss": 1.3866,
+ "epoch": 6.55,
+ "learning_rate": 0.00011761363636363636,
+ "loss": 0.8732,
"step": 580
},
{
- "epoch": 11.76,
- "learning_rate": 0.00012589285714285713,
- "loss": 1.42,
+ "epoch": 6.56,
+ "learning_rate": 0.00011747159090909092,
+ "loss": 0.8582,
"step": 581
},
{
- "epoch": 11.78,
- "learning_rate": 0.000125765306122449,
- "loss": 1.3562,
+ "epoch": 6.58,
+ "learning_rate": 0.00011732954545454546,
+ "loss": 0.8744,
"step": 582
},
{
- "epoch": 11.8,
- "learning_rate": 0.00012563775510204082,
- "loss": 1.3249,
+ "epoch": 6.59,
+ "learning_rate": 0.00011718750000000001,
+ "loss": 0.8694,
"step": 583
},
{
- "epoch": 11.82,
- "learning_rate": 0.00012551020408163265,
- "loss": 1.4277,
+ "epoch": 6.6,
+ "learning_rate": 0.00011704545454545454,
+ "loss": 0.8565,
"step": 584
},
{
- "epoch": 11.84,
- "learning_rate": 0.0001253826530612245,
- "loss": 1.3734,
+ "epoch": 6.61,
+ "learning_rate": 0.00011690340909090909,
+ "loss": 0.8584,
"step": 585
},
{
- "epoch": 11.86,
- "learning_rate": 0.00012525510204081634,
- "loss": 1.3765,
+ "epoch": 6.62,
+ "learning_rate": 0.00011676136363636366,
+ "loss": 0.8859,
"step": 586
},
{
- "epoch": 11.88,
- "learning_rate": 0.00012512755102040817,
- "loss": 1.4153,
+ "epoch": 6.63,
+ "learning_rate": 0.00011661931818181819,
+ "loss": 0.8452,
"step": 587
},
{
- "epoch": 11.9,
- "learning_rate": 0.000125,
- "loss": 1.3847,
+ "epoch": 6.64,
+ "learning_rate": 0.00011647727272727273,
+ "loss": 0.8323,
"step": 588
},
{
- "epoch": 11.92,
- "learning_rate": 0.00012487244897959186,
- "loss": 1.3824,
+ "epoch": 6.65,
+ "learning_rate": 0.00011633522727272728,
+ "loss": 0.8548,
"step": 589
},
{
- "epoch": 11.94,
- "learning_rate": 0.00012474489795918366,
- "loss": 1.3938,
+ "epoch": 6.67,
+ "learning_rate": 0.00011619318181818181,
+ "loss": 0.8506,
"step": 590
},
{
- "epoch": 11.96,
- "learning_rate": 0.00012461734693877552,
- "loss": 1.4143,
+ "epoch": 6.68,
+ "learning_rate": 0.00011605113636363636,
+ "loss": 0.8556,
"step": 591
},
{
- "epoch": 11.98,
- "learning_rate": 0.00012448979591836735,
- "loss": 1.3794,
+ "epoch": 6.69,
+ "learning_rate": 0.00011590909090909093,
+ "loss": 0.8459,
"step": 592
},
{
- "epoch": 12.0,
- "learning_rate": 0.00012436224489795918,
- "loss": 1.3755,
+ "epoch": 6.7,
+ "learning_rate": 0.00011576704545454546,
+ "loss": 0.8432,
"step": 593
},
{
- "epoch": 12.02,
- "learning_rate": 0.00012423469387755101,
- "loss": 1.3736,
+ "epoch": 6.71,
+ "learning_rate": 0.000115625,
+ "loss": 0.8645,
"step": 594
},
{
- "epoch": 12.04,
- "learning_rate": 0.00012410714285714287,
- "loss": 1.2957,
+ "epoch": 6.72,
+ "learning_rate": 0.00011548295454545455,
+ "loss": 0.86,
"step": 595
},
{
- "epoch": 12.06,
- "learning_rate": 0.0001239795918367347,
- "loss": 1.2996,
+ "epoch": 6.73,
+ "learning_rate": 0.00011534090909090908,
+ "loss": 0.8161,
"step": 596
},
{
- "epoch": 12.08,
- "learning_rate": 0.00012385204081632653,
- "loss": 1.3648,
+ "epoch": 6.74,
+ "learning_rate": 0.00011519886363636365,
+ "loss": 0.8133,
"step": 597
},
{
- "epoch": 12.1,
- "learning_rate": 0.00012372448979591837,
- "loss": 1.3031,
+ "epoch": 6.76,
+ "learning_rate": 0.0001150568181818182,
+ "loss": 0.8372,
"step": 598
},
{
- "epoch": 12.12,
- "learning_rate": 0.00012359693877551022,
- "loss": 1.2933,
+ "epoch": 6.77,
+ "learning_rate": 0.00011491477272727273,
+ "loss": 0.8222,
"step": 599
},
{
- "epoch": 12.14,
- "learning_rate": 0.00012346938775510203,
- "loss": 1.322,
+ "epoch": 6.78,
+ "learning_rate": 0.00011477272727272728,
+ "loss": 0.8372,
"step": 600
},
{
- "epoch": 12.16,
- "learning_rate": 0.00012334183673469389,
- "loss": 1.3123,
+ "epoch": 6.79,
+ "learning_rate": 0.00011463068181818182,
+ "loss": 0.837,
"step": 601
},
{
- "epoch": 12.18,
- "learning_rate": 0.00012321428571428572,
- "loss": 1.3187,
+ "epoch": 6.8,
+ "learning_rate": 0.00011448863636363637,
+ "loss": 0.8406,
"step": 602
},
{
- "epoch": 12.2,
- "learning_rate": 0.00012308673469387755,
- "loss": 1.3353,
+ "epoch": 6.81,
+ "learning_rate": 0.00011434659090909092,
+ "loss": 0.836,
"step": 603
},
{
- "epoch": 12.22,
- "learning_rate": 0.0001229591836734694,
- "loss": 1.3221,
+ "epoch": 6.82,
+ "learning_rate": 0.00011420454545454547,
+ "loss": 0.8476,
"step": 604
},
{
- "epoch": 12.24,
- "learning_rate": 0.00012283163265306124,
- "loss": 1.3458,
+ "epoch": 6.83,
+ "learning_rate": 0.0001140625,
+ "loss": 0.8368,
"step": 605
},
{
- "epoch": 12.26,
- "learning_rate": 0.00012270408163265307,
- "loss": 1.275,
+ "epoch": 6.85,
+ "learning_rate": 0.00011392045454545455,
+ "loss": 0.822,
"step": 606
},
{
- "epoch": 12.28,
- "learning_rate": 0.0001225765306122449,
- "loss": 1.3455,
+ "epoch": 6.86,
+ "learning_rate": 0.00011377840909090909,
+ "loss": 0.8107,
"step": 607
},
{
- "epoch": 12.3,
- "learning_rate": 0.00012244897959183676,
- "loss": 1.2769,
+ "epoch": 6.87,
+ "learning_rate": 0.00011363636363636365,
+ "loss": 0.8395,
"step": 608
},
{
- "epoch": 12.32,
- "learning_rate": 0.00012232142857142859,
- "loss": 1.3201,
+ "epoch": 6.88,
+ "learning_rate": 0.0001134943181818182,
+ "loss": 0.8083,
"step": 609
},
{
- "epoch": 12.34,
- "learning_rate": 0.00012219387755102042,
- "loss": 1.3073,
+ "epoch": 6.89,
+ "learning_rate": 0.00011335227272727274,
+ "loss": 0.828,
"step": 610
},
{
- "epoch": 12.36,
- "learning_rate": 0.00012206632653061225,
- "loss": 1.3103,
+ "epoch": 6.9,
+ "learning_rate": 0.00011321022727272727,
+ "loss": 0.8494,
"step": 611
},
{
- "epoch": 12.38,
- "learning_rate": 0.00012193877551020409,
- "loss": 1.4437,
+ "epoch": 6.91,
+ "learning_rate": 0.00011306818181818182,
+ "loss": 0.8169,
"step": 612
},
{
- "epoch": 12.4,
- "learning_rate": 0.00012181122448979591,
- "loss": 1.3086,
+ "epoch": 6.93,
+ "learning_rate": 0.00011292613636363636,
+ "loss": 0.8224,
"step": 613
},
{
- "epoch": 12.42,
- "learning_rate": 0.00012168367346938775,
- "loss": 1.3867,
+ "epoch": 6.94,
+ "learning_rate": 0.00011278409090909092,
+ "loss": 0.8173,
"step": 614
},
{
- "epoch": 12.44,
- "learning_rate": 0.0001215561224489796,
- "loss": 1.2565,
+ "epoch": 6.95,
+ "learning_rate": 0.00011264204545454547,
+ "loss": 0.7961,
"step": 615
},
{
- "epoch": 12.46,
- "learning_rate": 0.00012142857142857143,
- "loss": 1.335,
+ "epoch": 6.96,
+ "learning_rate": 0.00011250000000000001,
+ "loss": 0.7948,
"step": 616
},
{
- "epoch": 12.48,
- "learning_rate": 0.00012130102040816327,
- "loss": 1.3423,
+ "epoch": 6.97,
+ "learning_rate": 0.00011235795454545454,
+ "loss": 0.7746,
"step": 617
},
{
- "epoch": 12.5,
- "learning_rate": 0.00012117346938775512,
- "loss": 1.3433,
+ "epoch": 6.98,
+ "learning_rate": 0.00011221590909090909,
+ "loss": 0.8325,
"step": 618
},
{
- "epoch": 12.52,
- "learning_rate": 0.00012104591836734695,
- "loss": 1.3387,
+ "epoch": 6.99,
+ "learning_rate": 0.00011207386363636365,
+ "loss": 0.8149,
"step": 619
},
{
- "epoch": 12.55,
- "learning_rate": 0.00012091836734693878,
- "loss": 1.3923,
+ "epoch": 7.0,
+ "learning_rate": 0.00011193181818181819,
+ "loss": 0.7516,
"step": 620
},
{
- "epoch": 12.57,
- "learning_rate": 0.00012079081632653062,
- "loss": 1.3774,
+ "epoch": 7.02,
+ "learning_rate": 0.00011178977272727274,
+ "loss": 0.7571,
"step": 621
},
{
- "epoch": 12.59,
- "learning_rate": 0.00012066326530612247,
- "loss": 1.3203,
+ "epoch": 7.03,
+ "learning_rate": 0.00011164772727272728,
+ "loss": 0.7397,
"step": 622
},
{
- "epoch": 12.61,
- "learning_rate": 0.00012053571428571429,
- "loss": 1.2924,
+ "epoch": 7.04,
+ "learning_rate": 0.00011150568181818181,
+ "loss": 0.761,
"step": 623
},
{
- "epoch": 12.63,
- "learning_rate": 0.00012040816326530613,
- "loss": 1.3292,
+ "epoch": 7.05,
+ "learning_rate": 0.00011136363636363636,
+ "loss": 0.7783,
"step": 624
},
{
- "epoch": 12.65,
- "learning_rate": 0.00012028061224489798,
- "loss": 1.3161,
+ "epoch": 7.06,
+ "learning_rate": 0.00011122159090909092,
+ "loss": 0.7571,
"step": 625
},
{
- "epoch": 12.67,
- "learning_rate": 0.00012015306122448979,
- "loss": 1.352,
+ "epoch": 7.07,
+ "learning_rate": 0.00011107954545454546,
+ "loss": 0.7628,
"step": 626
},
{
- "epoch": 12.69,
- "learning_rate": 0.00012002551020408164,
- "loss": 1.3577,
+ "epoch": 7.08,
+ "learning_rate": 0.0001109375,
+ "loss": 0.7561,
"step": 627
},
{
- "epoch": 12.71,
- "learning_rate": 0.00011989795918367348,
- "loss": 1.3575,
+ "epoch": 7.09,
+ "learning_rate": 0.00011079545454545455,
+ "loss": 0.7432,
"step": 628
},
{
- "epoch": 12.73,
- "learning_rate": 0.0001197704081632653,
- "loss": 1.3727,
+ "epoch": 7.11,
+ "learning_rate": 0.00011065340909090908,
+ "loss": 0.7245,
"step": 629
},
{
- "epoch": 12.75,
- "learning_rate": 0.00011964285714285714,
- "loss": 1.3312,
+ "epoch": 7.12,
+ "learning_rate": 0.00011051136363636366,
+ "loss": 0.7279,
"step": 630
},
{
- "epoch": 12.77,
- "learning_rate": 0.00011951530612244899,
- "loss": 1.3378,
+ "epoch": 7.13,
+ "learning_rate": 0.00011036931818181819,
+ "loss": 0.7347,
"step": 631
},
{
- "epoch": 12.79,
- "learning_rate": 0.00011938775510204083,
- "loss": 1.295,
+ "epoch": 7.14,
+ "learning_rate": 0.00011022727272727273,
+ "loss": 0.7427,
"step": 632
},
{
- "epoch": 12.81,
- "learning_rate": 0.00011926020408163265,
- "loss": 1.3447,
+ "epoch": 7.15,
+ "learning_rate": 0.00011008522727272728,
+ "loss": 0.7339,
"step": 633
},
{
- "epoch": 12.83,
- "learning_rate": 0.0001191326530612245,
- "loss": 1.3835,
+ "epoch": 7.16,
+ "learning_rate": 0.00010994318181818182,
+ "loss": 0.7375,
"step": 634
},
{
- "epoch": 12.85,
- "learning_rate": 0.00011900510204081634,
- "loss": 1.3222,
+ "epoch": 7.17,
+ "learning_rate": 0.00010980113636363635,
+ "loss": 0.7182,
"step": 635
},
{
- "epoch": 12.87,
- "learning_rate": 0.00011887755102040817,
- "loss": 1.2851,
+ "epoch": 7.19,
+ "learning_rate": 0.00010965909090909093,
+ "loss": 0.7452,
"step": 636
},
{
- "epoch": 12.89,
- "learning_rate": 0.00011875,
- "loss": 1.2723,
+ "epoch": 7.2,
+ "learning_rate": 0.00010951704545454546,
+ "loss": 0.7565,
"step": 637
},
{
- "epoch": 12.91,
- "learning_rate": 0.00011862244897959184,
- "loss": 1.3924,
+ "epoch": 7.21,
+ "learning_rate": 0.000109375,
+ "loss": 0.7296,
"step": 638
},
{
- "epoch": 12.93,
- "learning_rate": 0.00011849489795918368,
- "loss": 1.4625,
+ "epoch": 7.22,
+ "learning_rate": 0.00010923295454545455,
+ "loss": 0.7484,
"step": 639
},
{
- "epoch": 12.95,
- "learning_rate": 0.00011836734693877552,
- "loss": 1.3245,
+ "epoch": 7.23,
+ "learning_rate": 0.00010909090909090909,
+ "loss": 0.732,
"step": 640
},
{
- "epoch": 12.97,
- "learning_rate": 0.00011823979591836736,
- "loss": 1.4042,
+ "epoch": 7.24,
+ "learning_rate": 0.00010894886363636365,
+ "loss": 0.7415,
"step": 641
},
{
- "epoch": 12.99,
- "learning_rate": 0.00011811224489795918,
- "loss": 1.3761,
+ "epoch": 7.25,
+ "learning_rate": 0.0001088068181818182,
+ "loss": 0.7344,
"step": 642
},
{
- "epoch": 13.01,
- "learning_rate": 0.00011798469387755103,
- "loss": 1.3376,
+ "epoch": 7.26,
+ "learning_rate": 0.00010866477272727274,
+ "loss": 0.7267,
"step": 643
},
{
- "epoch": 13.03,
- "learning_rate": 0.00011785714285714287,
- "loss": 1.2174,
+ "epoch": 7.28,
+ "learning_rate": 0.00010852272727272727,
+ "loss": 0.7543,
"step": 644
},
{
- "epoch": 13.05,
- "learning_rate": 0.00011772959183673471,
- "loss": 1.3602,
+ "epoch": 7.29,
+ "learning_rate": 0.00010838068181818182,
+ "loss": 0.7266,
"step": 645
},
{
- "epoch": 13.07,
- "learning_rate": 0.00011760204081632653,
- "loss": 1.3002,
+ "epoch": 7.3,
+ "learning_rate": 0.00010823863636363636,
+ "loss": 0.7449,
"step": 646
},
{
- "epoch": 13.09,
- "learning_rate": 0.00011747448979591838,
- "loss": 1.2262,
+ "epoch": 7.31,
+ "learning_rate": 0.00010809659090909092,
+ "loss": 0.7324,
"step": 647
},
{
- "epoch": 13.11,
- "learning_rate": 0.00011734693877551022,
- "loss": 1.3048,
+ "epoch": 7.32,
+ "learning_rate": 0.00010795454545454547,
+ "loss": 0.7268,
"step": 648
},
{
- "epoch": 13.13,
- "learning_rate": 0.00011721938775510204,
- "loss": 1.2231,
+ "epoch": 7.33,
+ "learning_rate": 0.00010781250000000001,
+ "loss": 0.7172,
"step": 649
},
{
- "epoch": 13.15,
- "learning_rate": 0.00011709183673469388,
- "loss": 1.2996,
+ "epoch": 7.34,
+ "learning_rate": 0.00010767045454545454,
+ "loss": 0.7169,
"step": 650
},
{
- "epoch": 13.17,
- "learning_rate": 0.00011696428571428573,
- "loss": 1.2708,
+ "epoch": 7.35,
+ "learning_rate": 0.00010752840909090909,
+ "loss": 0.7194,
"step": 651
},
{
- "epoch": 13.19,
- "learning_rate": 0.00011683673469387754,
- "loss": 1.2776,
+ "epoch": 7.37,
+ "learning_rate": 0.00010738636363636365,
+ "loss": 0.7223,
"step": 652
},
{
- "epoch": 13.21,
- "learning_rate": 0.00011670918367346939,
- "loss": 1.248,
+ "epoch": 7.38,
+ "learning_rate": 0.00010724431818181819,
+ "loss": 0.7158,
"step": 653
},
{
- "epoch": 13.23,
- "learning_rate": 0.00011658163265306123,
- "loss": 1.2582,
+ "epoch": 7.39,
+ "learning_rate": 0.00010710227272727274,
+ "loss": 0.7122,
"step": 654
},
{
- "epoch": 13.25,
- "learning_rate": 0.00011645408163265305,
- "loss": 1.3011,
+ "epoch": 7.4,
+ "learning_rate": 0.00010696022727272728,
+ "loss": 0.7225,
"step": 655
},
{
- "epoch": 13.27,
- "learning_rate": 0.0001163265306122449,
- "loss": 1.2969,
+ "epoch": 7.41,
+ "learning_rate": 0.00010681818181818181,
+ "loss": 0.7102,
"step": 656
},
{
- "epoch": 13.29,
- "learning_rate": 0.00011619897959183674,
- "loss": 1.2454,
+ "epoch": 7.42,
+ "learning_rate": 0.00010667613636363636,
+ "loss": 0.7251,
"step": 657
},
{
- "epoch": 13.31,
- "learning_rate": 0.00011607142857142858,
- "loss": 1.1914,
+ "epoch": 7.43,
+ "learning_rate": 0.00010653409090909092,
+ "loss": 0.7191,
"step": 658
},
{
- "epoch": 13.33,
- "learning_rate": 0.00011594387755102041,
- "loss": 1.34,
+ "epoch": 7.45,
+ "learning_rate": 0.00010639204545454546,
+ "loss": 0.7015,
"step": 659
},
{
- "epoch": 13.35,
- "learning_rate": 0.00011581632653061225,
- "loss": 1.2828,
+ "epoch": 7.46,
+ "learning_rate": 0.00010625000000000001,
+ "loss": 0.693,
"step": 660
},
{
- "epoch": 13.37,
- "learning_rate": 0.00011568877551020409,
- "loss": 1.2962,
+ "epoch": 7.47,
+ "learning_rate": 0.00010610795454545455,
+ "loss": 0.7039,
"step": 661
},
{
- "epoch": 13.39,
- "learning_rate": 0.00011556122448979592,
- "loss": 1.3334,
+ "epoch": 7.48,
+ "learning_rate": 0.00010596590909090908,
+ "loss": 0.7305,
"step": 662
},
{
- "epoch": 13.42,
- "learning_rate": 0.00011543367346938776,
- "loss": 1.2832,
+ "epoch": 7.49,
+ "learning_rate": 0.00010582386363636366,
+ "loss": 0.6978,
"step": 663
},
{
- "epoch": 13.44,
- "learning_rate": 0.00011530612244897961,
- "loss": 1.3012,
+ "epoch": 7.5,
+ "learning_rate": 0.00010568181818181819,
+ "loss": 0.7219,
"step": 664
},
{
- "epoch": 13.46,
- "learning_rate": 0.00011517857142857143,
- "loss": 1.2857,
+ "epoch": 7.51,
+ "learning_rate": 0.00010553977272727273,
+ "loss": 0.7199,
"step": 665
},
{
- "epoch": 13.48,
- "learning_rate": 0.00011505102040816327,
- "loss": 1.2855,
+ "epoch": 7.52,
+ "learning_rate": 0.00010539772727272728,
+ "loss": 0.6979,
"step": 666
},
{
- "epoch": 13.5,
- "learning_rate": 0.00011492346938775512,
- "loss": 1.3077,
+ "epoch": 7.54,
+ "learning_rate": 0.00010525568181818182,
+ "loss": 0.7058,
"step": 667
},
{
- "epoch": 13.52,
- "learning_rate": 0.00011479591836734696,
- "loss": 1.3139,
+ "epoch": 7.55,
+ "learning_rate": 0.00010511363636363635,
+ "loss": 0.6994,
"step": 668
},
{
- "epoch": 13.54,
- "learning_rate": 0.00011466836734693878,
- "loss": 1.3138,
+ "epoch": 7.56,
+ "learning_rate": 0.00010497159090909093,
+ "loss": 0.7141,
"step": 669
},
{
- "epoch": 13.56,
- "learning_rate": 0.00011454081632653062,
- "loss": 1.2808,
+ "epoch": 7.57,
+ "learning_rate": 0.00010482954545454546,
+ "loss": 0.7092,
"step": 670
},
{
- "epoch": 13.58,
- "learning_rate": 0.00011441326530612247,
- "loss": 1.2492,
+ "epoch": 7.58,
+ "learning_rate": 0.0001046875,
+ "loss": 0.7059,
"step": 671
},
{
- "epoch": 13.6,
- "learning_rate": 0.00011428571428571428,
- "loss": 1.2027,
+ "epoch": 7.59,
+ "learning_rate": 0.00010454545454545455,
+ "loss": 0.6904,
"step": 672
},
{
- "epoch": 13.62,
- "learning_rate": 0.00011415816326530613,
- "loss": 1.33,
+ "epoch": 7.6,
+ "learning_rate": 0.0001044034090909091,
+ "loss": 0.7115,
"step": 673
},
{
- "epoch": 13.64,
- "learning_rate": 0.00011403061224489797,
- "loss": 1.3112,
+ "epoch": 7.61,
+ "learning_rate": 0.00010426136363636365,
+ "loss": 0.7254,
"step": 674
},
{
- "epoch": 13.66,
- "learning_rate": 0.00011390306122448979,
- "loss": 1.2772,
+ "epoch": 7.63,
+ "learning_rate": 0.0001041193181818182,
+ "loss": 0.7181,
"step": 675
},
{
- "epoch": 13.68,
- "learning_rate": 0.00011377551020408163,
- "loss": 1.2701,
+ "epoch": 7.64,
+ "learning_rate": 0.00010397727272727273,
+ "loss": 0.6867,
"step": 676
},
{
- "epoch": 13.7,
- "learning_rate": 0.00011364795918367348,
- "loss": 1.1973,
+ "epoch": 7.65,
+ "learning_rate": 0.00010383522727272727,
+ "loss": 0.6917,
"step": 677
},
{
- "epoch": 13.72,
- "learning_rate": 0.0001135204081632653,
- "loss": 1.3124,
+ "epoch": 7.66,
+ "learning_rate": 0.00010369318181818182,
+ "loss": 0.6908,
"step": 678
},
{
- "epoch": 13.74,
- "learning_rate": 0.00011339285714285714,
- "loss": 1.3085,
+ "epoch": 7.67,
+ "learning_rate": 0.00010355113636363636,
+ "loss": 0.6871,
"step": 679
},
{
- "epoch": 13.76,
- "learning_rate": 0.00011326530612244898,
- "loss": 1.3457,
+ "epoch": 7.68,
+ "learning_rate": 0.00010340909090909092,
+ "loss": 0.682,
"step": 680
},
{
- "epoch": 13.78,
- "learning_rate": 0.00011313775510204083,
- "loss": 1.3338,
+ "epoch": 7.69,
+ "learning_rate": 0.00010326704545454547,
+ "loss": 0.6737,
"step": 681
},
{
- "epoch": 13.8,
- "learning_rate": 0.00011301020408163266,
- "loss": 1.2753,
+ "epoch": 7.7,
+ "learning_rate": 0.000103125,
+ "loss": 0.7023,
"step": 682
},
{
- "epoch": 13.82,
- "learning_rate": 0.00011288265306122449,
- "loss": 1.2786,
+ "epoch": 7.72,
+ "learning_rate": 0.00010298295454545454,
+ "loss": 0.7079,
"step": 683
},
{
- "epoch": 13.84,
- "learning_rate": 0.00011275510204081634,
- "loss": 1.2584,
+ "epoch": 7.73,
+ "learning_rate": 0.00010284090909090909,
+ "loss": 0.6954,
"step": 684
},
{
- "epoch": 13.86,
- "learning_rate": 0.00011262755102040817,
- "loss": 1.2779,
+ "epoch": 7.74,
+ "learning_rate": 0.00010269886363636365,
+ "loss": 0.6834,
"step": 685
},
{
- "epoch": 13.88,
- "learning_rate": 0.00011250000000000001,
- "loss": 1.3502,
+ "epoch": 7.75,
+ "learning_rate": 0.0001025568181818182,
+ "loss": 0.6706,
"step": 686
},
{
- "epoch": 13.9,
- "learning_rate": 0.00011237244897959185,
- "loss": 1.3251,
+ "epoch": 7.76,
+ "learning_rate": 0.00010241477272727274,
+ "loss": 0.6706,
"step": 687
},
{
- "epoch": 13.92,
- "learning_rate": 0.00011224489795918367,
- "loss": 1.273,
+ "epoch": 7.77,
+ "learning_rate": 0.00010227272727272727,
+ "loss": 0.681,
"step": 688
},
{
- "epoch": 13.94,
- "learning_rate": 0.00011211734693877552,
- "loss": 1.3341,
+ "epoch": 7.78,
+ "learning_rate": 0.00010213068181818182,
+ "loss": 0.6853,
"step": 689
},
{
- "epoch": 13.96,
- "learning_rate": 0.00011198979591836736,
- "loss": 1.2654,
+ "epoch": 7.8,
+ "learning_rate": 0.00010198863636363636,
+ "loss": 0.6772,
"step": 690
},
{
- "epoch": 13.98,
- "learning_rate": 0.00011186224489795918,
- "loss": 1.3333,
+ "epoch": 7.81,
+ "learning_rate": 0.00010184659090909092,
+ "loss": 0.6635,
"step": 691
},
{
- "epoch": 14.0,
- "learning_rate": 0.00011173469387755102,
- "loss": 1.3246,
+ "epoch": 7.82,
+ "learning_rate": 0.00010170454545454546,
+ "loss": 0.6712,
"step": 692
},
{
- "epoch": 14.02,
- "learning_rate": 0.00011160714285714287,
- "loss": 1.2547,
+ "epoch": 7.83,
+ "learning_rate": 0.00010156250000000001,
+ "loss": 0.6884,
"step": 693
},
{
- "epoch": 14.04,
- "learning_rate": 0.00011147959183673471,
- "loss": 1.208,
+ "epoch": 7.84,
+ "learning_rate": 0.00010142045454545454,
+ "loss": 0.6641,
"step": 694
},
{
- "epoch": 14.06,
- "learning_rate": 0.00011135204081632653,
- "loss": 1.223,
+ "epoch": 7.85,
+ "learning_rate": 0.00010127840909090909,
+ "loss": 0.6838,
"step": 695
},
{
- "epoch": 14.08,
- "learning_rate": 0.00011122448979591837,
- "loss": 1.2483,
+ "epoch": 7.86,
+ "learning_rate": 0.00010113636363636366,
+ "loss": 0.675,
"step": 696
},
{
- "epoch": 14.1,
- "learning_rate": 0.00011109693877551022,
- "loss": 1.2823,
+ "epoch": 7.87,
+ "learning_rate": 0.00010099431818181819,
+ "loss": 0.6626,
"step": 697
},
{
- "epoch": 14.12,
- "learning_rate": 0.00011096938775510204,
- "loss": 1.2013,
+ "epoch": 7.89,
+ "learning_rate": 0.00010085227272727273,
+ "loss": 0.6605,
"step": 698
},
{
- "epoch": 14.14,
- "learning_rate": 0.00011084183673469388,
- "loss": 1.1883,
+ "epoch": 7.9,
+ "learning_rate": 0.00010071022727272728,
+ "loss": 0.6777,
"step": 699
},
{
- "epoch": 14.16,
- "learning_rate": 0.00011071428571428572,
- "loss": 1.2364,
+ "epoch": 7.91,
+ "learning_rate": 0.00010056818181818181,
+ "loss": 0.6347,
"step": 700
}
],
"logging_steps": 1,
- "max_steps": 1568,
- "num_train_epochs": 32,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
"save_steps": 100,
- "total_flos": 1.0356683330832384e+18,
+ "total_flos": 9.550264840009421e+17,
"trial_name": null,
"trial_params": null
}
diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin
index db23e07d097c18532e52f58a70eb72d22e39c8c1..ee7ddb867f05d9a969f71467a8eb88994865cf51 100644
--- a/checkpoint-700/training_args.bin
+++ b/checkpoint-700/training_args.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
size 4155
diff --git a/checkpoint-800/adapter_model.bin b/checkpoint-800/adapter_model.bin
index cee32efffd1b20413bbd86ddf1c6b5e172aff0ad..5e2cf0fd2fd7c18345726dfa575faed0d4840e70 100644
--- a/checkpoint-800/adapter_model.bin
+++ b/checkpoint-800/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:f1d0c9cf78a0287e75a067e9f589df56d88beac420ee2db9171f4dc9525fa2ca
+oid sha256:c96e945f63003849e24de01bb42bf53589067a6378304f2f2bdbc259148446f7
size 39409357
diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt
index b0d866f2df62fc478638a4259af93b239d1fe68d..d5c1d7d0df396b867ae4aad1ef5aaa141aa5f1b7 100644
--- a/checkpoint-800/optimizer.pt
+++ b/checkpoint-800/optimizer.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:07dbe2f482aa556941cc3c2c9287c9031960f1c986eb88f6af216069cf2f4eca
+oid sha256:37fa9f63942fee0e6bc2badebc69bd612f8a781c402497c088b4a2e4afca1e2f
size 78844421
diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth
index b879e8b3e27b533241ce1d1d17eb9d40184e6556..929acb13fd6e1d91a9fa525251307f2db4c55db6 100644
--- a/checkpoint-800/rng_state.pth
+++ b/checkpoint-800/rng_state.pth
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:ef5771dabc82868bc27d459c4a2a8532048b4914b817944e763d47579f3a8c81
+oid sha256:f0e0f30c7754637247f97149558697a4932915f961818f7360cfc62855116ca0
size 14575
diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt
index 472e441060b50c337f61e375e95c2d2202b3a99c..6ee10a9418fae9c93ed2ba1e1917c1f7886e9427 100644
--- a/checkpoint-800/scheduler.pt
+++ b/checkpoint-800/scheduler.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:eb093730edb340d1b1812e0604570255eef4ca2d6126dada512bcd3e775c93af
+oid sha256:df029c6d7c683e322312c658d0b6a0e5e9499bad68e681717b9bb9d001e67907
size 627
diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json
index 23776a4314c0fade06a35f724e76e246d7aa5dc8..748471aa026988124683f3b8b7ebd368407dc1cf 100644
--- a/checkpoint-800/trainer_state.json
+++ b/checkpoint-800/trainer_state.json
@@ -1,7 +1,7 @@
{
"best_metric": null,
"best_model_checkpoint": null,
- "epoch": 16.187164084729687,
+ "epoch": 9.037952338923212,
"eval_steps": 500,
"global_step": 800,
"is_hyper_param_search": false,
@@ -9,4811 +9,4811 @@
"is_world_process_zero": true,
"log_history": [
{
- "epoch": 0.02,
- "learning_rate": 0.00019987244897959184,
- "loss": 3.2215,
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
"step": 1
},
{
- "epoch": 0.04,
- "learning_rate": 0.00019974489795918367,
- "loss": 2.8365,
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
"step": 2
},
{
- "epoch": 0.06,
- "learning_rate": 0.00019961734693877553,
- "loss": 2.602,
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
"step": 3
},
{
- "epoch": 0.08,
- "learning_rate": 0.00019948979591836736,
- "loss": 2.4196,
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
"step": 4
},
{
- "epoch": 0.1,
- "learning_rate": 0.0001993622448979592,
- "loss": 2.2574,
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
"step": 5
},
{
- "epoch": 0.12,
- "learning_rate": 0.00019923469387755102,
- "loss": 2.2239,
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
"step": 6
},
{
- "epoch": 0.14,
- "learning_rate": 0.00019910714285714288,
- "loss": 2.1661,
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
"step": 7
},
{
- "epoch": 0.16,
- "learning_rate": 0.0001989795918367347,
- "loss": 2.0987,
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
"step": 8
},
{
- "epoch": 0.18,
- "learning_rate": 0.00019885204081632654,
- "loss": 2.015,
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
"step": 9
},
{
- "epoch": 0.2,
- "learning_rate": 0.00019872448979591837,
- "loss": 1.9771,
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
"step": 10
},
{
- "epoch": 0.22,
- "learning_rate": 0.00019859693877551023,
- "loss": 2.0271,
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
"step": 11
},
{
- "epoch": 0.24,
- "learning_rate": 0.00019846938775510203,
- "loss": 1.9812,
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
"step": 12
},
{
- "epoch": 0.26,
- "learning_rate": 0.0001983418367346939,
- "loss": 2.0834,
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
"step": 13
},
{
- "epoch": 0.28,
- "learning_rate": 0.00019821428571428572,
- "loss": 1.9174,
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
"step": 14
},
{
- "epoch": 0.3,
- "learning_rate": 0.00019808673469387755,
- "loss": 1.8409,
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
"step": 15
},
{
- "epoch": 0.32,
- "learning_rate": 0.00019795918367346938,
- "loss": 1.929,
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
"step": 16
},
{
- "epoch": 0.34,
- "learning_rate": 0.00019783163265306124,
- "loss": 2.0041,
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
"step": 17
},
{
- "epoch": 0.36,
- "learning_rate": 0.00019770408163265305,
- "loss": 1.9385,
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
"step": 18
},
{
- "epoch": 0.38,
- "learning_rate": 0.0001975765306122449,
- "loss": 1.9592,
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
"step": 19
},
{
- "epoch": 0.4,
- "learning_rate": 0.00019744897959183674,
- "loss": 1.9701,
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
"step": 20
},
{
- "epoch": 0.42,
- "learning_rate": 0.0001973214285714286,
- "loss": 1.9277,
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
"step": 21
},
{
- "epoch": 0.45,
- "learning_rate": 0.00019719387755102042,
- "loss": 1.8394,
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
"step": 22
},
{
- "epoch": 0.47,
- "learning_rate": 0.00019706632653061226,
- "loss": 1.8666,
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
"step": 23
},
{
- "epoch": 0.49,
- "learning_rate": 0.00019693877551020409,
- "loss": 1.8997,
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
"step": 24
},
{
- "epoch": 0.51,
- "learning_rate": 0.00019681122448979592,
- "loss": 1.9432,
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
"step": 25
},
{
- "epoch": 0.53,
- "learning_rate": 0.00019668367346938777,
- "loss": 1.9137,
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
"step": 26
},
{
- "epoch": 0.55,
- "learning_rate": 0.0001965561224489796,
- "loss": 1.905,
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
"step": 27
},
{
- "epoch": 0.57,
- "learning_rate": 0.00019642857142857144,
- "loss": 1.8708,
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
"step": 28
},
{
- "epoch": 0.59,
- "learning_rate": 0.00019630102040816327,
- "loss": 1.9097,
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
"step": 29
},
{
- "epoch": 0.61,
- "learning_rate": 0.00019617346938775513,
- "loss": 1.896,
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
"step": 30
},
{
- "epoch": 0.63,
- "learning_rate": 0.00019604591836734696,
- "loss": 1.8834,
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
"step": 31
},
{
- "epoch": 0.65,
- "learning_rate": 0.0001959183673469388,
- "loss": 1.8323,
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
"step": 32
},
{
- "epoch": 0.67,
- "learning_rate": 0.00019579081632653062,
- "loss": 1.804,
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
"step": 33
},
{
- "epoch": 0.69,
- "learning_rate": 0.00019566326530612248,
- "loss": 1.8906,
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
"step": 34
},
{
- "epoch": 0.71,
- "learning_rate": 0.00019553571428571428,
- "loss": 1.8693,
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
"step": 35
},
{
- "epoch": 0.73,
- "learning_rate": 0.00019540816326530614,
- "loss": 1.9308,
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
"step": 36
},
{
- "epoch": 0.75,
- "learning_rate": 0.00019528061224489797,
- "loss": 1.8082,
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
"step": 37
},
{
- "epoch": 0.77,
- "learning_rate": 0.0001951530612244898,
- "loss": 1.848,
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
"step": 38
},
{
- "epoch": 0.79,
- "learning_rate": 0.00019502551020408163,
- "loss": 1.8866,
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
"step": 39
},
{
- "epoch": 0.81,
- "learning_rate": 0.0001948979591836735,
- "loss": 1.7844,
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
"step": 40
},
{
- "epoch": 0.83,
- "learning_rate": 0.0001947704081632653,
- "loss": 1.8485,
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
"step": 41
},
{
- "epoch": 0.85,
- "learning_rate": 0.00019464285714285715,
- "loss": 1.7917,
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
"step": 42
},
{
- "epoch": 0.87,
- "learning_rate": 0.00019451530612244898,
- "loss": 1.7342,
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
"step": 43
},
{
- "epoch": 0.89,
- "learning_rate": 0.00019438775510204084,
- "loss": 1.8479,
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
"step": 44
},
{
- "epoch": 0.91,
- "learning_rate": 0.00019426020408163267,
- "loss": 1.8639,
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
"step": 45
},
{
- "epoch": 0.93,
- "learning_rate": 0.0001941326530612245,
- "loss": 1.8166,
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
"step": 46
},
{
- "epoch": 0.95,
- "learning_rate": 0.00019400510204081633,
- "loss": 1.7566,
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
"step": 47
},
{
- "epoch": 0.97,
- "learning_rate": 0.00019387755102040816,
- "loss": 1.8071,
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
"step": 48
},
{
- "epoch": 0.99,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.8612,
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
"step": 49
},
{
- "epoch": 1.01,
- "learning_rate": 0.00019362244897959185,
- "loss": 1.7819,
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
"step": 50
},
{
- "epoch": 1.03,
- "learning_rate": 0.00019349489795918368,
- "loss": 1.8647,
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
"step": 51
},
{
- "epoch": 1.05,
- "learning_rate": 0.0001933673469387755,
- "loss": 1.8196,
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
"step": 52
},
{
- "epoch": 1.07,
- "learning_rate": 0.00019323979591836737,
- "loss": 1.8027,
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
"step": 53
},
{
- "epoch": 1.09,
- "learning_rate": 0.00019311224489795917,
- "loss": 1.8927,
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
"step": 54
},
{
- "epoch": 1.11,
- "learning_rate": 0.00019298469387755103,
- "loss": 1.8481,
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
"step": 55
},
{
- "epoch": 1.13,
- "learning_rate": 0.00019285714285714286,
- "loss": 1.7781,
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
"step": 56
},
{
- "epoch": 1.15,
- "learning_rate": 0.00019272959183673472,
- "loss": 1.8101,
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
"step": 57
},
{
- "epoch": 1.17,
- "learning_rate": 0.00019260204081632653,
- "loss": 1.7257,
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
"step": 58
},
{
- "epoch": 1.19,
- "learning_rate": 0.00019247448979591838,
- "loss": 1.8185,
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
"step": 59
},
{
- "epoch": 1.21,
- "learning_rate": 0.00019234693877551021,
- "loss": 1.8557,
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
"step": 60
},
{
- "epoch": 1.23,
- "learning_rate": 0.00019221938775510204,
- "loss": 1.7418,
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
"step": 61
},
{
- "epoch": 1.25,
- "learning_rate": 0.00019209183673469388,
- "loss": 1.6879,
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
"step": 62
},
{
- "epoch": 1.27,
- "learning_rate": 0.00019196428571428573,
- "loss": 1.7651,
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
"step": 63
},
{
- "epoch": 1.29,
- "learning_rate": 0.00019183673469387756,
- "loss": 1.7759,
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
"step": 64
},
{
- "epoch": 1.32,
- "learning_rate": 0.0001917091836734694,
- "loss": 1.7691,
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
"step": 65
},
{
- "epoch": 1.34,
- "learning_rate": 0.00019158163265306123,
- "loss": 1.7794,
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
"step": 66
},
{
- "epoch": 1.36,
- "learning_rate": 0.00019145408163265306,
- "loss": 1.8152,
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
"step": 67
},
{
- "epoch": 1.38,
- "learning_rate": 0.00019132653061224492,
- "loss": 1.8052,
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
"step": 68
},
{
- "epoch": 1.4,
- "learning_rate": 0.00019119897959183675,
- "loss": 1.8054,
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
"step": 69
},
{
- "epoch": 1.42,
- "learning_rate": 0.00019107142857142858,
- "loss": 1.8114,
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
"step": 70
},
{
- "epoch": 1.44,
- "learning_rate": 0.0001909438775510204,
- "loss": 1.7749,
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
"step": 71
},
{
- "epoch": 1.46,
- "learning_rate": 0.00019081632653061227,
- "loss": 1.777,
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
"step": 72
},
{
- "epoch": 1.48,
- "learning_rate": 0.0001906887755102041,
- "loss": 1.7896,
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
"step": 73
},
{
- "epoch": 1.5,
- "learning_rate": 0.00019056122448979593,
- "loss": 1.8335,
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
"step": 74
},
{
- "epoch": 1.52,
- "learning_rate": 0.00019043367346938776,
- "loss": 1.8155,
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
"step": 75
},
{
- "epoch": 1.54,
- "learning_rate": 0.00019030612244897962,
- "loss": 1.8224,
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
"step": 76
},
{
- "epoch": 1.56,
- "learning_rate": 0.00019017857142857142,
- "loss": 1.7889,
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
"step": 77
},
{
- "epoch": 1.58,
- "learning_rate": 0.00019005102040816328,
- "loss": 1.8866,
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
"step": 78
},
{
- "epoch": 1.6,
- "learning_rate": 0.0001899234693877551,
- "loss": 1.8439,
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
"step": 79
},
{
- "epoch": 1.62,
- "learning_rate": 0.00018979591836734697,
- "loss": 1.7906,
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
"step": 80
},
{
- "epoch": 1.64,
- "learning_rate": 0.00018966836734693877,
- "loss": 1.8627,
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
"step": 81
},
{
- "epoch": 1.66,
- "learning_rate": 0.00018954081632653063,
- "loss": 1.7497,
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
"step": 82
},
{
- "epoch": 1.68,
- "learning_rate": 0.00018941326530612246,
- "loss": 1.7936,
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
"step": 83
},
{
- "epoch": 1.7,
- "learning_rate": 0.0001892857142857143,
- "loss": 1.8341,
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
"step": 84
},
{
- "epoch": 1.72,
- "learning_rate": 0.00018915816326530612,
- "loss": 1.7868,
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
"step": 85
},
{
- "epoch": 1.74,
- "learning_rate": 0.00018903061224489798,
- "loss": 1.7493,
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
"step": 86
},
{
- "epoch": 1.76,
- "learning_rate": 0.0001889030612244898,
- "loss": 1.7926,
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
"step": 87
},
{
- "epoch": 1.78,
- "learning_rate": 0.00018877551020408164,
- "loss": 1.8278,
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
"step": 88
},
{
- "epoch": 1.8,
- "learning_rate": 0.00018864795918367347,
- "loss": 1.7387,
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
"step": 89
},
{
- "epoch": 1.82,
- "learning_rate": 0.0001885204081632653,
- "loss": 1.7669,
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
"step": 90
},
{
- "epoch": 1.84,
- "learning_rate": 0.00018839285714285716,
- "loss": 1.7686,
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
"step": 91
},
{
- "epoch": 1.86,
- "learning_rate": 0.000188265306122449,
- "loss": 1.7759,
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
"step": 92
},
{
- "epoch": 1.88,
- "learning_rate": 0.00018813775510204082,
- "loss": 1.7016,
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
"step": 93
},
{
- "epoch": 1.9,
- "learning_rate": 0.00018801020408163265,
- "loss": 1.8123,
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
"step": 94
},
{
- "epoch": 1.92,
- "learning_rate": 0.0001878826530612245,
- "loss": 1.8315,
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
"step": 95
},
{
- "epoch": 1.94,
- "learning_rate": 0.00018775510204081634,
- "loss": 1.7679,
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
"step": 96
},
{
- "epoch": 1.96,
- "learning_rate": 0.00018762755102040817,
- "loss": 1.7874,
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
"step": 97
},
{
- "epoch": 1.98,
- "learning_rate": 0.0001875,
- "loss": 1.8008,
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
"step": 98
},
{
- "epoch": 2.0,
- "learning_rate": 0.00018737244897959186,
- "loss": 1.7177,
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
"step": 99
},
{
- "epoch": 2.02,
- "learning_rate": 0.00018724489795918367,
- "loss": 1.7272,
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
"step": 100
},
{
- "epoch": 2.04,
- "learning_rate": 0.00018711734693877552,
- "loss": 1.7848,
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
"step": 101
},
{
- "epoch": 2.06,
- "learning_rate": 0.00018698979591836735,
- "loss": 1.744,
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
"step": 102
},
{
- "epoch": 2.08,
- "learning_rate": 0.00018686224489795919,
- "loss": 1.7005,
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
"step": 103
},
{
- "epoch": 2.1,
- "learning_rate": 0.00018673469387755102,
- "loss": 1.8247,
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
"step": 104
},
{
- "epoch": 2.12,
- "learning_rate": 0.00018660714285714287,
- "loss": 1.6855,
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
"step": 105
},
{
- "epoch": 2.14,
- "learning_rate": 0.0001864795918367347,
- "loss": 1.7627,
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
"step": 106
},
{
- "epoch": 2.17,
- "learning_rate": 0.00018635204081632654,
- "loss": 1.7564,
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
"step": 107
},
{
- "epoch": 2.19,
- "learning_rate": 0.00018622448979591837,
- "loss": 1.8237,
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
"step": 108
},
{
- "epoch": 2.21,
- "learning_rate": 0.00018609693877551022,
- "loss": 1.7421,
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
"step": 109
},
{
- "epoch": 2.23,
- "learning_rate": 0.00018596938775510206,
- "loss": 1.7517,
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
"step": 110
},
{
- "epoch": 2.25,
- "learning_rate": 0.0001858418367346939,
- "loss": 1.7515,
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
"step": 111
},
{
- "epoch": 2.27,
- "learning_rate": 0.00018571428571428572,
- "loss": 1.7842,
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
"step": 112
},
{
- "epoch": 2.29,
- "learning_rate": 0.00018558673469387755,
- "loss": 1.8001,
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
"step": 113
},
{
- "epoch": 2.31,
- "learning_rate": 0.0001854591836734694,
- "loss": 1.7653,
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
"step": 114
},
{
- "epoch": 2.33,
- "learning_rate": 0.00018533163265306124,
- "loss": 1.694,
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
"step": 115
},
{
- "epoch": 2.35,
- "learning_rate": 0.00018520408163265307,
- "loss": 1.7457,
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
"step": 116
},
{
- "epoch": 2.37,
- "learning_rate": 0.0001850765306122449,
- "loss": 1.7899,
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
"step": 117
},
{
- "epoch": 2.39,
- "learning_rate": 0.00018494897959183676,
- "loss": 1.7473,
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
"step": 118
},
{
- "epoch": 2.41,
- "learning_rate": 0.0001848214285714286,
- "loss": 1.6639,
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
"step": 119
},
{
- "epoch": 2.43,
- "learning_rate": 0.00018469387755102042,
- "loss": 1.762,
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
"step": 120
},
{
- "epoch": 2.45,
- "learning_rate": 0.00018456632653061225,
- "loss": 1.7378,
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
"step": 121
},
{
- "epoch": 2.47,
- "learning_rate": 0.0001844387755102041,
- "loss": 1.672,
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
"step": 122
},
{
- "epoch": 2.49,
- "learning_rate": 0.0001843112244897959,
- "loss": 1.7267,
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
"step": 123
},
{
- "epoch": 2.51,
- "learning_rate": 0.00018418367346938777,
- "loss": 1.7825,
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
"step": 124
},
{
- "epoch": 2.53,
- "learning_rate": 0.0001840561224489796,
- "loss": 1.7566,
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
"step": 125
},
{
- "epoch": 2.55,
- "learning_rate": 0.00018392857142857143,
- "loss": 1.8169,
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
"step": 126
},
{
- "epoch": 2.57,
- "learning_rate": 0.00018380102040816326,
- "loss": 1.6801,
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
"step": 127
},
{
- "epoch": 2.59,
- "learning_rate": 0.00018367346938775512,
- "loss": 1.7292,
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
"step": 128
},
{
- "epoch": 2.61,
- "learning_rate": 0.00018354591836734695,
- "loss": 1.737,
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
"step": 129
},
{
- "epoch": 2.63,
- "learning_rate": 0.00018341836734693878,
- "loss": 1.7696,
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
"step": 130
},
{
- "epoch": 2.65,
- "learning_rate": 0.0001832908163265306,
- "loss": 1.7239,
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
"step": 131
},
{
- "epoch": 2.67,
- "learning_rate": 0.00018316326530612247,
- "loss": 1.7441,
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
"step": 132
},
{
- "epoch": 2.69,
- "learning_rate": 0.0001830357142857143,
- "loss": 1.7825,
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
"step": 133
},
{
- "epoch": 2.71,
- "learning_rate": 0.00018290816326530613,
- "loss": 1.7411,
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
"step": 134
},
{
- "epoch": 2.73,
- "learning_rate": 0.00018278061224489796,
- "loss": 1.7119,
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
"step": 135
},
{
- "epoch": 2.75,
- "learning_rate": 0.0001826530612244898,
- "loss": 1.7443,
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
"step": 136
},
{
- "epoch": 2.77,
- "learning_rate": 0.00018252551020408165,
- "loss": 1.7197,
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
"step": 137
},
{
- "epoch": 2.79,
- "learning_rate": 0.00018239795918367348,
- "loss": 1.7273,
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
"step": 138
},
{
- "epoch": 2.81,
- "learning_rate": 0.0001822704081632653,
- "loss": 1.7681,
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
"step": 139
},
{
- "epoch": 2.83,
- "learning_rate": 0.00018214285714285714,
- "loss": 1.8088,
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
"step": 140
},
{
- "epoch": 2.85,
- "learning_rate": 0.000182015306122449,
- "loss": 1.7301,
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
"step": 141
},
{
- "epoch": 2.87,
- "learning_rate": 0.00018188775510204083,
- "loss": 1.6853,
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
"step": 142
},
{
- "epoch": 2.89,
- "learning_rate": 0.00018176020408163266,
- "loss": 1.6966,
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
"step": 143
},
{
- "epoch": 2.91,
- "learning_rate": 0.0001816326530612245,
- "loss": 1.7938,
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
"step": 144
},
{
- "epoch": 2.93,
- "learning_rate": 0.00018150510204081635,
- "loss": 1.7639,
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
"step": 145
},
{
- "epoch": 2.95,
- "learning_rate": 0.00018137755102040816,
- "loss": 1.7527,
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
"step": 146
},
{
- "epoch": 2.97,
- "learning_rate": 0.00018125000000000001,
- "loss": 1.7386,
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
"step": 147
},
{
- "epoch": 2.99,
- "learning_rate": 0.00018112244897959185,
- "loss": 1.7223,
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
"step": 148
},
{
- "epoch": 3.01,
- "learning_rate": 0.00018099489795918368,
- "loss": 1.7571,
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
"step": 149
},
{
- "epoch": 3.04,
- "learning_rate": 0.0001808673469387755,
- "loss": 1.7054,
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
"step": 150
},
{
- "epoch": 3.06,
- "learning_rate": 0.00018073979591836737,
- "loss": 1.6581,
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
"step": 151
},
{
- "epoch": 3.08,
- "learning_rate": 0.00018061224489795917,
- "loss": 1.681,
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
"step": 152
},
{
- "epoch": 3.1,
- "learning_rate": 0.00018048469387755103,
- "loss": 1.7425,
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
"step": 153
},
{
- "epoch": 3.12,
- "learning_rate": 0.00018035714285714286,
- "loss": 1.7108,
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
"step": 154
},
{
- "epoch": 3.14,
- "learning_rate": 0.00018022959183673472,
- "loss": 1.7194,
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
"step": 155
},
{
- "epoch": 3.16,
- "learning_rate": 0.00018010204081632655,
- "loss": 1.6953,
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
"step": 156
},
{
- "epoch": 3.18,
- "learning_rate": 0.00017997448979591838,
- "loss": 1.669,
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
"step": 157
},
{
- "epoch": 3.2,
- "learning_rate": 0.0001798469387755102,
- "loss": 1.744,
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
"step": 158
},
{
- "epoch": 3.22,
- "learning_rate": 0.00017971938775510204,
- "loss": 1.6467,
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
"step": 159
},
{
- "epoch": 3.24,
- "learning_rate": 0.0001795918367346939,
- "loss": 1.7103,
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
"step": 160
},
{
- "epoch": 3.26,
- "learning_rate": 0.00017946428571428573,
- "loss": 1.6662,
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
"step": 161
},
{
- "epoch": 3.28,
- "learning_rate": 0.00017933673469387756,
- "loss": 1.6657,
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
"step": 162
},
{
- "epoch": 3.3,
- "learning_rate": 0.0001792091836734694,
- "loss": 1.791,
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
"step": 163
},
{
- "epoch": 3.32,
- "learning_rate": 0.00017908163265306125,
- "loss": 1.7704,
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
"step": 164
},
{
- "epoch": 3.34,
- "learning_rate": 0.00017895408163265305,
- "loss": 1.7229,
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
"step": 165
},
{
- "epoch": 3.36,
- "learning_rate": 0.0001788265306122449,
- "loss": 1.76,
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
"step": 166
},
{
- "epoch": 3.38,
- "learning_rate": 0.00017869897959183674,
- "loss": 1.6482,
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
"step": 167
},
{
- "epoch": 3.4,
- "learning_rate": 0.0001785714285714286,
- "loss": 1.8076,
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
"step": 168
},
{
- "epoch": 3.42,
- "learning_rate": 0.0001784438775510204,
- "loss": 1.7368,
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
"step": 169
},
{
- "epoch": 3.44,
- "learning_rate": 0.00017831632653061226,
- "loss": 1.6264,
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
"step": 170
},
{
- "epoch": 3.46,
- "learning_rate": 0.0001781887755102041,
- "loss": 1.6289,
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
"step": 171
},
{
- "epoch": 3.48,
- "learning_rate": 0.00017806122448979592,
- "loss": 1.7913,
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
"step": 172
},
{
- "epoch": 3.5,
- "learning_rate": 0.00017793367346938775,
- "loss": 1.6985,
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
"step": 173
},
{
- "epoch": 3.52,
- "learning_rate": 0.0001778061224489796,
- "loss": 1.6936,
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
"step": 174
},
{
- "epoch": 3.54,
- "learning_rate": 0.00017767857142857141,
- "loss": 1.8068,
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
"step": 175
},
{
- "epoch": 3.56,
- "learning_rate": 0.00017755102040816327,
- "loss": 1.7243,
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
"step": 176
},
{
- "epoch": 3.58,
- "learning_rate": 0.0001774234693877551,
- "loss": 1.6893,
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
"step": 177
},
{
- "epoch": 3.6,
- "learning_rate": 0.00017729591836734696,
- "loss": 1.8122,
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
"step": 178
},
{
- "epoch": 3.62,
- "learning_rate": 0.0001771683673469388,
- "loss": 1.6562,
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
"step": 179
},
{
- "epoch": 3.64,
- "learning_rate": 0.00017704081632653062,
- "loss": 1.6999,
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
"step": 180
},
{
- "epoch": 3.66,
- "learning_rate": 0.00017691326530612245,
- "loss": 1.7229,
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
"step": 181
},
{
- "epoch": 3.68,
- "learning_rate": 0.00017678571428571428,
- "loss": 1.6764,
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
"step": 182
},
{
- "epoch": 3.7,
- "learning_rate": 0.00017665816326530614,
- "loss": 1.6982,
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
"step": 183
},
{
- "epoch": 3.72,
- "learning_rate": 0.00017653061224489797,
- "loss": 1.696,
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
"step": 184
},
{
- "epoch": 3.74,
- "learning_rate": 0.0001764030612244898,
- "loss": 1.6797,
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
"step": 185
},
{
- "epoch": 3.76,
- "learning_rate": 0.00017627551020408164,
- "loss": 1.637,
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
"step": 186
},
{
- "epoch": 3.78,
- "learning_rate": 0.0001761479591836735,
- "loss": 1.7074,
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
"step": 187
},
{
- "epoch": 3.8,
- "learning_rate": 0.0001760204081632653,
- "loss": 1.705,
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
"step": 188
},
{
- "epoch": 3.82,
- "learning_rate": 0.00017589285714285716,
- "loss": 1.6153,
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
"step": 189
},
{
- "epoch": 3.84,
- "learning_rate": 0.00017576530612244899,
- "loss": 1.7354,
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
"step": 190
},
{
- "epoch": 3.86,
- "learning_rate": 0.00017563775510204084,
- "loss": 1.6941,
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
"step": 191
},
{
- "epoch": 3.88,
- "learning_rate": 0.00017551020408163265,
- "loss": 1.7231,
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
"step": 192
},
{
- "epoch": 3.91,
- "learning_rate": 0.0001753826530612245,
- "loss": 1.7663,
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
"step": 193
},
{
- "epoch": 3.93,
- "learning_rate": 0.00017525510204081634,
- "loss": 1.6532,
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
"step": 194
},
{
- "epoch": 3.95,
- "learning_rate": 0.00017512755102040817,
- "loss": 1.7115,
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
"step": 195
},
{
- "epoch": 3.97,
- "learning_rate": 0.000175,
- "loss": 1.6955,
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
"step": 196
},
{
- "epoch": 3.99,
- "learning_rate": 0.00017487244897959186,
- "loss": 1.6863,
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
"step": 197
},
{
- "epoch": 4.01,
- "learning_rate": 0.00017474489795918366,
- "loss": 1.7012,
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
"step": 198
},
{
- "epoch": 4.03,
- "learning_rate": 0.00017461734693877552,
- "loss": 1.5927,
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
"step": 199
},
{
- "epoch": 4.05,
- "learning_rate": 0.00017448979591836735,
- "loss": 1.6272,
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
"step": 200
},
{
- "epoch": 4.07,
- "learning_rate": 0.00017436224489795918,
- "loss": 1.5994,
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
"step": 201
},
{
- "epoch": 4.09,
- "learning_rate": 0.00017423469387755104,
- "loss": 1.7141,
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
"step": 202
},
{
- "epoch": 4.11,
- "learning_rate": 0.00017410714285714287,
- "loss": 1.7547,
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
"step": 203
},
{
- "epoch": 4.13,
- "learning_rate": 0.0001739795918367347,
- "loss": 1.6254,
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
"step": 204
},
{
- "epoch": 4.15,
- "learning_rate": 0.00017385204081632653,
- "loss": 1.6686,
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
"step": 205
},
{
- "epoch": 4.17,
- "learning_rate": 0.0001737244897959184,
- "loss": 1.6684,
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
"step": 206
},
{
- "epoch": 4.19,
- "learning_rate": 0.00017359693877551022,
- "loss": 1.6724,
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
"step": 207
},
{
- "epoch": 4.21,
- "learning_rate": 0.00017346938775510205,
- "loss": 1.7361,
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
"step": 208
},
{
- "epoch": 4.23,
- "learning_rate": 0.00017334183673469388,
- "loss": 1.7167,
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
"step": 209
},
{
- "epoch": 4.25,
- "learning_rate": 0.00017321428571428574,
- "loss": 1.7226,
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
"step": 210
},
{
- "epoch": 4.27,
- "learning_rate": 0.00017308673469387754,
- "loss": 1.7133,
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
"step": 211
},
{
- "epoch": 4.29,
- "learning_rate": 0.0001729591836734694,
- "loss": 1.649,
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
"step": 212
},
{
- "epoch": 4.31,
- "learning_rate": 0.00017283163265306123,
- "loss": 1.7104,
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
"step": 213
},
{
- "epoch": 4.33,
- "learning_rate": 0.00017270408163265306,
- "loss": 1.6861,
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
"step": 214
},
{
- "epoch": 4.35,
- "learning_rate": 0.0001725765306122449,
- "loss": 1.648,
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
"step": 215
},
{
- "epoch": 4.37,
- "learning_rate": 0.00017244897959183675,
- "loss": 1.6215,
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
"step": 216
},
{
- "epoch": 4.39,
- "learning_rate": 0.00017232142857142858,
- "loss": 1.6334,
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
"step": 217
},
{
- "epoch": 4.41,
- "learning_rate": 0.0001721938775510204,
- "loss": 1.6283,
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
"step": 218
},
{
- "epoch": 4.43,
- "learning_rate": 0.00017206632653061224,
- "loss": 1.6462,
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
"step": 219
},
{
- "epoch": 4.45,
- "learning_rate": 0.0001719387755102041,
- "loss": 1.7233,
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
"step": 220
},
{
- "epoch": 4.47,
- "learning_rate": 0.0001718112244897959,
- "loss": 1.7839,
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
"step": 221
},
{
- "epoch": 4.49,
- "learning_rate": 0.00017168367346938776,
- "loss": 1.7204,
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
"step": 222
},
{
- "epoch": 4.51,
- "learning_rate": 0.0001715561224489796,
- "loss": 1.7671,
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
"step": 223
},
{
- "epoch": 4.53,
- "learning_rate": 0.00017142857142857143,
- "loss": 1.6824,
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
"step": 224
},
{
- "epoch": 4.55,
- "learning_rate": 0.00017130102040816328,
- "loss": 1.7068,
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
"step": 225
},
{
- "epoch": 4.57,
- "learning_rate": 0.00017117346938775511,
- "loss": 1.6515,
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
"step": 226
},
{
- "epoch": 4.59,
- "learning_rate": 0.00017104591836734694,
- "loss": 1.6586,
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
"step": 227
},
{
- "epoch": 4.61,
- "learning_rate": 0.00017091836734693878,
- "loss": 1.6355,
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
"step": 228
},
{
- "epoch": 4.63,
- "learning_rate": 0.00017079081632653063,
- "loss": 1.7173,
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
"step": 229
},
{
- "epoch": 4.65,
- "learning_rate": 0.00017066326530612246,
- "loss": 1.6585,
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
"step": 230
},
{
- "epoch": 4.67,
- "learning_rate": 0.0001705357142857143,
- "loss": 1.5856,
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
"step": 231
},
{
- "epoch": 4.69,
- "learning_rate": 0.00017040816326530613,
- "loss": 1.5923,
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
"step": 232
},
{
- "epoch": 4.71,
- "learning_rate": 0.00017028061224489798,
- "loss": 1.7128,
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
"step": 233
},
{
- "epoch": 4.73,
- "learning_rate": 0.0001701530612244898,
- "loss": 1.6971,
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
"step": 234
},
{
- "epoch": 4.75,
- "learning_rate": 0.00017002551020408165,
- "loss": 1.6416,
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
"step": 235
},
{
- "epoch": 4.78,
- "learning_rate": 0.00016989795918367348,
- "loss": 1.645,
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
"step": 236
},
{
- "epoch": 4.8,
- "learning_rate": 0.0001697704081632653,
- "loss": 1.6792,
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
"step": 237
},
{
- "epoch": 4.82,
- "learning_rate": 0.00016964285714285714,
- "loss": 1.6522,
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
"step": 238
},
{
- "epoch": 4.84,
- "learning_rate": 0.000169515306122449,
- "loss": 1.6315,
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
"step": 239
},
{
- "epoch": 4.86,
- "learning_rate": 0.00016938775510204083,
- "loss": 1.6622,
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
"step": 240
},
{
- "epoch": 4.88,
- "learning_rate": 0.00016926020408163266,
- "loss": 1.6566,
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
"step": 241
},
{
- "epoch": 4.9,
- "learning_rate": 0.0001691326530612245,
- "loss": 1.7141,
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
"step": 242
},
{
- "epoch": 4.92,
- "learning_rate": 0.00016900510204081635,
- "loss": 1.5873,
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
"step": 243
},
{
- "epoch": 4.94,
- "learning_rate": 0.00016887755102040818,
- "loss": 1.6571,
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
"step": 244
},
{
- "epoch": 4.96,
- "learning_rate": 0.00016875,
- "loss": 1.6829,
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
"step": 245
},
{
- "epoch": 4.98,
- "learning_rate": 0.00016862244897959184,
- "loss": 1.6935,
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
"step": 246
},
{
- "epoch": 5.0,
- "learning_rate": 0.00016849489795918367,
- "loss": 1.6782,
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
"step": 247
},
{
- "epoch": 5.02,
- "learning_rate": 0.00016836734693877553,
- "loss": 1.622,
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
"step": 248
},
{
- "epoch": 5.04,
- "learning_rate": 0.00016823979591836736,
- "loss": 1.6596,
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
"step": 249
},
{
- "epoch": 5.06,
- "learning_rate": 0.0001681122448979592,
- "loss": 1.5821,
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
"step": 250
},
{
- "epoch": 5.08,
- "learning_rate": 0.00016798469387755102,
- "loss": 1.7292,
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
"step": 251
},
{
- "epoch": 5.1,
- "learning_rate": 0.00016785714285714288,
- "loss": 1.646,
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
"step": 252
},
{
- "epoch": 5.12,
- "learning_rate": 0.0001677295918367347,
- "loss": 1.6969,
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
"step": 253
},
{
- "epoch": 5.14,
- "learning_rate": 0.00016760204081632654,
- "loss": 1.6082,
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
"step": 254
},
{
- "epoch": 5.16,
- "learning_rate": 0.00016747448979591837,
- "loss": 1.5843,
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
"step": 255
},
{
- "epoch": 5.18,
- "learning_rate": 0.00016734693877551023,
- "loss": 1.6827,
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
"step": 256
},
{
- "epoch": 5.2,
- "learning_rate": 0.00016721938775510203,
- "loss": 1.5824,
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
"step": 257
},
{
- "epoch": 5.22,
- "learning_rate": 0.0001670918367346939,
- "loss": 1.6795,
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
"step": 258
},
{
- "epoch": 5.24,
- "learning_rate": 0.00016696428571428572,
- "loss": 1.5639,
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
"step": 259
},
{
- "epoch": 5.26,
- "learning_rate": 0.00016683673469387755,
- "loss": 1.592,
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
"step": 260
},
{
- "epoch": 5.28,
- "learning_rate": 0.00016670918367346938,
- "loss": 1.65,
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
"step": 261
},
{
- "epoch": 5.3,
- "learning_rate": 0.00016658163265306124,
- "loss": 1.5592,
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
"step": 262
},
{
- "epoch": 5.32,
- "learning_rate": 0.00016645408163265305,
- "loss": 1.5091,
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
"step": 263
},
{
- "epoch": 5.34,
- "learning_rate": 0.0001663265306122449,
- "loss": 1.6138,
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
"step": 264
},
{
- "epoch": 5.36,
- "learning_rate": 0.00016619897959183673,
- "loss": 1.625,
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
"step": 265
},
{
- "epoch": 5.38,
- "learning_rate": 0.0001660714285714286,
- "loss": 1.5757,
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
"step": 266
},
{
- "epoch": 5.4,
- "learning_rate": 0.00016594387755102042,
- "loss": 1.6372,
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
"step": 267
},
{
- "epoch": 5.42,
- "learning_rate": 0.00016581632653061225,
- "loss": 1.5891,
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
"step": 268
},
{
- "epoch": 5.44,
- "learning_rate": 0.00016568877551020409,
- "loss": 1.6893,
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
"step": 269
},
{
- "epoch": 5.46,
- "learning_rate": 0.00016556122448979592,
- "loss": 1.6662,
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
"step": 270
},
{
- "epoch": 5.48,
- "learning_rate": 0.00016543367346938777,
- "loss": 1.7132,
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
"step": 271
},
{
- "epoch": 5.5,
- "learning_rate": 0.0001653061224489796,
- "loss": 1.5835,
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
"step": 272
},
{
- "epoch": 5.52,
- "learning_rate": 0.00016517857142857144,
- "loss": 1.6342,
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
"step": 273
},
{
- "epoch": 5.54,
- "learning_rate": 0.00016505102040816327,
- "loss": 1.6717,
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
"step": 274
},
{
- "epoch": 5.56,
- "learning_rate": 0.00016492346938775512,
- "loss": 1.6248,
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
"step": 275
},
{
- "epoch": 5.58,
- "learning_rate": 0.00016479591836734696,
- "loss": 1.6117,
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
"step": 276
},
{
- "epoch": 5.6,
- "learning_rate": 0.0001646683673469388,
- "loss": 1.6798,
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
"step": 277
},
{
- "epoch": 5.63,
- "learning_rate": 0.00016454081632653062,
- "loss": 1.6406,
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
"step": 278
},
{
- "epoch": 5.65,
- "learning_rate": 0.00016441326530612248,
- "loss": 1.6512,
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
"step": 279
},
{
- "epoch": 5.67,
- "learning_rate": 0.00016428571428571428,
- "loss": 1.6102,
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
"step": 280
},
{
- "epoch": 5.69,
- "learning_rate": 0.00016415816326530614,
- "loss": 1.6113,
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
"step": 281
},
{
- "epoch": 5.71,
- "learning_rate": 0.00016403061224489797,
- "loss": 1.7116,
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
"step": 282
},
{
- "epoch": 5.73,
- "learning_rate": 0.0001639030612244898,
- "loss": 1.6846,
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
"step": 283
},
{
- "epoch": 5.75,
- "learning_rate": 0.00016377551020408163,
- "loss": 1.6911,
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
"step": 284
},
{
- "epoch": 5.77,
- "learning_rate": 0.0001636479591836735,
- "loss": 1.6202,
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
"step": 285
},
{
- "epoch": 5.79,
- "learning_rate": 0.0001635204081632653,
- "loss": 1.5715,
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
"step": 286
},
{
- "epoch": 5.81,
- "learning_rate": 0.00016339285714285715,
- "loss": 1.6461,
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
"step": 287
},
{
- "epoch": 5.83,
- "learning_rate": 0.00016326530612244898,
- "loss": 1.6624,
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
"step": 288
},
{
- "epoch": 5.85,
- "learning_rate": 0.00016313775510204084,
- "loss": 1.6535,
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
"step": 289
},
{
- "epoch": 5.87,
- "learning_rate": 0.00016301020408163267,
- "loss": 1.6275,
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
"step": 290
},
{
- "epoch": 5.89,
- "learning_rate": 0.0001628826530612245,
- "loss": 1.6636,
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
"step": 291
},
{
- "epoch": 5.91,
- "learning_rate": 0.00016275510204081633,
- "loss": 1.6546,
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
"step": 292
},
{
- "epoch": 5.93,
- "learning_rate": 0.00016262755102040816,
- "loss": 1.7274,
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
"step": 293
},
{
- "epoch": 5.95,
- "learning_rate": 0.00016250000000000002,
- "loss": 1.5901,
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
"step": 294
},
{
- "epoch": 5.97,
- "learning_rate": 0.00016237244897959185,
- "loss": 1.6046,
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
"step": 295
},
{
- "epoch": 5.99,
- "learning_rate": 0.00016224489795918368,
- "loss": 1.5828,
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
"step": 296
},
{
- "epoch": 6.01,
- "learning_rate": 0.0001621173469387755,
- "loss": 1.6435,
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
"step": 297
},
{
- "epoch": 6.03,
- "learning_rate": 0.00016198979591836737,
- "loss": 1.6263,
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
"step": 298
},
{
- "epoch": 6.05,
- "learning_rate": 0.00016186224489795917,
- "loss": 1.4944,
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
"step": 299
},
{
- "epoch": 6.07,
- "learning_rate": 0.00016173469387755103,
- "loss": 1.6286,
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
"step": 300
},
{
- "epoch": 6.09,
- "learning_rate": 0.00016160714285714286,
- "loss": 1.694,
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
"step": 301
},
{
- "epoch": 6.11,
- "learning_rate": 0.00016147959183673472,
- "loss": 1.6197,
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
"step": 302
},
{
- "epoch": 6.13,
- "learning_rate": 0.00016135204081632652,
- "loss": 1.5597,
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
"step": 303
},
{
- "epoch": 6.15,
- "learning_rate": 0.00016122448979591838,
- "loss": 1.5487,
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
"step": 304
},
{
- "epoch": 6.17,
- "learning_rate": 0.0001610969387755102,
- "loss": 1.5769,
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
"step": 305
},
{
- "epoch": 6.19,
- "learning_rate": 0.00016096938775510204,
- "loss": 1.6367,
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
"step": 306
},
{
- "epoch": 6.21,
- "learning_rate": 0.00016084183673469388,
- "loss": 1.583,
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
"step": 307
},
{
- "epoch": 6.23,
- "learning_rate": 0.00016071428571428573,
- "loss": 1.6201,
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
"step": 308
},
{
- "epoch": 6.25,
- "learning_rate": 0.00016058673469387754,
- "loss": 1.6586,
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
"step": 309
},
{
- "epoch": 6.27,
- "learning_rate": 0.0001604591836734694,
- "loss": 1.6711,
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
"step": 310
},
{
- "epoch": 6.29,
- "learning_rate": 0.00016033163265306123,
- "loss": 1.6402,
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
"step": 311
},
{
- "epoch": 6.31,
- "learning_rate": 0.00016020408163265306,
- "loss": 1.5247,
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
"step": 312
},
{
- "epoch": 6.33,
- "learning_rate": 0.00016007653061224491,
- "loss": 1.5356,
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
"step": 313
},
{
- "epoch": 6.35,
- "learning_rate": 0.00015994897959183675,
- "loss": 1.564,
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
"step": 314
},
{
- "epoch": 6.37,
- "learning_rate": 0.00015982142857142858,
- "loss": 1.563,
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
"step": 315
},
{
- "epoch": 6.39,
- "learning_rate": 0.0001596938775510204,
- "loss": 1.5198,
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
"step": 316
},
{
- "epoch": 6.41,
- "learning_rate": 0.00015956632653061227,
- "loss": 1.6558,
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
"step": 317
},
{
- "epoch": 6.43,
- "learning_rate": 0.0001594387755102041,
- "loss": 1.5534,
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
"step": 318
},
{
- "epoch": 6.45,
- "learning_rate": 0.00015931122448979593,
- "loss": 1.6239,
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
"step": 319
},
{
- "epoch": 6.47,
- "learning_rate": 0.00015918367346938776,
- "loss": 1.5645,
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
"step": 320
},
{
- "epoch": 6.5,
- "learning_rate": 0.00015905612244897962,
- "loss": 1.5713,
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
"step": 321
},
{
- "epoch": 6.52,
- "learning_rate": 0.00015892857142857142,
- "loss": 1.6176,
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
"step": 322
},
{
- "epoch": 6.54,
- "learning_rate": 0.00015880102040816328,
- "loss": 1.502,
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
"step": 323
},
{
- "epoch": 6.56,
- "learning_rate": 0.0001586734693877551,
- "loss": 1.645,
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
"step": 324
},
{
- "epoch": 6.58,
- "learning_rate": 0.00015854591836734697,
- "loss": 1.5904,
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
"step": 325
},
{
- "epoch": 6.6,
- "learning_rate": 0.00015841836734693877,
- "loss": 1.6149,
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
"step": 326
},
{
- "epoch": 6.62,
- "learning_rate": 0.00015829081632653063,
- "loss": 1.6757,
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
"step": 327
},
{
- "epoch": 6.64,
- "learning_rate": 0.00015816326530612246,
- "loss": 1.541,
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
"step": 328
},
{
- "epoch": 6.66,
- "learning_rate": 0.0001580357142857143,
- "loss": 1.5898,
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
"step": 329
},
{
- "epoch": 6.68,
- "learning_rate": 0.00015790816326530612,
- "loss": 1.5441,
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
"step": 330
},
{
- "epoch": 6.7,
- "learning_rate": 0.00015778061224489798,
- "loss": 1.61,
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
"step": 331
},
{
- "epoch": 6.72,
- "learning_rate": 0.00015765306122448978,
- "loss": 1.615,
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
"step": 332
},
{
- "epoch": 6.74,
- "learning_rate": 0.00015752551020408164,
- "loss": 1.6575,
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
"step": 333
},
{
- "epoch": 6.76,
- "learning_rate": 0.00015739795918367347,
- "loss": 1.6702,
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
"step": 334
},
{
- "epoch": 6.78,
- "learning_rate": 0.0001572704081632653,
- "loss": 1.6009,
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
"step": 335
},
{
- "epoch": 6.8,
- "learning_rate": 0.00015714285714285716,
- "loss": 1.5568,
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
"step": 336
},
{
- "epoch": 6.82,
- "learning_rate": 0.000157015306122449,
- "loss": 1.619,
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
"step": 337
},
{
- "epoch": 6.84,
- "learning_rate": 0.00015688775510204082,
- "loss": 1.5563,
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
"step": 338
},
{
- "epoch": 6.86,
- "learning_rate": 0.00015676020408163265,
- "loss": 1.6328,
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
"step": 339
},
{
- "epoch": 6.88,
- "learning_rate": 0.0001566326530612245,
- "loss": 1.5726,
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
"step": 340
},
{
- "epoch": 6.9,
- "learning_rate": 0.00015650510204081634,
- "loss": 1.6199,
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
"step": 341
},
{
- "epoch": 6.92,
- "learning_rate": 0.00015637755102040817,
- "loss": 1.5722,
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
"step": 342
},
{
- "epoch": 6.94,
- "learning_rate": 0.00015625,
- "loss": 1.5685,
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
"step": 343
},
{
- "epoch": 6.96,
- "learning_rate": 0.00015612244897959186,
- "loss": 1.5615,
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
"step": 344
},
{
- "epoch": 6.98,
- "learning_rate": 0.00015599489795918366,
- "loss": 1.5994,
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
"step": 345
},
{
- "epoch": 7.0,
- "learning_rate": 0.00015586734693877552,
- "loss": 1.5579,
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
"step": 346
},
{
- "epoch": 7.02,
- "learning_rate": 0.00015573979591836735,
- "loss": 1.547,
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
"step": 347
},
{
- "epoch": 7.04,
- "learning_rate": 0.00015561224489795918,
- "loss": 1.5292,
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
"step": 348
},
{
- "epoch": 7.06,
- "learning_rate": 0.00015548469387755102,
- "loss": 1.6032,
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
"step": 349
},
{
- "epoch": 7.08,
- "learning_rate": 0.00015535714285714287,
- "loss": 1.5149,
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
"step": 350
},
{
- "epoch": 7.1,
- "learning_rate": 0.0001552295918367347,
- "loss": 1.6093,
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
"step": 351
},
{
- "epoch": 7.12,
- "learning_rate": 0.00015510204081632654,
- "loss": 1.5421,
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
"step": 352
},
{
- "epoch": 7.14,
- "learning_rate": 0.00015497448979591837,
- "loss": 1.5733,
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
"step": 353
},
{
- "epoch": 7.16,
- "learning_rate": 0.00015484693877551022,
- "loss": 1.5703,
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
"step": 354
},
{
- "epoch": 7.18,
- "learning_rate": 0.00015471938775510203,
- "loss": 1.6141,
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
"step": 355
},
{
- "epoch": 7.2,
- "learning_rate": 0.00015459183673469389,
- "loss": 1.5526,
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
"step": 356
},
{
- "epoch": 7.22,
- "learning_rate": 0.00015446428571428572,
- "loss": 1.5347,
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
"step": 357
},
{
- "epoch": 7.24,
- "learning_rate": 0.00015433673469387755,
- "loss": 1.5682,
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
"step": 358
},
{
- "epoch": 7.26,
- "learning_rate": 0.0001542091836734694,
- "loss": 1.5292,
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
"step": 359
},
{
- "epoch": 7.28,
- "learning_rate": 0.00015408163265306124,
- "loss": 1.499,
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
"step": 360
},
{
- "epoch": 7.3,
- "learning_rate": 0.00015395408163265307,
- "loss": 1.5624,
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
"step": 361
},
{
- "epoch": 7.32,
- "learning_rate": 0.0001538265306122449,
- "loss": 1.627,
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
"step": 362
},
{
- "epoch": 7.34,
- "learning_rate": 0.00015369897959183676,
- "loss": 1.5327,
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
"step": 363
},
{
- "epoch": 7.37,
- "learning_rate": 0.0001535714285714286,
- "loss": 1.5622,
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
"step": 364
},
{
- "epoch": 7.39,
- "learning_rate": 0.00015344387755102042,
- "loss": 1.5659,
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
"step": 365
},
{
- "epoch": 7.41,
- "learning_rate": 0.00015331632653061225,
- "loss": 1.5019,
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
"step": 366
},
{
- "epoch": 7.43,
- "learning_rate": 0.0001531887755102041,
- "loss": 1.5921,
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
"step": 367
},
{
- "epoch": 7.45,
- "learning_rate": 0.0001530612244897959,
- "loss": 1.5914,
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
"step": 368
},
{
- "epoch": 7.47,
- "learning_rate": 0.00015293367346938777,
- "loss": 1.5045,
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
"step": 369
},
{
- "epoch": 7.49,
- "learning_rate": 0.0001528061224489796,
- "loss": 1.6209,
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
"step": 370
},
{
- "epoch": 7.51,
- "learning_rate": 0.00015267857142857143,
- "loss": 1.5198,
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
"step": 371
},
{
- "epoch": 7.53,
- "learning_rate": 0.00015255102040816326,
- "loss": 1.5363,
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
"step": 372
},
{
- "epoch": 7.55,
- "learning_rate": 0.00015242346938775512,
- "loss": 1.5391,
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
"step": 373
},
{
- "epoch": 7.57,
- "learning_rate": 0.00015229591836734695,
- "loss": 1.4546,
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
"step": 374
},
{
- "epoch": 7.59,
- "learning_rate": 0.00015216836734693878,
- "loss": 1.5546,
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
"step": 375
},
{
- "epoch": 7.61,
- "learning_rate": 0.0001520408163265306,
- "loss": 1.5629,
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
"step": 376
},
{
- "epoch": 7.63,
- "learning_rate": 0.00015191326530612247,
- "loss": 1.6002,
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
"step": 377
},
{
- "epoch": 7.65,
- "learning_rate": 0.00015178571428571427,
- "loss": 1.5543,
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
"step": 378
},
{
- "epoch": 7.67,
- "learning_rate": 0.00015165816326530613,
- "loss": 1.5925,
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
"step": 379
},
{
- "epoch": 7.69,
- "learning_rate": 0.00015153061224489796,
- "loss": 1.5631,
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
"step": 380
},
{
- "epoch": 7.71,
- "learning_rate": 0.0001514030612244898,
- "loss": 1.5677,
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
"step": 381
},
{
- "epoch": 7.73,
- "learning_rate": 0.00015127551020408165,
- "loss": 1.5828,
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
"step": 382
},
{
- "epoch": 7.75,
- "learning_rate": 0.00015114795918367348,
- "loss": 1.6494,
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
"step": 383
},
{
- "epoch": 7.77,
- "learning_rate": 0.0001510204081632653,
- "loss": 1.553,
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
"step": 384
},
{
- "epoch": 7.79,
- "learning_rate": 0.00015089285714285714,
- "loss": 1.6156,
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
"step": 385
},
{
- "epoch": 7.81,
- "learning_rate": 0.000150765306122449,
- "loss": 1.5001,
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
"step": 386
},
{
- "epoch": 7.83,
- "learning_rate": 0.00015063775510204083,
- "loss": 1.5321,
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
"step": 387
},
{
- "epoch": 7.85,
- "learning_rate": 0.00015051020408163266,
- "loss": 1.5307,
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
"step": 388
},
{
- "epoch": 7.87,
- "learning_rate": 0.0001503826530612245,
- "loss": 1.5639,
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
"step": 389
},
{
- "epoch": 7.89,
- "learning_rate": 0.00015025510204081635,
- "loss": 1.517,
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
"step": 390
},
{
- "epoch": 7.91,
- "learning_rate": 0.00015012755102040816,
- "loss": 1.4776,
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
"step": 391
},
{
- "epoch": 7.93,
- "learning_rate": 0.00015000000000000001,
- "loss": 1.5368,
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
"step": 392
},
{
- "epoch": 7.95,
- "learning_rate": 0.00014987244897959184,
- "loss": 1.5636,
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
"step": 393
},
{
- "epoch": 7.97,
- "learning_rate": 0.00014974489795918368,
- "loss": 1.6004,
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
"step": 394
},
{
- "epoch": 7.99,
- "learning_rate": 0.0001496173469387755,
- "loss": 1.5524,
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
"step": 395
},
{
- "epoch": 8.01,
- "learning_rate": 0.00014948979591836736,
- "loss": 1.5307,
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
"step": 396
},
{
- "epoch": 8.03,
- "learning_rate": 0.00014936224489795917,
- "loss": 1.5123,
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
"step": 397
},
{
- "epoch": 8.05,
- "learning_rate": 0.00014923469387755103,
- "loss": 1.5132,
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
"step": 398
},
{
- "epoch": 8.07,
- "learning_rate": 0.00014910714285714286,
- "loss": 1.5109,
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
"step": 399
},
{
- "epoch": 8.09,
- "learning_rate": 0.00014897959183673472,
- "loss": 1.5302,
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
"step": 400
},
{
- "epoch": 8.11,
- "learning_rate": 0.00014885204081632652,
- "loss": 1.5238,
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
"step": 401
},
{
- "epoch": 8.13,
- "learning_rate": 0.00014872448979591838,
- "loss": 1.4781,
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
"step": 402
},
{
- "epoch": 8.15,
- "learning_rate": 0.0001485969387755102,
- "loss": 1.5446,
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
"step": 403
},
{
- "epoch": 8.17,
- "learning_rate": 0.00014846938775510204,
- "loss": 1.5,
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
"step": 404
},
{
- "epoch": 8.19,
- "learning_rate": 0.0001483418367346939,
- "loss": 1.5458,
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
"step": 405
},
{
- "epoch": 8.21,
- "learning_rate": 0.00014821428571428573,
- "loss": 1.5257,
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
"step": 406
},
{
- "epoch": 8.24,
- "learning_rate": 0.00014808673469387756,
- "loss": 1.4607,
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
"step": 407
},
{
- "epoch": 8.26,
- "learning_rate": 0.0001479591836734694,
- "loss": 1.4282,
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
"step": 408
},
{
- "epoch": 8.28,
- "learning_rate": 0.00014783163265306125,
- "loss": 1.4519,
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
"step": 409
},
{
- "epoch": 8.3,
- "learning_rate": 0.00014770408163265305,
- "loss": 1.475,
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
"step": 410
},
{
- "epoch": 8.32,
- "learning_rate": 0.0001475765306122449,
- "loss": 1.5425,
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
"step": 411
},
{
- "epoch": 8.34,
- "learning_rate": 0.00014744897959183674,
- "loss": 1.5407,
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
"step": 412
},
{
- "epoch": 8.36,
- "learning_rate": 0.0001473214285714286,
- "loss": 1.5698,
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
"step": 413
},
{
- "epoch": 8.38,
- "learning_rate": 0.0001471938775510204,
- "loss": 1.4282,
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
"step": 414
},
{
- "epoch": 8.4,
- "learning_rate": 0.00014706632653061226,
- "loss": 1.5301,
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
"step": 415
},
{
- "epoch": 8.42,
- "learning_rate": 0.0001469387755102041,
- "loss": 1.5083,
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
"step": 416
},
{
- "epoch": 8.44,
- "learning_rate": 0.00014681122448979592,
- "loss": 1.5712,
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
"step": 417
},
{
- "epoch": 8.46,
- "learning_rate": 0.00014668367346938775,
- "loss": 1.4363,
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
"step": 418
},
{
- "epoch": 8.48,
- "learning_rate": 0.0001465561224489796,
- "loss": 1.4463,
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
"step": 419
},
{
- "epoch": 8.5,
- "learning_rate": 0.00014642857142857141,
- "loss": 1.4738,
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
"step": 420
},
{
- "epoch": 8.52,
- "learning_rate": 0.00014630102040816327,
- "loss": 1.5396,
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
"step": 421
},
{
- "epoch": 8.54,
- "learning_rate": 0.0001461734693877551,
- "loss": 1.4384,
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
"step": 422
},
{
- "epoch": 8.56,
- "learning_rate": 0.00014604591836734696,
- "loss": 1.5345,
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
"step": 423
},
{
- "epoch": 8.58,
- "learning_rate": 0.0001459183673469388,
- "loss": 1.5355,
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
"step": 424
},
{
- "epoch": 8.6,
- "learning_rate": 0.00014579081632653062,
- "loss": 1.5188,
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
"step": 425
},
{
- "epoch": 8.62,
- "learning_rate": 0.00014566326530612245,
- "loss": 1.5575,
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
"step": 426
},
{
- "epoch": 8.64,
- "learning_rate": 0.00014553571428571428,
- "loss": 1.5279,
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
"step": 427
},
{
- "epoch": 8.66,
- "learning_rate": 0.00014540816326530614,
- "loss": 1.5484,
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
"step": 428
},
{
- "epoch": 8.68,
- "learning_rate": 0.00014528061224489797,
- "loss": 1.4878,
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
"step": 429
},
{
- "epoch": 8.7,
- "learning_rate": 0.0001451530612244898,
- "loss": 1.503,
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
"step": 430
},
{
- "epoch": 8.72,
- "learning_rate": 0.00014502551020408163,
- "loss": 1.4723,
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
"step": 431
},
{
- "epoch": 8.74,
- "learning_rate": 0.0001448979591836735,
- "loss": 1.5579,
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
"step": 432
},
{
- "epoch": 8.76,
- "learning_rate": 0.0001447704081632653,
- "loss": 1.4789,
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
"step": 433
},
{
- "epoch": 8.78,
- "learning_rate": 0.00014464285714285715,
- "loss": 1.5501,
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
"step": 434
},
{
- "epoch": 8.8,
- "learning_rate": 0.00014451530612244899,
- "loss": 1.5204,
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
"step": 435
},
{
- "epoch": 8.82,
- "learning_rate": 0.00014438775510204084,
- "loss": 1.5489,
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
"step": 436
},
{
- "epoch": 8.84,
- "learning_rate": 0.00014426020408163265,
- "loss": 1.5464,
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
"step": 437
},
{
- "epoch": 8.86,
- "learning_rate": 0.0001441326530612245,
- "loss": 1.5896,
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
"step": 438
},
{
- "epoch": 8.88,
- "learning_rate": 0.00014400510204081634,
- "loss": 1.5465,
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
"step": 439
},
{
- "epoch": 8.9,
- "learning_rate": 0.00014387755102040817,
- "loss": 1.5094,
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
"step": 440
},
{
- "epoch": 8.92,
- "learning_rate": 0.00014375,
- "loss": 1.5144,
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
"step": 441
},
{
- "epoch": 8.94,
- "learning_rate": 0.00014362244897959186,
- "loss": 1.4919,
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
"step": 442
},
{
- "epoch": 8.96,
- "learning_rate": 0.00014349489795918366,
- "loss": 1.4702,
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
"step": 443
},
{
- "epoch": 8.98,
- "learning_rate": 0.00014336734693877552,
- "loss": 1.4996,
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
"step": 444
},
{
- "epoch": 9.0,
- "learning_rate": 0.00014323979591836735,
- "loss": 1.5503,
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
"step": 445
},
{
- "epoch": 9.02,
- "learning_rate": 0.00014311224489795918,
- "loss": 1.4125,
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
"step": 446
},
{
- "epoch": 9.04,
- "learning_rate": 0.00014298469387755104,
- "loss": 1.4722,
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
"step": 447
},
{
- "epoch": 9.06,
- "learning_rate": 0.00014285714285714287,
- "loss": 1.5199,
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
"step": 448
},
{
- "epoch": 9.09,
- "learning_rate": 0.0001427295918367347,
- "loss": 1.4571,
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
"step": 449
},
{
- "epoch": 9.11,
- "learning_rate": 0.00014260204081632653,
- "loss": 1.4996,
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
"step": 450
},
{
- "epoch": 9.13,
- "learning_rate": 0.0001424744897959184,
- "loss": 1.4092,
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
"step": 451
},
{
- "epoch": 9.15,
- "learning_rate": 0.00014234693877551022,
- "loss": 1.4198,
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
"step": 452
},
{
- "epoch": 9.17,
- "learning_rate": 0.00014221938775510205,
- "loss": 1.4916,
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
"step": 453
},
{
- "epoch": 9.19,
- "learning_rate": 0.00014209183673469388,
- "loss": 1.5051,
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
"step": 454
},
{
- "epoch": 9.21,
- "learning_rate": 0.00014196428571428574,
- "loss": 1.4321,
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
"step": 455
},
{
- "epoch": 9.23,
- "learning_rate": 0.00014183673469387754,
- "loss": 1.4097,
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
"step": 456
},
{
- "epoch": 9.25,
- "learning_rate": 0.0001417091836734694,
- "loss": 1.4853,
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
"step": 457
},
{
- "epoch": 9.27,
- "learning_rate": 0.00014158163265306123,
- "loss": 1.4593,
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
"step": 458
},
{
- "epoch": 9.29,
- "learning_rate": 0.00014145408163265306,
- "loss": 1.3729,
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
"step": 459
},
{
- "epoch": 9.31,
- "learning_rate": 0.0001413265306122449,
- "loss": 1.4467,
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
"step": 460
},
{
- "epoch": 9.33,
- "learning_rate": 0.00014119897959183675,
- "loss": 1.4467,
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
"step": 461
},
{
- "epoch": 9.35,
- "learning_rate": 0.00014107142857142858,
- "loss": 1.4785,
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
"step": 462
},
{
- "epoch": 9.37,
- "learning_rate": 0.0001409438775510204,
- "loss": 1.4089,
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
"step": 463
},
{
- "epoch": 9.39,
- "learning_rate": 0.00014081632653061224,
- "loss": 1.5026,
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
"step": 464
},
{
- "epoch": 9.41,
- "learning_rate": 0.0001406887755102041,
- "loss": 1.4857,
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
"step": 465
},
{
- "epoch": 9.43,
- "learning_rate": 0.0001405612244897959,
- "loss": 1.3745,
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
"step": 466
},
{
- "epoch": 9.45,
- "learning_rate": 0.00014043367346938776,
- "loss": 1.4733,
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
"step": 467
},
{
- "epoch": 9.47,
- "learning_rate": 0.0001403061224489796,
- "loss": 1.5212,
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
"step": 468
},
{
- "epoch": 9.49,
- "learning_rate": 0.00014017857142857142,
- "loss": 1.5398,
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
"step": 469
},
{
- "epoch": 9.51,
- "learning_rate": 0.00014005102040816328,
- "loss": 1.478,
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
"step": 470
},
{
- "epoch": 9.53,
- "learning_rate": 0.0001399234693877551,
- "loss": 1.496,
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
"step": 471
},
{
- "epoch": 9.55,
- "learning_rate": 0.00013979591836734694,
- "loss": 1.4837,
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
"step": 472
},
{
- "epoch": 9.57,
- "learning_rate": 0.00013966836734693878,
- "loss": 1.4724,
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
"step": 473
},
{
- "epoch": 9.59,
- "learning_rate": 0.00013954081632653063,
- "loss": 1.4828,
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
"step": 474
},
{
- "epoch": 9.61,
- "learning_rate": 0.00013941326530612246,
- "loss": 1.5012,
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
"step": 475
},
{
- "epoch": 9.63,
- "learning_rate": 0.0001392857142857143,
- "loss": 1.4879,
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
"step": 476
},
{
- "epoch": 9.65,
- "learning_rate": 0.00013915816326530613,
- "loss": 1.4196,
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
"step": 477
},
{
- "epoch": 9.67,
- "learning_rate": 0.00013903061224489798,
- "loss": 1.4915,
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
"step": 478
},
{
- "epoch": 9.69,
- "learning_rate": 0.0001389030612244898,
- "loss": 1.3878,
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
"step": 479
},
{
- "epoch": 9.71,
- "learning_rate": 0.00013877551020408165,
- "loss": 1.466,
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
"step": 480
},
{
- "epoch": 9.73,
- "learning_rate": 0.00013864795918367348,
- "loss": 1.4582,
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
"step": 481
},
{
- "epoch": 9.75,
- "learning_rate": 0.0001385204081632653,
- "loss": 1.533,
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
"step": 482
},
{
- "epoch": 9.77,
- "learning_rate": 0.00013839285714285714,
- "loss": 1.4697,
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
"step": 483
},
{
- "epoch": 9.79,
- "learning_rate": 0.000138265306122449,
- "loss": 1.3989,
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
"step": 484
},
{
- "epoch": 9.81,
- "learning_rate": 0.00013813775510204083,
- "loss": 1.4361,
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
"step": 485
},
{
- "epoch": 9.83,
- "learning_rate": 0.00013801020408163266,
- "loss": 1.5271,
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
"step": 486
},
{
- "epoch": 9.85,
- "learning_rate": 0.0001378826530612245,
- "loss": 1.4905,
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
"step": 487
},
{
- "epoch": 9.87,
- "learning_rate": 0.00013775510204081635,
- "loss": 1.4757,
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
"step": 488
},
{
- "epoch": 9.89,
- "learning_rate": 0.00013762755102040815,
- "loss": 1.5485,
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
"step": 489
},
{
- "epoch": 9.91,
- "learning_rate": 0.0001375,
- "loss": 1.4783,
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
"step": 490
},
{
- "epoch": 9.93,
- "learning_rate": 0.00013737244897959184,
- "loss": 1.4849,
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
"step": 491
},
{
- "epoch": 9.96,
- "learning_rate": 0.00013724489795918367,
- "loss": 1.5382,
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
"step": 492
},
{
- "epoch": 9.98,
- "learning_rate": 0.00013711734693877553,
- "loss": 1.4902,
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
"step": 493
},
{
- "epoch": 10.0,
- "learning_rate": 0.00013698979591836736,
- "loss": 1.4865,
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
"step": 494
},
{
- "epoch": 10.02,
- "learning_rate": 0.0001368622448979592,
- "loss": 1.4436,
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
"step": 495
},
{
- "epoch": 10.04,
- "learning_rate": 0.00013673469387755102,
- "loss": 1.408,
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
"step": 496
},
{
- "epoch": 10.06,
- "learning_rate": 0.00013660714285714288,
- "loss": 1.4764,
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
"step": 497
},
{
- "epoch": 10.08,
- "learning_rate": 0.0001364795918367347,
- "loss": 1.4646,
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
"step": 498
},
{
- "epoch": 10.1,
- "learning_rate": 0.00013635204081632654,
- "loss": 1.406,
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
"step": 499
},
{
- "epoch": 10.12,
- "learning_rate": 0.00013622448979591837,
- "loss": 1.4785,
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
"step": 500
},
{
- "epoch": 10.14,
- "learning_rate": 0.00013609693877551023,
- "loss": 1.4117,
+ "epoch": 5.66,
+ "learning_rate": 0.00012883522727272727,
+ "loss": 1.0755,
"step": 501
},
{
- "epoch": 10.16,
- "learning_rate": 0.00013596938775510203,
- "loss": 1.4108,
+ "epoch": 5.67,
+ "learning_rate": 0.00012869318181818183,
+ "loss": 1.0755,
"step": 502
},
{
- "epoch": 10.18,
- "learning_rate": 0.0001358418367346939,
- "loss": 1.4155,
+ "epoch": 5.68,
+ "learning_rate": 0.00012855113636363636,
+ "loss": 1.0869,
"step": 503
},
{
- "epoch": 10.2,
- "learning_rate": 0.00013571428571428572,
- "loss": 1.4021,
+ "epoch": 5.69,
+ "learning_rate": 0.00012840909090909092,
+ "loss": 1.0673,
"step": 504
},
{
- "epoch": 10.22,
- "learning_rate": 0.00013558673469387755,
- "loss": 1.411,
+ "epoch": 5.71,
+ "learning_rate": 0.00012826704545454545,
+ "loss": 1.0692,
"step": 505
},
{
- "epoch": 10.24,
- "learning_rate": 0.00013545918367346938,
- "loss": 1.3851,
+ "epoch": 5.72,
+ "learning_rate": 0.000128125,
+ "loss": 1.0474,
"step": 506
},
{
- "epoch": 10.26,
- "learning_rate": 0.00013533163265306124,
- "loss": 1.387,
+ "epoch": 5.73,
+ "learning_rate": 0.00012798295454545454,
+ "loss": 1.0749,
"step": 507
},
{
- "epoch": 10.28,
- "learning_rate": 0.00013520408163265305,
- "loss": 1.4163,
+ "epoch": 5.74,
+ "learning_rate": 0.0001278409090909091,
+ "loss": 1.0519,
"step": 508
},
{
- "epoch": 10.3,
- "learning_rate": 0.0001350765306122449,
- "loss": 1.3343,
+ "epoch": 5.75,
+ "learning_rate": 0.00012769886363636366,
+ "loss": 1.0566,
"step": 509
},
{
- "epoch": 10.32,
- "learning_rate": 0.00013494897959183673,
- "loss": 1.4811,
+ "epoch": 5.76,
+ "learning_rate": 0.0001275568181818182,
+ "loss": 1.06,
"step": 510
},
{
- "epoch": 10.34,
- "learning_rate": 0.0001348214285714286,
- "loss": 1.4086,
+ "epoch": 5.77,
+ "learning_rate": 0.00012741477272727272,
+ "loss": 1.0618,
"step": 511
},
{
- "epoch": 10.36,
- "learning_rate": 0.0001346938775510204,
- "loss": 1.3879,
+ "epoch": 5.78,
+ "learning_rate": 0.00012727272727272728,
+ "loss": 1.0643,
"step": 512
},
{
- "epoch": 10.38,
- "learning_rate": 0.00013456632653061225,
- "loss": 1.4204,
+ "epoch": 5.8,
+ "learning_rate": 0.0001271306818181818,
+ "loss": 1.026,
"step": 513
},
{
- "epoch": 10.4,
- "learning_rate": 0.00013443877551020408,
- "loss": 1.4158,
+ "epoch": 5.81,
+ "learning_rate": 0.00012698863636363637,
+ "loss": 1.0335,
"step": 514
},
{
- "epoch": 10.42,
- "learning_rate": 0.00013431122448979592,
- "loss": 1.4521,
+ "epoch": 5.82,
+ "learning_rate": 0.00012684659090909093,
+ "loss": 1.0205,
"step": 515
},
{
- "epoch": 10.44,
- "learning_rate": 0.00013418367346938777,
- "loss": 1.4196,
+ "epoch": 5.83,
+ "learning_rate": 0.00012670454545454546,
+ "loss": 1.0594,
"step": 516
},
{
- "epoch": 10.46,
- "learning_rate": 0.0001340561224489796,
- "loss": 1.4361,
+ "epoch": 5.84,
+ "learning_rate": 0.0001265625,
+ "loss": 1.0136,
"step": 517
},
{
- "epoch": 10.48,
- "learning_rate": 0.00013392857142857144,
- "loss": 1.4482,
+ "epoch": 5.85,
+ "learning_rate": 0.00012642045454545455,
+ "loss": 1.0244,
"step": 518
},
{
- "epoch": 10.5,
- "learning_rate": 0.00013380102040816327,
- "loss": 1.4801,
+ "epoch": 5.86,
+ "learning_rate": 0.00012627840909090908,
+ "loss": 1.0569,
"step": 519
},
{
- "epoch": 10.52,
- "learning_rate": 0.00013367346938775512,
- "loss": 1.4556,
+ "epoch": 5.87,
+ "learning_rate": 0.00012613636363636364,
+ "loss": 1.0416,
"step": 520
},
{
- "epoch": 10.54,
- "learning_rate": 0.00013354591836734695,
- "loss": 1.3902,
+ "epoch": 5.89,
+ "learning_rate": 0.0001259943181818182,
+ "loss": 0.9884,
"step": 521
},
{
- "epoch": 10.56,
- "learning_rate": 0.00013341836734693879,
- "loss": 1.4269,
+ "epoch": 5.9,
+ "learning_rate": 0.00012585227272727273,
+ "loss": 1.0351,
"step": 522
},
{
- "epoch": 10.58,
- "learning_rate": 0.00013329081632653062,
- "loss": 1.4899,
+ "epoch": 5.91,
+ "learning_rate": 0.00012571022727272726,
+ "loss": 1.0037,
"step": 523
},
{
- "epoch": 10.6,
- "learning_rate": 0.00013316326530612247,
- "loss": 1.3952,
+ "epoch": 5.92,
+ "learning_rate": 0.00012556818181818182,
+ "loss": 1.0219,
"step": 524
},
{
- "epoch": 10.62,
- "learning_rate": 0.00013303571428571428,
- "loss": 1.4116,
+ "epoch": 5.93,
+ "learning_rate": 0.00012542613636363635,
+ "loss": 1.0533,
"step": 525
},
{
- "epoch": 10.64,
- "learning_rate": 0.00013290816326530614,
- "loss": 1.4583,
+ "epoch": 5.94,
+ "learning_rate": 0.0001252840909090909,
+ "loss": 1.0031,
"step": 526
},
{
- "epoch": 10.66,
- "learning_rate": 0.00013278061224489797,
- "loss": 1.4466,
+ "epoch": 5.95,
+ "learning_rate": 0.00012514204545454547,
+ "loss": 1.0454,
"step": 527
},
{
- "epoch": 10.68,
- "learning_rate": 0.0001326530612244898,
- "loss": 1.4242,
+ "epoch": 5.97,
+ "learning_rate": 0.000125,
+ "loss": 1.0195,
"step": 528
},
{
- "epoch": 10.7,
- "learning_rate": 0.00013252551020408163,
- "loss": 1.3717,
+ "epoch": 5.98,
+ "learning_rate": 0.00012485795454545453,
+ "loss": 1.0076,
"step": 529
},
{
- "epoch": 10.72,
- "learning_rate": 0.0001323979591836735,
- "loss": 1.4583,
+ "epoch": 5.99,
+ "learning_rate": 0.0001247159090909091,
+ "loss": 1.0378,
"step": 530
},
{
- "epoch": 10.74,
- "learning_rate": 0.0001322704081632653,
- "loss": 1.4185,
+ "epoch": 6.0,
+ "learning_rate": 0.00012457386363636365,
+ "loss": 0.9795,
"step": 531
},
{
- "epoch": 10.76,
- "learning_rate": 0.00013214285714285715,
- "loss": 1.4287,
+ "epoch": 6.01,
+ "learning_rate": 0.00012443181818181818,
+ "loss": 0.9405,
"step": 532
},
{
- "epoch": 10.78,
- "learning_rate": 0.00013201530612244898,
- "loss": 1.4385,
+ "epoch": 6.02,
+ "learning_rate": 0.00012428977272727274,
+ "loss": 0.9503,
"step": 533
},
{
- "epoch": 10.8,
- "learning_rate": 0.00013188775510204084,
- "loss": 1.453,
+ "epoch": 6.03,
+ "learning_rate": 0.00012414772727272727,
+ "loss": 0.9456,
"step": 534
},
{
- "epoch": 10.83,
- "learning_rate": 0.00013176020408163264,
- "loss": 1.4161,
+ "epoch": 6.04,
+ "learning_rate": 0.0001240056818181818,
+ "loss": 0.9536,
"step": 535
},
{
- "epoch": 10.85,
- "learning_rate": 0.0001316326530612245,
- "loss": 1.457,
+ "epoch": 6.06,
+ "learning_rate": 0.00012386363636363636,
+ "loss": 0.9412,
"step": 536
},
{
- "epoch": 10.87,
- "learning_rate": 0.00013150510204081633,
- "loss": 1.4367,
+ "epoch": 6.07,
+ "learning_rate": 0.00012372159090909092,
+ "loss": 0.9315,
"step": 537
},
{
- "epoch": 10.89,
- "learning_rate": 0.00013137755102040816,
- "loss": 1.4256,
+ "epoch": 6.08,
+ "learning_rate": 0.00012357954545454545,
+ "loss": 0.9486,
"step": 538
},
{
- "epoch": 10.91,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.424,
+ "epoch": 6.09,
+ "learning_rate": 0.0001234375,
+ "loss": 0.9405,
"step": 539
},
{
- "epoch": 10.93,
- "learning_rate": 0.00013112244897959185,
- "loss": 1.3923,
+ "epoch": 6.1,
+ "learning_rate": 0.00012329545454545454,
+ "loss": 0.9269,
"step": 540
},
{
- "epoch": 10.95,
- "learning_rate": 0.00013099489795918368,
- "loss": 1.4225,
+ "epoch": 6.11,
+ "learning_rate": 0.0001231534090909091,
+ "loss": 0.9378,
"step": 541
},
{
- "epoch": 10.97,
- "learning_rate": 0.0001308673469387755,
- "loss": 1.3969,
+ "epoch": 6.12,
+ "learning_rate": 0.00012301136363636366,
+ "loss": 0.9431,
"step": 542
},
{
- "epoch": 10.99,
- "learning_rate": 0.00013073979591836737,
- "loss": 1.4446,
+ "epoch": 6.13,
+ "learning_rate": 0.0001228693181818182,
+ "loss": 0.9256,
"step": 543
},
{
- "epoch": 11.01,
- "learning_rate": 0.00013061224489795917,
- "loss": 1.4375,
+ "epoch": 6.15,
+ "learning_rate": 0.00012272727272727272,
+ "loss": 0.919,
"step": 544
},
{
- "epoch": 11.03,
- "learning_rate": 0.00013048469387755103,
- "loss": 1.4064,
+ "epoch": 6.16,
+ "learning_rate": 0.00012258522727272728,
+ "loss": 0.9188,
"step": 545
},
{
- "epoch": 11.05,
- "learning_rate": 0.00013035714285714286,
- "loss": 1.3454,
+ "epoch": 6.17,
+ "learning_rate": 0.00012244318181818181,
+ "loss": 0.9447,
"step": 546
},
{
- "epoch": 11.07,
- "learning_rate": 0.00013022959183673472,
- "loss": 1.3234,
+ "epoch": 6.18,
+ "learning_rate": 0.00012230113636363637,
+ "loss": 0.9261,
"step": 547
},
{
- "epoch": 11.09,
- "learning_rate": 0.00013010204081632652,
- "loss": 1.3759,
+ "epoch": 6.19,
+ "learning_rate": 0.00012215909090909093,
+ "loss": 0.9302,
"step": 548
},
{
- "epoch": 11.11,
- "learning_rate": 0.00012997448979591838,
- "loss": 1.4221,
+ "epoch": 6.2,
+ "learning_rate": 0.00012201704545454546,
+ "loss": 0.9161,
"step": 549
},
{
- "epoch": 11.13,
- "learning_rate": 0.0001298469387755102,
- "loss": 1.4261,
+ "epoch": 6.21,
+ "learning_rate": 0.00012187500000000001,
+ "loss": 0.9521,
"step": 550
},
{
- "epoch": 11.15,
- "learning_rate": 0.00012971938775510204,
- "loss": 1.3341,
+ "epoch": 6.22,
+ "learning_rate": 0.00012173295454545455,
+ "loss": 0.9026,
"step": 551
},
{
- "epoch": 11.17,
- "learning_rate": 0.00012959183673469387,
- "loss": 1.3994,
+ "epoch": 6.24,
+ "learning_rate": 0.00012159090909090908,
+ "loss": 0.9361,
"step": 552
},
{
- "epoch": 11.19,
- "learning_rate": 0.00012946428571428573,
- "loss": 1.3894,
+ "epoch": 6.25,
+ "learning_rate": 0.00012144886363636366,
+ "loss": 0.8944,
"step": 553
},
{
- "epoch": 11.21,
- "learning_rate": 0.00012933673469387754,
- "loss": 1.3585,
+ "epoch": 6.26,
+ "learning_rate": 0.00012130681818181819,
+ "loss": 0.895,
"step": 554
},
{
- "epoch": 11.23,
- "learning_rate": 0.0001292091836734694,
- "loss": 1.3763,
+ "epoch": 6.27,
+ "learning_rate": 0.00012116477272727273,
+ "loss": 0.8956,
"step": 555
},
{
- "epoch": 11.25,
- "learning_rate": 0.00012908163265306123,
- "loss": 1.3623,
+ "epoch": 6.28,
+ "learning_rate": 0.00012102272727272728,
+ "loss": 0.8998,
"step": 556
},
{
- "epoch": 11.27,
- "learning_rate": 0.00012895408163265306,
- "loss": 1.3907,
+ "epoch": 6.29,
+ "learning_rate": 0.00012088068181818182,
+ "loss": 0.915,
"step": 557
},
{
- "epoch": 11.29,
- "learning_rate": 0.0001288265306122449,
- "loss": 1.3807,
+ "epoch": 6.3,
+ "learning_rate": 0.00012073863636363636,
+ "loss": 0.9282,
"step": 558
},
{
- "epoch": 11.31,
- "learning_rate": 0.00012869897959183674,
- "loss": 1.4045,
+ "epoch": 6.32,
+ "learning_rate": 0.00012059659090909093,
+ "loss": 0.8938,
"step": 559
},
{
- "epoch": 11.33,
- "learning_rate": 0.00012857142857142858,
- "loss": 1.4038,
+ "epoch": 6.33,
+ "learning_rate": 0.00012045454545454546,
+ "loss": 0.8886,
"step": 560
},
{
- "epoch": 11.35,
- "learning_rate": 0.0001284438775510204,
- "loss": 1.3466,
+ "epoch": 6.34,
+ "learning_rate": 0.0001203125,
+ "loss": 0.8988,
"step": 561
},
{
- "epoch": 11.37,
- "learning_rate": 0.00012831632653061226,
- "loss": 1.3449,
+ "epoch": 6.35,
+ "learning_rate": 0.00012017045454545455,
+ "loss": 0.8852,
"step": 562
},
{
- "epoch": 11.39,
- "learning_rate": 0.0001281887755102041,
- "loss": 1.3866,
+ "epoch": 6.36,
+ "learning_rate": 0.0001200284090909091,
+ "loss": 0.8818,
"step": 563
},
{
- "epoch": 11.41,
- "learning_rate": 0.00012806122448979593,
- "loss": 1.3106,
+ "epoch": 6.37,
+ "learning_rate": 0.00011988636363636365,
+ "loss": 0.8881,
"step": 564
},
{
- "epoch": 11.43,
- "learning_rate": 0.00012793367346938776,
- "loss": 1.4414,
+ "epoch": 6.38,
+ "learning_rate": 0.0001197443181818182,
+ "loss": 0.9226,
"step": 565
},
{
- "epoch": 11.45,
- "learning_rate": 0.00012780612244897962,
- "loss": 1.3737,
+ "epoch": 6.39,
+ "learning_rate": 0.00011960227272727273,
+ "loss": 0.8849,
"step": 566
},
{
- "epoch": 11.47,
- "learning_rate": 0.00012767857142857142,
- "loss": 1.4053,
+ "epoch": 6.41,
+ "learning_rate": 0.00011946022727272727,
+ "loss": 0.8894,
"step": 567
},
{
- "epoch": 11.49,
- "learning_rate": 0.00012755102040816328,
- "loss": 1.4561,
+ "epoch": 6.42,
+ "learning_rate": 0.00011931818181818182,
+ "loss": 0.9207,
"step": 568
},
{
- "epoch": 11.51,
- "learning_rate": 0.0001274234693877551,
- "loss": 1.3684,
+ "epoch": 6.43,
+ "learning_rate": 0.00011917613636363636,
+ "loss": 0.9105,
"step": 569
},
{
- "epoch": 11.53,
- "learning_rate": 0.00012729591836734697,
- "loss": 1.3117,
+ "epoch": 6.44,
+ "learning_rate": 0.00011903409090909092,
+ "loss": 0.8762,
"step": 570
},
{
- "epoch": 11.55,
- "learning_rate": 0.00012716836734693877,
- "loss": 1.3474,
+ "epoch": 6.45,
+ "learning_rate": 0.00011889204545454547,
+ "loss": 0.8926,
"step": 571
},
{
- "epoch": 11.57,
- "learning_rate": 0.00012704081632653063,
- "loss": 1.3804,
+ "epoch": 6.46,
+ "learning_rate": 0.00011875,
+ "loss": 0.8719,
"step": 572
},
{
- "epoch": 11.59,
- "learning_rate": 0.00012691326530612246,
- "loss": 1.3656,
+ "epoch": 6.47,
+ "learning_rate": 0.00011860795454545454,
+ "loss": 0.9198,
"step": 573
},
{
- "epoch": 11.61,
- "learning_rate": 0.0001267857142857143,
- "loss": 1.3133,
+ "epoch": 6.48,
+ "learning_rate": 0.00011846590909090909,
+ "loss": 0.8846,
"step": 574
},
{
- "epoch": 11.63,
- "learning_rate": 0.00012665816326530612,
- "loss": 1.4077,
+ "epoch": 6.5,
+ "learning_rate": 0.00011832386363636365,
+ "loss": 0.8495,
"step": 575
},
{
- "epoch": 11.65,
- "learning_rate": 0.00012653061224489798,
- "loss": 1.4087,
+ "epoch": 6.51,
+ "learning_rate": 0.0001181818181818182,
+ "loss": 0.8953,
"step": 576
},
{
- "epoch": 11.67,
- "learning_rate": 0.00012640306122448978,
- "loss": 1.3524,
+ "epoch": 6.52,
+ "learning_rate": 0.00011803977272727274,
+ "loss": 0.8686,
"step": 577
},
{
- "epoch": 11.7,
- "learning_rate": 0.00012627551020408164,
- "loss": 1.3481,
+ "epoch": 6.53,
+ "learning_rate": 0.00011789772727272727,
+ "loss": 0.8841,
"step": 578
},
{
- "epoch": 11.72,
- "learning_rate": 0.00012614795918367347,
- "loss": 1.4497,
+ "epoch": 6.54,
+ "learning_rate": 0.00011775568181818182,
+ "loss": 0.8681,
"step": 579
},
{
- "epoch": 11.74,
- "learning_rate": 0.0001260204081632653,
- "loss": 1.3866,
+ "epoch": 6.55,
+ "learning_rate": 0.00011761363636363636,
+ "loss": 0.8732,
"step": 580
},
{
- "epoch": 11.76,
- "learning_rate": 0.00012589285714285713,
- "loss": 1.42,
+ "epoch": 6.56,
+ "learning_rate": 0.00011747159090909092,
+ "loss": 0.8582,
"step": 581
},
{
- "epoch": 11.78,
- "learning_rate": 0.000125765306122449,
- "loss": 1.3562,
+ "epoch": 6.58,
+ "learning_rate": 0.00011732954545454546,
+ "loss": 0.8744,
"step": 582
},
{
- "epoch": 11.8,
- "learning_rate": 0.00012563775510204082,
- "loss": 1.3249,
+ "epoch": 6.59,
+ "learning_rate": 0.00011718750000000001,
+ "loss": 0.8694,
"step": 583
},
{
- "epoch": 11.82,
- "learning_rate": 0.00012551020408163265,
- "loss": 1.4277,
+ "epoch": 6.6,
+ "learning_rate": 0.00011704545454545454,
+ "loss": 0.8565,
"step": 584
},
{
- "epoch": 11.84,
- "learning_rate": 0.0001253826530612245,
- "loss": 1.3734,
+ "epoch": 6.61,
+ "learning_rate": 0.00011690340909090909,
+ "loss": 0.8584,
"step": 585
},
{
- "epoch": 11.86,
- "learning_rate": 0.00012525510204081634,
- "loss": 1.3765,
+ "epoch": 6.62,
+ "learning_rate": 0.00011676136363636366,
+ "loss": 0.8859,
"step": 586
},
{
- "epoch": 11.88,
- "learning_rate": 0.00012512755102040817,
- "loss": 1.4153,
+ "epoch": 6.63,
+ "learning_rate": 0.00011661931818181819,
+ "loss": 0.8452,
"step": 587
},
{
- "epoch": 11.9,
- "learning_rate": 0.000125,
- "loss": 1.3847,
+ "epoch": 6.64,
+ "learning_rate": 0.00011647727272727273,
+ "loss": 0.8323,
"step": 588
},
{
- "epoch": 11.92,
- "learning_rate": 0.00012487244897959186,
- "loss": 1.3824,
+ "epoch": 6.65,
+ "learning_rate": 0.00011633522727272728,
+ "loss": 0.8548,
"step": 589
},
{
- "epoch": 11.94,
- "learning_rate": 0.00012474489795918366,
- "loss": 1.3938,
+ "epoch": 6.67,
+ "learning_rate": 0.00011619318181818181,
+ "loss": 0.8506,
"step": 590
},
{
- "epoch": 11.96,
- "learning_rate": 0.00012461734693877552,
- "loss": 1.4143,
+ "epoch": 6.68,
+ "learning_rate": 0.00011605113636363636,
+ "loss": 0.8556,
"step": 591
},
{
- "epoch": 11.98,
- "learning_rate": 0.00012448979591836735,
- "loss": 1.3794,
+ "epoch": 6.69,
+ "learning_rate": 0.00011590909090909093,
+ "loss": 0.8459,
"step": 592
},
{
- "epoch": 12.0,
- "learning_rate": 0.00012436224489795918,
- "loss": 1.3755,
+ "epoch": 6.7,
+ "learning_rate": 0.00011576704545454546,
+ "loss": 0.8432,
"step": 593
},
{
- "epoch": 12.02,
- "learning_rate": 0.00012423469387755101,
- "loss": 1.3736,
+ "epoch": 6.71,
+ "learning_rate": 0.000115625,
+ "loss": 0.8645,
"step": 594
},
{
- "epoch": 12.04,
- "learning_rate": 0.00012410714285714287,
- "loss": 1.2957,
+ "epoch": 6.72,
+ "learning_rate": 0.00011548295454545455,
+ "loss": 0.86,
"step": 595
},
{
- "epoch": 12.06,
- "learning_rate": 0.0001239795918367347,
- "loss": 1.2996,
+ "epoch": 6.73,
+ "learning_rate": 0.00011534090909090908,
+ "loss": 0.8161,
"step": 596
},
{
- "epoch": 12.08,
- "learning_rate": 0.00012385204081632653,
- "loss": 1.3648,
+ "epoch": 6.74,
+ "learning_rate": 0.00011519886363636365,
+ "loss": 0.8133,
"step": 597
},
{
- "epoch": 12.1,
- "learning_rate": 0.00012372448979591837,
- "loss": 1.3031,
+ "epoch": 6.76,
+ "learning_rate": 0.0001150568181818182,
+ "loss": 0.8372,
"step": 598
},
{
- "epoch": 12.12,
- "learning_rate": 0.00012359693877551022,
- "loss": 1.2933,
+ "epoch": 6.77,
+ "learning_rate": 0.00011491477272727273,
+ "loss": 0.8222,
"step": 599
},
{
- "epoch": 12.14,
- "learning_rate": 0.00012346938775510203,
- "loss": 1.322,
+ "epoch": 6.78,
+ "learning_rate": 0.00011477272727272728,
+ "loss": 0.8372,
"step": 600
},
{
- "epoch": 12.16,
- "learning_rate": 0.00012334183673469389,
- "loss": 1.3123,
+ "epoch": 6.79,
+ "learning_rate": 0.00011463068181818182,
+ "loss": 0.837,
"step": 601
},
{
- "epoch": 12.18,
- "learning_rate": 0.00012321428571428572,
- "loss": 1.3187,
+ "epoch": 6.8,
+ "learning_rate": 0.00011448863636363637,
+ "loss": 0.8406,
"step": 602
},
{
- "epoch": 12.2,
- "learning_rate": 0.00012308673469387755,
- "loss": 1.3353,
+ "epoch": 6.81,
+ "learning_rate": 0.00011434659090909092,
+ "loss": 0.836,
"step": 603
},
{
- "epoch": 12.22,
- "learning_rate": 0.0001229591836734694,
- "loss": 1.3221,
+ "epoch": 6.82,
+ "learning_rate": 0.00011420454545454547,
+ "loss": 0.8476,
"step": 604
},
{
- "epoch": 12.24,
- "learning_rate": 0.00012283163265306124,
- "loss": 1.3458,
+ "epoch": 6.83,
+ "learning_rate": 0.0001140625,
+ "loss": 0.8368,
"step": 605
},
{
- "epoch": 12.26,
- "learning_rate": 0.00012270408163265307,
- "loss": 1.275,
+ "epoch": 6.85,
+ "learning_rate": 0.00011392045454545455,
+ "loss": 0.822,
"step": 606
},
{
- "epoch": 12.28,
- "learning_rate": 0.0001225765306122449,
- "loss": 1.3455,
+ "epoch": 6.86,
+ "learning_rate": 0.00011377840909090909,
+ "loss": 0.8107,
"step": 607
},
{
- "epoch": 12.3,
- "learning_rate": 0.00012244897959183676,
- "loss": 1.2769,
+ "epoch": 6.87,
+ "learning_rate": 0.00011363636363636365,
+ "loss": 0.8395,
"step": 608
},
{
- "epoch": 12.32,
- "learning_rate": 0.00012232142857142859,
- "loss": 1.3201,
+ "epoch": 6.88,
+ "learning_rate": 0.0001134943181818182,
+ "loss": 0.8083,
"step": 609
},
{
- "epoch": 12.34,
- "learning_rate": 0.00012219387755102042,
- "loss": 1.3073,
+ "epoch": 6.89,
+ "learning_rate": 0.00011335227272727274,
+ "loss": 0.828,
"step": 610
},
{
- "epoch": 12.36,
- "learning_rate": 0.00012206632653061225,
- "loss": 1.3103,
+ "epoch": 6.9,
+ "learning_rate": 0.00011321022727272727,
+ "loss": 0.8494,
"step": 611
},
{
- "epoch": 12.38,
- "learning_rate": 0.00012193877551020409,
- "loss": 1.4437,
+ "epoch": 6.91,
+ "learning_rate": 0.00011306818181818182,
+ "loss": 0.8169,
"step": 612
},
{
- "epoch": 12.4,
- "learning_rate": 0.00012181122448979591,
- "loss": 1.3086,
+ "epoch": 6.93,
+ "learning_rate": 0.00011292613636363636,
+ "loss": 0.8224,
"step": 613
},
{
- "epoch": 12.42,
- "learning_rate": 0.00012168367346938775,
- "loss": 1.3867,
+ "epoch": 6.94,
+ "learning_rate": 0.00011278409090909092,
+ "loss": 0.8173,
"step": 614
},
{
- "epoch": 12.44,
- "learning_rate": 0.0001215561224489796,
- "loss": 1.2565,
+ "epoch": 6.95,
+ "learning_rate": 0.00011264204545454547,
+ "loss": 0.7961,
"step": 615
},
{
- "epoch": 12.46,
- "learning_rate": 0.00012142857142857143,
- "loss": 1.335,
+ "epoch": 6.96,
+ "learning_rate": 0.00011250000000000001,
+ "loss": 0.7948,
"step": 616
},
{
- "epoch": 12.48,
- "learning_rate": 0.00012130102040816327,
- "loss": 1.3423,
+ "epoch": 6.97,
+ "learning_rate": 0.00011235795454545454,
+ "loss": 0.7746,
"step": 617
},
{
- "epoch": 12.5,
- "learning_rate": 0.00012117346938775512,
- "loss": 1.3433,
+ "epoch": 6.98,
+ "learning_rate": 0.00011221590909090909,
+ "loss": 0.8325,
"step": 618
},
{
- "epoch": 12.52,
- "learning_rate": 0.00012104591836734695,
- "loss": 1.3387,
+ "epoch": 6.99,
+ "learning_rate": 0.00011207386363636365,
+ "loss": 0.8149,
"step": 619
},
{
- "epoch": 12.55,
- "learning_rate": 0.00012091836734693878,
- "loss": 1.3923,
+ "epoch": 7.0,
+ "learning_rate": 0.00011193181818181819,
+ "loss": 0.7516,
"step": 620
},
{
- "epoch": 12.57,
- "learning_rate": 0.00012079081632653062,
- "loss": 1.3774,
+ "epoch": 7.02,
+ "learning_rate": 0.00011178977272727274,
+ "loss": 0.7571,
"step": 621
},
{
- "epoch": 12.59,
- "learning_rate": 0.00012066326530612247,
- "loss": 1.3203,
+ "epoch": 7.03,
+ "learning_rate": 0.00011164772727272728,
+ "loss": 0.7397,
"step": 622
},
{
- "epoch": 12.61,
- "learning_rate": 0.00012053571428571429,
- "loss": 1.2924,
+ "epoch": 7.04,
+ "learning_rate": 0.00011150568181818181,
+ "loss": 0.761,
"step": 623
},
{
- "epoch": 12.63,
- "learning_rate": 0.00012040816326530613,
- "loss": 1.3292,
+ "epoch": 7.05,
+ "learning_rate": 0.00011136363636363636,
+ "loss": 0.7783,
"step": 624
},
{
- "epoch": 12.65,
- "learning_rate": 0.00012028061224489798,
- "loss": 1.3161,
+ "epoch": 7.06,
+ "learning_rate": 0.00011122159090909092,
+ "loss": 0.7571,
"step": 625
},
{
- "epoch": 12.67,
- "learning_rate": 0.00012015306122448979,
- "loss": 1.352,
+ "epoch": 7.07,
+ "learning_rate": 0.00011107954545454546,
+ "loss": 0.7628,
"step": 626
},
{
- "epoch": 12.69,
- "learning_rate": 0.00012002551020408164,
- "loss": 1.3577,
+ "epoch": 7.08,
+ "learning_rate": 0.0001109375,
+ "loss": 0.7561,
"step": 627
},
{
- "epoch": 12.71,
- "learning_rate": 0.00011989795918367348,
- "loss": 1.3575,
+ "epoch": 7.09,
+ "learning_rate": 0.00011079545454545455,
+ "loss": 0.7432,
"step": 628
},
{
- "epoch": 12.73,
- "learning_rate": 0.0001197704081632653,
- "loss": 1.3727,
+ "epoch": 7.11,
+ "learning_rate": 0.00011065340909090908,
+ "loss": 0.7245,
"step": 629
},
{
- "epoch": 12.75,
- "learning_rate": 0.00011964285714285714,
- "loss": 1.3312,
+ "epoch": 7.12,
+ "learning_rate": 0.00011051136363636366,
+ "loss": 0.7279,
"step": 630
},
{
- "epoch": 12.77,
- "learning_rate": 0.00011951530612244899,
- "loss": 1.3378,
+ "epoch": 7.13,
+ "learning_rate": 0.00011036931818181819,
+ "loss": 0.7347,
"step": 631
},
{
- "epoch": 12.79,
- "learning_rate": 0.00011938775510204083,
- "loss": 1.295,
+ "epoch": 7.14,
+ "learning_rate": 0.00011022727272727273,
+ "loss": 0.7427,
"step": 632
},
{
- "epoch": 12.81,
- "learning_rate": 0.00011926020408163265,
- "loss": 1.3447,
+ "epoch": 7.15,
+ "learning_rate": 0.00011008522727272728,
+ "loss": 0.7339,
"step": 633
},
{
- "epoch": 12.83,
- "learning_rate": 0.0001191326530612245,
- "loss": 1.3835,
+ "epoch": 7.16,
+ "learning_rate": 0.00010994318181818182,
+ "loss": 0.7375,
"step": 634
},
{
- "epoch": 12.85,
- "learning_rate": 0.00011900510204081634,
- "loss": 1.3222,
+ "epoch": 7.17,
+ "learning_rate": 0.00010980113636363635,
+ "loss": 0.7182,
"step": 635
},
{
- "epoch": 12.87,
- "learning_rate": 0.00011887755102040817,
- "loss": 1.2851,
+ "epoch": 7.19,
+ "learning_rate": 0.00010965909090909093,
+ "loss": 0.7452,
"step": 636
},
{
- "epoch": 12.89,
- "learning_rate": 0.00011875,
- "loss": 1.2723,
+ "epoch": 7.2,
+ "learning_rate": 0.00010951704545454546,
+ "loss": 0.7565,
"step": 637
},
{
- "epoch": 12.91,
- "learning_rate": 0.00011862244897959184,
- "loss": 1.3924,
+ "epoch": 7.21,
+ "learning_rate": 0.000109375,
+ "loss": 0.7296,
"step": 638
},
{
- "epoch": 12.93,
- "learning_rate": 0.00011849489795918368,
- "loss": 1.4625,
+ "epoch": 7.22,
+ "learning_rate": 0.00010923295454545455,
+ "loss": 0.7484,
"step": 639
},
{
- "epoch": 12.95,
- "learning_rate": 0.00011836734693877552,
- "loss": 1.3245,
+ "epoch": 7.23,
+ "learning_rate": 0.00010909090909090909,
+ "loss": 0.732,
"step": 640
},
{
- "epoch": 12.97,
- "learning_rate": 0.00011823979591836736,
- "loss": 1.4042,
+ "epoch": 7.24,
+ "learning_rate": 0.00010894886363636365,
+ "loss": 0.7415,
"step": 641
},
{
- "epoch": 12.99,
- "learning_rate": 0.00011811224489795918,
- "loss": 1.3761,
+ "epoch": 7.25,
+ "learning_rate": 0.0001088068181818182,
+ "loss": 0.7344,
"step": 642
},
{
- "epoch": 13.01,
- "learning_rate": 0.00011798469387755103,
- "loss": 1.3376,
+ "epoch": 7.26,
+ "learning_rate": 0.00010866477272727274,
+ "loss": 0.7267,
"step": 643
},
{
- "epoch": 13.03,
- "learning_rate": 0.00011785714285714287,
- "loss": 1.2174,
+ "epoch": 7.28,
+ "learning_rate": 0.00010852272727272727,
+ "loss": 0.7543,
"step": 644
},
{
- "epoch": 13.05,
- "learning_rate": 0.00011772959183673471,
- "loss": 1.3602,
+ "epoch": 7.29,
+ "learning_rate": 0.00010838068181818182,
+ "loss": 0.7266,
"step": 645
},
{
- "epoch": 13.07,
- "learning_rate": 0.00011760204081632653,
- "loss": 1.3002,
+ "epoch": 7.3,
+ "learning_rate": 0.00010823863636363636,
+ "loss": 0.7449,
"step": 646
},
{
- "epoch": 13.09,
- "learning_rate": 0.00011747448979591838,
- "loss": 1.2262,
+ "epoch": 7.31,
+ "learning_rate": 0.00010809659090909092,
+ "loss": 0.7324,
"step": 647
},
{
- "epoch": 13.11,
- "learning_rate": 0.00011734693877551022,
- "loss": 1.3048,
+ "epoch": 7.32,
+ "learning_rate": 0.00010795454545454547,
+ "loss": 0.7268,
"step": 648
},
{
- "epoch": 13.13,
- "learning_rate": 0.00011721938775510204,
- "loss": 1.2231,
+ "epoch": 7.33,
+ "learning_rate": 0.00010781250000000001,
+ "loss": 0.7172,
"step": 649
},
{
- "epoch": 13.15,
- "learning_rate": 0.00011709183673469388,
- "loss": 1.2996,
+ "epoch": 7.34,
+ "learning_rate": 0.00010767045454545454,
+ "loss": 0.7169,
"step": 650
},
{
- "epoch": 13.17,
- "learning_rate": 0.00011696428571428573,
- "loss": 1.2708,
+ "epoch": 7.35,
+ "learning_rate": 0.00010752840909090909,
+ "loss": 0.7194,
"step": 651
},
{
- "epoch": 13.19,
- "learning_rate": 0.00011683673469387754,
- "loss": 1.2776,
+ "epoch": 7.37,
+ "learning_rate": 0.00010738636363636365,
+ "loss": 0.7223,
"step": 652
},
{
- "epoch": 13.21,
- "learning_rate": 0.00011670918367346939,
- "loss": 1.248,
+ "epoch": 7.38,
+ "learning_rate": 0.00010724431818181819,
+ "loss": 0.7158,
"step": 653
},
{
- "epoch": 13.23,
- "learning_rate": 0.00011658163265306123,
- "loss": 1.2582,
+ "epoch": 7.39,
+ "learning_rate": 0.00010710227272727274,
+ "loss": 0.7122,
"step": 654
},
{
- "epoch": 13.25,
- "learning_rate": 0.00011645408163265305,
- "loss": 1.3011,
+ "epoch": 7.4,
+ "learning_rate": 0.00010696022727272728,
+ "loss": 0.7225,
"step": 655
},
{
- "epoch": 13.27,
- "learning_rate": 0.0001163265306122449,
- "loss": 1.2969,
+ "epoch": 7.41,
+ "learning_rate": 0.00010681818181818181,
+ "loss": 0.7102,
"step": 656
},
{
- "epoch": 13.29,
- "learning_rate": 0.00011619897959183674,
- "loss": 1.2454,
+ "epoch": 7.42,
+ "learning_rate": 0.00010667613636363636,
+ "loss": 0.7251,
"step": 657
},
{
- "epoch": 13.31,
- "learning_rate": 0.00011607142857142858,
- "loss": 1.1914,
+ "epoch": 7.43,
+ "learning_rate": 0.00010653409090909092,
+ "loss": 0.7191,
"step": 658
},
{
- "epoch": 13.33,
- "learning_rate": 0.00011594387755102041,
- "loss": 1.34,
+ "epoch": 7.45,
+ "learning_rate": 0.00010639204545454546,
+ "loss": 0.7015,
"step": 659
},
{
- "epoch": 13.35,
- "learning_rate": 0.00011581632653061225,
- "loss": 1.2828,
+ "epoch": 7.46,
+ "learning_rate": 0.00010625000000000001,
+ "loss": 0.693,
"step": 660
},
{
- "epoch": 13.37,
- "learning_rate": 0.00011568877551020409,
- "loss": 1.2962,
+ "epoch": 7.47,
+ "learning_rate": 0.00010610795454545455,
+ "loss": 0.7039,
"step": 661
},
{
- "epoch": 13.39,
- "learning_rate": 0.00011556122448979592,
- "loss": 1.3334,
+ "epoch": 7.48,
+ "learning_rate": 0.00010596590909090908,
+ "loss": 0.7305,
"step": 662
},
{
- "epoch": 13.42,
- "learning_rate": 0.00011543367346938776,
- "loss": 1.2832,
+ "epoch": 7.49,
+ "learning_rate": 0.00010582386363636366,
+ "loss": 0.6978,
"step": 663
},
{
- "epoch": 13.44,
- "learning_rate": 0.00011530612244897961,
- "loss": 1.3012,
+ "epoch": 7.5,
+ "learning_rate": 0.00010568181818181819,
+ "loss": 0.7219,
"step": 664
},
{
- "epoch": 13.46,
- "learning_rate": 0.00011517857142857143,
- "loss": 1.2857,
+ "epoch": 7.51,
+ "learning_rate": 0.00010553977272727273,
+ "loss": 0.7199,
"step": 665
},
{
- "epoch": 13.48,
- "learning_rate": 0.00011505102040816327,
- "loss": 1.2855,
+ "epoch": 7.52,
+ "learning_rate": 0.00010539772727272728,
+ "loss": 0.6979,
"step": 666
},
{
- "epoch": 13.5,
- "learning_rate": 0.00011492346938775512,
- "loss": 1.3077,
+ "epoch": 7.54,
+ "learning_rate": 0.00010525568181818182,
+ "loss": 0.7058,
"step": 667
},
{
- "epoch": 13.52,
- "learning_rate": 0.00011479591836734696,
- "loss": 1.3139,
+ "epoch": 7.55,
+ "learning_rate": 0.00010511363636363635,
+ "loss": 0.6994,
"step": 668
},
{
- "epoch": 13.54,
- "learning_rate": 0.00011466836734693878,
- "loss": 1.3138,
+ "epoch": 7.56,
+ "learning_rate": 0.00010497159090909093,
+ "loss": 0.7141,
"step": 669
},
{
- "epoch": 13.56,
- "learning_rate": 0.00011454081632653062,
- "loss": 1.2808,
+ "epoch": 7.57,
+ "learning_rate": 0.00010482954545454546,
+ "loss": 0.7092,
"step": 670
},
{
- "epoch": 13.58,
- "learning_rate": 0.00011441326530612247,
- "loss": 1.2492,
+ "epoch": 7.58,
+ "learning_rate": 0.0001046875,
+ "loss": 0.7059,
"step": 671
},
{
- "epoch": 13.6,
- "learning_rate": 0.00011428571428571428,
- "loss": 1.2027,
+ "epoch": 7.59,
+ "learning_rate": 0.00010454545454545455,
+ "loss": 0.6904,
"step": 672
},
{
- "epoch": 13.62,
- "learning_rate": 0.00011415816326530613,
- "loss": 1.33,
+ "epoch": 7.6,
+ "learning_rate": 0.0001044034090909091,
+ "loss": 0.7115,
"step": 673
},
{
- "epoch": 13.64,
- "learning_rate": 0.00011403061224489797,
- "loss": 1.3112,
+ "epoch": 7.61,
+ "learning_rate": 0.00010426136363636365,
+ "loss": 0.7254,
"step": 674
},
{
- "epoch": 13.66,
- "learning_rate": 0.00011390306122448979,
- "loss": 1.2772,
+ "epoch": 7.63,
+ "learning_rate": 0.0001041193181818182,
+ "loss": 0.7181,
"step": 675
},
{
- "epoch": 13.68,
- "learning_rate": 0.00011377551020408163,
- "loss": 1.2701,
+ "epoch": 7.64,
+ "learning_rate": 0.00010397727272727273,
+ "loss": 0.6867,
"step": 676
},
{
- "epoch": 13.7,
- "learning_rate": 0.00011364795918367348,
- "loss": 1.1973,
+ "epoch": 7.65,
+ "learning_rate": 0.00010383522727272727,
+ "loss": 0.6917,
"step": 677
},
{
- "epoch": 13.72,
- "learning_rate": 0.0001135204081632653,
- "loss": 1.3124,
+ "epoch": 7.66,
+ "learning_rate": 0.00010369318181818182,
+ "loss": 0.6908,
"step": 678
},
{
- "epoch": 13.74,
- "learning_rate": 0.00011339285714285714,
- "loss": 1.3085,
+ "epoch": 7.67,
+ "learning_rate": 0.00010355113636363636,
+ "loss": 0.6871,
"step": 679
},
{
- "epoch": 13.76,
- "learning_rate": 0.00011326530612244898,
- "loss": 1.3457,
+ "epoch": 7.68,
+ "learning_rate": 0.00010340909090909092,
+ "loss": 0.682,
"step": 680
},
{
- "epoch": 13.78,
- "learning_rate": 0.00011313775510204083,
- "loss": 1.3338,
+ "epoch": 7.69,
+ "learning_rate": 0.00010326704545454547,
+ "loss": 0.6737,
"step": 681
},
{
- "epoch": 13.8,
- "learning_rate": 0.00011301020408163266,
- "loss": 1.2753,
+ "epoch": 7.7,
+ "learning_rate": 0.000103125,
+ "loss": 0.7023,
"step": 682
},
{
- "epoch": 13.82,
- "learning_rate": 0.00011288265306122449,
- "loss": 1.2786,
+ "epoch": 7.72,
+ "learning_rate": 0.00010298295454545454,
+ "loss": 0.7079,
"step": 683
},
{
- "epoch": 13.84,
- "learning_rate": 0.00011275510204081634,
- "loss": 1.2584,
+ "epoch": 7.73,
+ "learning_rate": 0.00010284090909090909,
+ "loss": 0.6954,
"step": 684
},
{
- "epoch": 13.86,
- "learning_rate": 0.00011262755102040817,
- "loss": 1.2779,
+ "epoch": 7.74,
+ "learning_rate": 0.00010269886363636365,
+ "loss": 0.6834,
"step": 685
},
{
- "epoch": 13.88,
- "learning_rate": 0.00011250000000000001,
- "loss": 1.3502,
+ "epoch": 7.75,
+ "learning_rate": 0.0001025568181818182,
+ "loss": 0.6706,
"step": 686
},
{
- "epoch": 13.9,
- "learning_rate": 0.00011237244897959185,
- "loss": 1.3251,
+ "epoch": 7.76,
+ "learning_rate": 0.00010241477272727274,
+ "loss": 0.6706,
"step": 687
},
{
- "epoch": 13.92,
- "learning_rate": 0.00011224489795918367,
- "loss": 1.273,
+ "epoch": 7.77,
+ "learning_rate": 0.00010227272727272727,
+ "loss": 0.681,
"step": 688
},
{
- "epoch": 13.94,
- "learning_rate": 0.00011211734693877552,
- "loss": 1.3341,
+ "epoch": 7.78,
+ "learning_rate": 0.00010213068181818182,
+ "loss": 0.6853,
"step": 689
},
{
- "epoch": 13.96,
- "learning_rate": 0.00011198979591836736,
- "loss": 1.2654,
+ "epoch": 7.8,
+ "learning_rate": 0.00010198863636363636,
+ "loss": 0.6772,
"step": 690
},
{
- "epoch": 13.98,
- "learning_rate": 0.00011186224489795918,
- "loss": 1.3333,
+ "epoch": 7.81,
+ "learning_rate": 0.00010184659090909092,
+ "loss": 0.6635,
"step": 691
},
{
- "epoch": 14.0,
- "learning_rate": 0.00011173469387755102,
- "loss": 1.3246,
+ "epoch": 7.82,
+ "learning_rate": 0.00010170454545454546,
+ "loss": 0.6712,
"step": 692
},
{
- "epoch": 14.02,
- "learning_rate": 0.00011160714285714287,
- "loss": 1.2547,
+ "epoch": 7.83,
+ "learning_rate": 0.00010156250000000001,
+ "loss": 0.6884,
"step": 693
},
{
- "epoch": 14.04,
- "learning_rate": 0.00011147959183673471,
- "loss": 1.208,
+ "epoch": 7.84,
+ "learning_rate": 0.00010142045454545454,
+ "loss": 0.6641,
"step": 694
},
{
- "epoch": 14.06,
- "learning_rate": 0.00011135204081632653,
- "loss": 1.223,
+ "epoch": 7.85,
+ "learning_rate": 0.00010127840909090909,
+ "loss": 0.6838,
"step": 695
},
{
- "epoch": 14.08,
- "learning_rate": 0.00011122448979591837,
- "loss": 1.2483,
+ "epoch": 7.86,
+ "learning_rate": 0.00010113636363636366,
+ "loss": 0.675,
"step": 696
},
{
- "epoch": 14.1,
- "learning_rate": 0.00011109693877551022,
- "loss": 1.2823,
+ "epoch": 7.87,
+ "learning_rate": 0.00010099431818181819,
+ "loss": 0.6626,
"step": 697
},
{
- "epoch": 14.12,
- "learning_rate": 0.00011096938775510204,
- "loss": 1.2013,
+ "epoch": 7.89,
+ "learning_rate": 0.00010085227272727273,
+ "loss": 0.6605,
"step": 698
},
{
- "epoch": 14.14,
- "learning_rate": 0.00011084183673469388,
- "loss": 1.1883,
+ "epoch": 7.9,
+ "learning_rate": 0.00010071022727272728,
+ "loss": 0.6777,
"step": 699
},
{
- "epoch": 14.16,
- "learning_rate": 0.00011071428571428572,
- "loss": 1.2364,
+ "epoch": 7.91,
+ "learning_rate": 0.00010056818181818181,
+ "loss": 0.6347,
"step": 700
},
{
- "epoch": 14.18,
- "learning_rate": 0.00011058673469387754,
- "loss": 1.2069,
+ "epoch": 7.92,
+ "learning_rate": 0.00010042613636363636,
+ "loss": 0.6857,
"step": 701
},
{
- "epoch": 14.2,
- "learning_rate": 0.00011045918367346939,
- "loss": 1.1968,
+ "epoch": 7.93,
+ "learning_rate": 0.00010028409090909093,
+ "loss": 0.6677,
"step": 702
},
{
- "epoch": 14.22,
- "learning_rate": 0.00011033163265306123,
- "loss": 1.2236,
+ "epoch": 7.94,
+ "learning_rate": 0.00010014204545454546,
+ "loss": 0.6697,
"step": 703
},
{
- "epoch": 14.24,
- "learning_rate": 0.00011020408163265306,
- "loss": 1.1942,
+ "epoch": 7.95,
+ "learning_rate": 0.0001,
+ "loss": 0.6375,
"step": 704
},
{
- "epoch": 14.26,
- "learning_rate": 0.0001100765306122449,
- "loss": 1.2561,
+ "epoch": 7.96,
+ "learning_rate": 9.985795454545455e-05,
+ "loss": 0.6572,
"step": 705
},
{
- "epoch": 14.29,
- "learning_rate": 0.00010994897959183674,
- "loss": 1.1839,
+ "epoch": 7.98,
+ "learning_rate": 9.97159090909091e-05,
+ "loss": 0.668,
"step": 706
},
{
- "epoch": 14.31,
- "learning_rate": 0.00010982142857142858,
- "loss": 1.2128,
+ "epoch": 7.99,
+ "learning_rate": 9.957386363636364e-05,
+ "loss": 0.6797,
"step": 707
},
{
- "epoch": 14.33,
- "learning_rate": 0.00010969387755102041,
- "loss": 1.3086,
+ "epoch": 8.0,
+ "learning_rate": 9.943181818181819e-05,
+ "loss": 0.6784,
"step": 708
},
{
- "epoch": 14.35,
- "learning_rate": 0.00010956632653061226,
- "loss": 1.2379,
+ "epoch": 8.01,
+ "learning_rate": 9.928977272727273e-05,
+ "loss": 0.6192,
"step": 709
},
{
- "epoch": 14.37,
- "learning_rate": 0.0001094387755102041,
- "loss": 1.176,
+ "epoch": 8.02,
+ "learning_rate": 9.914772727272728e-05,
+ "loss": 0.6287,
"step": 710
},
{
- "epoch": 14.39,
- "learning_rate": 0.00010931122448979592,
- "loss": 1.2105,
+ "epoch": 8.03,
+ "learning_rate": 9.900568181818183e-05,
+ "loss": 0.6034,
"step": 711
},
{
- "epoch": 14.41,
- "learning_rate": 0.00010918367346938776,
- "loss": 1.2149,
+ "epoch": 8.04,
+ "learning_rate": 9.886363636363637e-05,
+ "loss": 0.6167,
"step": 712
},
{
- "epoch": 14.43,
- "learning_rate": 0.0001090561224489796,
- "loss": 1.2392,
+ "epoch": 8.06,
+ "learning_rate": 9.872159090909091e-05,
+ "loss": 0.6353,
"step": 713
},
{
- "epoch": 14.45,
- "learning_rate": 0.00010892857142857142,
- "loss": 1.2471,
+ "epoch": 8.07,
+ "learning_rate": 9.857954545454547e-05,
+ "loss": 0.6222,
"step": 714
},
{
- "epoch": 14.47,
- "learning_rate": 0.00010880102040816327,
- "loss": 1.2561,
+ "epoch": 8.08,
+ "learning_rate": 9.84375e-05,
+ "loss": 0.5963,
"step": 715
},
{
- "epoch": 14.49,
- "learning_rate": 0.00010867346938775511,
- "loss": 1.2179,
+ "epoch": 8.09,
+ "learning_rate": 9.829545454545455e-05,
+ "loss": 0.6042,
"step": 716
},
{
- "epoch": 14.51,
- "learning_rate": 0.00010854591836734696,
- "loss": 1.2459,
+ "epoch": 8.1,
+ "learning_rate": 9.81534090909091e-05,
+ "loss": 0.612,
"step": 717
},
{
- "epoch": 14.53,
- "learning_rate": 0.00010841836734693877,
- "loss": 1.2933,
+ "epoch": 8.11,
+ "learning_rate": 9.801136363636364e-05,
+ "loss": 0.6069,
"step": 718
},
{
- "epoch": 14.55,
- "learning_rate": 0.00010829081632653062,
- "loss": 1.2862,
+ "epoch": 8.12,
+ "learning_rate": 9.786931818181818e-05,
+ "loss": 0.6001,
"step": 719
},
{
- "epoch": 14.57,
- "learning_rate": 0.00010816326530612246,
- "loss": 1.2976,
+ "epoch": 8.13,
+ "learning_rate": 9.772727272727274e-05,
+ "loss": 0.6007,
"step": 720
},
{
- "epoch": 14.59,
- "learning_rate": 0.00010803571428571428,
- "loss": 1.231,
+ "epoch": 8.15,
+ "learning_rate": 9.758522727272727e-05,
+ "loss": 0.6079,
"step": 721
},
{
- "epoch": 14.61,
- "learning_rate": 0.00010790816326530613,
- "loss": 1.2464,
+ "epoch": 8.16,
+ "learning_rate": 9.744318181818183e-05,
+ "loss": 0.6216,
"step": 722
},
{
- "epoch": 14.63,
- "learning_rate": 0.00010778061224489797,
- "loss": 1.2181,
+ "epoch": 8.17,
+ "learning_rate": 9.730113636363637e-05,
+ "loss": 0.6321,
"step": 723
},
{
- "epoch": 14.65,
- "learning_rate": 0.00010765306122448979,
- "loss": 1.3307,
+ "epoch": 8.18,
+ "learning_rate": 9.71590909090909e-05,
+ "loss": 0.6044,
"step": 724
},
{
- "epoch": 14.67,
- "learning_rate": 0.00010752551020408163,
- "loss": 1.1723,
+ "epoch": 8.19,
+ "learning_rate": 9.701704545454547e-05,
+ "loss": 0.6028,
"step": 725
},
{
- "epoch": 14.69,
- "learning_rate": 0.00010739795918367348,
- "loss": 1.1528,
+ "epoch": 8.2,
+ "learning_rate": 9.687500000000001e-05,
+ "loss": 0.6098,
"step": 726
},
{
- "epoch": 14.71,
- "learning_rate": 0.0001072704081632653,
- "loss": 1.215,
+ "epoch": 8.21,
+ "learning_rate": 9.673295454545454e-05,
+ "loss": 0.6032,
"step": 727
},
{
- "epoch": 14.73,
- "learning_rate": 0.00010714285714285715,
- "loss": 1.2624,
+ "epoch": 8.22,
+ "learning_rate": 9.65909090909091e-05,
+ "loss": 0.6298,
"step": 728
},
{
- "epoch": 14.75,
- "learning_rate": 0.00010701530612244898,
- "loss": 1.3117,
+ "epoch": 8.24,
+ "learning_rate": 9.644886363636365e-05,
+ "loss": 0.6115,
"step": 729
},
{
- "epoch": 14.77,
- "learning_rate": 0.00010688775510204083,
- "loss": 1.2572,
+ "epoch": 8.25,
+ "learning_rate": 9.630681818181818e-05,
+ "loss": 0.6052,
"step": 730
},
{
- "epoch": 14.79,
- "learning_rate": 0.00010676020408163266,
- "loss": 1.222,
+ "epoch": 8.26,
+ "learning_rate": 9.616477272727274e-05,
+ "loss": 0.6097,
"step": 731
},
{
- "epoch": 14.81,
- "learning_rate": 0.0001066326530612245,
- "loss": 1.2881,
+ "epoch": 8.27,
+ "learning_rate": 9.602272727272728e-05,
+ "loss": 0.6062,
"step": 732
},
{
- "epoch": 14.83,
- "learning_rate": 0.00010650510204081635,
- "loss": 1.2676,
+ "epoch": 8.28,
+ "learning_rate": 9.588068181818183e-05,
+ "loss": 0.5984,
"step": 733
},
{
- "epoch": 14.85,
- "learning_rate": 0.00010637755102040816,
- "loss": 1.2734,
+ "epoch": 8.29,
+ "learning_rate": 9.573863636363637e-05,
+ "loss": 0.6432,
"step": 734
},
{
- "epoch": 14.87,
- "learning_rate": 0.00010625000000000001,
- "loss": 1.2885,
+ "epoch": 8.3,
+ "learning_rate": 9.559659090909092e-05,
+ "loss": 0.5814,
"step": 735
},
{
- "epoch": 14.89,
- "learning_rate": 0.00010612244897959185,
- "loss": 1.2764,
+ "epoch": 8.31,
+ "learning_rate": 9.545454545454546e-05,
+ "loss": 0.5965,
"step": 736
},
{
- "epoch": 14.91,
- "learning_rate": 0.00010599489795918367,
- "loss": 1.3267,
+ "epoch": 8.33,
+ "learning_rate": 9.53125e-05,
+ "loss": 0.6102,
"step": 737
},
{
- "epoch": 14.93,
- "learning_rate": 0.00010586734693877551,
- "loss": 1.2445,
+ "epoch": 8.34,
+ "learning_rate": 9.517045454545455e-05,
+ "loss": 0.5849,
"step": 738
},
{
- "epoch": 14.95,
- "learning_rate": 0.00010573979591836736,
- "loss": 1.3359,
+ "epoch": 8.35,
+ "learning_rate": 9.50284090909091e-05,
+ "loss": 0.6062,
"step": 739
},
{
- "epoch": 14.97,
- "learning_rate": 0.00010561224489795918,
- "loss": 1.2508,
+ "epoch": 8.36,
+ "learning_rate": 9.488636363636364e-05,
+ "loss": 0.6031,
"step": 740
},
{
- "epoch": 14.99,
- "learning_rate": 0.00010548469387755102,
- "loss": 1.2227,
+ "epoch": 8.37,
+ "learning_rate": 9.474431818181819e-05,
+ "loss": 0.5932,
"step": 741
},
{
- "epoch": 15.01,
- "learning_rate": 0.00010535714285714286,
- "loss": 1.1889,
+ "epoch": 8.38,
+ "learning_rate": 9.460227272727273e-05,
+ "loss": 0.589,
"step": 742
},
{
- "epoch": 15.03,
- "learning_rate": 0.00010522959183673471,
- "loss": 1.1919,
+ "epoch": 8.39,
+ "learning_rate": 9.446022727272728e-05,
+ "loss": 0.6096,
"step": 743
},
{
- "epoch": 15.05,
- "learning_rate": 0.00010510204081632653,
- "loss": 1.2383,
+ "epoch": 8.41,
+ "learning_rate": 9.431818181818182e-05,
+ "loss": 0.601,
"step": 744
},
{
- "epoch": 15.07,
- "learning_rate": 0.00010497448979591837,
- "loss": 1.2401,
+ "epoch": 8.42,
+ "learning_rate": 9.417613636363637e-05,
+ "loss": 0.5798,
"step": 745
},
{
- "epoch": 15.09,
- "learning_rate": 0.00010484693877551021,
- "loss": 1.2015,
+ "epoch": 8.43,
+ "learning_rate": 9.403409090909091e-05,
+ "loss": 0.59,
"step": 746
},
{
- "epoch": 15.11,
- "learning_rate": 0.00010471938775510203,
- "loss": 1.1509,
+ "epoch": 8.44,
+ "learning_rate": 9.389204545454546e-05,
+ "loss": 0.5988,
"step": 747
},
{
- "epoch": 15.13,
- "learning_rate": 0.00010459183673469388,
- "loss": 1.1878,
+ "epoch": 8.45,
+ "learning_rate": 9.375e-05,
+ "loss": 0.5591,
"step": 748
},
{
- "epoch": 15.16,
- "learning_rate": 0.00010446428571428572,
- "loss": 1.1706,
+ "epoch": 8.46,
+ "learning_rate": 9.360795454545455e-05,
+ "loss": 0.5939,
"step": 749
},
{
- "epoch": 15.18,
- "learning_rate": 0.00010433673469387755,
- "loss": 1.1285,
+ "epoch": 8.47,
+ "learning_rate": 9.346590909090909e-05,
+ "loss": 0.5886,
"step": 750
},
{
- "epoch": 15.2,
- "learning_rate": 0.0001042091836734694,
- "loss": 1.1608,
+ "epoch": 8.48,
+ "learning_rate": 9.332386363636364e-05,
+ "loss": 0.5994,
"step": 751
},
{
- "epoch": 15.22,
- "learning_rate": 0.00010408163265306123,
- "loss": 1.1178,
+ "epoch": 8.5,
+ "learning_rate": 9.318181818181818e-05,
+ "loss": 0.5821,
"step": 752
},
{
- "epoch": 15.24,
- "learning_rate": 0.00010395408163265306,
- "loss": 1.1293,
+ "epoch": 8.51,
+ "learning_rate": 9.303977272727273e-05,
+ "loss": 0.602,
"step": 753
},
{
- "epoch": 15.26,
- "learning_rate": 0.0001038265306122449,
- "loss": 1.2306,
+ "epoch": 8.52,
+ "learning_rate": 9.289772727272727e-05,
+ "loss": 0.5708,
"step": 754
},
{
- "epoch": 15.28,
- "learning_rate": 0.00010369897959183675,
- "loss": 1.1541,
+ "epoch": 8.53,
+ "learning_rate": 9.275568181818183e-05,
+ "loss": 0.5902,
"step": 755
},
{
- "epoch": 15.3,
- "learning_rate": 0.00010357142857142859,
- "loss": 1.1702,
+ "epoch": 8.54,
+ "learning_rate": 9.261363636363636e-05,
+ "loss": 0.6053,
"step": 756
},
{
- "epoch": 15.32,
- "learning_rate": 0.00010344387755102041,
- "loss": 1.2119,
+ "epoch": 8.55,
+ "learning_rate": 9.247159090909091e-05,
+ "loss": 0.5797,
"step": 757
},
{
- "epoch": 15.34,
- "learning_rate": 0.00010331632653061225,
- "loss": 1.2239,
+ "epoch": 8.56,
+ "learning_rate": 9.232954545454547e-05,
+ "loss": 0.5965,
"step": 758
},
{
- "epoch": 15.36,
- "learning_rate": 0.0001031887755102041,
- "loss": 1.2019,
+ "epoch": 8.57,
+ "learning_rate": 9.21875e-05,
+ "loss": 0.5738,
"step": 759
},
{
- "epoch": 15.38,
- "learning_rate": 0.00010306122448979591,
- "loss": 1.2197,
+ "epoch": 8.59,
+ "learning_rate": 9.204545454545454e-05,
+ "loss": 0.5819,
"step": 760
},
{
- "epoch": 15.4,
- "learning_rate": 0.00010293367346938776,
- "loss": 1.1769,
+ "epoch": 8.6,
+ "learning_rate": 9.19034090909091e-05,
+ "loss": 0.5994,
"step": 761
},
{
- "epoch": 15.42,
- "learning_rate": 0.0001028061224489796,
- "loss": 1.1907,
+ "epoch": 8.61,
+ "learning_rate": 9.176136363636363e-05,
+ "loss": 0.5738,
"step": 762
},
{
- "epoch": 15.44,
- "learning_rate": 0.00010267857142857142,
- "loss": 1.2089,
+ "epoch": 8.62,
+ "learning_rate": 9.161931818181818e-05,
+ "loss": 0.5663,
"step": 763
},
{
- "epoch": 15.46,
- "learning_rate": 0.00010255102040816327,
- "loss": 1.1335,
+ "epoch": 8.63,
+ "learning_rate": 9.147727272727274e-05,
+ "loss": 0.5798,
"step": 764
},
{
- "epoch": 15.48,
- "learning_rate": 0.00010242346938775511,
- "loss": 1.1633,
+ "epoch": 8.64,
+ "learning_rate": 9.133522727272727e-05,
+ "loss": 0.5705,
"step": 765
},
{
- "epoch": 15.5,
- "learning_rate": 0.00010229591836734695,
- "loss": 1.1578,
+ "epoch": 8.65,
+ "learning_rate": 9.119318181818183e-05,
+ "loss": 0.5943,
"step": 766
},
{
- "epoch": 15.52,
- "learning_rate": 0.00010216836734693877,
- "loss": 1.2236,
+ "epoch": 8.67,
+ "learning_rate": 9.105113636363637e-05,
+ "loss": 0.6019,
"step": 767
},
{
- "epoch": 15.54,
- "learning_rate": 0.00010204081632653062,
- "loss": 1.1941,
+ "epoch": 8.68,
+ "learning_rate": 9.090909090909092e-05,
+ "loss": 0.5733,
"step": 768
},
{
- "epoch": 15.56,
- "learning_rate": 0.00010191326530612246,
- "loss": 1.2666,
+ "epoch": 8.69,
+ "learning_rate": 9.076704545454546e-05,
+ "loss": 0.575,
"step": 769
},
{
- "epoch": 15.58,
- "learning_rate": 0.00010178571428571428,
- "loss": 1.1232,
+ "epoch": 8.7,
+ "learning_rate": 9.062500000000001e-05,
+ "loss": 0.5675,
"step": 770
},
{
- "epoch": 15.6,
- "learning_rate": 0.00010165816326530612,
- "loss": 1.2242,
+ "epoch": 8.71,
+ "learning_rate": 9.048295454545455e-05,
+ "loss": 0.566,
"step": 771
},
{
- "epoch": 15.62,
- "learning_rate": 0.00010153061224489797,
- "loss": 1.1852,
+ "epoch": 8.72,
+ "learning_rate": 9.03409090909091e-05,
+ "loss": 0.5513,
"step": 772
},
{
- "epoch": 15.64,
- "learning_rate": 0.0001014030612244898,
- "loss": 1.2626,
+ "epoch": 8.73,
+ "learning_rate": 9.019886363636364e-05,
+ "loss": 0.5682,
"step": 773
},
{
- "epoch": 15.66,
- "learning_rate": 0.00010127551020408164,
- "loss": 1.1873,
+ "epoch": 8.74,
+ "learning_rate": 9.005681818181819e-05,
+ "loss": 0.5508,
"step": 774
},
{
- "epoch": 15.68,
- "learning_rate": 0.00010114795918367349,
- "loss": 1.3005,
+ "epoch": 8.76,
+ "learning_rate": 8.991477272727273e-05,
+ "loss": 0.5668,
"step": 775
},
{
- "epoch": 15.7,
- "learning_rate": 0.0001010204081632653,
- "loss": 1.1904,
+ "epoch": 8.77,
+ "learning_rate": 8.977272727272728e-05,
+ "loss": 0.569,
"step": 776
},
{
- "epoch": 15.72,
- "learning_rate": 0.00010089285714285715,
- "loss": 1.2927,
+ "epoch": 8.78,
+ "learning_rate": 8.963068181818182e-05,
+ "loss": 0.5897,
"step": 777
},
{
- "epoch": 15.74,
- "learning_rate": 0.00010076530612244899,
- "loss": 1.179,
+ "epoch": 8.79,
+ "learning_rate": 8.948863636363637e-05,
+ "loss": 0.5738,
"step": 778
},
{
- "epoch": 15.76,
- "learning_rate": 0.00010063775510204084,
- "loss": 1.2027,
+ "epoch": 8.8,
+ "learning_rate": 8.934659090909091e-05,
+ "loss": 0.5511,
"step": 779
},
{
- "epoch": 15.78,
- "learning_rate": 0.00010051020408163265,
- "loss": 1.2428,
+ "epoch": 8.81,
+ "learning_rate": 8.920454545454546e-05,
+ "loss": 0.5659,
"step": 780
},
{
- "epoch": 15.8,
- "learning_rate": 0.0001003826530612245,
- "loss": 1.2324,
+ "epoch": 8.82,
+ "learning_rate": 8.90625e-05,
+ "loss": 0.5649,
"step": 781
},
{
- "epoch": 15.82,
- "learning_rate": 0.00010025510204081634,
- "loss": 1.1251,
+ "epoch": 8.83,
+ "learning_rate": 8.892045454545455e-05,
+ "loss": 0.5618,
"step": 782
},
{
- "epoch": 15.84,
- "learning_rate": 0.00010012755102040816,
- "loss": 1.2405,
+ "epoch": 8.85,
+ "learning_rate": 8.87784090909091e-05,
+ "loss": 0.5602,
"step": 783
},
{
- "epoch": 15.86,
- "learning_rate": 0.0001,
- "loss": 1.2005,
+ "epoch": 8.86,
+ "learning_rate": 8.863636363636364e-05,
+ "loss": 0.5723,
"step": 784
},
{
- "epoch": 15.88,
- "learning_rate": 9.987244897959184e-05,
- "loss": 1.2259,
+ "epoch": 8.87,
+ "learning_rate": 8.849431818181818e-05,
+ "loss": 0.5816,
"step": 785
},
{
- "epoch": 15.9,
- "learning_rate": 9.974489795918368e-05,
- "loss": 1.1576,
+ "epoch": 8.88,
+ "learning_rate": 8.835227272727273e-05,
+ "loss": 0.555,
"step": 786
},
{
- "epoch": 15.92,
- "learning_rate": 9.961734693877551e-05,
- "loss": 1.1834,
+ "epoch": 8.89,
+ "learning_rate": 8.821022727272727e-05,
+ "loss": 0.5563,
"step": 787
},
{
- "epoch": 15.94,
- "learning_rate": 9.948979591836736e-05,
- "loss": 1.2396,
+ "epoch": 8.9,
+ "learning_rate": 8.806818181818183e-05,
+ "loss": 0.554,
"step": 788
},
{
- "epoch": 15.96,
- "learning_rate": 9.936224489795919e-05,
- "loss": 1.1865,
+ "epoch": 8.91,
+ "learning_rate": 8.792613636363636e-05,
+ "loss": 0.5671,
"step": 789
},
{
- "epoch": 15.98,
- "learning_rate": 9.923469387755102e-05,
- "loss": 1.2356,
+ "epoch": 8.92,
+ "learning_rate": 8.778409090909091e-05,
+ "loss": 0.5485,
"step": 790
},
{
- "epoch": 16.01,
- "learning_rate": 9.910714285714286e-05,
- "loss": 1.2639,
+ "epoch": 8.94,
+ "learning_rate": 8.764204545454547e-05,
+ "loss": 0.5712,
"step": 791
},
{
- "epoch": 16.03,
- "learning_rate": 9.897959183673469e-05,
- "loss": 1.1216,
+ "epoch": 8.95,
+ "learning_rate": 8.75e-05,
+ "loss": 0.5507,
"step": 792
},
{
- "epoch": 16.05,
- "learning_rate": 9.885204081632652e-05,
- "loss": 1.1051,
+ "epoch": 8.96,
+ "learning_rate": 8.735795454545454e-05,
+ "loss": 0.5718,
"step": 793
},
{
- "epoch": 16.07,
- "learning_rate": 9.872448979591837e-05,
- "loss": 1.0864,
+ "epoch": 8.97,
+ "learning_rate": 8.72159090909091e-05,
+ "loss": 0.5585,
"step": 794
},
{
- "epoch": 16.09,
- "learning_rate": 9.859693877551021e-05,
- "loss": 1.182,
+ "epoch": 8.98,
+ "learning_rate": 8.707386363636363e-05,
+ "loss": 0.5563,
"step": 795
},
{
- "epoch": 16.11,
- "learning_rate": 9.846938775510204e-05,
- "loss": 1.1272,
+ "epoch": 8.99,
+ "learning_rate": 8.693181818181818e-05,
+ "loss": 0.581,
"step": 796
},
{
- "epoch": 16.13,
- "learning_rate": 9.834183673469389e-05,
- "loss": 1.1946,
+ "epoch": 9.0,
+ "learning_rate": 8.678977272727274e-05,
+ "loss": 0.5511,
"step": 797
},
{
- "epoch": 16.15,
- "learning_rate": 9.821428571428572e-05,
- "loss": 1.0875,
+ "epoch": 9.02,
+ "learning_rate": 8.664772727272727e-05,
+ "loss": 0.5103,
"step": 798
},
{
- "epoch": 16.17,
- "learning_rate": 9.808673469387756e-05,
- "loss": 1.1671,
+ "epoch": 9.03,
+ "learning_rate": 8.650568181818183e-05,
+ "loss": 0.5323,
"step": 799
},
{
- "epoch": 16.19,
- "learning_rate": 9.79591836734694e-05,
- "loss": 1.1502,
+ "epoch": 9.04,
+ "learning_rate": 8.636363636363637e-05,
+ "loss": 0.5092,
"step": 800
}
],
"logging_steps": 1,
- "max_steps": 1568,
- "num_train_epochs": 32,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
"save_steps": 100,
- "total_flos": 1.1836061421370368e+18,
+ "total_flos": 1.0915376160523162e+18,
"trial_name": null,
"trial_params": null
}
diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin
index db23e07d097c18532e52f58a70eb72d22e39c8c1..ee7ddb867f05d9a969f71467a8eb88994865cf51 100644
--- a/checkpoint-800/training_args.bin
+++ b/checkpoint-800/training_args.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
size 4155
diff --git a/checkpoint-900/adapter_model.bin b/checkpoint-900/adapter_model.bin
index db7ed4f6ae4a91e62162d01678a6701bba9864f2..e9b913951f0eafb85b209a393e5f742ac4bf6408 100644
--- a/checkpoint-900/adapter_model.bin
+++ b/checkpoint-900/adapter_model.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:f51c1d84f0d247f48d41fba2b15457feed1d404eeff6da6d13cabd701e815176
+oid sha256:ed6e90196f5a274b5d5ff0f18e648b6396fc99189dc82111fcfd2e83656a72f7
size 39409357
diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt
index 24c7142a336fb1d38f0ad6b55a013afa82c328c9..1590a6e8ae4cbf800ea484118a40f6570d2e685f 100644
--- a/checkpoint-900/optimizer.pt
+++ b/checkpoint-900/optimizer.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:450feba545ce1622e78b86c9c73450f53cd2c861fd82ef80a705f3ff9afe3e5a
+oid sha256:2fe640e1cc583a2fcc1f7be360da696c6de30f28f00d5f64bbb3f586eab33160
size 78844421
diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth
index 318fa43e6207ee82707af116de91e1ec428b2697..df08b4983b9f5bfcf57aaaceb89bc51479bfd216 100644
--- a/checkpoint-900/rng_state.pth
+++ b/checkpoint-900/rng_state.pth
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:18451c8480ecb75a9e33d086345a13c29ae0a8eae26b215a820f4299cc32f2a0
+oid sha256:ab62043be50b93d4eb28964be2d945176db3d64fe73ddd052a7656ba9141c683
size 14575
diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt
index 819e0686a4ea5e085317f0dd042805cc2503ad09..8310496ea86f52d12b55338abbc5ec74b78210b3 100644
--- a/checkpoint-900/scheduler.pt
+++ b/checkpoint-900/scheduler.pt
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:8f7ed7c2c4b503d29d3bdb091842bdfbacee353eb03798fc384008a89c404484
+oid sha256:7b34852b759fa1b56e14c21698a89fa4737f1160151f73515f2ad9b2b1334acd
size 627
diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json
index 64e9788c0c92d579e2bac3e81f871d41896de5f2..8a9d005ceb7bbeefb60d1077adafe99907c2a0e3 100644
--- a/checkpoint-900/trainer_state.json
+++ b/checkpoint-900/trainer_state.json
@@ -1,7 +1,7 @@
{
"best_metric": null,
"best_model_checkpoint": null,
- "epoch": 18.2105595953209,
+ "epoch": 10.167696381288614,
"eval_steps": 500,
"global_step": 900,
"is_hyper_param_search": false,
@@ -9,5411 +9,5411 @@
"is_world_process_zero": true,
"log_history": [
{
- "epoch": 0.02,
- "learning_rate": 0.00019987244897959184,
- "loss": 3.2215,
+ "epoch": 0.01,
+ "learning_rate": 0.00019985795454545454,
+ "loss": 3.3254,
"step": 1
},
{
- "epoch": 0.04,
- "learning_rate": 0.00019974489795918367,
- "loss": 2.8365,
+ "epoch": 0.02,
+ "learning_rate": 0.0001997159090909091,
+ "loss": 3.1222,
"step": 2
},
{
- "epoch": 0.06,
- "learning_rate": 0.00019961734693877553,
- "loss": 2.602,
+ "epoch": 0.03,
+ "learning_rate": 0.00019957386363636366,
+ "loss": 2.9506,
"step": 3
},
{
- "epoch": 0.08,
- "learning_rate": 0.00019948979591836736,
- "loss": 2.4196,
+ "epoch": 0.05,
+ "learning_rate": 0.0001994318181818182,
+ "loss": 2.8459,
"step": 4
},
{
- "epoch": 0.1,
- "learning_rate": 0.0001993622448979592,
- "loss": 2.2574,
+ "epoch": 0.06,
+ "learning_rate": 0.00019928977272727275,
+ "loss": 2.7277,
"step": 5
},
{
- "epoch": 0.12,
- "learning_rate": 0.00019923469387755102,
- "loss": 2.2239,
+ "epoch": 0.07,
+ "learning_rate": 0.00019914772727272728,
+ "loss": 2.6184,
"step": 6
},
{
- "epoch": 0.14,
- "learning_rate": 0.00019910714285714288,
- "loss": 2.1661,
+ "epoch": 0.08,
+ "learning_rate": 0.0001990056818181818,
+ "loss": 2.5151,
"step": 7
},
{
- "epoch": 0.16,
- "learning_rate": 0.0001989795918367347,
- "loss": 2.0987,
+ "epoch": 0.09,
+ "learning_rate": 0.00019886363636363637,
+ "loss": 2.4234,
"step": 8
},
{
- "epoch": 0.18,
- "learning_rate": 0.00019885204081632654,
- "loss": 2.015,
+ "epoch": 0.1,
+ "learning_rate": 0.00019872159090909093,
+ "loss": 2.3795,
"step": 9
},
{
- "epoch": 0.2,
- "learning_rate": 0.00019872448979591837,
- "loss": 1.9771,
+ "epoch": 0.11,
+ "learning_rate": 0.00019857954545454546,
+ "loss": 2.3629,
"step": 10
},
{
- "epoch": 0.22,
- "learning_rate": 0.00019859693877551023,
- "loss": 2.0271,
+ "epoch": 0.12,
+ "learning_rate": 0.00019843750000000002,
+ "loss": 2.3246,
"step": 11
},
{
- "epoch": 0.24,
- "learning_rate": 0.00019846938775510203,
- "loss": 1.9812,
+ "epoch": 0.14,
+ "learning_rate": 0.00019829545454545455,
+ "loss": 2.2274,
"step": 12
},
{
- "epoch": 0.26,
- "learning_rate": 0.0001983418367346939,
- "loss": 2.0834,
+ "epoch": 0.15,
+ "learning_rate": 0.00019815340909090908,
+ "loss": 2.2545,
"step": 13
},
{
- "epoch": 0.28,
- "learning_rate": 0.00019821428571428572,
- "loss": 1.9174,
+ "epoch": 0.16,
+ "learning_rate": 0.00019801136363636367,
+ "loss": 2.2814,
"step": 14
},
{
- "epoch": 0.3,
- "learning_rate": 0.00019808673469387755,
- "loss": 1.8409,
+ "epoch": 0.17,
+ "learning_rate": 0.0001978693181818182,
+ "loss": 2.2004,
"step": 15
},
{
- "epoch": 0.32,
- "learning_rate": 0.00019795918367346938,
- "loss": 1.929,
+ "epoch": 0.18,
+ "learning_rate": 0.00019772727272727273,
+ "loss": 2.1897,
"step": 16
},
{
- "epoch": 0.34,
- "learning_rate": 0.00019783163265306124,
- "loss": 2.0041,
+ "epoch": 0.19,
+ "learning_rate": 0.0001975852272727273,
+ "loss": 2.2214,
"step": 17
},
{
- "epoch": 0.36,
- "learning_rate": 0.00019770408163265305,
- "loss": 1.9385,
+ "epoch": 0.2,
+ "learning_rate": 0.00019744318181818182,
+ "loss": 2.2103,
"step": 18
},
{
- "epoch": 0.38,
- "learning_rate": 0.0001975765306122449,
- "loss": 1.9592,
+ "epoch": 0.21,
+ "learning_rate": 0.00019730113636363635,
+ "loss": 2.1747,
"step": 19
},
{
- "epoch": 0.4,
- "learning_rate": 0.00019744897959183674,
- "loss": 1.9701,
+ "epoch": 0.23,
+ "learning_rate": 0.00019715909090909094,
+ "loss": 2.2067,
"step": 20
},
{
- "epoch": 0.42,
- "learning_rate": 0.0001973214285714286,
- "loss": 1.9277,
+ "epoch": 0.24,
+ "learning_rate": 0.00019701704545454547,
+ "loss": 2.1944,
"step": 21
},
{
- "epoch": 0.45,
- "learning_rate": 0.00019719387755102042,
- "loss": 1.8394,
+ "epoch": 0.25,
+ "learning_rate": 0.000196875,
+ "loss": 2.2088,
"step": 22
},
{
- "epoch": 0.47,
- "learning_rate": 0.00019706632653061226,
- "loss": 1.8666,
+ "epoch": 0.26,
+ "learning_rate": 0.00019673295454545456,
+ "loss": 2.1786,
"step": 23
},
{
- "epoch": 0.49,
- "learning_rate": 0.00019693877551020409,
- "loss": 1.8997,
+ "epoch": 0.27,
+ "learning_rate": 0.0001965909090909091,
+ "loss": 2.1242,
"step": 24
},
{
- "epoch": 0.51,
- "learning_rate": 0.00019681122448979592,
- "loss": 1.9432,
+ "epoch": 0.28,
+ "learning_rate": 0.00019644886363636365,
+ "loss": 2.1233,
"step": 25
},
{
- "epoch": 0.53,
- "learning_rate": 0.00019668367346938777,
- "loss": 1.9137,
+ "epoch": 0.29,
+ "learning_rate": 0.0001963068181818182,
+ "loss": 2.1616,
"step": 26
},
{
- "epoch": 0.55,
- "learning_rate": 0.0001965561224489796,
- "loss": 1.905,
+ "epoch": 0.31,
+ "learning_rate": 0.00019616477272727274,
+ "loss": 2.1175,
"step": 27
},
{
- "epoch": 0.57,
- "learning_rate": 0.00019642857142857144,
- "loss": 1.8708,
+ "epoch": 0.32,
+ "learning_rate": 0.00019602272727272727,
+ "loss": 2.1242,
"step": 28
},
{
- "epoch": 0.59,
- "learning_rate": 0.00019630102040816327,
- "loss": 1.9097,
+ "epoch": 0.33,
+ "learning_rate": 0.00019588068181818183,
+ "loss": 2.186,
"step": 29
},
{
- "epoch": 0.61,
- "learning_rate": 0.00019617346938775513,
- "loss": 1.896,
+ "epoch": 0.34,
+ "learning_rate": 0.00019573863636363636,
+ "loss": 2.1319,
"step": 30
},
{
- "epoch": 0.63,
- "learning_rate": 0.00019604591836734696,
- "loss": 1.8834,
+ "epoch": 0.35,
+ "learning_rate": 0.00019559659090909092,
+ "loss": 2.1219,
"step": 31
},
{
- "epoch": 0.65,
- "learning_rate": 0.0001959183673469388,
- "loss": 1.8323,
+ "epoch": 0.36,
+ "learning_rate": 0.00019545454545454548,
+ "loss": 2.1094,
"step": 32
},
{
- "epoch": 0.67,
- "learning_rate": 0.00019579081632653062,
- "loss": 1.804,
+ "epoch": 0.37,
+ "learning_rate": 0.0001953125,
+ "loss": 2.1355,
"step": 33
},
{
- "epoch": 0.69,
- "learning_rate": 0.00019566326530612248,
- "loss": 1.8906,
+ "epoch": 0.38,
+ "learning_rate": 0.00019517045454545454,
+ "loss": 2.1231,
"step": 34
},
{
- "epoch": 0.71,
- "learning_rate": 0.00019553571428571428,
- "loss": 1.8693,
+ "epoch": 0.4,
+ "learning_rate": 0.0001950284090909091,
+ "loss": 2.1089,
"step": 35
},
{
- "epoch": 0.73,
- "learning_rate": 0.00019540816326530614,
- "loss": 1.9308,
+ "epoch": 0.41,
+ "learning_rate": 0.00019488636363636366,
+ "loss": 2.1329,
"step": 36
},
{
- "epoch": 0.75,
- "learning_rate": 0.00019528061224489797,
- "loss": 1.8082,
+ "epoch": 0.42,
+ "learning_rate": 0.0001947443181818182,
+ "loss": 2.1159,
"step": 37
},
{
- "epoch": 0.77,
- "learning_rate": 0.0001951530612244898,
- "loss": 1.848,
+ "epoch": 0.43,
+ "learning_rate": 0.00019460227272727275,
+ "loss": 2.1001,
"step": 38
},
{
- "epoch": 0.79,
- "learning_rate": 0.00019502551020408163,
- "loss": 1.8866,
+ "epoch": 0.44,
+ "learning_rate": 0.00019446022727272728,
+ "loss": 2.1084,
"step": 39
},
{
- "epoch": 0.81,
- "learning_rate": 0.0001948979591836735,
- "loss": 1.7844,
+ "epoch": 0.45,
+ "learning_rate": 0.0001943181818181818,
+ "loss": 2.1431,
"step": 40
},
{
- "epoch": 0.83,
- "learning_rate": 0.0001947704081632653,
- "loss": 1.8485,
+ "epoch": 0.46,
+ "learning_rate": 0.00019417613636363637,
+ "loss": 2.1111,
"step": 41
},
{
- "epoch": 0.85,
- "learning_rate": 0.00019464285714285715,
- "loss": 1.7917,
+ "epoch": 0.47,
+ "learning_rate": 0.00019403409090909093,
+ "loss": 2.1067,
"step": 42
},
{
- "epoch": 0.87,
- "learning_rate": 0.00019451530612244898,
- "loss": 1.7342,
+ "epoch": 0.49,
+ "learning_rate": 0.00019389204545454546,
+ "loss": 2.0974,
"step": 43
},
{
- "epoch": 0.89,
- "learning_rate": 0.00019438775510204084,
- "loss": 1.8479,
+ "epoch": 0.5,
+ "learning_rate": 0.00019375000000000002,
+ "loss": 2.1001,
"step": 44
},
{
- "epoch": 0.91,
- "learning_rate": 0.00019426020408163267,
- "loss": 1.8639,
+ "epoch": 0.51,
+ "learning_rate": 0.00019360795454545455,
+ "loss": 2.0721,
"step": 45
},
{
- "epoch": 0.93,
- "learning_rate": 0.0001941326530612245,
- "loss": 1.8166,
+ "epoch": 0.52,
+ "learning_rate": 0.00019346590909090908,
+ "loss": 2.0786,
"step": 46
},
{
- "epoch": 0.95,
- "learning_rate": 0.00019400510204081633,
- "loss": 1.7566,
+ "epoch": 0.53,
+ "learning_rate": 0.00019332386363636367,
+ "loss": 2.0882,
"step": 47
},
{
- "epoch": 0.97,
- "learning_rate": 0.00019387755102040816,
- "loss": 1.8071,
+ "epoch": 0.54,
+ "learning_rate": 0.0001931818181818182,
+ "loss": 2.083,
"step": 48
},
{
- "epoch": 0.99,
- "learning_rate": 0.00019375000000000002,
- "loss": 1.8612,
+ "epoch": 0.55,
+ "learning_rate": 0.00019303977272727273,
+ "loss": 2.1016,
"step": 49
},
{
- "epoch": 1.01,
- "learning_rate": 0.00019362244897959185,
- "loss": 1.7819,
+ "epoch": 0.56,
+ "learning_rate": 0.0001928977272727273,
+ "loss": 2.0844,
"step": 50
},
{
- "epoch": 1.03,
- "learning_rate": 0.00019349489795918368,
- "loss": 1.8647,
+ "epoch": 0.58,
+ "learning_rate": 0.00019275568181818182,
+ "loss": 2.0891,
"step": 51
},
{
- "epoch": 1.05,
- "learning_rate": 0.0001933673469387755,
- "loss": 1.8196,
+ "epoch": 0.59,
+ "learning_rate": 0.00019261363636363635,
+ "loss": 2.053,
"step": 52
},
{
- "epoch": 1.07,
- "learning_rate": 0.00019323979591836737,
- "loss": 1.8027,
+ "epoch": 0.6,
+ "learning_rate": 0.00019247159090909094,
+ "loss": 2.1013,
"step": 53
},
{
- "epoch": 1.09,
- "learning_rate": 0.00019311224489795917,
- "loss": 1.8927,
+ "epoch": 0.61,
+ "learning_rate": 0.00019232954545454547,
+ "loss": 2.127,
"step": 54
},
{
- "epoch": 1.11,
- "learning_rate": 0.00019298469387755103,
- "loss": 1.8481,
+ "epoch": 0.62,
+ "learning_rate": 0.0001921875,
+ "loss": 2.0909,
"step": 55
},
{
- "epoch": 1.13,
- "learning_rate": 0.00019285714285714286,
- "loss": 1.7781,
+ "epoch": 0.63,
+ "learning_rate": 0.00019204545454545456,
+ "loss": 2.1026,
"step": 56
},
{
- "epoch": 1.15,
- "learning_rate": 0.00019272959183673472,
- "loss": 1.8101,
+ "epoch": 0.64,
+ "learning_rate": 0.0001919034090909091,
+ "loss": 2.0689,
"step": 57
},
{
- "epoch": 1.17,
- "learning_rate": 0.00019260204081632653,
- "loss": 1.7257,
+ "epoch": 0.66,
+ "learning_rate": 0.00019176136363636365,
+ "loss": 2.0475,
"step": 58
},
{
- "epoch": 1.19,
- "learning_rate": 0.00019247448979591838,
- "loss": 1.8185,
+ "epoch": 0.67,
+ "learning_rate": 0.0001916193181818182,
+ "loss": 2.0645,
"step": 59
},
{
- "epoch": 1.21,
- "learning_rate": 0.00019234693877551021,
- "loss": 1.8557,
+ "epoch": 0.68,
+ "learning_rate": 0.00019147727272727274,
+ "loss": 2.0469,
"step": 60
},
{
- "epoch": 1.23,
- "learning_rate": 0.00019221938775510204,
- "loss": 1.7418,
+ "epoch": 0.69,
+ "learning_rate": 0.00019133522727272727,
+ "loss": 2.081,
"step": 61
},
{
- "epoch": 1.25,
- "learning_rate": 0.00019209183673469388,
- "loss": 1.6879,
+ "epoch": 0.7,
+ "learning_rate": 0.00019119318181818183,
+ "loss": 2.0682,
"step": 62
},
{
- "epoch": 1.27,
- "learning_rate": 0.00019196428571428573,
- "loss": 1.7651,
+ "epoch": 0.71,
+ "learning_rate": 0.00019105113636363636,
+ "loss": 2.0794,
"step": 63
},
{
- "epoch": 1.29,
- "learning_rate": 0.00019183673469387756,
- "loss": 1.7759,
+ "epoch": 0.72,
+ "learning_rate": 0.00019090909090909092,
+ "loss": 2.0218,
"step": 64
},
{
- "epoch": 1.32,
- "learning_rate": 0.0001917091836734694,
- "loss": 1.7691,
+ "epoch": 0.73,
+ "learning_rate": 0.00019076704545454548,
+ "loss": 2.0791,
"step": 65
},
{
- "epoch": 1.34,
- "learning_rate": 0.00019158163265306123,
- "loss": 1.7794,
+ "epoch": 0.75,
+ "learning_rate": 0.000190625,
+ "loss": 2.0506,
"step": 66
},
{
- "epoch": 1.36,
- "learning_rate": 0.00019145408163265306,
- "loss": 1.8152,
+ "epoch": 0.76,
+ "learning_rate": 0.00019048295454545454,
+ "loss": 2.0581,
"step": 67
},
{
- "epoch": 1.38,
- "learning_rate": 0.00019132653061224492,
- "loss": 1.8052,
+ "epoch": 0.77,
+ "learning_rate": 0.0001903409090909091,
+ "loss": 2.0614,
"step": 68
},
{
- "epoch": 1.4,
- "learning_rate": 0.00019119897959183675,
- "loss": 1.8054,
+ "epoch": 0.78,
+ "learning_rate": 0.00019019886363636366,
+ "loss": 2.0743,
"step": 69
},
{
- "epoch": 1.42,
- "learning_rate": 0.00019107142857142858,
- "loss": 1.8114,
+ "epoch": 0.79,
+ "learning_rate": 0.0001900568181818182,
+ "loss": 2.0934,
"step": 70
},
{
- "epoch": 1.44,
- "learning_rate": 0.0001909438775510204,
- "loss": 1.7749,
+ "epoch": 0.8,
+ "learning_rate": 0.00018991477272727275,
+ "loss": 2.0695,
"step": 71
},
{
- "epoch": 1.46,
- "learning_rate": 0.00019081632653061227,
- "loss": 1.777,
+ "epoch": 0.81,
+ "learning_rate": 0.00018977272727272728,
+ "loss": 2.0651,
"step": 72
},
{
- "epoch": 1.48,
- "learning_rate": 0.0001906887755102041,
- "loss": 1.7896,
+ "epoch": 0.82,
+ "learning_rate": 0.00018963068181818181,
+ "loss": 2.1002,
"step": 73
},
{
- "epoch": 1.5,
- "learning_rate": 0.00019056122448979593,
- "loss": 1.8335,
+ "epoch": 0.84,
+ "learning_rate": 0.00018948863636363637,
+ "loss": 2.0691,
"step": 74
},
{
- "epoch": 1.52,
- "learning_rate": 0.00019043367346938776,
- "loss": 1.8155,
+ "epoch": 0.85,
+ "learning_rate": 0.00018934659090909093,
+ "loss": 2.0596,
"step": 75
},
{
- "epoch": 1.54,
- "learning_rate": 0.00019030612244897962,
- "loss": 1.8224,
+ "epoch": 0.86,
+ "learning_rate": 0.00018920454545454546,
+ "loss": 2.0542,
"step": 76
},
{
- "epoch": 1.56,
- "learning_rate": 0.00019017857142857142,
- "loss": 1.7889,
+ "epoch": 0.87,
+ "learning_rate": 0.00018906250000000002,
+ "loss": 2.0543,
"step": 77
},
{
- "epoch": 1.58,
- "learning_rate": 0.00019005102040816328,
- "loss": 1.8866,
+ "epoch": 0.88,
+ "learning_rate": 0.00018892045454545455,
+ "loss": 2.0042,
"step": 78
},
{
- "epoch": 1.6,
- "learning_rate": 0.0001899234693877551,
- "loss": 1.8439,
+ "epoch": 0.89,
+ "learning_rate": 0.00018877840909090908,
+ "loss": 2.0072,
"step": 79
},
{
- "epoch": 1.62,
- "learning_rate": 0.00018979591836734697,
- "loss": 1.7906,
+ "epoch": 0.9,
+ "learning_rate": 0.00018863636363636364,
+ "loss": 2.0926,
"step": 80
},
{
- "epoch": 1.64,
- "learning_rate": 0.00018966836734693877,
- "loss": 1.8627,
+ "epoch": 0.92,
+ "learning_rate": 0.0001884943181818182,
+ "loss": 2.0015,
"step": 81
},
{
- "epoch": 1.66,
- "learning_rate": 0.00018954081632653063,
- "loss": 1.7497,
+ "epoch": 0.93,
+ "learning_rate": 0.00018835227272727273,
+ "loss": 2.0591,
"step": 82
},
{
- "epoch": 1.68,
- "learning_rate": 0.00018941326530612246,
- "loss": 1.7936,
+ "epoch": 0.94,
+ "learning_rate": 0.0001882102272727273,
+ "loss": 2.0522,
"step": 83
},
{
- "epoch": 1.7,
- "learning_rate": 0.0001892857142857143,
- "loss": 1.8341,
+ "epoch": 0.95,
+ "learning_rate": 0.00018806818181818182,
+ "loss": 2.0131,
"step": 84
},
{
- "epoch": 1.72,
- "learning_rate": 0.00018915816326530612,
- "loss": 1.7868,
+ "epoch": 0.96,
+ "learning_rate": 0.00018792613636363636,
+ "loss": 2.0572,
"step": 85
},
{
- "epoch": 1.74,
- "learning_rate": 0.00018903061224489798,
- "loss": 1.7493,
+ "epoch": 0.97,
+ "learning_rate": 0.00018778409090909091,
+ "loss": 2.0352,
"step": 86
},
{
- "epoch": 1.76,
- "learning_rate": 0.0001889030612244898,
- "loss": 1.7926,
+ "epoch": 0.98,
+ "learning_rate": 0.00018764204545454547,
+ "loss": 1.9937,
"step": 87
},
{
- "epoch": 1.78,
- "learning_rate": 0.00018877551020408164,
- "loss": 1.8278,
+ "epoch": 0.99,
+ "learning_rate": 0.0001875,
+ "loss": 2.0534,
"step": 88
},
{
- "epoch": 1.8,
- "learning_rate": 0.00018864795918367347,
- "loss": 1.7387,
+ "epoch": 1.01,
+ "learning_rate": 0.00018735795454545456,
+ "loss": 2.0151,
"step": 89
},
{
- "epoch": 1.82,
- "learning_rate": 0.0001885204081632653,
- "loss": 1.7669,
+ "epoch": 1.02,
+ "learning_rate": 0.0001872159090909091,
+ "loss": 2.0281,
"step": 90
},
{
- "epoch": 1.84,
- "learning_rate": 0.00018839285714285716,
- "loss": 1.7686,
+ "epoch": 1.03,
+ "learning_rate": 0.00018707386363636365,
+ "loss": 2.0582,
"step": 91
},
{
- "epoch": 1.86,
- "learning_rate": 0.000188265306122449,
- "loss": 1.7759,
+ "epoch": 1.04,
+ "learning_rate": 0.00018693181818181818,
+ "loss": 2.0173,
"step": 92
},
{
- "epoch": 1.88,
- "learning_rate": 0.00018813775510204082,
- "loss": 1.7016,
+ "epoch": 1.05,
+ "learning_rate": 0.00018678977272727274,
+ "loss": 2.0318,
"step": 93
},
{
- "epoch": 1.9,
- "learning_rate": 0.00018801020408163265,
- "loss": 1.8123,
+ "epoch": 1.06,
+ "learning_rate": 0.00018664772727272727,
+ "loss": 2.0747,
"step": 94
},
{
- "epoch": 1.92,
- "learning_rate": 0.0001878826530612245,
- "loss": 1.8315,
+ "epoch": 1.07,
+ "learning_rate": 0.00018650568181818183,
+ "loss": 2.0036,
"step": 95
},
{
- "epoch": 1.94,
- "learning_rate": 0.00018775510204081634,
- "loss": 1.7679,
+ "epoch": 1.08,
+ "learning_rate": 0.00018636363636363636,
+ "loss": 2.0215,
"step": 96
},
{
- "epoch": 1.96,
- "learning_rate": 0.00018762755102040817,
- "loss": 1.7874,
+ "epoch": 1.1,
+ "learning_rate": 0.00018622159090909092,
+ "loss": 2.0385,
"step": 97
},
{
- "epoch": 1.98,
- "learning_rate": 0.0001875,
- "loss": 1.8008,
+ "epoch": 1.11,
+ "learning_rate": 0.00018607954545454545,
+ "loss": 2.0247,
"step": 98
},
{
- "epoch": 2.0,
- "learning_rate": 0.00018737244897959186,
- "loss": 1.7177,
+ "epoch": 1.12,
+ "learning_rate": 0.0001859375,
+ "loss": 2.0075,
"step": 99
},
{
- "epoch": 2.02,
- "learning_rate": 0.00018724489795918367,
- "loss": 1.7272,
+ "epoch": 1.13,
+ "learning_rate": 0.00018579545454545454,
+ "loss": 2.0134,
"step": 100
},
{
- "epoch": 2.04,
- "learning_rate": 0.00018711734693877552,
- "loss": 1.7848,
+ "epoch": 1.14,
+ "learning_rate": 0.0001856534090909091,
+ "loss": 1.9908,
"step": 101
},
{
- "epoch": 2.06,
- "learning_rate": 0.00018698979591836735,
- "loss": 1.744,
+ "epoch": 1.15,
+ "learning_rate": 0.00018551136363636366,
+ "loss": 2.0048,
"step": 102
},
{
- "epoch": 2.08,
- "learning_rate": 0.00018686224489795919,
- "loss": 1.7005,
+ "epoch": 1.16,
+ "learning_rate": 0.0001853693181818182,
+ "loss": 1.9929,
"step": 103
},
{
- "epoch": 2.1,
- "learning_rate": 0.00018673469387755102,
- "loss": 1.8247,
+ "epoch": 1.17,
+ "learning_rate": 0.00018522727272727273,
+ "loss": 2.0545,
"step": 104
},
{
- "epoch": 2.12,
- "learning_rate": 0.00018660714285714287,
- "loss": 1.6855,
+ "epoch": 1.19,
+ "learning_rate": 0.00018508522727272728,
+ "loss": 2.0212,
"step": 105
},
{
- "epoch": 2.14,
- "learning_rate": 0.0001864795918367347,
- "loss": 1.7627,
+ "epoch": 1.2,
+ "learning_rate": 0.00018494318181818182,
+ "loss": 2.0154,
"step": 106
},
{
- "epoch": 2.17,
- "learning_rate": 0.00018635204081632654,
- "loss": 1.7564,
+ "epoch": 1.21,
+ "learning_rate": 0.00018480113636363637,
+ "loss": 1.988,
"step": 107
},
{
- "epoch": 2.19,
- "learning_rate": 0.00018622448979591837,
- "loss": 1.8237,
+ "epoch": 1.22,
+ "learning_rate": 0.00018465909090909093,
+ "loss": 2.004,
"step": 108
},
{
- "epoch": 2.21,
- "learning_rate": 0.00018609693877551022,
- "loss": 1.7421,
+ "epoch": 1.23,
+ "learning_rate": 0.00018451704545454546,
+ "loss": 1.9902,
"step": 109
},
{
- "epoch": 2.23,
- "learning_rate": 0.00018596938775510206,
- "loss": 1.7517,
+ "epoch": 1.24,
+ "learning_rate": 0.000184375,
+ "loss": 2.0044,
"step": 110
},
{
- "epoch": 2.25,
- "learning_rate": 0.0001858418367346939,
- "loss": 1.7515,
+ "epoch": 1.25,
+ "learning_rate": 0.00018423295454545455,
+ "loss": 2.028,
"step": 111
},
{
- "epoch": 2.27,
- "learning_rate": 0.00018571428571428572,
- "loss": 1.7842,
+ "epoch": 1.27,
+ "learning_rate": 0.00018409090909090909,
+ "loss": 1.975,
"step": 112
},
{
- "epoch": 2.29,
- "learning_rate": 0.00018558673469387755,
- "loss": 1.8001,
+ "epoch": 1.28,
+ "learning_rate": 0.00018394886363636364,
+ "loss": 1.9654,
"step": 113
},
{
- "epoch": 2.31,
- "learning_rate": 0.0001854591836734694,
- "loss": 1.7653,
+ "epoch": 1.29,
+ "learning_rate": 0.0001838068181818182,
+ "loss": 2.013,
"step": 114
},
{
- "epoch": 2.33,
- "learning_rate": 0.00018533163265306124,
- "loss": 1.694,
+ "epoch": 1.3,
+ "learning_rate": 0.00018366477272727273,
+ "loss": 1.9918,
"step": 115
},
{
- "epoch": 2.35,
- "learning_rate": 0.00018520408163265307,
- "loss": 1.7457,
+ "epoch": 1.31,
+ "learning_rate": 0.00018352272727272727,
+ "loss": 2.0028,
"step": 116
},
{
- "epoch": 2.37,
- "learning_rate": 0.0001850765306122449,
- "loss": 1.7899,
+ "epoch": 1.32,
+ "learning_rate": 0.00018338068181818182,
+ "loss": 1.9906,
"step": 117
},
{
- "epoch": 2.39,
- "learning_rate": 0.00018494897959183676,
- "loss": 1.7473,
+ "epoch": 1.33,
+ "learning_rate": 0.00018323863636363636,
+ "loss": 1.9781,
"step": 118
},
{
- "epoch": 2.41,
- "learning_rate": 0.0001848214285714286,
- "loss": 1.6639,
+ "epoch": 1.34,
+ "learning_rate": 0.00018309659090909091,
+ "loss": 1.994,
"step": 119
},
{
- "epoch": 2.43,
- "learning_rate": 0.00018469387755102042,
- "loss": 1.762,
+ "epoch": 1.36,
+ "learning_rate": 0.00018295454545454547,
+ "loss": 1.9732,
"step": 120
},
{
- "epoch": 2.45,
- "learning_rate": 0.00018456632653061225,
- "loss": 1.7378,
+ "epoch": 1.37,
+ "learning_rate": 0.0001828125,
+ "loss": 1.9985,
"step": 121
},
{
- "epoch": 2.47,
- "learning_rate": 0.0001844387755102041,
- "loss": 1.672,
+ "epoch": 1.38,
+ "learning_rate": 0.00018267045454545454,
+ "loss": 2.032,
"step": 122
},
{
- "epoch": 2.49,
- "learning_rate": 0.0001843112244897959,
- "loss": 1.7267,
+ "epoch": 1.39,
+ "learning_rate": 0.0001825284090909091,
+ "loss": 1.9743,
"step": 123
},
{
- "epoch": 2.51,
- "learning_rate": 0.00018418367346938777,
- "loss": 1.7825,
+ "epoch": 1.4,
+ "learning_rate": 0.00018238636363636365,
+ "loss": 1.9857,
"step": 124
},
{
- "epoch": 2.53,
- "learning_rate": 0.0001840561224489796,
- "loss": 1.7566,
+ "epoch": 1.41,
+ "learning_rate": 0.00018224431818181819,
+ "loss": 2.0118,
"step": 125
},
{
- "epoch": 2.55,
- "learning_rate": 0.00018392857142857143,
- "loss": 1.8169,
+ "epoch": 1.42,
+ "learning_rate": 0.00018210227272727274,
+ "loss": 2.0151,
"step": 126
},
{
- "epoch": 2.57,
- "learning_rate": 0.00018380102040816326,
- "loss": 1.6801,
+ "epoch": 1.43,
+ "learning_rate": 0.00018196022727272728,
+ "loss": 1.9863,
"step": 127
},
{
- "epoch": 2.59,
- "learning_rate": 0.00018367346938775512,
- "loss": 1.7292,
+ "epoch": 1.45,
+ "learning_rate": 0.00018181818181818183,
+ "loss": 1.9959,
"step": 128
},
{
- "epoch": 2.61,
- "learning_rate": 0.00018354591836734695,
- "loss": 1.737,
+ "epoch": 1.46,
+ "learning_rate": 0.00018167613636363637,
+ "loss": 1.9642,
"step": 129
},
{
- "epoch": 2.63,
- "learning_rate": 0.00018341836734693878,
- "loss": 1.7696,
+ "epoch": 1.47,
+ "learning_rate": 0.00018153409090909092,
+ "loss": 1.953,
"step": 130
},
{
- "epoch": 2.65,
- "learning_rate": 0.0001832908163265306,
- "loss": 1.7239,
+ "epoch": 1.48,
+ "learning_rate": 0.00018139204545454546,
+ "loss": 1.9994,
"step": 131
},
{
- "epoch": 2.67,
- "learning_rate": 0.00018316326530612247,
- "loss": 1.7441,
+ "epoch": 1.49,
+ "learning_rate": 0.00018125000000000001,
+ "loss": 1.9557,
"step": 132
},
{
- "epoch": 2.69,
- "learning_rate": 0.0001830357142857143,
- "loss": 1.7825,
+ "epoch": 1.5,
+ "learning_rate": 0.00018110795454545455,
+ "loss": 2.0051,
"step": 133
},
{
- "epoch": 2.71,
- "learning_rate": 0.00018290816326530613,
- "loss": 1.7411,
+ "epoch": 1.51,
+ "learning_rate": 0.0001809659090909091,
+ "loss": 1.9799,
"step": 134
},
{
- "epoch": 2.73,
- "learning_rate": 0.00018278061224489796,
- "loss": 1.7119,
+ "epoch": 1.53,
+ "learning_rate": 0.00018082386363636366,
+ "loss": 1.9696,
"step": 135
},
{
- "epoch": 2.75,
- "learning_rate": 0.0001826530612244898,
- "loss": 1.7443,
+ "epoch": 1.54,
+ "learning_rate": 0.0001806818181818182,
+ "loss": 1.9664,
"step": 136
},
{
- "epoch": 2.77,
- "learning_rate": 0.00018252551020408165,
- "loss": 1.7197,
+ "epoch": 1.55,
+ "learning_rate": 0.00018053977272727273,
+ "loss": 1.9619,
"step": 137
},
{
- "epoch": 2.79,
- "learning_rate": 0.00018239795918367348,
- "loss": 1.7273,
+ "epoch": 1.56,
+ "learning_rate": 0.00018039772727272729,
+ "loss": 1.9833,
"step": 138
},
{
- "epoch": 2.81,
- "learning_rate": 0.0001822704081632653,
- "loss": 1.7681,
+ "epoch": 1.57,
+ "learning_rate": 0.00018025568181818182,
+ "loss": 1.9791,
"step": 139
},
{
- "epoch": 2.83,
- "learning_rate": 0.00018214285714285714,
- "loss": 1.8088,
+ "epoch": 1.58,
+ "learning_rate": 0.00018011363636363638,
+ "loss": 1.9777,
"step": 140
},
{
- "epoch": 2.85,
- "learning_rate": 0.000182015306122449,
- "loss": 1.7301,
+ "epoch": 1.59,
+ "learning_rate": 0.00017997159090909093,
+ "loss": 1.9361,
"step": 141
},
{
- "epoch": 2.87,
- "learning_rate": 0.00018188775510204083,
- "loss": 1.6853,
+ "epoch": 1.6,
+ "learning_rate": 0.00017982954545454547,
+ "loss": 1.9449,
"step": 142
},
{
- "epoch": 2.89,
- "learning_rate": 0.00018176020408163266,
- "loss": 1.6966,
+ "epoch": 1.62,
+ "learning_rate": 0.0001796875,
+ "loss": 1.9541,
"step": 143
},
{
- "epoch": 2.91,
- "learning_rate": 0.0001816326530612245,
- "loss": 1.7938,
+ "epoch": 1.63,
+ "learning_rate": 0.00017954545454545456,
+ "loss": 1.9867,
"step": 144
},
{
- "epoch": 2.93,
- "learning_rate": 0.00018150510204081635,
- "loss": 1.7639,
+ "epoch": 1.64,
+ "learning_rate": 0.0001794034090909091,
+ "loss": 1.9433,
"step": 145
},
{
- "epoch": 2.95,
- "learning_rate": 0.00018137755102040816,
- "loss": 1.7527,
+ "epoch": 1.65,
+ "learning_rate": 0.00017926136363636365,
+ "loss": 1.9789,
"step": 146
},
{
- "epoch": 2.97,
- "learning_rate": 0.00018125000000000001,
- "loss": 1.7386,
+ "epoch": 1.66,
+ "learning_rate": 0.0001791193181818182,
+ "loss": 1.9942,
"step": 147
},
{
- "epoch": 2.99,
- "learning_rate": 0.00018112244897959185,
- "loss": 1.7223,
+ "epoch": 1.67,
+ "learning_rate": 0.00017897727272727274,
+ "loss": 1.9724,
"step": 148
},
{
- "epoch": 3.01,
- "learning_rate": 0.00018099489795918368,
- "loss": 1.7571,
+ "epoch": 1.68,
+ "learning_rate": 0.00017883522727272727,
+ "loss": 1.9938,
"step": 149
},
{
- "epoch": 3.04,
- "learning_rate": 0.0001808673469387755,
- "loss": 1.7054,
+ "epoch": 1.69,
+ "learning_rate": 0.00017869318181818183,
+ "loss": 1.9264,
"step": 150
},
{
- "epoch": 3.06,
- "learning_rate": 0.00018073979591836737,
- "loss": 1.6581,
+ "epoch": 1.71,
+ "learning_rate": 0.00017855113636363636,
+ "loss": 1.9372,
"step": 151
},
{
- "epoch": 3.08,
- "learning_rate": 0.00018061224489795917,
- "loss": 1.681,
+ "epoch": 1.72,
+ "learning_rate": 0.00017840909090909092,
+ "loss": 1.9463,
"step": 152
},
{
- "epoch": 3.1,
- "learning_rate": 0.00018048469387755103,
- "loss": 1.7425,
+ "epoch": 1.73,
+ "learning_rate": 0.00017826704545454547,
+ "loss": 1.9244,
"step": 153
},
{
- "epoch": 3.12,
- "learning_rate": 0.00018035714285714286,
- "loss": 1.7108,
+ "epoch": 1.74,
+ "learning_rate": 0.000178125,
+ "loss": 1.9139,
"step": 154
},
{
- "epoch": 3.14,
- "learning_rate": 0.00018022959183673472,
- "loss": 1.7194,
+ "epoch": 1.75,
+ "learning_rate": 0.00017798295454545454,
+ "loss": 1.9612,
"step": 155
},
{
- "epoch": 3.16,
- "learning_rate": 0.00018010204081632655,
- "loss": 1.6953,
+ "epoch": 1.76,
+ "learning_rate": 0.0001778409090909091,
+ "loss": 1.9399,
"step": 156
},
{
- "epoch": 3.18,
- "learning_rate": 0.00017997448979591838,
- "loss": 1.669,
+ "epoch": 1.77,
+ "learning_rate": 0.00017769886363636366,
+ "loss": 1.906,
"step": 157
},
{
- "epoch": 3.2,
- "learning_rate": 0.0001798469387755102,
- "loss": 1.744,
+ "epoch": 1.78,
+ "learning_rate": 0.0001775568181818182,
+ "loss": 1.9294,
"step": 158
},
{
- "epoch": 3.22,
- "learning_rate": 0.00017971938775510204,
- "loss": 1.6467,
+ "epoch": 1.8,
+ "learning_rate": 0.00017741477272727275,
+ "loss": 1.9663,
"step": 159
},
{
- "epoch": 3.24,
- "learning_rate": 0.0001795918367346939,
- "loss": 1.7103,
+ "epoch": 1.81,
+ "learning_rate": 0.00017727272727272728,
+ "loss": 1.9257,
"step": 160
},
{
- "epoch": 3.26,
- "learning_rate": 0.00017946428571428573,
- "loss": 1.6662,
+ "epoch": 1.82,
+ "learning_rate": 0.0001771306818181818,
+ "loss": 1.9416,
"step": 161
},
{
- "epoch": 3.28,
- "learning_rate": 0.00017933673469387756,
- "loss": 1.6657,
+ "epoch": 1.83,
+ "learning_rate": 0.00017698863636363637,
+ "loss": 1.94,
"step": 162
},
{
- "epoch": 3.3,
- "learning_rate": 0.0001792091836734694,
- "loss": 1.791,
+ "epoch": 1.84,
+ "learning_rate": 0.00017684659090909093,
+ "loss": 1.9064,
"step": 163
},
{
- "epoch": 3.32,
- "learning_rate": 0.00017908163265306125,
- "loss": 1.7704,
+ "epoch": 1.85,
+ "learning_rate": 0.00017670454545454546,
+ "loss": 1.9363,
"step": 164
},
{
- "epoch": 3.34,
- "learning_rate": 0.00017895408163265305,
- "loss": 1.7229,
+ "epoch": 1.86,
+ "learning_rate": 0.00017656250000000002,
+ "loss": 1.9414,
"step": 165
},
{
- "epoch": 3.36,
- "learning_rate": 0.0001788265306122449,
- "loss": 1.76,
+ "epoch": 1.88,
+ "learning_rate": 0.00017642045454545455,
+ "loss": 1.9526,
"step": 166
},
{
- "epoch": 3.38,
- "learning_rate": 0.00017869897959183674,
- "loss": 1.6482,
+ "epoch": 1.89,
+ "learning_rate": 0.00017627840909090908,
+ "loss": 1.9263,
"step": 167
},
{
- "epoch": 3.4,
- "learning_rate": 0.0001785714285714286,
- "loss": 1.8076,
+ "epoch": 1.9,
+ "learning_rate": 0.00017613636363636366,
+ "loss": 1.9251,
"step": 168
},
{
- "epoch": 3.42,
- "learning_rate": 0.0001784438775510204,
- "loss": 1.7368,
+ "epoch": 1.91,
+ "learning_rate": 0.0001759943181818182,
+ "loss": 1.9085,
"step": 169
},
{
- "epoch": 3.44,
- "learning_rate": 0.00017831632653061226,
- "loss": 1.6264,
+ "epoch": 1.92,
+ "learning_rate": 0.00017585227272727273,
+ "loss": 1.9287,
"step": 170
},
{
- "epoch": 3.46,
- "learning_rate": 0.0001781887755102041,
- "loss": 1.6289,
+ "epoch": 1.93,
+ "learning_rate": 0.00017571022727272729,
+ "loss": 1.9246,
"step": 171
},
{
- "epoch": 3.48,
- "learning_rate": 0.00017806122448979592,
- "loss": 1.7913,
+ "epoch": 1.94,
+ "learning_rate": 0.00017556818181818182,
+ "loss": 1.916,
"step": 172
},
{
- "epoch": 3.5,
- "learning_rate": 0.00017793367346938775,
- "loss": 1.6985,
+ "epoch": 1.95,
+ "learning_rate": 0.00017542613636363635,
+ "loss": 1.9297,
"step": 173
},
{
- "epoch": 3.52,
- "learning_rate": 0.0001778061224489796,
- "loss": 1.6936,
+ "epoch": 1.97,
+ "learning_rate": 0.00017528409090909094,
+ "loss": 1.8881,
"step": 174
},
{
- "epoch": 3.54,
- "learning_rate": 0.00017767857142857141,
- "loss": 1.8068,
+ "epoch": 1.98,
+ "learning_rate": 0.00017514204545454547,
+ "loss": 1.9208,
"step": 175
},
{
- "epoch": 3.56,
- "learning_rate": 0.00017755102040816327,
- "loss": 1.7243,
+ "epoch": 1.99,
+ "learning_rate": 0.000175,
+ "loss": 1.9233,
"step": 176
},
{
- "epoch": 3.58,
- "learning_rate": 0.0001774234693877551,
- "loss": 1.6893,
+ "epoch": 2.0,
+ "learning_rate": 0.00017485795454545456,
+ "loss": 1.9309,
"step": 177
},
{
- "epoch": 3.6,
- "learning_rate": 0.00017729591836734696,
- "loss": 1.8122,
+ "epoch": 2.01,
+ "learning_rate": 0.0001747159090909091,
+ "loss": 1.877,
"step": 178
},
{
- "epoch": 3.62,
- "learning_rate": 0.0001771683673469388,
- "loss": 1.6562,
+ "epoch": 2.02,
+ "learning_rate": 0.00017457386363636365,
+ "loss": 1.9083,
"step": 179
},
{
- "epoch": 3.64,
- "learning_rate": 0.00017704081632653062,
- "loss": 1.6999,
+ "epoch": 2.03,
+ "learning_rate": 0.0001744318181818182,
+ "loss": 1.8733,
"step": 180
},
{
- "epoch": 3.66,
- "learning_rate": 0.00017691326530612245,
- "loss": 1.7229,
+ "epoch": 2.04,
+ "learning_rate": 0.00017428977272727274,
+ "loss": 1.8905,
"step": 181
},
{
- "epoch": 3.68,
- "learning_rate": 0.00017678571428571428,
- "loss": 1.6764,
+ "epoch": 2.06,
+ "learning_rate": 0.00017414772727272727,
+ "loss": 1.9175,
"step": 182
},
{
- "epoch": 3.7,
- "learning_rate": 0.00017665816326530614,
- "loss": 1.6982,
+ "epoch": 2.07,
+ "learning_rate": 0.00017400568181818183,
+ "loss": 1.8846,
"step": 183
},
{
- "epoch": 3.72,
- "learning_rate": 0.00017653061224489797,
- "loss": 1.696,
+ "epoch": 2.08,
+ "learning_rate": 0.00017386363636363636,
+ "loss": 1.8847,
"step": 184
},
{
- "epoch": 3.74,
- "learning_rate": 0.0001764030612244898,
- "loss": 1.6797,
+ "epoch": 2.09,
+ "learning_rate": 0.00017372159090909092,
+ "loss": 1.8948,
"step": 185
},
{
- "epoch": 3.76,
- "learning_rate": 0.00017627551020408164,
- "loss": 1.637,
+ "epoch": 2.1,
+ "learning_rate": 0.00017357954545454548,
+ "loss": 1.8728,
"step": 186
},
{
- "epoch": 3.78,
- "learning_rate": 0.0001761479591836735,
- "loss": 1.7074,
+ "epoch": 2.11,
+ "learning_rate": 0.0001734375,
+ "loss": 1.8934,
"step": 187
},
{
- "epoch": 3.8,
- "learning_rate": 0.0001760204081632653,
- "loss": 1.705,
+ "epoch": 2.12,
+ "learning_rate": 0.00017329545454545454,
+ "loss": 1.8796,
"step": 188
},
{
- "epoch": 3.82,
- "learning_rate": 0.00017589285714285716,
- "loss": 1.6153,
+ "epoch": 2.14,
+ "learning_rate": 0.0001731534090909091,
+ "loss": 1.902,
"step": 189
},
{
- "epoch": 3.84,
- "learning_rate": 0.00017576530612244899,
- "loss": 1.7354,
+ "epoch": 2.15,
+ "learning_rate": 0.00017301136363636366,
+ "loss": 1.8864,
"step": 190
},
{
- "epoch": 3.86,
- "learning_rate": 0.00017563775510204084,
- "loss": 1.6941,
+ "epoch": 2.16,
+ "learning_rate": 0.0001728693181818182,
+ "loss": 1.8682,
"step": 191
},
{
- "epoch": 3.88,
- "learning_rate": 0.00017551020408163265,
- "loss": 1.7231,
+ "epoch": 2.17,
+ "learning_rate": 0.00017272727272727275,
+ "loss": 1.8662,
"step": 192
},
{
- "epoch": 3.91,
- "learning_rate": 0.0001753826530612245,
- "loss": 1.7663,
+ "epoch": 2.18,
+ "learning_rate": 0.00017258522727272728,
+ "loss": 1.8526,
"step": 193
},
{
- "epoch": 3.93,
- "learning_rate": 0.00017525510204081634,
- "loss": 1.6532,
+ "epoch": 2.19,
+ "learning_rate": 0.0001724431818181818,
+ "loss": 1.8682,
"step": 194
},
{
- "epoch": 3.95,
- "learning_rate": 0.00017512755102040817,
- "loss": 1.7115,
+ "epoch": 2.2,
+ "learning_rate": 0.00017230113636363637,
+ "loss": 1.8205,
"step": 195
},
{
- "epoch": 3.97,
- "learning_rate": 0.000175,
- "loss": 1.6955,
+ "epoch": 2.21,
+ "learning_rate": 0.00017215909090909093,
+ "loss": 1.8726,
"step": 196
},
{
- "epoch": 3.99,
- "learning_rate": 0.00017487244897959186,
- "loss": 1.6863,
+ "epoch": 2.23,
+ "learning_rate": 0.00017201704545454546,
+ "loss": 1.8241,
"step": 197
},
{
- "epoch": 4.01,
- "learning_rate": 0.00017474489795918366,
- "loss": 1.7012,
+ "epoch": 2.24,
+ "learning_rate": 0.00017187500000000002,
+ "loss": 1.9,
"step": 198
},
{
- "epoch": 4.03,
- "learning_rate": 0.00017461734693877552,
- "loss": 1.5927,
+ "epoch": 2.25,
+ "learning_rate": 0.00017173295454545455,
+ "loss": 1.8496,
"step": 199
},
{
- "epoch": 4.05,
- "learning_rate": 0.00017448979591836735,
- "loss": 1.6272,
+ "epoch": 2.26,
+ "learning_rate": 0.00017159090909090908,
+ "loss": 1.8562,
"step": 200
},
{
- "epoch": 4.07,
- "learning_rate": 0.00017436224489795918,
- "loss": 1.5994,
+ "epoch": 2.27,
+ "learning_rate": 0.00017144886363636367,
+ "loss": 1.8594,
"step": 201
},
{
- "epoch": 4.09,
- "learning_rate": 0.00017423469387755104,
- "loss": 1.7141,
+ "epoch": 2.28,
+ "learning_rate": 0.0001713068181818182,
+ "loss": 1.8606,
"step": 202
},
{
- "epoch": 4.11,
- "learning_rate": 0.00017410714285714287,
- "loss": 1.7547,
+ "epoch": 2.29,
+ "learning_rate": 0.00017116477272727273,
+ "loss": 1.8712,
"step": 203
},
{
- "epoch": 4.13,
- "learning_rate": 0.0001739795918367347,
- "loss": 1.6254,
+ "epoch": 2.3,
+ "learning_rate": 0.0001710227272727273,
+ "loss": 1.897,
"step": 204
},
{
- "epoch": 4.15,
- "learning_rate": 0.00017385204081632653,
- "loss": 1.6686,
+ "epoch": 2.32,
+ "learning_rate": 0.00017088068181818182,
+ "loss": 1.8287,
"step": 205
},
{
- "epoch": 4.17,
- "learning_rate": 0.0001737244897959184,
- "loss": 1.6684,
+ "epoch": 2.33,
+ "learning_rate": 0.00017073863636363635,
+ "loss": 1.8698,
"step": 206
},
{
- "epoch": 4.19,
- "learning_rate": 0.00017359693877551022,
- "loss": 1.6724,
+ "epoch": 2.34,
+ "learning_rate": 0.00017059659090909094,
+ "loss": 1.8611,
"step": 207
},
{
- "epoch": 4.21,
- "learning_rate": 0.00017346938775510205,
- "loss": 1.7361,
+ "epoch": 2.35,
+ "learning_rate": 0.00017045454545454547,
+ "loss": 1.8161,
"step": 208
},
{
- "epoch": 4.23,
- "learning_rate": 0.00017334183673469388,
- "loss": 1.7167,
+ "epoch": 2.36,
+ "learning_rate": 0.0001703125,
+ "loss": 1.8303,
"step": 209
},
{
- "epoch": 4.25,
- "learning_rate": 0.00017321428571428574,
- "loss": 1.7226,
+ "epoch": 2.37,
+ "learning_rate": 0.00017017045454545456,
+ "loss": 1.8423,
"step": 210
},
{
- "epoch": 4.27,
- "learning_rate": 0.00017308673469387754,
- "loss": 1.7133,
+ "epoch": 2.38,
+ "learning_rate": 0.0001700284090909091,
+ "loss": 1.861,
"step": 211
},
{
- "epoch": 4.29,
- "learning_rate": 0.0001729591836734694,
- "loss": 1.649,
+ "epoch": 2.4,
+ "learning_rate": 0.00016988636363636365,
+ "loss": 1.864,
"step": 212
},
{
- "epoch": 4.31,
- "learning_rate": 0.00017283163265306123,
- "loss": 1.7104,
+ "epoch": 2.41,
+ "learning_rate": 0.0001697443181818182,
+ "loss": 1.8448,
"step": 213
},
{
- "epoch": 4.33,
- "learning_rate": 0.00017270408163265306,
- "loss": 1.6861,
+ "epoch": 2.42,
+ "learning_rate": 0.00016960227272727274,
+ "loss": 1.8463,
"step": 214
},
{
- "epoch": 4.35,
- "learning_rate": 0.0001725765306122449,
- "loss": 1.648,
+ "epoch": 2.43,
+ "learning_rate": 0.00016946022727272727,
+ "loss": 1.8482,
"step": 215
},
{
- "epoch": 4.37,
- "learning_rate": 0.00017244897959183675,
- "loss": 1.6215,
+ "epoch": 2.44,
+ "learning_rate": 0.00016931818181818183,
+ "loss": 1.8289,
"step": 216
},
{
- "epoch": 4.39,
- "learning_rate": 0.00017232142857142858,
- "loss": 1.6334,
+ "epoch": 2.45,
+ "learning_rate": 0.00016917613636363636,
+ "loss": 1.8352,
"step": 217
},
{
- "epoch": 4.41,
- "learning_rate": 0.0001721938775510204,
- "loss": 1.6283,
+ "epoch": 2.46,
+ "learning_rate": 0.00016903409090909092,
+ "loss": 1.8161,
"step": 218
},
{
- "epoch": 4.43,
- "learning_rate": 0.00017206632653061224,
- "loss": 1.6462,
+ "epoch": 2.47,
+ "learning_rate": 0.00016889204545454548,
+ "loss": 1.8512,
"step": 219
},
{
- "epoch": 4.45,
- "learning_rate": 0.0001719387755102041,
- "loss": 1.7233,
+ "epoch": 2.49,
+ "learning_rate": 0.00016875,
+ "loss": 1.8211,
"step": 220
},
{
- "epoch": 4.47,
- "learning_rate": 0.0001718112244897959,
- "loss": 1.7839,
+ "epoch": 2.5,
+ "learning_rate": 0.00016860795454545454,
+ "loss": 1.7831,
"step": 221
},
{
- "epoch": 4.49,
- "learning_rate": 0.00017168367346938776,
- "loss": 1.7204,
+ "epoch": 2.51,
+ "learning_rate": 0.0001684659090909091,
+ "loss": 1.8232,
"step": 222
},
{
- "epoch": 4.51,
- "learning_rate": 0.0001715561224489796,
- "loss": 1.7671,
+ "epoch": 2.52,
+ "learning_rate": 0.00016832386363636366,
+ "loss": 1.8253,
"step": 223
},
{
- "epoch": 4.53,
- "learning_rate": 0.00017142857142857143,
- "loss": 1.6824,
+ "epoch": 2.53,
+ "learning_rate": 0.0001681818181818182,
+ "loss": 1.7994,
"step": 224
},
{
- "epoch": 4.55,
- "learning_rate": 0.00017130102040816328,
- "loss": 1.7068,
+ "epoch": 2.54,
+ "learning_rate": 0.00016803977272727275,
+ "loss": 1.8405,
"step": 225
},
{
- "epoch": 4.57,
- "learning_rate": 0.00017117346938775511,
- "loss": 1.6515,
+ "epoch": 2.55,
+ "learning_rate": 0.00016789772727272728,
+ "loss": 1.816,
"step": 226
},
{
- "epoch": 4.59,
- "learning_rate": 0.00017104591836734694,
- "loss": 1.6586,
+ "epoch": 2.56,
+ "learning_rate": 0.0001677556818181818,
+ "loss": 1.8343,
"step": 227
},
{
- "epoch": 4.61,
- "learning_rate": 0.00017091836734693878,
- "loss": 1.6355,
+ "epoch": 2.58,
+ "learning_rate": 0.00016761363636363637,
+ "loss": 1.8068,
"step": 228
},
{
- "epoch": 4.63,
- "learning_rate": 0.00017079081632653063,
- "loss": 1.7173,
+ "epoch": 2.59,
+ "learning_rate": 0.00016747159090909093,
+ "loss": 1.8337,
"step": 229
},
{
- "epoch": 4.65,
- "learning_rate": 0.00017066326530612246,
- "loss": 1.6585,
+ "epoch": 2.6,
+ "learning_rate": 0.00016732954545454546,
+ "loss": 1.8269,
"step": 230
},
{
- "epoch": 4.67,
- "learning_rate": 0.0001705357142857143,
- "loss": 1.5856,
+ "epoch": 2.61,
+ "learning_rate": 0.00016718750000000002,
+ "loss": 1.8243,
"step": 231
},
{
- "epoch": 4.69,
- "learning_rate": 0.00017040816326530613,
- "loss": 1.5923,
+ "epoch": 2.62,
+ "learning_rate": 0.00016704545454545455,
+ "loss": 1.7766,
"step": 232
},
{
- "epoch": 4.71,
- "learning_rate": 0.00017028061224489798,
- "loss": 1.7128,
+ "epoch": 2.63,
+ "learning_rate": 0.00016690340909090908,
+ "loss": 1.8144,
"step": 233
},
{
- "epoch": 4.73,
- "learning_rate": 0.0001701530612244898,
- "loss": 1.6971,
+ "epoch": 2.64,
+ "learning_rate": 0.00016676136363636367,
+ "loss": 1.8113,
"step": 234
},
{
- "epoch": 4.75,
- "learning_rate": 0.00017002551020408165,
- "loss": 1.6416,
+ "epoch": 2.65,
+ "learning_rate": 0.0001666193181818182,
+ "loss": 1.8086,
"step": 235
},
{
- "epoch": 4.78,
- "learning_rate": 0.00016989795918367348,
- "loss": 1.645,
+ "epoch": 2.67,
+ "learning_rate": 0.00016647727272727273,
+ "loss": 1.785,
"step": 236
},
{
- "epoch": 4.8,
- "learning_rate": 0.0001697704081632653,
- "loss": 1.6792,
+ "epoch": 2.68,
+ "learning_rate": 0.0001663352272727273,
+ "loss": 1.7884,
"step": 237
},
{
- "epoch": 4.82,
- "learning_rate": 0.00016964285714285714,
- "loss": 1.6522,
+ "epoch": 2.69,
+ "learning_rate": 0.00016619318181818182,
+ "loss": 1.7953,
"step": 238
},
{
- "epoch": 4.84,
- "learning_rate": 0.000169515306122449,
- "loss": 1.6315,
+ "epoch": 2.7,
+ "learning_rate": 0.00016605113636363635,
+ "loss": 1.8013,
"step": 239
},
{
- "epoch": 4.86,
- "learning_rate": 0.00016938775510204083,
- "loss": 1.6622,
+ "epoch": 2.71,
+ "learning_rate": 0.00016590909090909094,
+ "loss": 1.8074,
"step": 240
},
{
- "epoch": 4.88,
- "learning_rate": 0.00016926020408163266,
- "loss": 1.6566,
+ "epoch": 2.72,
+ "learning_rate": 0.00016576704545454547,
+ "loss": 1.82,
"step": 241
},
{
- "epoch": 4.9,
- "learning_rate": 0.0001691326530612245,
- "loss": 1.7141,
+ "epoch": 2.73,
+ "learning_rate": 0.000165625,
+ "loss": 1.7665,
"step": 242
},
{
- "epoch": 4.92,
- "learning_rate": 0.00016900510204081635,
- "loss": 1.5873,
+ "epoch": 2.75,
+ "learning_rate": 0.00016548295454545456,
+ "loss": 1.7638,
"step": 243
},
{
- "epoch": 4.94,
- "learning_rate": 0.00016887755102040818,
- "loss": 1.6571,
+ "epoch": 2.76,
+ "learning_rate": 0.0001653409090909091,
+ "loss": 1.7724,
"step": 244
},
{
- "epoch": 4.96,
- "learning_rate": 0.00016875,
- "loss": 1.6829,
+ "epoch": 2.77,
+ "learning_rate": 0.00016519886363636365,
+ "loss": 1.7917,
"step": 245
},
{
- "epoch": 4.98,
- "learning_rate": 0.00016862244897959184,
- "loss": 1.6935,
+ "epoch": 2.78,
+ "learning_rate": 0.0001650568181818182,
+ "loss": 1.8442,
"step": 246
},
{
- "epoch": 5.0,
- "learning_rate": 0.00016849489795918367,
- "loss": 1.6782,
+ "epoch": 2.79,
+ "learning_rate": 0.00016491477272727274,
+ "loss": 1.7887,
"step": 247
},
{
- "epoch": 5.02,
- "learning_rate": 0.00016836734693877553,
- "loss": 1.622,
+ "epoch": 2.8,
+ "learning_rate": 0.00016477272727272727,
+ "loss": 1.8055,
"step": 248
},
{
- "epoch": 5.04,
- "learning_rate": 0.00016823979591836736,
- "loss": 1.6596,
+ "epoch": 2.81,
+ "learning_rate": 0.00016463068181818183,
+ "loss": 1.7754,
"step": 249
},
{
- "epoch": 5.06,
- "learning_rate": 0.0001681122448979592,
- "loss": 1.5821,
+ "epoch": 2.82,
+ "learning_rate": 0.00016448863636363636,
+ "loss": 1.7948,
"step": 250
},
{
- "epoch": 5.08,
- "learning_rate": 0.00016798469387755102,
- "loss": 1.7292,
+ "epoch": 2.84,
+ "learning_rate": 0.00016434659090909092,
+ "loss": 1.8332,
"step": 251
},
{
- "epoch": 5.1,
- "learning_rate": 0.00016785714285714288,
- "loss": 1.646,
+ "epoch": 2.85,
+ "learning_rate": 0.00016420454545454548,
+ "loss": 1.772,
"step": 252
},
{
- "epoch": 5.12,
- "learning_rate": 0.0001677295918367347,
- "loss": 1.6969,
+ "epoch": 2.86,
+ "learning_rate": 0.0001640625,
+ "loss": 1.7781,
"step": 253
},
{
- "epoch": 5.14,
- "learning_rate": 0.00016760204081632654,
- "loss": 1.6082,
+ "epoch": 2.87,
+ "learning_rate": 0.00016392045454545454,
+ "loss": 1.7714,
"step": 254
},
{
- "epoch": 5.16,
- "learning_rate": 0.00016747448979591837,
- "loss": 1.5843,
+ "epoch": 2.88,
+ "learning_rate": 0.0001637784090909091,
+ "loss": 1.793,
"step": 255
},
{
- "epoch": 5.18,
- "learning_rate": 0.00016734693877551023,
- "loss": 1.6827,
+ "epoch": 2.89,
+ "learning_rate": 0.00016363636363636366,
+ "loss": 1.8038,
"step": 256
},
{
- "epoch": 5.2,
- "learning_rate": 0.00016721938775510203,
- "loss": 1.5824,
+ "epoch": 2.9,
+ "learning_rate": 0.0001634943181818182,
+ "loss": 1.8137,
"step": 257
},
{
- "epoch": 5.22,
- "learning_rate": 0.0001670918367346939,
- "loss": 1.6795,
+ "epoch": 2.91,
+ "learning_rate": 0.00016335227272727275,
+ "loss": 1.7726,
"step": 258
},
{
- "epoch": 5.24,
- "learning_rate": 0.00016696428571428572,
- "loss": 1.5639,
+ "epoch": 2.93,
+ "learning_rate": 0.00016321022727272728,
+ "loss": 1.7753,
"step": 259
},
{
- "epoch": 5.26,
- "learning_rate": 0.00016683673469387755,
- "loss": 1.592,
+ "epoch": 2.94,
+ "learning_rate": 0.0001630681818181818,
+ "loss": 1.7553,
"step": 260
},
{
- "epoch": 5.28,
- "learning_rate": 0.00016670918367346938,
- "loss": 1.65,
+ "epoch": 2.95,
+ "learning_rate": 0.00016292613636363637,
+ "loss": 1.7518,
"step": 261
},
{
- "epoch": 5.3,
- "learning_rate": 0.00016658163265306124,
- "loss": 1.5592,
+ "epoch": 2.96,
+ "learning_rate": 0.00016278409090909093,
+ "loss": 1.7724,
"step": 262
},
{
- "epoch": 5.32,
- "learning_rate": 0.00016645408163265305,
- "loss": 1.5091,
+ "epoch": 2.97,
+ "learning_rate": 0.00016264204545454546,
+ "loss": 1.7266,
"step": 263
},
{
- "epoch": 5.34,
- "learning_rate": 0.0001663265306122449,
- "loss": 1.6138,
+ "epoch": 2.98,
+ "learning_rate": 0.00016250000000000002,
+ "loss": 1.8032,
"step": 264
},
{
- "epoch": 5.36,
- "learning_rate": 0.00016619897959183673,
- "loss": 1.625,
+ "epoch": 2.99,
+ "learning_rate": 0.00016235795454545455,
+ "loss": 1.7345,
"step": 265
},
{
- "epoch": 5.38,
- "learning_rate": 0.0001660714285714286,
- "loss": 1.5757,
+ "epoch": 3.01,
+ "learning_rate": 0.00016221590909090908,
+ "loss": 1.7249,
"step": 266
},
{
- "epoch": 5.4,
- "learning_rate": 0.00016594387755102042,
- "loss": 1.6372,
+ "epoch": 3.02,
+ "learning_rate": 0.00016207386363636364,
+ "loss": 1.7218,
"step": 267
},
{
- "epoch": 5.42,
- "learning_rate": 0.00016581632653061225,
- "loss": 1.5891,
+ "epoch": 3.03,
+ "learning_rate": 0.0001619318181818182,
+ "loss": 1.7092,
"step": 268
},
{
- "epoch": 5.44,
- "learning_rate": 0.00016568877551020409,
- "loss": 1.6893,
+ "epoch": 3.04,
+ "learning_rate": 0.00016178977272727273,
+ "loss": 1.6807,
"step": 269
},
{
- "epoch": 5.46,
- "learning_rate": 0.00016556122448979592,
- "loss": 1.6662,
+ "epoch": 3.05,
+ "learning_rate": 0.0001616477272727273,
+ "loss": 1.7264,
"step": 270
},
{
- "epoch": 5.48,
- "learning_rate": 0.00016543367346938777,
- "loss": 1.7132,
+ "epoch": 3.06,
+ "learning_rate": 0.00016150568181818182,
+ "loss": 1.726,
"step": 271
},
{
- "epoch": 5.5,
- "learning_rate": 0.0001653061224489796,
- "loss": 1.5835,
+ "epoch": 3.07,
+ "learning_rate": 0.00016136363636363635,
+ "loss": 1.6986,
"step": 272
},
{
- "epoch": 5.52,
- "learning_rate": 0.00016517857142857144,
- "loss": 1.6342,
+ "epoch": 3.08,
+ "learning_rate": 0.0001612215909090909,
+ "loss": 1.68,
"step": 273
},
{
- "epoch": 5.54,
- "learning_rate": 0.00016505102040816327,
- "loss": 1.6717,
+ "epoch": 3.1,
+ "learning_rate": 0.00016107954545454547,
+ "loss": 1.6677,
"step": 274
},
{
- "epoch": 5.56,
- "learning_rate": 0.00016492346938775512,
- "loss": 1.6248,
+ "epoch": 3.11,
+ "learning_rate": 0.0001609375,
+ "loss": 1.7137,
"step": 275
},
{
- "epoch": 5.58,
- "learning_rate": 0.00016479591836734696,
- "loss": 1.6117,
+ "epoch": 3.12,
+ "learning_rate": 0.00016079545454545456,
+ "loss": 1.6671,
"step": 276
},
{
- "epoch": 5.6,
- "learning_rate": 0.0001646683673469388,
- "loss": 1.6798,
+ "epoch": 3.13,
+ "learning_rate": 0.0001606534090909091,
+ "loss": 1.6873,
"step": 277
},
{
- "epoch": 5.63,
- "learning_rate": 0.00016454081632653062,
- "loss": 1.6406,
+ "epoch": 3.14,
+ "learning_rate": 0.00016051136363636365,
+ "loss": 1.6694,
"step": 278
},
{
- "epoch": 5.65,
- "learning_rate": 0.00016441326530612248,
- "loss": 1.6512,
+ "epoch": 3.15,
+ "learning_rate": 0.00016036931818181818,
+ "loss": 1.7003,
"step": 279
},
{
- "epoch": 5.67,
- "learning_rate": 0.00016428571428571428,
- "loss": 1.6102,
+ "epoch": 3.16,
+ "learning_rate": 0.00016022727272727274,
+ "loss": 1.6861,
"step": 280
},
{
- "epoch": 5.69,
- "learning_rate": 0.00016415816326530614,
- "loss": 1.6113,
+ "epoch": 3.17,
+ "learning_rate": 0.00016008522727272727,
+ "loss": 1.6881,
"step": 281
},
{
- "epoch": 5.71,
- "learning_rate": 0.00016403061224489797,
- "loss": 1.7116,
+ "epoch": 3.19,
+ "learning_rate": 0.00015994318181818183,
+ "loss": 1.6848,
"step": 282
},
{
- "epoch": 5.73,
- "learning_rate": 0.0001639030612244898,
- "loss": 1.6846,
+ "epoch": 3.2,
+ "learning_rate": 0.00015980113636363636,
+ "loss": 1.6872,
"step": 283
},
{
- "epoch": 5.75,
- "learning_rate": 0.00016377551020408163,
- "loss": 1.6911,
+ "epoch": 3.21,
+ "learning_rate": 0.00015965909090909092,
+ "loss": 1.6975,
"step": 284
},
{
- "epoch": 5.77,
- "learning_rate": 0.0001636479591836735,
- "loss": 1.6202,
+ "epoch": 3.22,
+ "learning_rate": 0.00015951704545454545,
+ "loss": 1.6708,
"step": 285
},
{
- "epoch": 5.79,
- "learning_rate": 0.0001635204081632653,
- "loss": 1.5715,
+ "epoch": 3.23,
+ "learning_rate": 0.000159375,
+ "loss": 1.6985,
"step": 286
},
{
- "epoch": 5.81,
- "learning_rate": 0.00016339285714285715,
- "loss": 1.6461,
+ "epoch": 3.24,
+ "learning_rate": 0.00015923295454545454,
+ "loss": 1.6586,
"step": 287
},
{
- "epoch": 5.83,
- "learning_rate": 0.00016326530612244898,
- "loss": 1.6624,
+ "epoch": 3.25,
+ "learning_rate": 0.0001590909090909091,
+ "loss": 1.6707,
"step": 288
},
{
- "epoch": 5.85,
- "learning_rate": 0.00016313775510204084,
- "loss": 1.6535,
+ "epoch": 3.26,
+ "learning_rate": 0.00015894886363636366,
+ "loss": 1.6576,
"step": 289
},
{
- "epoch": 5.87,
- "learning_rate": 0.00016301020408163267,
- "loss": 1.6275,
+ "epoch": 3.28,
+ "learning_rate": 0.0001588068181818182,
+ "loss": 1.6625,
"step": 290
},
{
- "epoch": 5.89,
- "learning_rate": 0.0001628826530612245,
- "loss": 1.6636,
+ "epoch": 3.29,
+ "learning_rate": 0.00015866477272727275,
+ "loss": 1.677,
"step": 291
},
{
- "epoch": 5.91,
- "learning_rate": 0.00016275510204081633,
- "loss": 1.6546,
+ "epoch": 3.3,
+ "learning_rate": 0.00015852272727272728,
+ "loss": 1.6599,
"step": 292
},
{
- "epoch": 5.93,
- "learning_rate": 0.00016262755102040816,
- "loss": 1.7274,
+ "epoch": 3.31,
+ "learning_rate": 0.0001583806818181818,
+ "loss": 1.6674,
"step": 293
},
{
- "epoch": 5.95,
- "learning_rate": 0.00016250000000000002,
- "loss": 1.5901,
+ "epoch": 3.32,
+ "learning_rate": 0.00015823863636363637,
+ "loss": 1.6707,
"step": 294
},
{
- "epoch": 5.97,
- "learning_rate": 0.00016237244897959185,
- "loss": 1.6046,
+ "epoch": 3.33,
+ "learning_rate": 0.00015809659090909093,
+ "loss": 1.6788,
"step": 295
},
{
- "epoch": 5.99,
- "learning_rate": 0.00016224489795918368,
- "loss": 1.5828,
+ "epoch": 3.34,
+ "learning_rate": 0.00015795454545454546,
+ "loss": 1.6686,
"step": 296
},
{
- "epoch": 6.01,
- "learning_rate": 0.0001621173469387755,
- "loss": 1.6435,
+ "epoch": 3.36,
+ "learning_rate": 0.00015781250000000002,
+ "loss": 1.6488,
"step": 297
},
{
- "epoch": 6.03,
- "learning_rate": 0.00016198979591836737,
- "loss": 1.6263,
+ "epoch": 3.37,
+ "learning_rate": 0.00015767045454545455,
+ "loss": 1.6806,
"step": 298
},
{
- "epoch": 6.05,
- "learning_rate": 0.00016186224489795917,
- "loss": 1.4944,
+ "epoch": 3.38,
+ "learning_rate": 0.00015752840909090908,
+ "loss": 1.6862,
"step": 299
},
{
- "epoch": 6.07,
- "learning_rate": 0.00016173469387755103,
- "loss": 1.6286,
+ "epoch": 3.39,
+ "learning_rate": 0.00015738636363636364,
+ "loss": 1.6499,
"step": 300
},
{
- "epoch": 6.09,
- "learning_rate": 0.00016160714285714286,
- "loss": 1.694,
+ "epoch": 3.4,
+ "learning_rate": 0.0001572443181818182,
+ "loss": 1.6245,
"step": 301
},
{
- "epoch": 6.11,
- "learning_rate": 0.00016147959183673472,
- "loss": 1.6197,
+ "epoch": 3.41,
+ "learning_rate": 0.00015710227272727273,
+ "loss": 1.6268,
"step": 302
},
{
- "epoch": 6.13,
- "learning_rate": 0.00016135204081632652,
- "loss": 1.5597,
+ "epoch": 3.42,
+ "learning_rate": 0.0001569602272727273,
+ "loss": 1.6438,
"step": 303
},
{
- "epoch": 6.15,
- "learning_rate": 0.00016122448979591838,
- "loss": 1.5487,
+ "epoch": 3.43,
+ "learning_rate": 0.00015681818181818182,
+ "loss": 1.6681,
"step": 304
},
{
- "epoch": 6.17,
- "learning_rate": 0.0001610969387755102,
- "loss": 1.5769,
+ "epoch": 3.45,
+ "learning_rate": 0.00015667613636363635,
+ "loss": 1.6582,
"step": 305
},
{
- "epoch": 6.19,
- "learning_rate": 0.00016096938775510204,
- "loss": 1.6367,
+ "epoch": 3.46,
+ "learning_rate": 0.0001565340909090909,
+ "loss": 1.6432,
"step": 306
},
{
- "epoch": 6.21,
- "learning_rate": 0.00016084183673469388,
- "loss": 1.583,
+ "epoch": 3.47,
+ "learning_rate": 0.00015639204545454547,
+ "loss": 1.617,
"step": 307
},
{
- "epoch": 6.23,
- "learning_rate": 0.00016071428571428573,
- "loss": 1.6201,
+ "epoch": 3.48,
+ "learning_rate": 0.00015625,
+ "loss": 1.6569,
"step": 308
},
{
- "epoch": 6.25,
- "learning_rate": 0.00016058673469387754,
- "loss": 1.6586,
+ "epoch": 3.49,
+ "learning_rate": 0.00015610795454545456,
+ "loss": 1.6276,
"step": 309
},
{
- "epoch": 6.27,
- "learning_rate": 0.0001604591836734694,
- "loss": 1.6711,
+ "epoch": 3.5,
+ "learning_rate": 0.0001559659090909091,
+ "loss": 1.6432,
"step": 310
},
{
- "epoch": 6.29,
- "learning_rate": 0.00016033163265306123,
- "loss": 1.6402,
+ "epoch": 3.51,
+ "learning_rate": 0.00015582386363636365,
+ "loss": 1.6132,
"step": 311
},
{
- "epoch": 6.31,
- "learning_rate": 0.00016020408163265306,
- "loss": 1.5247,
+ "epoch": 3.52,
+ "learning_rate": 0.00015568181818181818,
+ "loss": 1.5997,
"step": 312
},
{
- "epoch": 6.33,
- "learning_rate": 0.00016007653061224491,
- "loss": 1.5356,
+ "epoch": 3.54,
+ "learning_rate": 0.00015553977272727274,
+ "loss": 1.6154,
"step": 313
},
{
- "epoch": 6.35,
- "learning_rate": 0.00015994897959183675,
- "loss": 1.564,
+ "epoch": 3.55,
+ "learning_rate": 0.00015539772727272727,
+ "loss": 1.5862,
"step": 314
},
{
- "epoch": 6.37,
- "learning_rate": 0.00015982142857142858,
- "loss": 1.563,
+ "epoch": 3.56,
+ "learning_rate": 0.00015525568181818183,
+ "loss": 1.6233,
"step": 315
},
{
- "epoch": 6.39,
- "learning_rate": 0.0001596938775510204,
- "loss": 1.5198,
+ "epoch": 3.57,
+ "learning_rate": 0.00015511363636363636,
+ "loss": 1.6265,
"step": 316
},
{
- "epoch": 6.41,
- "learning_rate": 0.00015956632653061227,
- "loss": 1.6558,
+ "epoch": 3.58,
+ "learning_rate": 0.00015497159090909092,
+ "loss": 1.6171,
"step": 317
},
{
- "epoch": 6.43,
- "learning_rate": 0.0001594387755102041,
- "loss": 1.5534,
+ "epoch": 3.59,
+ "learning_rate": 0.00015482954545454545,
+ "loss": 1.6303,
"step": 318
},
{
- "epoch": 6.45,
- "learning_rate": 0.00015931122448979593,
- "loss": 1.6239,
+ "epoch": 3.6,
+ "learning_rate": 0.0001546875,
+ "loss": 1.6272,
"step": 319
},
{
- "epoch": 6.47,
- "learning_rate": 0.00015918367346938776,
- "loss": 1.5645,
+ "epoch": 3.62,
+ "learning_rate": 0.00015454545454545454,
+ "loss": 1.6183,
"step": 320
},
{
- "epoch": 6.5,
- "learning_rate": 0.00015905612244897962,
- "loss": 1.5713,
+ "epoch": 3.63,
+ "learning_rate": 0.0001544034090909091,
+ "loss": 1.6205,
"step": 321
},
{
- "epoch": 6.52,
- "learning_rate": 0.00015892857142857142,
- "loss": 1.6176,
+ "epoch": 3.64,
+ "learning_rate": 0.00015426136363636366,
+ "loss": 1.6099,
"step": 322
},
{
- "epoch": 6.54,
- "learning_rate": 0.00015880102040816328,
- "loss": 1.502,
+ "epoch": 3.65,
+ "learning_rate": 0.0001541193181818182,
+ "loss": 1.5973,
"step": 323
},
{
- "epoch": 6.56,
- "learning_rate": 0.0001586734693877551,
- "loss": 1.645,
+ "epoch": 3.66,
+ "learning_rate": 0.00015397727272727272,
+ "loss": 1.6247,
"step": 324
},
{
- "epoch": 6.58,
- "learning_rate": 0.00015854591836734697,
- "loss": 1.5904,
+ "epoch": 3.67,
+ "learning_rate": 0.00015383522727272728,
+ "loss": 1.6041,
"step": 325
},
{
- "epoch": 6.6,
- "learning_rate": 0.00015841836734693877,
- "loss": 1.6149,
+ "epoch": 3.68,
+ "learning_rate": 0.00015369318181818181,
+ "loss": 1.5835,
"step": 326
},
{
- "epoch": 6.62,
- "learning_rate": 0.00015829081632653063,
- "loss": 1.6757,
+ "epoch": 3.69,
+ "learning_rate": 0.00015355113636363637,
+ "loss": 1.608,
"step": 327
},
{
- "epoch": 6.64,
- "learning_rate": 0.00015816326530612246,
- "loss": 1.541,
+ "epoch": 3.71,
+ "learning_rate": 0.00015340909090909093,
+ "loss": 1.6155,
"step": 328
},
{
- "epoch": 6.66,
- "learning_rate": 0.0001580357142857143,
- "loss": 1.5898,
+ "epoch": 3.72,
+ "learning_rate": 0.00015326704545454546,
+ "loss": 1.5777,
"step": 329
},
{
- "epoch": 6.68,
- "learning_rate": 0.00015790816326530612,
- "loss": 1.5441,
+ "epoch": 3.73,
+ "learning_rate": 0.000153125,
+ "loss": 1.5969,
"step": 330
},
{
- "epoch": 6.7,
- "learning_rate": 0.00015778061224489798,
- "loss": 1.61,
+ "epoch": 3.74,
+ "learning_rate": 0.00015298295454545455,
+ "loss": 1.5904,
"step": 331
},
{
- "epoch": 6.72,
- "learning_rate": 0.00015765306122448978,
- "loss": 1.615,
+ "epoch": 3.75,
+ "learning_rate": 0.00015284090909090909,
+ "loss": 1.586,
"step": 332
},
{
- "epoch": 6.74,
- "learning_rate": 0.00015752551020408164,
- "loss": 1.6575,
+ "epoch": 3.76,
+ "learning_rate": 0.00015269886363636364,
+ "loss": 1.582,
"step": 333
},
{
- "epoch": 6.76,
- "learning_rate": 0.00015739795918367347,
- "loss": 1.6702,
+ "epoch": 3.77,
+ "learning_rate": 0.0001525568181818182,
+ "loss": 1.548,
"step": 334
},
{
- "epoch": 6.78,
- "learning_rate": 0.0001572704081632653,
- "loss": 1.6009,
+ "epoch": 3.78,
+ "learning_rate": 0.00015241477272727273,
+ "loss": 1.5564,
"step": 335
},
{
- "epoch": 6.8,
- "learning_rate": 0.00015714285714285716,
- "loss": 1.5568,
+ "epoch": 3.8,
+ "learning_rate": 0.00015227272727272727,
+ "loss": 1.5506,
"step": 336
},
{
- "epoch": 6.82,
- "learning_rate": 0.000157015306122449,
- "loss": 1.619,
+ "epoch": 3.81,
+ "learning_rate": 0.00015213068181818182,
+ "loss": 1.5526,
"step": 337
},
{
- "epoch": 6.84,
- "learning_rate": 0.00015688775510204082,
- "loss": 1.5563,
+ "epoch": 3.82,
+ "learning_rate": 0.00015198863636363636,
+ "loss": 1.5564,
"step": 338
},
{
- "epoch": 6.86,
- "learning_rate": 0.00015676020408163265,
- "loss": 1.6328,
+ "epoch": 3.83,
+ "learning_rate": 0.00015184659090909091,
+ "loss": 1.5598,
"step": 339
},
{
- "epoch": 6.88,
- "learning_rate": 0.0001566326530612245,
- "loss": 1.5726,
+ "epoch": 3.84,
+ "learning_rate": 0.00015170454545454547,
+ "loss": 1.5679,
"step": 340
},
{
- "epoch": 6.9,
- "learning_rate": 0.00015650510204081634,
- "loss": 1.6199,
+ "epoch": 3.85,
+ "learning_rate": 0.0001515625,
+ "loss": 1.549,
"step": 341
},
{
- "epoch": 6.92,
- "learning_rate": 0.00015637755102040817,
- "loss": 1.5722,
+ "epoch": 3.86,
+ "learning_rate": 0.00015142045454545454,
+ "loss": 1.5672,
"step": 342
},
{
- "epoch": 6.94,
- "learning_rate": 0.00015625,
- "loss": 1.5685,
+ "epoch": 3.88,
+ "learning_rate": 0.0001512784090909091,
+ "loss": 1.5399,
"step": 343
},
{
- "epoch": 6.96,
- "learning_rate": 0.00015612244897959186,
- "loss": 1.5615,
+ "epoch": 3.89,
+ "learning_rate": 0.00015113636363636365,
+ "loss": 1.5576,
"step": 344
},
{
- "epoch": 6.98,
- "learning_rate": 0.00015599489795918366,
- "loss": 1.5994,
+ "epoch": 3.9,
+ "learning_rate": 0.00015099431818181818,
+ "loss": 1.549,
"step": 345
},
{
- "epoch": 7.0,
- "learning_rate": 0.00015586734693877552,
- "loss": 1.5579,
+ "epoch": 3.91,
+ "learning_rate": 0.00015085227272727274,
+ "loss": 1.5345,
"step": 346
},
{
- "epoch": 7.02,
- "learning_rate": 0.00015573979591836735,
- "loss": 1.547,
+ "epoch": 3.92,
+ "learning_rate": 0.00015071022727272728,
+ "loss": 1.5015,
"step": 347
},
{
- "epoch": 7.04,
- "learning_rate": 0.00015561224489795918,
- "loss": 1.5292,
+ "epoch": 3.93,
+ "learning_rate": 0.0001505681818181818,
+ "loss": 1.5221,
"step": 348
},
{
- "epoch": 7.06,
- "learning_rate": 0.00015548469387755102,
- "loss": 1.6032,
+ "epoch": 3.94,
+ "learning_rate": 0.00015042613636363637,
+ "loss": 1.556,
"step": 349
},
{
- "epoch": 7.08,
- "learning_rate": 0.00015535714285714287,
- "loss": 1.5149,
+ "epoch": 3.95,
+ "learning_rate": 0.00015028409090909092,
+ "loss": 1.5276,
"step": 350
},
{
- "epoch": 7.1,
- "learning_rate": 0.0001552295918367347,
- "loss": 1.6093,
+ "epoch": 3.97,
+ "learning_rate": 0.00015014204545454546,
+ "loss": 1.552,
"step": 351
},
{
- "epoch": 7.12,
- "learning_rate": 0.00015510204081632654,
- "loss": 1.5421,
+ "epoch": 3.98,
+ "learning_rate": 0.00015000000000000001,
+ "loss": 1.5377,
"step": 352
},
{
- "epoch": 7.14,
- "learning_rate": 0.00015497448979591837,
- "loss": 1.5733,
+ "epoch": 3.99,
+ "learning_rate": 0.00014985795454545455,
+ "loss": 1.5576,
"step": 353
},
{
- "epoch": 7.16,
- "learning_rate": 0.00015484693877551022,
- "loss": 1.5703,
+ "epoch": 4.0,
+ "learning_rate": 0.00014971590909090908,
+ "loss": 1.5295,
"step": 354
},
{
- "epoch": 7.18,
- "learning_rate": 0.00015471938775510203,
- "loss": 1.6141,
+ "epoch": 4.01,
+ "learning_rate": 0.00014957386363636366,
+ "loss": 1.4842,
"step": 355
},
{
- "epoch": 7.2,
- "learning_rate": 0.00015459183673469389,
- "loss": 1.5526,
+ "epoch": 4.02,
+ "learning_rate": 0.0001494318181818182,
+ "loss": 1.4803,
"step": 356
},
{
- "epoch": 7.22,
- "learning_rate": 0.00015446428571428572,
- "loss": 1.5347,
+ "epoch": 4.03,
+ "learning_rate": 0.00014928977272727273,
+ "loss": 1.4559,
"step": 357
},
{
- "epoch": 7.24,
- "learning_rate": 0.00015433673469387755,
- "loss": 1.5682,
+ "epoch": 4.04,
+ "learning_rate": 0.00014914772727272728,
+ "loss": 1.4777,
"step": 358
},
{
- "epoch": 7.26,
- "learning_rate": 0.0001542091836734694,
- "loss": 1.5292,
+ "epoch": 4.06,
+ "learning_rate": 0.00014900568181818182,
+ "loss": 1.4343,
"step": 359
},
{
- "epoch": 7.28,
- "learning_rate": 0.00015408163265306124,
- "loss": 1.499,
+ "epoch": 4.07,
+ "learning_rate": 0.00014886363636363635,
+ "loss": 1.4699,
"step": 360
},
{
- "epoch": 7.3,
- "learning_rate": 0.00015395408163265307,
- "loss": 1.5624,
+ "epoch": 4.08,
+ "learning_rate": 0.00014872159090909093,
+ "loss": 1.4452,
"step": 361
},
{
- "epoch": 7.32,
- "learning_rate": 0.0001538265306122449,
- "loss": 1.627,
+ "epoch": 4.09,
+ "learning_rate": 0.00014857954545454546,
+ "loss": 1.4461,
"step": 362
},
{
- "epoch": 7.34,
- "learning_rate": 0.00015369897959183676,
- "loss": 1.5327,
+ "epoch": 4.1,
+ "learning_rate": 0.0001484375,
+ "loss": 1.4523,
"step": 363
},
{
- "epoch": 7.37,
- "learning_rate": 0.0001535714285714286,
- "loss": 1.5622,
+ "epoch": 4.11,
+ "learning_rate": 0.00014829545454545455,
+ "loss": 1.4425,
"step": 364
},
{
- "epoch": 7.39,
- "learning_rate": 0.00015344387755102042,
- "loss": 1.5659,
+ "epoch": 4.12,
+ "learning_rate": 0.0001481534090909091,
+ "loss": 1.4559,
"step": 365
},
{
- "epoch": 7.41,
- "learning_rate": 0.00015331632653061225,
- "loss": 1.5019,
+ "epoch": 4.13,
+ "learning_rate": 0.00014801136363636365,
+ "loss": 1.4193,
"step": 366
},
{
- "epoch": 7.43,
- "learning_rate": 0.0001531887755102041,
- "loss": 1.5921,
+ "epoch": 4.15,
+ "learning_rate": 0.0001478693181818182,
+ "loss": 1.4136,
"step": 367
},
{
- "epoch": 7.45,
- "learning_rate": 0.0001530612244897959,
- "loss": 1.5914,
+ "epoch": 4.16,
+ "learning_rate": 0.00014772727272727274,
+ "loss": 1.445,
"step": 368
},
{
- "epoch": 7.47,
- "learning_rate": 0.00015293367346938777,
- "loss": 1.5045,
+ "epoch": 4.17,
+ "learning_rate": 0.00014758522727272727,
+ "loss": 1.4304,
"step": 369
},
{
- "epoch": 7.49,
- "learning_rate": 0.0001528061224489796,
- "loss": 1.6209,
+ "epoch": 4.18,
+ "learning_rate": 0.00014744318181818183,
+ "loss": 1.3996,
"step": 370
},
{
- "epoch": 7.51,
- "learning_rate": 0.00015267857142857143,
- "loss": 1.5198,
+ "epoch": 4.19,
+ "learning_rate": 0.00014730113636363636,
+ "loss": 1.4247,
"step": 371
},
{
- "epoch": 7.53,
- "learning_rate": 0.00015255102040816326,
- "loss": 1.5363,
+ "epoch": 4.2,
+ "learning_rate": 0.00014715909090909092,
+ "loss": 1.4303,
"step": 372
},
{
- "epoch": 7.55,
- "learning_rate": 0.00015242346938775512,
- "loss": 1.5391,
+ "epoch": 4.21,
+ "learning_rate": 0.00014701704545454547,
+ "loss": 1.4219,
"step": 373
},
{
- "epoch": 7.57,
- "learning_rate": 0.00015229591836734695,
- "loss": 1.4546,
+ "epoch": 4.23,
+ "learning_rate": 0.000146875,
+ "loss": 1.4538,
"step": 374
},
{
- "epoch": 7.59,
- "learning_rate": 0.00015216836734693878,
- "loss": 1.5546,
+ "epoch": 4.24,
+ "learning_rate": 0.00014673295454545454,
+ "loss": 1.4391,
"step": 375
},
{
- "epoch": 7.61,
- "learning_rate": 0.0001520408163265306,
- "loss": 1.5629,
+ "epoch": 4.25,
+ "learning_rate": 0.0001465909090909091,
+ "loss": 1.4482,
"step": 376
},
{
- "epoch": 7.63,
- "learning_rate": 0.00015191326530612247,
- "loss": 1.6002,
+ "epoch": 4.26,
+ "learning_rate": 0.00014644886363636365,
+ "loss": 1.4208,
"step": 377
},
{
- "epoch": 7.65,
- "learning_rate": 0.00015178571428571427,
- "loss": 1.5543,
+ "epoch": 4.27,
+ "learning_rate": 0.00014630681818181819,
+ "loss": 1.4111,
"step": 378
},
{
- "epoch": 7.67,
- "learning_rate": 0.00015165816326530613,
- "loss": 1.5925,
+ "epoch": 4.28,
+ "learning_rate": 0.00014616477272727274,
+ "loss": 1.4318,
"step": 379
},
{
- "epoch": 7.69,
- "learning_rate": 0.00015153061224489796,
- "loss": 1.5631,
+ "epoch": 4.29,
+ "learning_rate": 0.00014602272727272728,
+ "loss": 1.3913,
"step": 380
},
{
- "epoch": 7.71,
- "learning_rate": 0.0001514030612244898,
- "loss": 1.5677,
+ "epoch": 4.3,
+ "learning_rate": 0.0001458806818181818,
+ "loss": 1.3847,
"step": 381
},
{
- "epoch": 7.73,
- "learning_rate": 0.00015127551020408165,
- "loss": 1.5828,
+ "epoch": 4.32,
+ "learning_rate": 0.00014573863636363637,
+ "loss": 1.4254,
"step": 382
},
{
- "epoch": 7.75,
- "learning_rate": 0.00015114795918367348,
- "loss": 1.6494,
+ "epoch": 4.33,
+ "learning_rate": 0.00014559659090909093,
+ "loss": 1.4143,
"step": 383
},
{
- "epoch": 7.77,
- "learning_rate": 0.0001510204081632653,
- "loss": 1.553,
+ "epoch": 4.34,
+ "learning_rate": 0.00014545454545454546,
+ "loss": 1.4362,
"step": 384
},
{
- "epoch": 7.79,
- "learning_rate": 0.00015089285714285714,
- "loss": 1.6156,
+ "epoch": 4.35,
+ "learning_rate": 0.00014531250000000002,
+ "loss": 1.386,
"step": 385
},
{
- "epoch": 7.81,
- "learning_rate": 0.000150765306122449,
- "loss": 1.5001,
+ "epoch": 4.36,
+ "learning_rate": 0.00014517045454545455,
+ "loss": 1.4009,
"step": 386
},
{
- "epoch": 7.83,
- "learning_rate": 0.00015063775510204083,
- "loss": 1.5321,
+ "epoch": 4.37,
+ "learning_rate": 0.00014502840909090908,
+ "loss": 1.4089,
"step": 387
},
{
- "epoch": 7.85,
- "learning_rate": 0.00015051020408163266,
- "loss": 1.5307,
+ "epoch": 4.38,
+ "learning_rate": 0.00014488636363636366,
+ "loss": 1.4117,
"step": 388
},
{
- "epoch": 7.87,
- "learning_rate": 0.0001503826530612245,
- "loss": 1.5639,
+ "epoch": 4.39,
+ "learning_rate": 0.0001447443181818182,
+ "loss": 1.3788,
"step": 389
},
{
- "epoch": 7.89,
- "learning_rate": 0.00015025510204081635,
- "loss": 1.517,
+ "epoch": 4.41,
+ "learning_rate": 0.00014460227272727273,
+ "loss": 1.3573,
"step": 390
},
{
- "epoch": 7.91,
- "learning_rate": 0.00015012755102040816,
- "loss": 1.4776,
+ "epoch": 4.42,
+ "learning_rate": 0.00014446022727272729,
+ "loss": 1.4133,
"step": 391
},
{
- "epoch": 7.93,
- "learning_rate": 0.00015000000000000001,
- "loss": 1.5368,
+ "epoch": 4.43,
+ "learning_rate": 0.00014431818181818182,
+ "loss": 1.3866,
"step": 392
},
{
- "epoch": 7.95,
- "learning_rate": 0.00014987244897959184,
- "loss": 1.5636,
+ "epoch": 4.44,
+ "learning_rate": 0.00014417613636363635,
+ "loss": 1.3883,
"step": 393
},
{
- "epoch": 7.97,
- "learning_rate": 0.00014974489795918368,
- "loss": 1.6004,
+ "epoch": 4.45,
+ "learning_rate": 0.00014403409090909093,
+ "loss": 1.3741,
"step": 394
},
{
- "epoch": 7.99,
- "learning_rate": 0.0001496173469387755,
- "loss": 1.5524,
+ "epoch": 4.46,
+ "learning_rate": 0.00014389204545454547,
+ "loss": 1.358,
"step": 395
},
{
- "epoch": 8.01,
- "learning_rate": 0.00014948979591836736,
- "loss": 1.5307,
+ "epoch": 4.47,
+ "learning_rate": 0.00014375,
+ "loss": 1.3893,
"step": 396
},
{
- "epoch": 8.03,
- "learning_rate": 0.00014936224489795917,
- "loss": 1.5123,
+ "epoch": 4.49,
+ "learning_rate": 0.00014360795454545456,
+ "loss": 1.4062,
"step": 397
},
{
- "epoch": 8.05,
- "learning_rate": 0.00014923469387755103,
- "loss": 1.5132,
+ "epoch": 4.5,
+ "learning_rate": 0.0001434659090909091,
+ "loss": 1.3795,
"step": 398
},
{
- "epoch": 8.07,
- "learning_rate": 0.00014910714285714286,
- "loss": 1.5109,
+ "epoch": 4.51,
+ "learning_rate": 0.00014332386363636365,
+ "loss": 1.3472,
"step": 399
},
{
- "epoch": 8.09,
- "learning_rate": 0.00014897959183673472,
- "loss": 1.5302,
+ "epoch": 4.52,
+ "learning_rate": 0.0001431818181818182,
+ "loss": 1.3408,
"step": 400
},
{
- "epoch": 8.11,
- "learning_rate": 0.00014885204081632652,
- "loss": 1.5238,
+ "epoch": 4.53,
+ "learning_rate": 0.00014303977272727274,
+ "loss": 1.3801,
"step": 401
},
{
- "epoch": 8.13,
- "learning_rate": 0.00014872448979591838,
- "loss": 1.4781,
+ "epoch": 4.54,
+ "learning_rate": 0.00014289772727272727,
+ "loss": 1.3709,
"step": 402
},
{
- "epoch": 8.15,
- "learning_rate": 0.0001485969387755102,
- "loss": 1.5446,
+ "epoch": 4.55,
+ "learning_rate": 0.00014275568181818183,
+ "loss": 1.3653,
"step": 403
},
{
- "epoch": 8.17,
- "learning_rate": 0.00014846938775510204,
- "loss": 1.5,
+ "epoch": 4.56,
+ "learning_rate": 0.00014261363636363636,
+ "loss": 1.4089,
"step": 404
},
{
- "epoch": 8.19,
- "learning_rate": 0.0001483418367346939,
- "loss": 1.5458,
+ "epoch": 4.58,
+ "learning_rate": 0.00014247159090909092,
+ "loss": 1.3281,
"step": 405
},
{
- "epoch": 8.21,
- "learning_rate": 0.00014821428571428573,
- "loss": 1.5257,
+ "epoch": 4.59,
+ "learning_rate": 0.00014232954545454548,
+ "loss": 1.328,
"step": 406
},
{
- "epoch": 8.24,
- "learning_rate": 0.00014808673469387756,
- "loss": 1.4607,
+ "epoch": 4.6,
+ "learning_rate": 0.0001421875,
+ "loss": 1.3458,
"step": 407
},
{
- "epoch": 8.26,
- "learning_rate": 0.0001479591836734694,
- "loss": 1.4282,
+ "epoch": 4.61,
+ "learning_rate": 0.00014204545454545454,
+ "loss": 1.3425,
"step": 408
},
{
- "epoch": 8.28,
- "learning_rate": 0.00014783163265306125,
- "loss": 1.4519,
+ "epoch": 4.62,
+ "learning_rate": 0.0001419034090909091,
+ "loss": 1.3236,
"step": 409
},
{
- "epoch": 8.3,
- "learning_rate": 0.00014770408163265305,
- "loss": 1.475,
+ "epoch": 4.63,
+ "learning_rate": 0.00014176136363636366,
+ "loss": 1.3439,
"step": 410
},
{
- "epoch": 8.32,
- "learning_rate": 0.0001475765306122449,
- "loss": 1.5425,
+ "epoch": 4.64,
+ "learning_rate": 0.0001416193181818182,
+ "loss": 1.3397,
"step": 411
},
{
- "epoch": 8.34,
- "learning_rate": 0.00014744897959183674,
- "loss": 1.5407,
+ "epoch": 4.65,
+ "learning_rate": 0.00014147727272727275,
+ "loss": 1.329,
"step": 412
},
{
- "epoch": 8.36,
- "learning_rate": 0.0001473214285714286,
- "loss": 1.5698,
+ "epoch": 4.67,
+ "learning_rate": 0.00014133522727272728,
+ "loss": 1.3377,
"step": 413
},
{
- "epoch": 8.38,
- "learning_rate": 0.0001471938775510204,
- "loss": 1.4282,
+ "epoch": 4.68,
+ "learning_rate": 0.0001411931818181818,
+ "loss": 1.343,
"step": 414
},
{
- "epoch": 8.4,
- "learning_rate": 0.00014706632653061226,
- "loss": 1.5301,
+ "epoch": 4.69,
+ "learning_rate": 0.00014105113636363637,
+ "loss": 1.3185,
"step": 415
},
{
- "epoch": 8.42,
- "learning_rate": 0.0001469387755102041,
- "loss": 1.5083,
+ "epoch": 4.7,
+ "learning_rate": 0.00014090909090909093,
+ "loss": 1.3174,
"step": 416
},
{
- "epoch": 8.44,
- "learning_rate": 0.00014681122448979592,
- "loss": 1.5712,
+ "epoch": 4.71,
+ "learning_rate": 0.00014076704545454546,
+ "loss": 1.3231,
"step": 417
},
{
- "epoch": 8.46,
- "learning_rate": 0.00014668367346938775,
- "loss": 1.4363,
+ "epoch": 4.72,
+ "learning_rate": 0.00014062500000000002,
+ "loss": 1.3407,
"step": 418
},
{
- "epoch": 8.48,
- "learning_rate": 0.0001465561224489796,
- "loss": 1.4463,
+ "epoch": 4.73,
+ "learning_rate": 0.00014048295454545455,
+ "loss": 1.3138,
"step": 419
},
{
- "epoch": 8.5,
- "learning_rate": 0.00014642857142857141,
- "loss": 1.4738,
+ "epoch": 4.74,
+ "learning_rate": 0.00014034090909090908,
+ "loss": 1.3134,
"step": 420
},
{
- "epoch": 8.52,
- "learning_rate": 0.00014630102040816327,
- "loss": 1.5396,
+ "epoch": 4.76,
+ "learning_rate": 0.00014019886363636367,
+ "loss": 1.3187,
"step": 421
},
{
- "epoch": 8.54,
- "learning_rate": 0.0001461734693877551,
- "loss": 1.4384,
+ "epoch": 4.77,
+ "learning_rate": 0.0001400568181818182,
+ "loss": 1.2781,
"step": 422
},
{
- "epoch": 8.56,
- "learning_rate": 0.00014604591836734696,
- "loss": 1.5345,
+ "epoch": 4.78,
+ "learning_rate": 0.00013991477272727273,
+ "loss": 1.3254,
"step": 423
},
{
- "epoch": 8.58,
- "learning_rate": 0.0001459183673469388,
- "loss": 1.5355,
+ "epoch": 4.79,
+ "learning_rate": 0.0001397727272727273,
+ "loss": 1.2929,
"step": 424
},
{
- "epoch": 8.6,
- "learning_rate": 0.00014579081632653062,
- "loss": 1.5188,
+ "epoch": 4.8,
+ "learning_rate": 0.00013963068181818182,
+ "loss": 1.2953,
"step": 425
},
{
- "epoch": 8.62,
- "learning_rate": 0.00014566326530612245,
- "loss": 1.5575,
+ "epoch": 4.81,
+ "learning_rate": 0.00013948863636363635,
+ "loss": 1.3202,
"step": 426
},
{
- "epoch": 8.64,
- "learning_rate": 0.00014553571428571428,
- "loss": 1.5279,
+ "epoch": 4.82,
+ "learning_rate": 0.00013934659090909094,
+ "loss": 1.3118,
"step": 427
},
{
- "epoch": 8.66,
- "learning_rate": 0.00014540816326530614,
- "loss": 1.5484,
+ "epoch": 4.84,
+ "learning_rate": 0.00013920454545454547,
+ "loss": 1.3046,
"step": 428
},
{
- "epoch": 8.68,
- "learning_rate": 0.00014528061224489797,
- "loss": 1.4878,
+ "epoch": 4.85,
+ "learning_rate": 0.0001390625,
+ "loss": 1.2708,
"step": 429
},
{
- "epoch": 8.7,
- "learning_rate": 0.0001451530612244898,
- "loss": 1.503,
+ "epoch": 4.86,
+ "learning_rate": 0.00013892045454545456,
+ "loss": 1.2835,
"step": 430
},
{
- "epoch": 8.72,
- "learning_rate": 0.00014502551020408163,
- "loss": 1.4723,
+ "epoch": 4.87,
+ "learning_rate": 0.0001387784090909091,
+ "loss": 1.2728,
"step": 431
},
{
- "epoch": 8.74,
- "learning_rate": 0.0001448979591836735,
- "loss": 1.5579,
+ "epoch": 4.88,
+ "learning_rate": 0.00013863636363636365,
+ "loss": 1.3107,
"step": 432
},
{
- "epoch": 8.76,
- "learning_rate": 0.0001447704081632653,
- "loss": 1.4789,
+ "epoch": 4.89,
+ "learning_rate": 0.0001384943181818182,
+ "loss": 1.2615,
"step": 433
},
{
- "epoch": 8.78,
- "learning_rate": 0.00014464285714285715,
- "loss": 1.5501,
+ "epoch": 4.9,
+ "learning_rate": 0.00013835227272727274,
+ "loss": 1.2754,
"step": 434
},
{
- "epoch": 8.8,
- "learning_rate": 0.00014451530612244899,
- "loss": 1.5204,
+ "epoch": 4.91,
+ "learning_rate": 0.00013821022727272727,
+ "loss": 1.3018,
"step": 435
},
{
- "epoch": 8.82,
- "learning_rate": 0.00014438775510204084,
- "loss": 1.5489,
+ "epoch": 4.93,
+ "learning_rate": 0.00013806818181818183,
+ "loss": 1.2878,
"step": 436
},
{
- "epoch": 8.84,
- "learning_rate": 0.00014426020408163265,
- "loss": 1.5464,
+ "epoch": 4.94,
+ "learning_rate": 0.00013792613636363636,
+ "loss": 1.2595,
"step": 437
},
{
- "epoch": 8.86,
- "learning_rate": 0.0001441326530612245,
- "loss": 1.5896,
+ "epoch": 4.95,
+ "learning_rate": 0.00013778409090909092,
+ "loss": 1.2688,
"step": 438
},
{
- "epoch": 8.88,
- "learning_rate": 0.00014400510204081634,
- "loss": 1.5465,
+ "epoch": 4.96,
+ "learning_rate": 0.00013764204545454548,
+ "loss": 1.2669,
"step": 439
},
{
- "epoch": 8.9,
- "learning_rate": 0.00014387755102040817,
- "loss": 1.5094,
+ "epoch": 4.97,
+ "learning_rate": 0.0001375,
+ "loss": 1.2861,
"step": 440
},
{
- "epoch": 8.92,
- "learning_rate": 0.00014375,
- "loss": 1.5144,
+ "epoch": 4.98,
+ "learning_rate": 0.00013735795454545454,
+ "loss": 1.2536,
"step": 441
},
{
- "epoch": 8.94,
- "learning_rate": 0.00014362244897959186,
- "loss": 1.4919,
+ "epoch": 4.99,
+ "learning_rate": 0.0001372159090909091,
+ "loss": 1.2584,
"step": 442
},
{
- "epoch": 8.96,
- "learning_rate": 0.00014349489795918366,
- "loss": 1.4702,
+ "epoch": 5.0,
+ "learning_rate": 0.00013707386363636366,
+ "loss": 1.2203,
"step": 443
},
{
- "epoch": 8.98,
- "learning_rate": 0.00014336734693877552,
- "loss": 1.4996,
+ "epoch": 5.02,
+ "learning_rate": 0.0001369318181818182,
+ "loss": 1.1796,
"step": 444
},
{
- "epoch": 9.0,
- "learning_rate": 0.00014323979591836735,
- "loss": 1.5503,
+ "epoch": 5.03,
+ "learning_rate": 0.00013678977272727275,
+ "loss": 1.1856,
"step": 445
},
{
- "epoch": 9.02,
- "learning_rate": 0.00014311224489795918,
- "loss": 1.4125,
+ "epoch": 5.04,
+ "learning_rate": 0.00013664772727272728,
+ "loss": 1.1801,
"step": 446
},
{
- "epoch": 9.04,
- "learning_rate": 0.00014298469387755104,
- "loss": 1.4722,
+ "epoch": 5.05,
+ "learning_rate": 0.0001365056818181818,
+ "loss": 1.1761,
"step": 447
},
{
- "epoch": 9.06,
- "learning_rate": 0.00014285714285714287,
- "loss": 1.5199,
+ "epoch": 5.06,
+ "learning_rate": 0.00013636363636363637,
+ "loss": 1.1495,
"step": 448
},
{
- "epoch": 9.09,
- "learning_rate": 0.0001427295918367347,
- "loss": 1.4571,
+ "epoch": 5.07,
+ "learning_rate": 0.00013622159090909093,
+ "loss": 1.1903,
"step": 449
},
{
- "epoch": 9.11,
- "learning_rate": 0.00014260204081632653,
- "loss": 1.4996,
+ "epoch": 5.08,
+ "learning_rate": 0.00013607954545454546,
+ "loss": 1.1778,
"step": 450
},
{
- "epoch": 9.13,
- "learning_rate": 0.0001424744897959184,
- "loss": 1.4092,
+ "epoch": 5.1,
+ "learning_rate": 0.00013593750000000002,
+ "loss": 1.1902,
"step": 451
},
{
- "epoch": 9.15,
- "learning_rate": 0.00014234693877551022,
- "loss": 1.4198,
+ "epoch": 5.11,
+ "learning_rate": 0.00013579545454545455,
+ "loss": 1.1597,
"step": 452
},
{
- "epoch": 9.17,
- "learning_rate": 0.00014221938775510205,
- "loss": 1.4916,
+ "epoch": 5.12,
+ "learning_rate": 0.00013565340909090908,
+ "loss": 1.1529,
"step": 453
},
{
- "epoch": 9.19,
- "learning_rate": 0.00014209183673469388,
- "loss": 1.5051,
+ "epoch": 5.13,
+ "learning_rate": 0.00013551136363636364,
+ "loss": 1.1627,
"step": 454
},
{
- "epoch": 9.21,
- "learning_rate": 0.00014196428571428574,
- "loss": 1.4321,
+ "epoch": 5.14,
+ "learning_rate": 0.0001353693181818182,
+ "loss": 1.1613,
"step": 455
},
{
- "epoch": 9.23,
- "learning_rate": 0.00014183673469387754,
- "loss": 1.4097,
+ "epoch": 5.15,
+ "learning_rate": 0.00013522727272727273,
+ "loss": 1.1336,
"step": 456
},
{
- "epoch": 9.25,
- "learning_rate": 0.0001417091836734694,
- "loss": 1.4853,
+ "epoch": 5.16,
+ "learning_rate": 0.0001350852272727273,
+ "loss": 1.1369,
"step": 457
},
{
- "epoch": 9.27,
- "learning_rate": 0.00014158163265306123,
- "loss": 1.4593,
+ "epoch": 5.17,
+ "learning_rate": 0.00013494318181818182,
+ "loss": 1.1592,
"step": 458
},
{
- "epoch": 9.29,
- "learning_rate": 0.00014145408163265306,
- "loss": 1.3729,
+ "epoch": 5.19,
+ "learning_rate": 0.00013480113636363635,
+ "loss": 1.1482,
"step": 459
},
{
- "epoch": 9.31,
- "learning_rate": 0.0001413265306122449,
- "loss": 1.4467,
+ "epoch": 5.2,
+ "learning_rate": 0.00013465909090909094,
+ "loss": 1.1857,
"step": 460
},
{
- "epoch": 9.33,
- "learning_rate": 0.00014119897959183675,
- "loss": 1.4467,
+ "epoch": 5.21,
+ "learning_rate": 0.00013451704545454547,
+ "loss": 1.1651,
"step": 461
},
{
- "epoch": 9.35,
- "learning_rate": 0.00014107142857142858,
- "loss": 1.4785,
+ "epoch": 5.22,
+ "learning_rate": 0.000134375,
+ "loss": 1.1544,
"step": 462
},
{
- "epoch": 9.37,
- "learning_rate": 0.0001409438775510204,
- "loss": 1.4089,
+ "epoch": 5.23,
+ "learning_rate": 0.00013423295454545456,
+ "loss": 1.125,
"step": 463
},
{
- "epoch": 9.39,
- "learning_rate": 0.00014081632653061224,
- "loss": 1.5026,
+ "epoch": 5.24,
+ "learning_rate": 0.0001340909090909091,
+ "loss": 1.167,
"step": 464
},
{
- "epoch": 9.41,
- "learning_rate": 0.0001406887755102041,
- "loss": 1.4857,
+ "epoch": 5.25,
+ "learning_rate": 0.00013394886363636365,
+ "loss": 1.1316,
"step": 465
},
{
- "epoch": 9.43,
- "learning_rate": 0.0001405612244897959,
- "loss": 1.3745,
+ "epoch": 5.26,
+ "learning_rate": 0.0001338068181818182,
+ "loss": 1.1604,
"step": 466
},
{
- "epoch": 9.45,
- "learning_rate": 0.00014043367346938776,
- "loss": 1.4733,
+ "epoch": 5.28,
+ "learning_rate": 0.00013366477272727274,
+ "loss": 1.2005,
"step": 467
},
{
- "epoch": 9.47,
- "learning_rate": 0.0001403061224489796,
- "loss": 1.5212,
+ "epoch": 5.29,
+ "learning_rate": 0.00013352272727272727,
+ "loss": 1.1496,
"step": 468
},
{
- "epoch": 9.49,
- "learning_rate": 0.00014017857142857142,
- "loss": 1.5398,
+ "epoch": 5.3,
+ "learning_rate": 0.00013338068181818183,
+ "loss": 1.1331,
"step": 469
},
{
- "epoch": 9.51,
- "learning_rate": 0.00014005102040816328,
- "loss": 1.478,
+ "epoch": 5.31,
+ "learning_rate": 0.00013323863636363636,
+ "loss": 1.1414,
"step": 470
},
{
- "epoch": 9.53,
- "learning_rate": 0.0001399234693877551,
- "loss": 1.496,
+ "epoch": 5.32,
+ "learning_rate": 0.00013309659090909092,
+ "loss": 1.0945,
"step": 471
},
{
- "epoch": 9.55,
- "learning_rate": 0.00013979591836734694,
- "loss": 1.4837,
+ "epoch": 5.33,
+ "learning_rate": 0.00013295454545454548,
+ "loss": 1.1305,
"step": 472
},
{
- "epoch": 9.57,
- "learning_rate": 0.00013966836734693878,
- "loss": 1.4724,
+ "epoch": 5.34,
+ "learning_rate": 0.0001328125,
+ "loss": 1.1293,
"step": 473
},
{
- "epoch": 9.59,
- "learning_rate": 0.00013954081632653063,
- "loss": 1.4828,
+ "epoch": 5.35,
+ "learning_rate": 0.00013267045454545454,
+ "loss": 1.163,
"step": 474
},
{
- "epoch": 9.61,
- "learning_rate": 0.00013941326530612246,
- "loss": 1.5012,
+ "epoch": 5.37,
+ "learning_rate": 0.0001325284090909091,
+ "loss": 1.1236,
"step": 475
},
{
- "epoch": 9.63,
- "learning_rate": 0.0001392857142857143,
- "loss": 1.4879,
+ "epoch": 5.38,
+ "learning_rate": 0.00013238636363636366,
+ "loss": 1.1236,
"step": 476
},
{
- "epoch": 9.65,
- "learning_rate": 0.00013915816326530613,
- "loss": 1.4196,
+ "epoch": 5.39,
+ "learning_rate": 0.0001322443181818182,
+ "loss": 1.1228,
"step": 477
},
{
- "epoch": 9.67,
- "learning_rate": 0.00013903061224489798,
- "loss": 1.4915,
+ "epoch": 5.4,
+ "learning_rate": 0.00013210227272727275,
+ "loss": 1.0993,
"step": 478
},
{
- "epoch": 9.69,
- "learning_rate": 0.0001389030612244898,
- "loss": 1.3878,
+ "epoch": 5.41,
+ "learning_rate": 0.00013196022727272728,
+ "loss": 1.1139,
"step": 479
},
{
- "epoch": 9.71,
- "learning_rate": 0.00013877551020408165,
- "loss": 1.466,
+ "epoch": 5.42,
+ "learning_rate": 0.0001318181818181818,
+ "loss": 1.1019,
"step": 480
},
{
- "epoch": 9.73,
- "learning_rate": 0.00013864795918367348,
- "loss": 1.4582,
+ "epoch": 5.43,
+ "learning_rate": 0.00013167613636363637,
+ "loss": 1.0935,
"step": 481
},
{
- "epoch": 9.75,
- "learning_rate": 0.0001385204081632653,
- "loss": 1.533,
+ "epoch": 5.45,
+ "learning_rate": 0.00013153409090909093,
+ "loss": 1.1067,
"step": 482
},
{
- "epoch": 9.77,
- "learning_rate": 0.00013839285714285714,
- "loss": 1.4697,
+ "epoch": 5.46,
+ "learning_rate": 0.00013139204545454546,
+ "loss": 1.0848,
"step": 483
},
{
- "epoch": 9.79,
- "learning_rate": 0.000138265306122449,
- "loss": 1.3989,
+ "epoch": 5.47,
+ "learning_rate": 0.00013125000000000002,
+ "loss": 1.1188,
"step": 484
},
{
- "epoch": 9.81,
- "learning_rate": 0.00013813775510204083,
- "loss": 1.4361,
+ "epoch": 5.48,
+ "learning_rate": 0.00013110795454545455,
+ "loss": 1.1275,
"step": 485
},
{
- "epoch": 9.83,
- "learning_rate": 0.00013801020408163266,
- "loss": 1.5271,
+ "epoch": 5.49,
+ "learning_rate": 0.00013096590909090908,
+ "loss": 1.1211,
"step": 486
},
{
- "epoch": 9.85,
- "learning_rate": 0.0001378826530612245,
- "loss": 1.4905,
+ "epoch": 5.5,
+ "learning_rate": 0.00013082386363636364,
+ "loss": 1.1049,
"step": 487
},
{
- "epoch": 9.87,
- "learning_rate": 0.00013775510204081635,
- "loss": 1.4757,
+ "epoch": 5.51,
+ "learning_rate": 0.0001306818181818182,
+ "loss": 1.1057,
"step": 488
},
{
- "epoch": 9.89,
- "learning_rate": 0.00013762755102040815,
- "loss": 1.5485,
+ "epoch": 5.52,
+ "learning_rate": 0.00013053977272727273,
+ "loss": 1.0909,
"step": 489
},
{
- "epoch": 9.91,
- "learning_rate": 0.0001375,
- "loss": 1.4783,
+ "epoch": 5.54,
+ "learning_rate": 0.0001303977272727273,
+ "loss": 1.1138,
"step": 490
},
{
- "epoch": 9.93,
- "learning_rate": 0.00013737244897959184,
- "loss": 1.4849,
+ "epoch": 5.55,
+ "learning_rate": 0.00013025568181818182,
+ "loss": 1.1094,
"step": 491
},
{
- "epoch": 9.96,
- "learning_rate": 0.00013724489795918367,
- "loss": 1.5382,
+ "epoch": 5.56,
+ "learning_rate": 0.00013011363636363635,
+ "loss": 1.1187,
"step": 492
},
{
- "epoch": 9.98,
- "learning_rate": 0.00013711734693877553,
- "loss": 1.4902,
+ "epoch": 5.57,
+ "learning_rate": 0.0001299715909090909,
+ "loss": 1.1039,
"step": 493
},
{
- "epoch": 10.0,
- "learning_rate": 0.00013698979591836736,
- "loss": 1.4865,
+ "epoch": 5.58,
+ "learning_rate": 0.00012982954545454547,
+ "loss": 1.056,
"step": 494
},
{
- "epoch": 10.02,
- "learning_rate": 0.0001368622448979592,
- "loss": 1.4436,
+ "epoch": 5.59,
+ "learning_rate": 0.0001296875,
+ "loss": 1.0842,
"step": 495
},
{
- "epoch": 10.04,
- "learning_rate": 0.00013673469387755102,
- "loss": 1.408,
+ "epoch": 5.6,
+ "learning_rate": 0.00012954545454545456,
+ "loss": 1.0749,
"step": 496
},
{
- "epoch": 10.06,
- "learning_rate": 0.00013660714285714288,
- "loss": 1.4764,
+ "epoch": 5.61,
+ "learning_rate": 0.0001294034090909091,
+ "loss": 1.1121,
"step": 497
},
{
- "epoch": 10.08,
- "learning_rate": 0.0001364795918367347,
- "loss": 1.4646,
+ "epoch": 5.63,
+ "learning_rate": 0.00012926136363636365,
+ "loss": 1.0772,
"step": 498
},
{
- "epoch": 10.1,
- "learning_rate": 0.00013635204081632654,
- "loss": 1.406,
+ "epoch": 5.64,
+ "learning_rate": 0.00012911931818181818,
+ "loss": 1.0845,
"step": 499
},
{
- "epoch": 10.12,
- "learning_rate": 0.00013622448979591837,
- "loss": 1.4785,
+ "epoch": 5.65,
+ "learning_rate": 0.00012897727272727274,
+ "loss": 1.0534,
"step": 500
},
{
- "epoch": 10.14,
- "learning_rate": 0.00013609693877551023,
- "loss": 1.4117,
+ "epoch": 5.66,
+ "learning_rate": 0.00012883522727272727,
+ "loss": 1.0755,
"step": 501
},
{
- "epoch": 10.16,
- "learning_rate": 0.00013596938775510203,
- "loss": 1.4108,
+ "epoch": 5.67,
+ "learning_rate": 0.00012869318181818183,
+ "loss": 1.0755,
"step": 502
},
{
- "epoch": 10.18,
- "learning_rate": 0.0001358418367346939,
- "loss": 1.4155,
+ "epoch": 5.68,
+ "learning_rate": 0.00012855113636363636,
+ "loss": 1.0869,
"step": 503
},
{
- "epoch": 10.2,
- "learning_rate": 0.00013571428571428572,
- "loss": 1.4021,
+ "epoch": 5.69,
+ "learning_rate": 0.00012840909090909092,
+ "loss": 1.0673,
"step": 504
},
{
- "epoch": 10.22,
- "learning_rate": 0.00013558673469387755,
- "loss": 1.411,
+ "epoch": 5.71,
+ "learning_rate": 0.00012826704545454545,
+ "loss": 1.0692,
"step": 505
},
{
- "epoch": 10.24,
- "learning_rate": 0.00013545918367346938,
- "loss": 1.3851,
+ "epoch": 5.72,
+ "learning_rate": 0.000128125,
+ "loss": 1.0474,
"step": 506
},
{
- "epoch": 10.26,
- "learning_rate": 0.00013533163265306124,
- "loss": 1.387,
+ "epoch": 5.73,
+ "learning_rate": 0.00012798295454545454,
+ "loss": 1.0749,
"step": 507
},
{
- "epoch": 10.28,
- "learning_rate": 0.00013520408163265305,
- "loss": 1.4163,
+ "epoch": 5.74,
+ "learning_rate": 0.0001278409090909091,
+ "loss": 1.0519,
"step": 508
},
{
- "epoch": 10.3,
- "learning_rate": 0.0001350765306122449,
- "loss": 1.3343,
+ "epoch": 5.75,
+ "learning_rate": 0.00012769886363636366,
+ "loss": 1.0566,
"step": 509
},
{
- "epoch": 10.32,
- "learning_rate": 0.00013494897959183673,
- "loss": 1.4811,
+ "epoch": 5.76,
+ "learning_rate": 0.0001275568181818182,
+ "loss": 1.06,
"step": 510
},
{
- "epoch": 10.34,
- "learning_rate": 0.0001348214285714286,
- "loss": 1.4086,
+ "epoch": 5.77,
+ "learning_rate": 0.00012741477272727272,
+ "loss": 1.0618,
"step": 511
},
{
- "epoch": 10.36,
- "learning_rate": 0.0001346938775510204,
- "loss": 1.3879,
+ "epoch": 5.78,
+ "learning_rate": 0.00012727272727272728,
+ "loss": 1.0643,
"step": 512
},
{
- "epoch": 10.38,
- "learning_rate": 0.00013456632653061225,
- "loss": 1.4204,
+ "epoch": 5.8,
+ "learning_rate": 0.0001271306818181818,
+ "loss": 1.026,
"step": 513
},
{
- "epoch": 10.4,
- "learning_rate": 0.00013443877551020408,
- "loss": 1.4158,
+ "epoch": 5.81,
+ "learning_rate": 0.00012698863636363637,
+ "loss": 1.0335,
"step": 514
},
{
- "epoch": 10.42,
- "learning_rate": 0.00013431122448979592,
- "loss": 1.4521,
+ "epoch": 5.82,
+ "learning_rate": 0.00012684659090909093,
+ "loss": 1.0205,
"step": 515
},
{
- "epoch": 10.44,
- "learning_rate": 0.00013418367346938777,
- "loss": 1.4196,
+ "epoch": 5.83,
+ "learning_rate": 0.00012670454545454546,
+ "loss": 1.0594,
"step": 516
},
{
- "epoch": 10.46,
- "learning_rate": 0.0001340561224489796,
- "loss": 1.4361,
+ "epoch": 5.84,
+ "learning_rate": 0.0001265625,
+ "loss": 1.0136,
"step": 517
},
{
- "epoch": 10.48,
- "learning_rate": 0.00013392857142857144,
- "loss": 1.4482,
+ "epoch": 5.85,
+ "learning_rate": 0.00012642045454545455,
+ "loss": 1.0244,
"step": 518
},
{
- "epoch": 10.5,
- "learning_rate": 0.00013380102040816327,
- "loss": 1.4801,
+ "epoch": 5.86,
+ "learning_rate": 0.00012627840909090908,
+ "loss": 1.0569,
"step": 519
},
{
- "epoch": 10.52,
- "learning_rate": 0.00013367346938775512,
- "loss": 1.4556,
+ "epoch": 5.87,
+ "learning_rate": 0.00012613636363636364,
+ "loss": 1.0416,
"step": 520
},
{
- "epoch": 10.54,
- "learning_rate": 0.00013354591836734695,
- "loss": 1.3902,
+ "epoch": 5.89,
+ "learning_rate": 0.0001259943181818182,
+ "loss": 0.9884,
"step": 521
},
{
- "epoch": 10.56,
- "learning_rate": 0.00013341836734693879,
- "loss": 1.4269,
+ "epoch": 5.9,
+ "learning_rate": 0.00012585227272727273,
+ "loss": 1.0351,
"step": 522
},
{
- "epoch": 10.58,
- "learning_rate": 0.00013329081632653062,
- "loss": 1.4899,
+ "epoch": 5.91,
+ "learning_rate": 0.00012571022727272726,
+ "loss": 1.0037,
"step": 523
},
{
- "epoch": 10.6,
- "learning_rate": 0.00013316326530612247,
- "loss": 1.3952,
+ "epoch": 5.92,
+ "learning_rate": 0.00012556818181818182,
+ "loss": 1.0219,
"step": 524
},
{
- "epoch": 10.62,
- "learning_rate": 0.00013303571428571428,
- "loss": 1.4116,
+ "epoch": 5.93,
+ "learning_rate": 0.00012542613636363635,
+ "loss": 1.0533,
"step": 525
},
{
- "epoch": 10.64,
- "learning_rate": 0.00013290816326530614,
- "loss": 1.4583,
+ "epoch": 5.94,
+ "learning_rate": 0.0001252840909090909,
+ "loss": 1.0031,
"step": 526
},
{
- "epoch": 10.66,
- "learning_rate": 0.00013278061224489797,
- "loss": 1.4466,
+ "epoch": 5.95,
+ "learning_rate": 0.00012514204545454547,
+ "loss": 1.0454,
"step": 527
},
{
- "epoch": 10.68,
- "learning_rate": 0.0001326530612244898,
- "loss": 1.4242,
+ "epoch": 5.97,
+ "learning_rate": 0.000125,
+ "loss": 1.0195,
"step": 528
},
{
- "epoch": 10.7,
- "learning_rate": 0.00013252551020408163,
- "loss": 1.3717,
+ "epoch": 5.98,
+ "learning_rate": 0.00012485795454545453,
+ "loss": 1.0076,
"step": 529
},
{
- "epoch": 10.72,
- "learning_rate": 0.0001323979591836735,
- "loss": 1.4583,
+ "epoch": 5.99,
+ "learning_rate": 0.0001247159090909091,
+ "loss": 1.0378,
"step": 530
},
{
- "epoch": 10.74,
- "learning_rate": 0.0001322704081632653,
- "loss": 1.4185,
+ "epoch": 6.0,
+ "learning_rate": 0.00012457386363636365,
+ "loss": 0.9795,
"step": 531
},
{
- "epoch": 10.76,
- "learning_rate": 0.00013214285714285715,
- "loss": 1.4287,
+ "epoch": 6.01,
+ "learning_rate": 0.00012443181818181818,
+ "loss": 0.9405,
"step": 532
},
{
- "epoch": 10.78,
- "learning_rate": 0.00013201530612244898,
- "loss": 1.4385,
+ "epoch": 6.02,
+ "learning_rate": 0.00012428977272727274,
+ "loss": 0.9503,
"step": 533
},
{
- "epoch": 10.8,
- "learning_rate": 0.00013188775510204084,
- "loss": 1.453,
+ "epoch": 6.03,
+ "learning_rate": 0.00012414772727272727,
+ "loss": 0.9456,
"step": 534
},
{
- "epoch": 10.83,
- "learning_rate": 0.00013176020408163264,
- "loss": 1.4161,
+ "epoch": 6.04,
+ "learning_rate": 0.0001240056818181818,
+ "loss": 0.9536,
"step": 535
},
{
- "epoch": 10.85,
- "learning_rate": 0.0001316326530612245,
- "loss": 1.457,
+ "epoch": 6.06,
+ "learning_rate": 0.00012386363636363636,
+ "loss": 0.9412,
"step": 536
},
{
- "epoch": 10.87,
- "learning_rate": 0.00013150510204081633,
- "loss": 1.4367,
+ "epoch": 6.07,
+ "learning_rate": 0.00012372159090909092,
+ "loss": 0.9315,
"step": 537
},
{
- "epoch": 10.89,
- "learning_rate": 0.00013137755102040816,
- "loss": 1.4256,
+ "epoch": 6.08,
+ "learning_rate": 0.00012357954545454545,
+ "loss": 0.9486,
"step": 538
},
{
- "epoch": 10.91,
- "learning_rate": 0.00013125000000000002,
- "loss": 1.424,
+ "epoch": 6.09,
+ "learning_rate": 0.0001234375,
+ "loss": 0.9405,
"step": 539
},
{
- "epoch": 10.93,
- "learning_rate": 0.00013112244897959185,
- "loss": 1.3923,
+ "epoch": 6.1,
+ "learning_rate": 0.00012329545454545454,
+ "loss": 0.9269,
"step": 540
},
{
- "epoch": 10.95,
- "learning_rate": 0.00013099489795918368,
- "loss": 1.4225,
+ "epoch": 6.11,
+ "learning_rate": 0.0001231534090909091,
+ "loss": 0.9378,
"step": 541
},
{
- "epoch": 10.97,
- "learning_rate": 0.0001308673469387755,
- "loss": 1.3969,
+ "epoch": 6.12,
+ "learning_rate": 0.00012301136363636366,
+ "loss": 0.9431,
"step": 542
},
{
- "epoch": 10.99,
- "learning_rate": 0.00013073979591836737,
- "loss": 1.4446,
+ "epoch": 6.13,
+ "learning_rate": 0.0001228693181818182,
+ "loss": 0.9256,
"step": 543
},
{
- "epoch": 11.01,
- "learning_rate": 0.00013061224489795917,
- "loss": 1.4375,
+ "epoch": 6.15,
+ "learning_rate": 0.00012272727272727272,
+ "loss": 0.919,
"step": 544
},
{
- "epoch": 11.03,
- "learning_rate": 0.00013048469387755103,
- "loss": 1.4064,
+ "epoch": 6.16,
+ "learning_rate": 0.00012258522727272728,
+ "loss": 0.9188,
"step": 545
},
{
- "epoch": 11.05,
- "learning_rate": 0.00013035714285714286,
- "loss": 1.3454,
+ "epoch": 6.17,
+ "learning_rate": 0.00012244318181818181,
+ "loss": 0.9447,
"step": 546
},
{
- "epoch": 11.07,
- "learning_rate": 0.00013022959183673472,
- "loss": 1.3234,
+ "epoch": 6.18,
+ "learning_rate": 0.00012230113636363637,
+ "loss": 0.9261,
"step": 547
},
{
- "epoch": 11.09,
- "learning_rate": 0.00013010204081632652,
- "loss": 1.3759,
+ "epoch": 6.19,
+ "learning_rate": 0.00012215909090909093,
+ "loss": 0.9302,
"step": 548
},
{
- "epoch": 11.11,
- "learning_rate": 0.00012997448979591838,
- "loss": 1.4221,
+ "epoch": 6.2,
+ "learning_rate": 0.00012201704545454546,
+ "loss": 0.9161,
"step": 549
},
{
- "epoch": 11.13,
- "learning_rate": 0.0001298469387755102,
- "loss": 1.4261,
+ "epoch": 6.21,
+ "learning_rate": 0.00012187500000000001,
+ "loss": 0.9521,
"step": 550
},
{
- "epoch": 11.15,
- "learning_rate": 0.00012971938775510204,
- "loss": 1.3341,
+ "epoch": 6.22,
+ "learning_rate": 0.00012173295454545455,
+ "loss": 0.9026,
"step": 551
},
{
- "epoch": 11.17,
- "learning_rate": 0.00012959183673469387,
- "loss": 1.3994,
+ "epoch": 6.24,
+ "learning_rate": 0.00012159090909090908,
+ "loss": 0.9361,
"step": 552
},
{
- "epoch": 11.19,
- "learning_rate": 0.00012946428571428573,
- "loss": 1.3894,
+ "epoch": 6.25,
+ "learning_rate": 0.00012144886363636366,
+ "loss": 0.8944,
"step": 553
},
{
- "epoch": 11.21,
- "learning_rate": 0.00012933673469387754,
- "loss": 1.3585,
+ "epoch": 6.26,
+ "learning_rate": 0.00012130681818181819,
+ "loss": 0.895,
"step": 554
},
{
- "epoch": 11.23,
- "learning_rate": 0.0001292091836734694,
- "loss": 1.3763,
+ "epoch": 6.27,
+ "learning_rate": 0.00012116477272727273,
+ "loss": 0.8956,
"step": 555
},
{
- "epoch": 11.25,
- "learning_rate": 0.00012908163265306123,
- "loss": 1.3623,
+ "epoch": 6.28,
+ "learning_rate": 0.00012102272727272728,
+ "loss": 0.8998,
"step": 556
},
{
- "epoch": 11.27,
- "learning_rate": 0.00012895408163265306,
- "loss": 1.3907,
+ "epoch": 6.29,
+ "learning_rate": 0.00012088068181818182,
+ "loss": 0.915,
"step": 557
},
{
- "epoch": 11.29,
- "learning_rate": 0.0001288265306122449,
- "loss": 1.3807,
+ "epoch": 6.3,
+ "learning_rate": 0.00012073863636363636,
+ "loss": 0.9282,
"step": 558
},
{
- "epoch": 11.31,
- "learning_rate": 0.00012869897959183674,
- "loss": 1.4045,
+ "epoch": 6.32,
+ "learning_rate": 0.00012059659090909093,
+ "loss": 0.8938,
"step": 559
},
{
- "epoch": 11.33,
- "learning_rate": 0.00012857142857142858,
- "loss": 1.4038,
+ "epoch": 6.33,
+ "learning_rate": 0.00012045454545454546,
+ "loss": 0.8886,
"step": 560
},
{
- "epoch": 11.35,
- "learning_rate": 0.0001284438775510204,
- "loss": 1.3466,
+ "epoch": 6.34,
+ "learning_rate": 0.0001203125,
+ "loss": 0.8988,
"step": 561
},
{
- "epoch": 11.37,
- "learning_rate": 0.00012831632653061226,
- "loss": 1.3449,
+ "epoch": 6.35,
+ "learning_rate": 0.00012017045454545455,
+ "loss": 0.8852,
"step": 562
},
{
- "epoch": 11.39,
- "learning_rate": 0.0001281887755102041,
- "loss": 1.3866,
+ "epoch": 6.36,
+ "learning_rate": 0.0001200284090909091,
+ "loss": 0.8818,
"step": 563
},
{
- "epoch": 11.41,
- "learning_rate": 0.00012806122448979593,
- "loss": 1.3106,
+ "epoch": 6.37,
+ "learning_rate": 0.00011988636363636365,
+ "loss": 0.8881,
"step": 564
},
{
- "epoch": 11.43,
- "learning_rate": 0.00012793367346938776,
- "loss": 1.4414,
+ "epoch": 6.38,
+ "learning_rate": 0.0001197443181818182,
+ "loss": 0.9226,
"step": 565
},
{
- "epoch": 11.45,
- "learning_rate": 0.00012780612244897962,
- "loss": 1.3737,
+ "epoch": 6.39,
+ "learning_rate": 0.00011960227272727273,
+ "loss": 0.8849,
"step": 566
},
{
- "epoch": 11.47,
- "learning_rate": 0.00012767857142857142,
- "loss": 1.4053,
+ "epoch": 6.41,
+ "learning_rate": 0.00011946022727272727,
+ "loss": 0.8894,
"step": 567
},
{
- "epoch": 11.49,
- "learning_rate": 0.00012755102040816328,
- "loss": 1.4561,
+ "epoch": 6.42,
+ "learning_rate": 0.00011931818181818182,
+ "loss": 0.9207,
"step": 568
},
{
- "epoch": 11.51,
- "learning_rate": 0.0001274234693877551,
- "loss": 1.3684,
+ "epoch": 6.43,
+ "learning_rate": 0.00011917613636363636,
+ "loss": 0.9105,
"step": 569
},
{
- "epoch": 11.53,
- "learning_rate": 0.00012729591836734697,
- "loss": 1.3117,
+ "epoch": 6.44,
+ "learning_rate": 0.00011903409090909092,
+ "loss": 0.8762,
"step": 570
},
{
- "epoch": 11.55,
- "learning_rate": 0.00012716836734693877,
- "loss": 1.3474,
+ "epoch": 6.45,
+ "learning_rate": 0.00011889204545454547,
+ "loss": 0.8926,
"step": 571
},
{
- "epoch": 11.57,
- "learning_rate": 0.00012704081632653063,
- "loss": 1.3804,
+ "epoch": 6.46,
+ "learning_rate": 0.00011875,
+ "loss": 0.8719,
"step": 572
},
{
- "epoch": 11.59,
- "learning_rate": 0.00012691326530612246,
- "loss": 1.3656,
+ "epoch": 6.47,
+ "learning_rate": 0.00011860795454545454,
+ "loss": 0.9198,
"step": 573
},
{
- "epoch": 11.61,
- "learning_rate": 0.0001267857142857143,
- "loss": 1.3133,
+ "epoch": 6.48,
+ "learning_rate": 0.00011846590909090909,
+ "loss": 0.8846,
"step": 574
},
{
- "epoch": 11.63,
- "learning_rate": 0.00012665816326530612,
- "loss": 1.4077,
+ "epoch": 6.5,
+ "learning_rate": 0.00011832386363636365,
+ "loss": 0.8495,
"step": 575
},
{
- "epoch": 11.65,
- "learning_rate": 0.00012653061224489798,
- "loss": 1.4087,
+ "epoch": 6.51,
+ "learning_rate": 0.0001181818181818182,
+ "loss": 0.8953,
"step": 576
},
{
- "epoch": 11.67,
- "learning_rate": 0.00012640306122448978,
- "loss": 1.3524,
+ "epoch": 6.52,
+ "learning_rate": 0.00011803977272727274,
+ "loss": 0.8686,
"step": 577
},
{
- "epoch": 11.7,
- "learning_rate": 0.00012627551020408164,
- "loss": 1.3481,
+ "epoch": 6.53,
+ "learning_rate": 0.00011789772727272727,
+ "loss": 0.8841,
"step": 578
},
{
- "epoch": 11.72,
- "learning_rate": 0.00012614795918367347,
- "loss": 1.4497,
+ "epoch": 6.54,
+ "learning_rate": 0.00011775568181818182,
+ "loss": 0.8681,
"step": 579
},
{
- "epoch": 11.74,
- "learning_rate": 0.0001260204081632653,
- "loss": 1.3866,
+ "epoch": 6.55,
+ "learning_rate": 0.00011761363636363636,
+ "loss": 0.8732,
"step": 580
},
{
- "epoch": 11.76,
- "learning_rate": 0.00012589285714285713,
- "loss": 1.42,
+ "epoch": 6.56,
+ "learning_rate": 0.00011747159090909092,
+ "loss": 0.8582,
"step": 581
},
{
- "epoch": 11.78,
- "learning_rate": 0.000125765306122449,
- "loss": 1.3562,
+ "epoch": 6.58,
+ "learning_rate": 0.00011732954545454546,
+ "loss": 0.8744,
"step": 582
},
{
- "epoch": 11.8,
- "learning_rate": 0.00012563775510204082,
- "loss": 1.3249,
+ "epoch": 6.59,
+ "learning_rate": 0.00011718750000000001,
+ "loss": 0.8694,
"step": 583
},
{
- "epoch": 11.82,
- "learning_rate": 0.00012551020408163265,
- "loss": 1.4277,
+ "epoch": 6.6,
+ "learning_rate": 0.00011704545454545454,
+ "loss": 0.8565,
"step": 584
},
{
- "epoch": 11.84,
- "learning_rate": 0.0001253826530612245,
- "loss": 1.3734,
+ "epoch": 6.61,
+ "learning_rate": 0.00011690340909090909,
+ "loss": 0.8584,
"step": 585
},
{
- "epoch": 11.86,
- "learning_rate": 0.00012525510204081634,
- "loss": 1.3765,
+ "epoch": 6.62,
+ "learning_rate": 0.00011676136363636366,
+ "loss": 0.8859,
"step": 586
},
{
- "epoch": 11.88,
- "learning_rate": 0.00012512755102040817,
- "loss": 1.4153,
+ "epoch": 6.63,
+ "learning_rate": 0.00011661931818181819,
+ "loss": 0.8452,
"step": 587
},
{
- "epoch": 11.9,
- "learning_rate": 0.000125,
- "loss": 1.3847,
+ "epoch": 6.64,
+ "learning_rate": 0.00011647727272727273,
+ "loss": 0.8323,
"step": 588
},
{
- "epoch": 11.92,
- "learning_rate": 0.00012487244897959186,
- "loss": 1.3824,
+ "epoch": 6.65,
+ "learning_rate": 0.00011633522727272728,
+ "loss": 0.8548,
"step": 589
},
{
- "epoch": 11.94,
- "learning_rate": 0.00012474489795918366,
- "loss": 1.3938,
+ "epoch": 6.67,
+ "learning_rate": 0.00011619318181818181,
+ "loss": 0.8506,
"step": 590
},
{
- "epoch": 11.96,
- "learning_rate": 0.00012461734693877552,
- "loss": 1.4143,
+ "epoch": 6.68,
+ "learning_rate": 0.00011605113636363636,
+ "loss": 0.8556,
"step": 591
},
{
- "epoch": 11.98,
- "learning_rate": 0.00012448979591836735,
- "loss": 1.3794,
+ "epoch": 6.69,
+ "learning_rate": 0.00011590909090909093,
+ "loss": 0.8459,
"step": 592
},
{
- "epoch": 12.0,
- "learning_rate": 0.00012436224489795918,
- "loss": 1.3755,
+ "epoch": 6.7,
+ "learning_rate": 0.00011576704545454546,
+ "loss": 0.8432,
"step": 593
},
{
- "epoch": 12.02,
- "learning_rate": 0.00012423469387755101,
- "loss": 1.3736,
+ "epoch": 6.71,
+ "learning_rate": 0.000115625,
+ "loss": 0.8645,
"step": 594
},
{
- "epoch": 12.04,
- "learning_rate": 0.00012410714285714287,
- "loss": 1.2957,
+ "epoch": 6.72,
+ "learning_rate": 0.00011548295454545455,
+ "loss": 0.86,
"step": 595
},
{
- "epoch": 12.06,
- "learning_rate": 0.0001239795918367347,
- "loss": 1.2996,
+ "epoch": 6.73,
+ "learning_rate": 0.00011534090909090908,
+ "loss": 0.8161,
"step": 596
},
{
- "epoch": 12.08,
- "learning_rate": 0.00012385204081632653,
- "loss": 1.3648,
+ "epoch": 6.74,
+ "learning_rate": 0.00011519886363636365,
+ "loss": 0.8133,
"step": 597
},
{
- "epoch": 12.1,
- "learning_rate": 0.00012372448979591837,
- "loss": 1.3031,
+ "epoch": 6.76,
+ "learning_rate": 0.0001150568181818182,
+ "loss": 0.8372,
"step": 598
},
{
- "epoch": 12.12,
- "learning_rate": 0.00012359693877551022,
- "loss": 1.2933,
+ "epoch": 6.77,
+ "learning_rate": 0.00011491477272727273,
+ "loss": 0.8222,
"step": 599
},
{
- "epoch": 12.14,
- "learning_rate": 0.00012346938775510203,
- "loss": 1.322,
+ "epoch": 6.78,
+ "learning_rate": 0.00011477272727272728,
+ "loss": 0.8372,
"step": 600
},
{
- "epoch": 12.16,
- "learning_rate": 0.00012334183673469389,
- "loss": 1.3123,
+ "epoch": 6.79,
+ "learning_rate": 0.00011463068181818182,
+ "loss": 0.837,
"step": 601
},
{
- "epoch": 12.18,
- "learning_rate": 0.00012321428571428572,
- "loss": 1.3187,
+ "epoch": 6.8,
+ "learning_rate": 0.00011448863636363637,
+ "loss": 0.8406,
"step": 602
},
{
- "epoch": 12.2,
- "learning_rate": 0.00012308673469387755,
- "loss": 1.3353,
+ "epoch": 6.81,
+ "learning_rate": 0.00011434659090909092,
+ "loss": 0.836,
"step": 603
},
{
- "epoch": 12.22,
- "learning_rate": 0.0001229591836734694,
- "loss": 1.3221,
+ "epoch": 6.82,
+ "learning_rate": 0.00011420454545454547,
+ "loss": 0.8476,
"step": 604
},
{
- "epoch": 12.24,
- "learning_rate": 0.00012283163265306124,
- "loss": 1.3458,
+ "epoch": 6.83,
+ "learning_rate": 0.0001140625,
+ "loss": 0.8368,
"step": 605
},
{
- "epoch": 12.26,
- "learning_rate": 0.00012270408163265307,
- "loss": 1.275,
+ "epoch": 6.85,
+ "learning_rate": 0.00011392045454545455,
+ "loss": 0.822,
"step": 606
},
{
- "epoch": 12.28,
- "learning_rate": 0.0001225765306122449,
- "loss": 1.3455,
+ "epoch": 6.86,
+ "learning_rate": 0.00011377840909090909,
+ "loss": 0.8107,
"step": 607
},
{
- "epoch": 12.3,
- "learning_rate": 0.00012244897959183676,
- "loss": 1.2769,
+ "epoch": 6.87,
+ "learning_rate": 0.00011363636363636365,
+ "loss": 0.8395,
"step": 608
},
{
- "epoch": 12.32,
- "learning_rate": 0.00012232142857142859,
- "loss": 1.3201,
+ "epoch": 6.88,
+ "learning_rate": 0.0001134943181818182,
+ "loss": 0.8083,
"step": 609
},
{
- "epoch": 12.34,
- "learning_rate": 0.00012219387755102042,
- "loss": 1.3073,
+ "epoch": 6.89,
+ "learning_rate": 0.00011335227272727274,
+ "loss": 0.828,
"step": 610
},
{
- "epoch": 12.36,
- "learning_rate": 0.00012206632653061225,
- "loss": 1.3103,
+ "epoch": 6.9,
+ "learning_rate": 0.00011321022727272727,
+ "loss": 0.8494,
"step": 611
},
{
- "epoch": 12.38,
- "learning_rate": 0.00012193877551020409,
- "loss": 1.4437,
+ "epoch": 6.91,
+ "learning_rate": 0.00011306818181818182,
+ "loss": 0.8169,
"step": 612
},
{
- "epoch": 12.4,
- "learning_rate": 0.00012181122448979591,
- "loss": 1.3086,
+ "epoch": 6.93,
+ "learning_rate": 0.00011292613636363636,
+ "loss": 0.8224,
"step": 613
},
{
- "epoch": 12.42,
- "learning_rate": 0.00012168367346938775,
- "loss": 1.3867,
+ "epoch": 6.94,
+ "learning_rate": 0.00011278409090909092,
+ "loss": 0.8173,
"step": 614
},
{
- "epoch": 12.44,
- "learning_rate": 0.0001215561224489796,
- "loss": 1.2565,
+ "epoch": 6.95,
+ "learning_rate": 0.00011264204545454547,
+ "loss": 0.7961,
"step": 615
},
{
- "epoch": 12.46,
- "learning_rate": 0.00012142857142857143,
- "loss": 1.335,
+ "epoch": 6.96,
+ "learning_rate": 0.00011250000000000001,
+ "loss": 0.7948,
"step": 616
},
{
- "epoch": 12.48,
- "learning_rate": 0.00012130102040816327,
- "loss": 1.3423,
+ "epoch": 6.97,
+ "learning_rate": 0.00011235795454545454,
+ "loss": 0.7746,
"step": 617
},
{
- "epoch": 12.5,
- "learning_rate": 0.00012117346938775512,
- "loss": 1.3433,
+ "epoch": 6.98,
+ "learning_rate": 0.00011221590909090909,
+ "loss": 0.8325,
"step": 618
},
{
- "epoch": 12.52,
- "learning_rate": 0.00012104591836734695,
- "loss": 1.3387,
+ "epoch": 6.99,
+ "learning_rate": 0.00011207386363636365,
+ "loss": 0.8149,
"step": 619
},
{
- "epoch": 12.55,
- "learning_rate": 0.00012091836734693878,
- "loss": 1.3923,
+ "epoch": 7.0,
+ "learning_rate": 0.00011193181818181819,
+ "loss": 0.7516,
"step": 620
},
{
- "epoch": 12.57,
- "learning_rate": 0.00012079081632653062,
- "loss": 1.3774,
+ "epoch": 7.02,
+ "learning_rate": 0.00011178977272727274,
+ "loss": 0.7571,
"step": 621
},
{
- "epoch": 12.59,
- "learning_rate": 0.00012066326530612247,
- "loss": 1.3203,
+ "epoch": 7.03,
+ "learning_rate": 0.00011164772727272728,
+ "loss": 0.7397,
"step": 622
},
{
- "epoch": 12.61,
- "learning_rate": 0.00012053571428571429,
- "loss": 1.2924,
+ "epoch": 7.04,
+ "learning_rate": 0.00011150568181818181,
+ "loss": 0.761,
"step": 623
},
{
- "epoch": 12.63,
- "learning_rate": 0.00012040816326530613,
- "loss": 1.3292,
+ "epoch": 7.05,
+ "learning_rate": 0.00011136363636363636,
+ "loss": 0.7783,
"step": 624
},
{
- "epoch": 12.65,
- "learning_rate": 0.00012028061224489798,
- "loss": 1.3161,
+ "epoch": 7.06,
+ "learning_rate": 0.00011122159090909092,
+ "loss": 0.7571,
"step": 625
},
{
- "epoch": 12.67,
- "learning_rate": 0.00012015306122448979,
- "loss": 1.352,
+ "epoch": 7.07,
+ "learning_rate": 0.00011107954545454546,
+ "loss": 0.7628,
"step": 626
},
{
- "epoch": 12.69,
- "learning_rate": 0.00012002551020408164,
- "loss": 1.3577,
+ "epoch": 7.08,
+ "learning_rate": 0.0001109375,
+ "loss": 0.7561,
"step": 627
},
{
- "epoch": 12.71,
- "learning_rate": 0.00011989795918367348,
- "loss": 1.3575,
+ "epoch": 7.09,
+ "learning_rate": 0.00011079545454545455,
+ "loss": 0.7432,
"step": 628
},
{
- "epoch": 12.73,
- "learning_rate": 0.0001197704081632653,
- "loss": 1.3727,
+ "epoch": 7.11,
+ "learning_rate": 0.00011065340909090908,
+ "loss": 0.7245,
"step": 629
},
{
- "epoch": 12.75,
- "learning_rate": 0.00011964285714285714,
- "loss": 1.3312,
+ "epoch": 7.12,
+ "learning_rate": 0.00011051136363636366,
+ "loss": 0.7279,
"step": 630
},
{
- "epoch": 12.77,
- "learning_rate": 0.00011951530612244899,
- "loss": 1.3378,
+ "epoch": 7.13,
+ "learning_rate": 0.00011036931818181819,
+ "loss": 0.7347,
"step": 631
},
{
- "epoch": 12.79,
- "learning_rate": 0.00011938775510204083,
- "loss": 1.295,
+ "epoch": 7.14,
+ "learning_rate": 0.00011022727272727273,
+ "loss": 0.7427,
"step": 632
},
{
- "epoch": 12.81,
- "learning_rate": 0.00011926020408163265,
- "loss": 1.3447,
+ "epoch": 7.15,
+ "learning_rate": 0.00011008522727272728,
+ "loss": 0.7339,
"step": 633
},
{
- "epoch": 12.83,
- "learning_rate": 0.0001191326530612245,
- "loss": 1.3835,
+ "epoch": 7.16,
+ "learning_rate": 0.00010994318181818182,
+ "loss": 0.7375,
"step": 634
},
{
- "epoch": 12.85,
- "learning_rate": 0.00011900510204081634,
- "loss": 1.3222,
+ "epoch": 7.17,
+ "learning_rate": 0.00010980113636363635,
+ "loss": 0.7182,
"step": 635
},
{
- "epoch": 12.87,
- "learning_rate": 0.00011887755102040817,
- "loss": 1.2851,
+ "epoch": 7.19,
+ "learning_rate": 0.00010965909090909093,
+ "loss": 0.7452,
"step": 636
},
{
- "epoch": 12.89,
- "learning_rate": 0.00011875,
- "loss": 1.2723,
+ "epoch": 7.2,
+ "learning_rate": 0.00010951704545454546,
+ "loss": 0.7565,
"step": 637
},
{
- "epoch": 12.91,
- "learning_rate": 0.00011862244897959184,
- "loss": 1.3924,
+ "epoch": 7.21,
+ "learning_rate": 0.000109375,
+ "loss": 0.7296,
"step": 638
},
{
- "epoch": 12.93,
- "learning_rate": 0.00011849489795918368,
- "loss": 1.4625,
+ "epoch": 7.22,
+ "learning_rate": 0.00010923295454545455,
+ "loss": 0.7484,
"step": 639
},
{
- "epoch": 12.95,
- "learning_rate": 0.00011836734693877552,
- "loss": 1.3245,
+ "epoch": 7.23,
+ "learning_rate": 0.00010909090909090909,
+ "loss": 0.732,
"step": 640
},
{
- "epoch": 12.97,
- "learning_rate": 0.00011823979591836736,
- "loss": 1.4042,
+ "epoch": 7.24,
+ "learning_rate": 0.00010894886363636365,
+ "loss": 0.7415,
"step": 641
},
{
- "epoch": 12.99,
- "learning_rate": 0.00011811224489795918,
- "loss": 1.3761,
+ "epoch": 7.25,
+ "learning_rate": 0.0001088068181818182,
+ "loss": 0.7344,
"step": 642
},
{
- "epoch": 13.01,
- "learning_rate": 0.00011798469387755103,
- "loss": 1.3376,
+ "epoch": 7.26,
+ "learning_rate": 0.00010866477272727274,
+ "loss": 0.7267,
"step": 643
},
{
- "epoch": 13.03,
- "learning_rate": 0.00011785714285714287,
- "loss": 1.2174,
+ "epoch": 7.28,
+ "learning_rate": 0.00010852272727272727,
+ "loss": 0.7543,
"step": 644
},
{
- "epoch": 13.05,
- "learning_rate": 0.00011772959183673471,
- "loss": 1.3602,
+ "epoch": 7.29,
+ "learning_rate": 0.00010838068181818182,
+ "loss": 0.7266,
"step": 645
},
{
- "epoch": 13.07,
- "learning_rate": 0.00011760204081632653,
- "loss": 1.3002,
+ "epoch": 7.3,
+ "learning_rate": 0.00010823863636363636,
+ "loss": 0.7449,
"step": 646
},
{
- "epoch": 13.09,
- "learning_rate": 0.00011747448979591838,
- "loss": 1.2262,
+ "epoch": 7.31,
+ "learning_rate": 0.00010809659090909092,
+ "loss": 0.7324,
"step": 647
},
{
- "epoch": 13.11,
- "learning_rate": 0.00011734693877551022,
- "loss": 1.3048,
+ "epoch": 7.32,
+ "learning_rate": 0.00010795454545454547,
+ "loss": 0.7268,
"step": 648
},
{
- "epoch": 13.13,
- "learning_rate": 0.00011721938775510204,
- "loss": 1.2231,
+ "epoch": 7.33,
+ "learning_rate": 0.00010781250000000001,
+ "loss": 0.7172,
"step": 649
},
{
- "epoch": 13.15,
- "learning_rate": 0.00011709183673469388,
- "loss": 1.2996,
+ "epoch": 7.34,
+ "learning_rate": 0.00010767045454545454,
+ "loss": 0.7169,
"step": 650
},
{
- "epoch": 13.17,
- "learning_rate": 0.00011696428571428573,
- "loss": 1.2708,
+ "epoch": 7.35,
+ "learning_rate": 0.00010752840909090909,
+ "loss": 0.7194,
"step": 651
},
{
- "epoch": 13.19,
- "learning_rate": 0.00011683673469387754,
- "loss": 1.2776,
+ "epoch": 7.37,
+ "learning_rate": 0.00010738636363636365,
+ "loss": 0.7223,
"step": 652
},
{
- "epoch": 13.21,
- "learning_rate": 0.00011670918367346939,
- "loss": 1.248,
+ "epoch": 7.38,
+ "learning_rate": 0.00010724431818181819,
+ "loss": 0.7158,
"step": 653
},
{
- "epoch": 13.23,
- "learning_rate": 0.00011658163265306123,
- "loss": 1.2582,
+ "epoch": 7.39,
+ "learning_rate": 0.00010710227272727274,
+ "loss": 0.7122,
"step": 654
},
{
- "epoch": 13.25,
- "learning_rate": 0.00011645408163265305,
- "loss": 1.3011,
+ "epoch": 7.4,
+ "learning_rate": 0.00010696022727272728,
+ "loss": 0.7225,
"step": 655
},
{
- "epoch": 13.27,
- "learning_rate": 0.0001163265306122449,
- "loss": 1.2969,
+ "epoch": 7.41,
+ "learning_rate": 0.00010681818181818181,
+ "loss": 0.7102,
"step": 656
},
{
- "epoch": 13.29,
- "learning_rate": 0.00011619897959183674,
- "loss": 1.2454,
+ "epoch": 7.42,
+ "learning_rate": 0.00010667613636363636,
+ "loss": 0.7251,
"step": 657
},
{
- "epoch": 13.31,
- "learning_rate": 0.00011607142857142858,
- "loss": 1.1914,
+ "epoch": 7.43,
+ "learning_rate": 0.00010653409090909092,
+ "loss": 0.7191,
"step": 658
},
{
- "epoch": 13.33,
- "learning_rate": 0.00011594387755102041,
- "loss": 1.34,
+ "epoch": 7.45,
+ "learning_rate": 0.00010639204545454546,
+ "loss": 0.7015,
"step": 659
},
{
- "epoch": 13.35,
- "learning_rate": 0.00011581632653061225,
- "loss": 1.2828,
+ "epoch": 7.46,
+ "learning_rate": 0.00010625000000000001,
+ "loss": 0.693,
"step": 660
},
{
- "epoch": 13.37,
- "learning_rate": 0.00011568877551020409,
- "loss": 1.2962,
+ "epoch": 7.47,
+ "learning_rate": 0.00010610795454545455,
+ "loss": 0.7039,
"step": 661
},
{
- "epoch": 13.39,
- "learning_rate": 0.00011556122448979592,
- "loss": 1.3334,
+ "epoch": 7.48,
+ "learning_rate": 0.00010596590909090908,
+ "loss": 0.7305,
"step": 662
},
{
- "epoch": 13.42,
- "learning_rate": 0.00011543367346938776,
- "loss": 1.2832,
+ "epoch": 7.49,
+ "learning_rate": 0.00010582386363636366,
+ "loss": 0.6978,
"step": 663
},
{
- "epoch": 13.44,
- "learning_rate": 0.00011530612244897961,
- "loss": 1.3012,
+ "epoch": 7.5,
+ "learning_rate": 0.00010568181818181819,
+ "loss": 0.7219,
"step": 664
},
{
- "epoch": 13.46,
- "learning_rate": 0.00011517857142857143,
- "loss": 1.2857,
+ "epoch": 7.51,
+ "learning_rate": 0.00010553977272727273,
+ "loss": 0.7199,
"step": 665
},
{
- "epoch": 13.48,
- "learning_rate": 0.00011505102040816327,
- "loss": 1.2855,
+ "epoch": 7.52,
+ "learning_rate": 0.00010539772727272728,
+ "loss": 0.6979,
"step": 666
},
{
- "epoch": 13.5,
- "learning_rate": 0.00011492346938775512,
- "loss": 1.3077,
+ "epoch": 7.54,
+ "learning_rate": 0.00010525568181818182,
+ "loss": 0.7058,
"step": 667
},
{
- "epoch": 13.52,
- "learning_rate": 0.00011479591836734696,
- "loss": 1.3139,
+ "epoch": 7.55,
+ "learning_rate": 0.00010511363636363635,
+ "loss": 0.6994,
"step": 668
},
{
- "epoch": 13.54,
- "learning_rate": 0.00011466836734693878,
- "loss": 1.3138,
+ "epoch": 7.56,
+ "learning_rate": 0.00010497159090909093,
+ "loss": 0.7141,
"step": 669
},
{
- "epoch": 13.56,
- "learning_rate": 0.00011454081632653062,
- "loss": 1.2808,
+ "epoch": 7.57,
+ "learning_rate": 0.00010482954545454546,
+ "loss": 0.7092,
"step": 670
},
{
- "epoch": 13.58,
- "learning_rate": 0.00011441326530612247,
- "loss": 1.2492,
+ "epoch": 7.58,
+ "learning_rate": 0.0001046875,
+ "loss": 0.7059,
"step": 671
},
{
- "epoch": 13.6,
- "learning_rate": 0.00011428571428571428,
- "loss": 1.2027,
+ "epoch": 7.59,
+ "learning_rate": 0.00010454545454545455,
+ "loss": 0.6904,
"step": 672
},
{
- "epoch": 13.62,
- "learning_rate": 0.00011415816326530613,
- "loss": 1.33,
+ "epoch": 7.6,
+ "learning_rate": 0.0001044034090909091,
+ "loss": 0.7115,
"step": 673
},
{
- "epoch": 13.64,
- "learning_rate": 0.00011403061224489797,
- "loss": 1.3112,
+ "epoch": 7.61,
+ "learning_rate": 0.00010426136363636365,
+ "loss": 0.7254,
"step": 674
},
{
- "epoch": 13.66,
- "learning_rate": 0.00011390306122448979,
- "loss": 1.2772,
+ "epoch": 7.63,
+ "learning_rate": 0.0001041193181818182,
+ "loss": 0.7181,
"step": 675
},
{
- "epoch": 13.68,
- "learning_rate": 0.00011377551020408163,
- "loss": 1.2701,
+ "epoch": 7.64,
+ "learning_rate": 0.00010397727272727273,
+ "loss": 0.6867,
"step": 676
},
{
- "epoch": 13.7,
- "learning_rate": 0.00011364795918367348,
- "loss": 1.1973,
+ "epoch": 7.65,
+ "learning_rate": 0.00010383522727272727,
+ "loss": 0.6917,
"step": 677
},
{
- "epoch": 13.72,
- "learning_rate": 0.0001135204081632653,
- "loss": 1.3124,
+ "epoch": 7.66,
+ "learning_rate": 0.00010369318181818182,
+ "loss": 0.6908,
"step": 678
},
{
- "epoch": 13.74,
- "learning_rate": 0.00011339285714285714,
- "loss": 1.3085,
+ "epoch": 7.67,
+ "learning_rate": 0.00010355113636363636,
+ "loss": 0.6871,
"step": 679
},
{
- "epoch": 13.76,
- "learning_rate": 0.00011326530612244898,
- "loss": 1.3457,
+ "epoch": 7.68,
+ "learning_rate": 0.00010340909090909092,
+ "loss": 0.682,
"step": 680
},
{
- "epoch": 13.78,
- "learning_rate": 0.00011313775510204083,
- "loss": 1.3338,
+ "epoch": 7.69,
+ "learning_rate": 0.00010326704545454547,
+ "loss": 0.6737,
"step": 681
},
{
- "epoch": 13.8,
- "learning_rate": 0.00011301020408163266,
- "loss": 1.2753,
+ "epoch": 7.7,
+ "learning_rate": 0.000103125,
+ "loss": 0.7023,
"step": 682
},
{
- "epoch": 13.82,
- "learning_rate": 0.00011288265306122449,
- "loss": 1.2786,
+ "epoch": 7.72,
+ "learning_rate": 0.00010298295454545454,
+ "loss": 0.7079,
"step": 683
},
{
- "epoch": 13.84,
- "learning_rate": 0.00011275510204081634,
- "loss": 1.2584,
+ "epoch": 7.73,
+ "learning_rate": 0.00010284090909090909,
+ "loss": 0.6954,
"step": 684
},
{
- "epoch": 13.86,
- "learning_rate": 0.00011262755102040817,
- "loss": 1.2779,
+ "epoch": 7.74,
+ "learning_rate": 0.00010269886363636365,
+ "loss": 0.6834,
"step": 685
},
{
- "epoch": 13.88,
- "learning_rate": 0.00011250000000000001,
- "loss": 1.3502,
+ "epoch": 7.75,
+ "learning_rate": 0.0001025568181818182,
+ "loss": 0.6706,
"step": 686
},
{
- "epoch": 13.9,
- "learning_rate": 0.00011237244897959185,
- "loss": 1.3251,
+ "epoch": 7.76,
+ "learning_rate": 0.00010241477272727274,
+ "loss": 0.6706,
"step": 687
},
{
- "epoch": 13.92,
- "learning_rate": 0.00011224489795918367,
- "loss": 1.273,
+ "epoch": 7.77,
+ "learning_rate": 0.00010227272727272727,
+ "loss": 0.681,
"step": 688
},
{
- "epoch": 13.94,
- "learning_rate": 0.00011211734693877552,
- "loss": 1.3341,
+ "epoch": 7.78,
+ "learning_rate": 0.00010213068181818182,
+ "loss": 0.6853,
"step": 689
},
{
- "epoch": 13.96,
- "learning_rate": 0.00011198979591836736,
- "loss": 1.2654,
+ "epoch": 7.8,
+ "learning_rate": 0.00010198863636363636,
+ "loss": 0.6772,
"step": 690
},
{
- "epoch": 13.98,
- "learning_rate": 0.00011186224489795918,
- "loss": 1.3333,
+ "epoch": 7.81,
+ "learning_rate": 0.00010184659090909092,
+ "loss": 0.6635,
"step": 691
},
{
- "epoch": 14.0,
- "learning_rate": 0.00011173469387755102,
- "loss": 1.3246,
+ "epoch": 7.82,
+ "learning_rate": 0.00010170454545454546,
+ "loss": 0.6712,
"step": 692
},
{
- "epoch": 14.02,
- "learning_rate": 0.00011160714285714287,
- "loss": 1.2547,
+ "epoch": 7.83,
+ "learning_rate": 0.00010156250000000001,
+ "loss": 0.6884,
"step": 693
},
{
- "epoch": 14.04,
- "learning_rate": 0.00011147959183673471,
- "loss": 1.208,
+ "epoch": 7.84,
+ "learning_rate": 0.00010142045454545454,
+ "loss": 0.6641,
"step": 694
},
{
- "epoch": 14.06,
- "learning_rate": 0.00011135204081632653,
- "loss": 1.223,
+ "epoch": 7.85,
+ "learning_rate": 0.00010127840909090909,
+ "loss": 0.6838,
"step": 695
},
{
- "epoch": 14.08,
- "learning_rate": 0.00011122448979591837,
- "loss": 1.2483,
+ "epoch": 7.86,
+ "learning_rate": 0.00010113636363636366,
+ "loss": 0.675,
"step": 696
},
{
- "epoch": 14.1,
- "learning_rate": 0.00011109693877551022,
- "loss": 1.2823,
+ "epoch": 7.87,
+ "learning_rate": 0.00010099431818181819,
+ "loss": 0.6626,
"step": 697
},
{
- "epoch": 14.12,
- "learning_rate": 0.00011096938775510204,
- "loss": 1.2013,
+ "epoch": 7.89,
+ "learning_rate": 0.00010085227272727273,
+ "loss": 0.6605,
"step": 698
},
{
- "epoch": 14.14,
- "learning_rate": 0.00011084183673469388,
- "loss": 1.1883,
+ "epoch": 7.9,
+ "learning_rate": 0.00010071022727272728,
+ "loss": 0.6777,
"step": 699
},
{
- "epoch": 14.16,
- "learning_rate": 0.00011071428571428572,
- "loss": 1.2364,
+ "epoch": 7.91,
+ "learning_rate": 0.00010056818181818181,
+ "loss": 0.6347,
"step": 700
},
{
- "epoch": 14.18,
- "learning_rate": 0.00011058673469387754,
- "loss": 1.2069,
+ "epoch": 7.92,
+ "learning_rate": 0.00010042613636363636,
+ "loss": 0.6857,
"step": 701
},
{
- "epoch": 14.2,
- "learning_rate": 0.00011045918367346939,
- "loss": 1.1968,
+ "epoch": 7.93,
+ "learning_rate": 0.00010028409090909093,
+ "loss": 0.6677,
"step": 702
},
{
- "epoch": 14.22,
- "learning_rate": 0.00011033163265306123,
- "loss": 1.2236,
+ "epoch": 7.94,
+ "learning_rate": 0.00010014204545454546,
+ "loss": 0.6697,
"step": 703
},
{
- "epoch": 14.24,
- "learning_rate": 0.00011020408163265306,
- "loss": 1.1942,
+ "epoch": 7.95,
+ "learning_rate": 0.0001,
+ "loss": 0.6375,
"step": 704
},
{
- "epoch": 14.26,
- "learning_rate": 0.0001100765306122449,
- "loss": 1.2561,
+ "epoch": 7.96,
+ "learning_rate": 9.985795454545455e-05,
+ "loss": 0.6572,
"step": 705
},
{
- "epoch": 14.29,
- "learning_rate": 0.00010994897959183674,
- "loss": 1.1839,
+ "epoch": 7.98,
+ "learning_rate": 9.97159090909091e-05,
+ "loss": 0.668,
"step": 706
},
{
- "epoch": 14.31,
- "learning_rate": 0.00010982142857142858,
- "loss": 1.2128,
+ "epoch": 7.99,
+ "learning_rate": 9.957386363636364e-05,
+ "loss": 0.6797,
"step": 707
},
{
- "epoch": 14.33,
- "learning_rate": 0.00010969387755102041,
- "loss": 1.3086,
+ "epoch": 8.0,
+ "learning_rate": 9.943181818181819e-05,
+ "loss": 0.6784,
"step": 708
},
{
- "epoch": 14.35,
- "learning_rate": 0.00010956632653061226,
- "loss": 1.2379,
+ "epoch": 8.01,
+ "learning_rate": 9.928977272727273e-05,
+ "loss": 0.6192,
"step": 709
},
{
- "epoch": 14.37,
- "learning_rate": 0.0001094387755102041,
- "loss": 1.176,
+ "epoch": 8.02,
+ "learning_rate": 9.914772727272728e-05,
+ "loss": 0.6287,
"step": 710
},
{
- "epoch": 14.39,
- "learning_rate": 0.00010931122448979592,
- "loss": 1.2105,
+ "epoch": 8.03,
+ "learning_rate": 9.900568181818183e-05,
+ "loss": 0.6034,
"step": 711
},
{
- "epoch": 14.41,
- "learning_rate": 0.00010918367346938776,
- "loss": 1.2149,
+ "epoch": 8.04,
+ "learning_rate": 9.886363636363637e-05,
+ "loss": 0.6167,
"step": 712
},
{
- "epoch": 14.43,
- "learning_rate": 0.0001090561224489796,
- "loss": 1.2392,
+ "epoch": 8.06,
+ "learning_rate": 9.872159090909091e-05,
+ "loss": 0.6353,
"step": 713
},
{
- "epoch": 14.45,
- "learning_rate": 0.00010892857142857142,
- "loss": 1.2471,
+ "epoch": 8.07,
+ "learning_rate": 9.857954545454547e-05,
+ "loss": 0.6222,
"step": 714
},
{
- "epoch": 14.47,
- "learning_rate": 0.00010880102040816327,
- "loss": 1.2561,
+ "epoch": 8.08,
+ "learning_rate": 9.84375e-05,
+ "loss": 0.5963,
"step": 715
},
{
- "epoch": 14.49,
- "learning_rate": 0.00010867346938775511,
- "loss": 1.2179,
+ "epoch": 8.09,
+ "learning_rate": 9.829545454545455e-05,
+ "loss": 0.6042,
"step": 716
},
{
- "epoch": 14.51,
- "learning_rate": 0.00010854591836734696,
- "loss": 1.2459,
+ "epoch": 8.1,
+ "learning_rate": 9.81534090909091e-05,
+ "loss": 0.612,
"step": 717
},
{
- "epoch": 14.53,
- "learning_rate": 0.00010841836734693877,
- "loss": 1.2933,
+ "epoch": 8.11,
+ "learning_rate": 9.801136363636364e-05,
+ "loss": 0.6069,
"step": 718
},
{
- "epoch": 14.55,
- "learning_rate": 0.00010829081632653062,
- "loss": 1.2862,
+ "epoch": 8.12,
+ "learning_rate": 9.786931818181818e-05,
+ "loss": 0.6001,
"step": 719
},
{
- "epoch": 14.57,
- "learning_rate": 0.00010816326530612246,
- "loss": 1.2976,
+ "epoch": 8.13,
+ "learning_rate": 9.772727272727274e-05,
+ "loss": 0.6007,
"step": 720
},
{
- "epoch": 14.59,
- "learning_rate": 0.00010803571428571428,
- "loss": 1.231,
+ "epoch": 8.15,
+ "learning_rate": 9.758522727272727e-05,
+ "loss": 0.6079,
"step": 721
},
{
- "epoch": 14.61,
- "learning_rate": 0.00010790816326530613,
- "loss": 1.2464,
+ "epoch": 8.16,
+ "learning_rate": 9.744318181818183e-05,
+ "loss": 0.6216,
"step": 722
},
{
- "epoch": 14.63,
- "learning_rate": 0.00010778061224489797,
- "loss": 1.2181,
+ "epoch": 8.17,
+ "learning_rate": 9.730113636363637e-05,
+ "loss": 0.6321,
"step": 723
},
{
- "epoch": 14.65,
- "learning_rate": 0.00010765306122448979,
- "loss": 1.3307,
+ "epoch": 8.18,
+ "learning_rate": 9.71590909090909e-05,
+ "loss": 0.6044,
"step": 724
},
{
- "epoch": 14.67,
- "learning_rate": 0.00010752551020408163,
- "loss": 1.1723,
+ "epoch": 8.19,
+ "learning_rate": 9.701704545454547e-05,
+ "loss": 0.6028,
"step": 725
},
{
- "epoch": 14.69,
- "learning_rate": 0.00010739795918367348,
- "loss": 1.1528,
+ "epoch": 8.2,
+ "learning_rate": 9.687500000000001e-05,
+ "loss": 0.6098,
"step": 726
},
{
- "epoch": 14.71,
- "learning_rate": 0.0001072704081632653,
- "loss": 1.215,
+ "epoch": 8.21,
+ "learning_rate": 9.673295454545454e-05,
+ "loss": 0.6032,
"step": 727
},
{
- "epoch": 14.73,
- "learning_rate": 0.00010714285714285715,
- "loss": 1.2624,
+ "epoch": 8.22,
+ "learning_rate": 9.65909090909091e-05,
+ "loss": 0.6298,
"step": 728
},
{
- "epoch": 14.75,
- "learning_rate": 0.00010701530612244898,
- "loss": 1.3117,
+ "epoch": 8.24,
+ "learning_rate": 9.644886363636365e-05,
+ "loss": 0.6115,
"step": 729
},
{
- "epoch": 14.77,
- "learning_rate": 0.00010688775510204083,
- "loss": 1.2572,
+ "epoch": 8.25,
+ "learning_rate": 9.630681818181818e-05,
+ "loss": 0.6052,
"step": 730
},
{
- "epoch": 14.79,
- "learning_rate": 0.00010676020408163266,
- "loss": 1.222,
+ "epoch": 8.26,
+ "learning_rate": 9.616477272727274e-05,
+ "loss": 0.6097,
"step": 731
},
{
- "epoch": 14.81,
- "learning_rate": 0.0001066326530612245,
- "loss": 1.2881,
+ "epoch": 8.27,
+ "learning_rate": 9.602272727272728e-05,
+ "loss": 0.6062,
"step": 732
},
{
- "epoch": 14.83,
- "learning_rate": 0.00010650510204081635,
- "loss": 1.2676,
+ "epoch": 8.28,
+ "learning_rate": 9.588068181818183e-05,
+ "loss": 0.5984,
"step": 733
},
{
- "epoch": 14.85,
- "learning_rate": 0.00010637755102040816,
- "loss": 1.2734,
+ "epoch": 8.29,
+ "learning_rate": 9.573863636363637e-05,
+ "loss": 0.6432,
"step": 734
},
{
- "epoch": 14.87,
- "learning_rate": 0.00010625000000000001,
- "loss": 1.2885,
+ "epoch": 8.3,
+ "learning_rate": 9.559659090909092e-05,
+ "loss": 0.5814,
"step": 735
},
{
- "epoch": 14.89,
- "learning_rate": 0.00010612244897959185,
- "loss": 1.2764,
+ "epoch": 8.31,
+ "learning_rate": 9.545454545454546e-05,
+ "loss": 0.5965,
"step": 736
},
{
- "epoch": 14.91,
- "learning_rate": 0.00010599489795918367,
- "loss": 1.3267,
+ "epoch": 8.33,
+ "learning_rate": 9.53125e-05,
+ "loss": 0.6102,
"step": 737
},
{
- "epoch": 14.93,
- "learning_rate": 0.00010586734693877551,
- "loss": 1.2445,
+ "epoch": 8.34,
+ "learning_rate": 9.517045454545455e-05,
+ "loss": 0.5849,
"step": 738
},
{
- "epoch": 14.95,
- "learning_rate": 0.00010573979591836736,
- "loss": 1.3359,
+ "epoch": 8.35,
+ "learning_rate": 9.50284090909091e-05,
+ "loss": 0.6062,
"step": 739
},
{
- "epoch": 14.97,
- "learning_rate": 0.00010561224489795918,
- "loss": 1.2508,
+ "epoch": 8.36,
+ "learning_rate": 9.488636363636364e-05,
+ "loss": 0.6031,
"step": 740
},
{
- "epoch": 14.99,
- "learning_rate": 0.00010548469387755102,
- "loss": 1.2227,
+ "epoch": 8.37,
+ "learning_rate": 9.474431818181819e-05,
+ "loss": 0.5932,
"step": 741
},
{
- "epoch": 15.01,
- "learning_rate": 0.00010535714285714286,
- "loss": 1.1889,
+ "epoch": 8.38,
+ "learning_rate": 9.460227272727273e-05,
+ "loss": 0.589,
"step": 742
},
{
- "epoch": 15.03,
- "learning_rate": 0.00010522959183673471,
- "loss": 1.1919,
+ "epoch": 8.39,
+ "learning_rate": 9.446022727272728e-05,
+ "loss": 0.6096,
"step": 743
},
{
- "epoch": 15.05,
- "learning_rate": 0.00010510204081632653,
- "loss": 1.2383,
+ "epoch": 8.41,
+ "learning_rate": 9.431818181818182e-05,
+ "loss": 0.601,
"step": 744
},
{
- "epoch": 15.07,
- "learning_rate": 0.00010497448979591837,
- "loss": 1.2401,
+ "epoch": 8.42,
+ "learning_rate": 9.417613636363637e-05,
+ "loss": 0.5798,
"step": 745
},
{
- "epoch": 15.09,
- "learning_rate": 0.00010484693877551021,
- "loss": 1.2015,
+ "epoch": 8.43,
+ "learning_rate": 9.403409090909091e-05,
+ "loss": 0.59,
"step": 746
},
{
- "epoch": 15.11,
- "learning_rate": 0.00010471938775510203,
- "loss": 1.1509,
+ "epoch": 8.44,
+ "learning_rate": 9.389204545454546e-05,
+ "loss": 0.5988,
"step": 747
},
{
- "epoch": 15.13,
- "learning_rate": 0.00010459183673469388,
- "loss": 1.1878,
+ "epoch": 8.45,
+ "learning_rate": 9.375e-05,
+ "loss": 0.5591,
"step": 748
},
{
- "epoch": 15.16,
- "learning_rate": 0.00010446428571428572,
- "loss": 1.1706,
+ "epoch": 8.46,
+ "learning_rate": 9.360795454545455e-05,
+ "loss": 0.5939,
"step": 749
},
{
- "epoch": 15.18,
- "learning_rate": 0.00010433673469387755,
- "loss": 1.1285,
+ "epoch": 8.47,
+ "learning_rate": 9.346590909090909e-05,
+ "loss": 0.5886,
"step": 750
},
{
- "epoch": 15.2,
- "learning_rate": 0.0001042091836734694,
- "loss": 1.1608,
+ "epoch": 8.48,
+ "learning_rate": 9.332386363636364e-05,
+ "loss": 0.5994,
"step": 751
},
{
- "epoch": 15.22,
- "learning_rate": 0.00010408163265306123,
- "loss": 1.1178,
+ "epoch": 8.5,
+ "learning_rate": 9.318181818181818e-05,
+ "loss": 0.5821,
"step": 752
},
{
- "epoch": 15.24,
- "learning_rate": 0.00010395408163265306,
- "loss": 1.1293,
+ "epoch": 8.51,
+ "learning_rate": 9.303977272727273e-05,
+ "loss": 0.602,
"step": 753
},
{
- "epoch": 15.26,
- "learning_rate": 0.0001038265306122449,
- "loss": 1.2306,
+ "epoch": 8.52,
+ "learning_rate": 9.289772727272727e-05,
+ "loss": 0.5708,
"step": 754
},
{
- "epoch": 15.28,
- "learning_rate": 0.00010369897959183675,
- "loss": 1.1541,
+ "epoch": 8.53,
+ "learning_rate": 9.275568181818183e-05,
+ "loss": 0.5902,
"step": 755
},
{
- "epoch": 15.3,
- "learning_rate": 0.00010357142857142859,
- "loss": 1.1702,
+ "epoch": 8.54,
+ "learning_rate": 9.261363636363636e-05,
+ "loss": 0.6053,
"step": 756
},
{
- "epoch": 15.32,
- "learning_rate": 0.00010344387755102041,
- "loss": 1.2119,
+ "epoch": 8.55,
+ "learning_rate": 9.247159090909091e-05,
+ "loss": 0.5797,
"step": 757
},
{
- "epoch": 15.34,
- "learning_rate": 0.00010331632653061225,
- "loss": 1.2239,
+ "epoch": 8.56,
+ "learning_rate": 9.232954545454547e-05,
+ "loss": 0.5965,
"step": 758
},
{
- "epoch": 15.36,
- "learning_rate": 0.0001031887755102041,
- "loss": 1.2019,
+ "epoch": 8.57,
+ "learning_rate": 9.21875e-05,
+ "loss": 0.5738,
"step": 759
},
{
- "epoch": 15.38,
- "learning_rate": 0.00010306122448979591,
- "loss": 1.2197,
+ "epoch": 8.59,
+ "learning_rate": 9.204545454545454e-05,
+ "loss": 0.5819,
"step": 760
},
{
- "epoch": 15.4,
- "learning_rate": 0.00010293367346938776,
- "loss": 1.1769,
+ "epoch": 8.6,
+ "learning_rate": 9.19034090909091e-05,
+ "loss": 0.5994,
"step": 761
},
{
- "epoch": 15.42,
- "learning_rate": 0.0001028061224489796,
- "loss": 1.1907,
+ "epoch": 8.61,
+ "learning_rate": 9.176136363636363e-05,
+ "loss": 0.5738,
"step": 762
},
{
- "epoch": 15.44,
- "learning_rate": 0.00010267857142857142,
- "loss": 1.2089,
+ "epoch": 8.62,
+ "learning_rate": 9.161931818181818e-05,
+ "loss": 0.5663,
"step": 763
},
{
- "epoch": 15.46,
- "learning_rate": 0.00010255102040816327,
- "loss": 1.1335,
+ "epoch": 8.63,
+ "learning_rate": 9.147727272727274e-05,
+ "loss": 0.5798,
"step": 764
},
{
- "epoch": 15.48,
- "learning_rate": 0.00010242346938775511,
- "loss": 1.1633,
+ "epoch": 8.64,
+ "learning_rate": 9.133522727272727e-05,
+ "loss": 0.5705,
"step": 765
},
{
- "epoch": 15.5,
- "learning_rate": 0.00010229591836734695,
- "loss": 1.1578,
+ "epoch": 8.65,
+ "learning_rate": 9.119318181818183e-05,
+ "loss": 0.5943,
"step": 766
},
{
- "epoch": 15.52,
- "learning_rate": 0.00010216836734693877,
- "loss": 1.2236,
+ "epoch": 8.67,
+ "learning_rate": 9.105113636363637e-05,
+ "loss": 0.6019,
"step": 767
},
{
- "epoch": 15.54,
- "learning_rate": 0.00010204081632653062,
- "loss": 1.1941,
+ "epoch": 8.68,
+ "learning_rate": 9.090909090909092e-05,
+ "loss": 0.5733,
"step": 768
},
{
- "epoch": 15.56,
- "learning_rate": 0.00010191326530612246,
- "loss": 1.2666,
+ "epoch": 8.69,
+ "learning_rate": 9.076704545454546e-05,
+ "loss": 0.575,
"step": 769
},
{
- "epoch": 15.58,
- "learning_rate": 0.00010178571428571428,
- "loss": 1.1232,
+ "epoch": 8.7,
+ "learning_rate": 9.062500000000001e-05,
+ "loss": 0.5675,
"step": 770
},
{
- "epoch": 15.6,
- "learning_rate": 0.00010165816326530612,
- "loss": 1.2242,
+ "epoch": 8.71,
+ "learning_rate": 9.048295454545455e-05,
+ "loss": 0.566,
"step": 771
},
{
- "epoch": 15.62,
- "learning_rate": 0.00010153061224489797,
- "loss": 1.1852,
+ "epoch": 8.72,
+ "learning_rate": 9.03409090909091e-05,
+ "loss": 0.5513,
"step": 772
},
{
- "epoch": 15.64,
- "learning_rate": 0.0001014030612244898,
- "loss": 1.2626,
+ "epoch": 8.73,
+ "learning_rate": 9.019886363636364e-05,
+ "loss": 0.5682,
"step": 773
},
{
- "epoch": 15.66,
- "learning_rate": 0.00010127551020408164,
- "loss": 1.1873,
+ "epoch": 8.74,
+ "learning_rate": 9.005681818181819e-05,
+ "loss": 0.5508,
"step": 774
},
{
- "epoch": 15.68,
- "learning_rate": 0.00010114795918367349,
- "loss": 1.3005,
+ "epoch": 8.76,
+ "learning_rate": 8.991477272727273e-05,
+ "loss": 0.5668,
"step": 775
},
{
- "epoch": 15.7,
- "learning_rate": 0.0001010204081632653,
- "loss": 1.1904,
+ "epoch": 8.77,
+ "learning_rate": 8.977272727272728e-05,
+ "loss": 0.569,
"step": 776
},
{
- "epoch": 15.72,
- "learning_rate": 0.00010089285714285715,
- "loss": 1.2927,
+ "epoch": 8.78,
+ "learning_rate": 8.963068181818182e-05,
+ "loss": 0.5897,
"step": 777
},
{
- "epoch": 15.74,
- "learning_rate": 0.00010076530612244899,
- "loss": 1.179,
+ "epoch": 8.79,
+ "learning_rate": 8.948863636363637e-05,
+ "loss": 0.5738,
"step": 778
},
{
- "epoch": 15.76,
- "learning_rate": 0.00010063775510204084,
- "loss": 1.2027,
+ "epoch": 8.8,
+ "learning_rate": 8.934659090909091e-05,
+ "loss": 0.5511,
"step": 779
},
{
- "epoch": 15.78,
- "learning_rate": 0.00010051020408163265,
- "loss": 1.2428,
+ "epoch": 8.81,
+ "learning_rate": 8.920454545454546e-05,
+ "loss": 0.5659,
"step": 780
},
{
- "epoch": 15.8,
- "learning_rate": 0.0001003826530612245,
- "loss": 1.2324,
+ "epoch": 8.82,
+ "learning_rate": 8.90625e-05,
+ "loss": 0.5649,
"step": 781
},
{
- "epoch": 15.82,
- "learning_rate": 0.00010025510204081634,
- "loss": 1.1251,
+ "epoch": 8.83,
+ "learning_rate": 8.892045454545455e-05,
+ "loss": 0.5618,
"step": 782
},
{
- "epoch": 15.84,
- "learning_rate": 0.00010012755102040816,
- "loss": 1.2405,
+ "epoch": 8.85,
+ "learning_rate": 8.87784090909091e-05,
+ "loss": 0.5602,
"step": 783
},
{
- "epoch": 15.86,
- "learning_rate": 0.0001,
- "loss": 1.2005,
+ "epoch": 8.86,
+ "learning_rate": 8.863636363636364e-05,
+ "loss": 0.5723,
"step": 784
},
{
- "epoch": 15.88,
- "learning_rate": 9.987244897959184e-05,
- "loss": 1.2259,
+ "epoch": 8.87,
+ "learning_rate": 8.849431818181818e-05,
+ "loss": 0.5816,
"step": 785
},
{
- "epoch": 15.9,
- "learning_rate": 9.974489795918368e-05,
- "loss": 1.1576,
+ "epoch": 8.88,
+ "learning_rate": 8.835227272727273e-05,
+ "loss": 0.555,
"step": 786
},
{
- "epoch": 15.92,
- "learning_rate": 9.961734693877551e-05,
- "loss": 1.1834,
+ "epoch": 8.89,
+ "learning_rate": 8.821022727272727e-05,
+ "loss": 0.5563,
"step": 787
},
{
- "epoch": 15.94,
- "learning_rate": 9.948979591836736e-05,
- "loss": 1.2396,
+ "epoch": 8.9,
+ "learning_rate": 8.806818181818183e-05,
+ "loss": 0.554,
"step": 788
},
{
- "epoch": 15.96,
- "learning_rate": 9.936224489795919e-05,
- "loss": 1.1865,
+ "epoch": 8.91,
+ "learning_rate": 8.792613636363636e-05,
+ "loss": 0.5671,
"step": 789
},
{
- "epoch": 15.98,
- "learning_rate": 9.923469387755102e-05,
- "loss": 1.2356,
+ "epoch": 8.92,
+ "learning_rate": 8.778409090909091e-05,
+ "loss": 0.5485,
"step": 790
},
{
- "epoch": 16.01,
- "learning_rate": 9.910714285714286e-05,
- "loss": 1.2639,
+ "epoch": 8.94,
+ "learning_rate": 8.764204545454547e-05,
+ "loss": 0.5712,
"step": 791
},
{
- "epoch": 16.03,
- "learning_rate": 9.897959183673469e-05,
- "loss": 1.1216,
+ "epoch": 8.95,
+ "learning_rate": 8.75e-05,
+ "loss": 0.5507,
"step": 792
},
{
- "epoch": 16.05,
- "learning_rate": 9.885204081632652e-05,
- "loss": 1.1051,
+ "epoch": 8.96,
+ "learning_rate": 8.735795454545454e-05,
+ "loss": 0.5718,
"step": 793
},
{
- "epoch": 16.07,
- "learning_rate": 9.872448979591837e-05,
- "loss": 1.0864,
+ "epoch": 8.97,
+ "learning_rate": 8.72159090909091e-05,
+ "loss": 0.5585,
"step": 794
},
{
- "epoch": 16.09,
- "learning_rate": 9.859693877551021e-05,
- "loss": 1.182,
+ "epoch": 8.98,
+ "learning_rate": 8.707386363636363e-05,
+ "loss": 0.5563,
"step": 795
},
{
- "epoch": 16.11,
- "learning_rate": 9.846938775510204e-05,
- "loss": 1.1272,
+ "epoch": 8.99,
+ "learning_rate": 8.693181818181818e-05,
+ "loss": 0.581,
"step": 796
},
{
- "epoch": 16.13,
- "learning_rate": 9.834183673469389e-05,
- "loss": 1.1946,
+ "epoch": 9.0,
+ "learning_rate": 8.678977272727274e-05,
+ "loss": 0.5511,
"step": 797
},
{
- "epoch": 16.15,
- "learning_rate": 9.821428571428572e-05,
- "loss": 1.0875,
+ "epoch": 9.02,
+ "learning_rate": 8.664772727272727e-05,
+ "loss": 0.5103,
"step": 798
},
{
- "epoch": 16.17,
- "learning_rate": 9.808673469387756e-05,
- "loss": 1.1671,
+ "epoch": 9.03,
+ "learning_rate": 8.650568181818183e-05,
+ "loss": 0.5323,
"step": 799
},
{
- "epoch": 16.19,
- "learning_rate": 9.79591836734694e-05,
- "loss": 1.1502,
+ "epoch": 9.04,
+ "learning_rate": 8.636363636363637e-05,
+ "loss": 0.5092,
"step": 800
},
{
- "epoch": 16.21,
- "learning_rate": 9.783163265306124e-05,
- "loss": 1.19,
+ "epoch": 9.05,
+ "learning_rate": 8.62215909090909e-05,
+ "loss": 0.5247,
"step": 801
},
{
- "epoch": 16.23,
- "learning_rate": 9.770408163265307e-05,
- "loss": 1.1258,
+ "epoch": 9.06,
+ "learning_rate": 8.607954545454546e-05,
+ "loss": 0.5403,
"step": 802
},
{
- "epoch": 16.25,
- "learning_rate": 9.75765306122449e-05,
- "loss": 1.1765,
+ "epoch": 9.07,
+ "learning_rate": 8.593750000000001e-05,
+ "loss": 0.5252,
"step": 803
},
{
- "epoch": 16.27,
- "learning_rate": 9.744897959183674e-05,
- "loss": 1.1217,
+ "epoch": 9.08,
+ "learning_rate": 8.579545454545454e-05,
+ "loss": 0.5296,
"step": 804
},
{
- "epoch": 16.29,
- "learning_rate": 9.732142857142858e-05,
- "loss": 1.1293,
+ "epoch": 9.09,
+ "learning_rate": 8.56534090909091e-05,
+ "loss": 0.5223,
"step": 805
},
{
- "epoch": 16.31,
- "learning_rate": 9.719387755102042e-05,
- "loss": 1.17,
+ "epoch": 9.11,
+ "learning_rate": 8.551136363636364e-05,
+ "loss": 0.4972,
"step": 806
},
{
- "epoch": 16.33,
- "learning_rate": 9.706632653061225e-05,
- "loss": 1.17,
+ "epoch": 9.12,
+ "learning_rate": 8.536931818181818e-05,
+ "loss": 0.5005,
"step": 807
},
{
- "epoch": 16.35,
- "learning_rate": 9.693877551020408e-05,
- "loss": 1.2004,
+ "epoch": 9.13,
+ "learning_rate": 8.522727272727273e-05,
+ "loss": 0.5249,
"step": 808
},
{
- "epoch": 16.37,
- "learning_rate": 9.681122448979593e-05,
- "loss": 1.1648,
+ "epoch": 9.14,
+ "learning_rate": 8.508522727272728e-05,
+ "loss": 0.5135,
"step": 809
},
{
- "epoch": 16.39,
- "learning_rate": 9.668367346938776e-05,
- "loss": 1.0688,
+ "epoch": 9.15,
+ "learning_rate": 8.494318181818182e-05,
+ "loss": 0.5053,
"step": 810
},
{
- "epoch": 16.41,
- "learning_rate": 9.655612244897959e-05,
- "loss": 1.1607,
+ "epoch": 9.16,
+ "learning_rate": 8.480113636363637e-05,
+ "loss": 0.5158,
"step": 811
},
{
- "epoch": 16.43,
- "learning_rate": 9.642857142857143e-05,
- "loss": 1.1298,
+ "epoch": 9.17,
+ "learning_rate": 8.465909090909091e-05,
+ "loss": 0.5061,
"step": 812
},
{
- "epoch": 16.45,
- "learning_rate": 9.630102040816326e-05,
- "loss": 1.1064,
+ "epoch": 9.18,
+ "learning_rate": 8.451704545454546e-05,
+ "loss": 0.4988,
"step": 813
},
{
- "epoch": 16.47,
- "learning_rate": 9.617346938775511e-05,
- "loss": 1.1472,
+ "epoch": 9.2,
+ "learning_rate": 8.4375e-05,
+ "loss": 0.5273,
"step": 814
},
{
- "epoch": 16.49,
- "learning_rate": 9.604591836734694e-05,
- "loss": 1.1577,
+ "epoch": 9.21,
+ "learning_rate": 8.423295454545455e-05,
+ "loss": 0.5332,
"step": 815
},
{
- "epoch": 16.51,
- "learning_rate": 9.591836734693878e-05,
- "loss": 1.1436,
+ "epoch": 9.22,
+ "learning_rate": 8.40909090909091e-05,
+ "loss": 0.5181,
"step": 816
},
{
- "epoch": 16.53,
- "learning_rate": 9.579081632653061e-05,
- "loss": 1.1657,
+ "epoch": 9.23,
+ "learning_rate": 8.394886363636364e-05,
+ "loss": 0.5085,
"step": 817
},
{
- "epoch": 16.55,
- "learning_rate": 9.566326530612246e-05,
- "loss": 1.1147,
+ "epoch": 9.24,
+ "learning_rate": 8.380681818181818e-05,
+ "loss": 0.5137,
"step": 818
},
{
- "epoch": 16.57,
- "learning_rate": 9.553571428571429e-05,
- "loss": 1.1839,
+ "epoch": 9.25,
+ "learning_rate": 8.366477272727273e-05,
+ "loss": 0.5195,
"step": 819
},
{
- "epoch": 16.59,
- "learning_rate": 9.540816326530613e-05,
- "loss": 1.1298,
+ "epoch": 9.26,
+ "learning_rate": 8.352272727272727e-05,
+ "loss": 0.5077,
"step": 820
},
{
- "epoch": 16.61,
- "learning_rate": 9.528061224489796e-05,
- "loss": 1.2141,
+ "epoch": 9.28,
+ "learning_rate": 8.338068181818183e-05,
+ "loss": 0.5074,
"step": 821
},
{
- "epoch": 16.63,
- "learning_rate": 9.515306122448981e-05,
- "loss": 1.2045,
+ "epoch": 9.29,
+ "learning_rate": 8.323863636363637e-05,
+ "loss": 0.5142,
"step": 822
},
{
- "epoch": 16.65,
- "learning_rate": 9.502551020408164e-05,
- "loss": 1.1791,
+ "epoch": 9.3,
+ "learning_rate": 8.309659090909091e-05,
+ "loss": 0.5116,
"step": 823
},
{
- "epoch": 16.67,
- "learning_rate": 9.489795918367348e-05,
- "loss": 1.1137,
+ "epoch": 9.31,
+ "learning_rate": 8.295454545454547e-05,
+ "loss": 0.4974,
"step": 824
},
{
- "epoch": 16.69,
- "learning_rate": 9.477040816326531e-05,
- "loss": 1.1312,
+ "epoch": 9.32,
+ "learning_rate": 8.28125e-05,
+ "loss": 0.5117,
"step": 825
},
{
- "epoch": 16.71,
- "learning_rate": 9.464285714285715e-05,
- "loss": 1.1102,
+ "epoch": 9.33,
+ "learning_rate": 8.267045454545455e-05,
+ "loss": 0.5114,
"step": 826
},
{
- "epoch": 16.73,
- "learning_rate": 9.451530612244899e-05,
- "loss": 1.1865,
+ "epoch": 9.34,
+ "learning_rate": 8.25284090909091e-05,
+ "loss": 0.5039,
"step": 827
},
{
- "epoch": 16.75,
- "learning_rate": 9.438775510204082e-05,
- "loss": 1.1232,
+ "epoch": 9.35,
+ "learning_rate": 8.238636363636364e-05,
+ "loss": 0.498,
"step": 828
},
{
- "epoch": 16.77,
- "learning_rate": 9.426020408163265e-05,
- "loss": 1.2068,
+ "epoch": 9.37,
+ "learning_rate": 8.224431818181818e-05,
+ "loss": 0.5042,
"step": 829
},
{
- "epoch": 16.79,
- "learning_rate": 9.41326530612245e-05,
- "loss": 1.1864,
+ "epoch": 9.38,
+ "learning_rate": 8.210227272727274e-05,
+ "loss": 0.5049,
"step": 830
},
{
- "epoch": 16.81,
- "learning_rate": 9.400510204081633e-05,
- "loss": 1.2195,
+ "epoch": 9.39,
+ "learning_rate": 8.196022727272727e-05,
+ "loss": 0.5123,
"step": 831
},
{
- "epoch": 16.83,
- "learning_rate": 9.387755102040817e-05,
- "loss": 1.2063,
+ "epoch": 9.4,
+ "learning_rate": 8.181818181818183e-05,
+ "loss": 0.4907,
"step": 832
},
{
- "epoch": 16.85,
- "learning_rate": 9.375e-05,
- "loss": 1.1455,
+ "epoch": 9.41,
+ "learning_rate": 8.167613636363637e-05,
+ "loss": 0.5267,
"step": 833
},
{
- "epoch": 16.88,
- "learning_rate": 9.362244897959183e-05,
- "loss": 1.1819,
+ "epoch": 9.42,
+ "learning_rate": 8.15340909090909e-05,
+ "loss": 0.5314,
"step": 834
},
{
- "epoch": 16.9,
- "learning_rate": 9.349489795918368e-05,
- "loss": 1.1887,
+ "epoch": 9.43,
+ "learning_rate": 8.139204545454546e-05,
+ "loss": 0.4952,
"step": 835
},
{
- "epoch": 16.92,
- "learning_rate": 9.336734693877551e-05,
- "loss": 1.1557,
+ "epoch": 9.44,
+ "learning_rate": 8.125000000000001e-05,
+ "loss": 0.5014,
"step": 836
},
{
- "epoch": 16.94,
- "learning_rate": 9.323979591836735e-05,
- "loss": 1.2094,
+ "epoch": 9.46,
+ "learning_rate": 8.110795454545454e-05,
+ "loss": 0.4967,
"step": 837
},
{
- "epoch": 16.96,
- "learning_rate": 9.311224489795918e-05,
- "loss": 1.1512,
+ "epoch": 9.47,
+ "learning_rate": 8.09659090909091e-05,
+ "loss": 0.5116,
"step": 838
},
{
- "epoch": 16.98,
- "learning_rate": 9.298469387755103e-05,
- "loss": 1.1463,
+ "epoch": 9.48,
+ "learning_rate": 8.082386363636365e-05,
+ "loss": 0.5119,
"step": 839
},
{
- "epoch": 17.0,
- "learning_rate": 9.285714285714286e-05,
- "loss": 1.155,
+ "epoch": 9.49,
+ "learning_rate": 8.068181818181818e-05,
+ "loss": 0.4987,
"step": 840
},
{
- "epoch": 17.02,
- "learning_rate": 9.27295918367347e-05,
- "loss": 1.1292,
+ "epoch": 9.5,
+ "learning_rate": 8.053977272727274e-05,
+ "loss": 0.5063,
"step": 841
},
{
- "epoch": 17.04,
- "learning_rate": 9.260204081632653e-05,
- "loss": 1.0996,
+ "epoch": 9.51,
+ "learning_rate": 8.039772727272728e-05,
+ "loss": 0.5019,
"step": 842
},
{
- "epoch": 17.06,
- "learning_rate": 9.247448979591838e-05,
- "loss": 1.0662,
+ "epoch": 9.52,
+ "learning_rate": 8.025568181818183e-05,
+ "loss": 0.5272,
"step": 843
},
{
- "epoch": 17.08,
- "learning_rate": 9.234693877551021e-05,
- "loss": 1.0931,
+ "epoch": 9.54,
+ "learning_rate": 8.011363636363637e-05,
+ "loss": 0.4969,
"step": 844
},
{
- "epoch": 17.1,
- "learning_rate": 9.221938775510205e-05,
- "loss": 1.0727,
+ "epoch": 9.55,
+ "learning_rate": 7.997159090909092e-05,
+ "loss": 0.5222,
"step": 845
},
{
- "epoch": 17.12,
- "learning_rate": 9.209183673469388e-05,
- "loss": 1.1043,
+ "epoch": 9.56,
+ "learning_rate": 7.982954545454546e-05,
+ "loss": 0.4729,
"step": 846
},
{
- "epoch": 17.14,
- "learning_rate": 9.196428571428572e-05,
- "loss": 1.0594,
+ "epoch": 9.57,
+ "learning_rate": 7.96875e-05,
+ "loss": 0.4976,
"step": 847
},
{
- "epoch": 17.16,
- "learning_rate": 9.183673469387756e-05,
- "loss": 1.0952,
+ "epoch": 9.58,
+ "learning_rate": 7.954545454545455e-05,
+ "loss": 0.4974,
"step": 848
},
{
- "epoch": 17.18,
- "learning_rate": 9.170918367346939e-05,
- "loss": 1.0639,
+ "epoch": 9.59,
+ "learning_rate": 7.94034090909091e-05,
+ "loss": 0.4849,
"step": 849
},
{
- "epoch": 17.2,
- "learning_rate": 9.158163265306124e-05,
- "loss": 1.132,
+ "epoch": 9.6,
+ "learning_rate": 7.926136363636364e-05,
+ "loss": 0.4897,
"step": 850
},
{
- "epoch": 17.22,
- "learning_rate": 9.145408163265307e-05,
- "loss": 1.1083,
+ "epoch": 9.61,
+ "learning_rate": 7.911931818181819e-05,
+ "loss": 0.4962,
"step": 851
},
{
- "epoch": 17.24,
- "learning_rate": 9.13265306122449e-05,
- "loss": 1.1282,
+ "epoch": 9.63,
+ "learning_rate": 7.897727272727273e-05,
+ "loss": 0.4877,
"step": 852
},
{
- "epoch": 17.26,
- "learning_rate": 9.119897959183674e-05,
- "loss": 1.0474,
+ "epoch": 9.64,
+ "learning_rate": 7.883522727272728e-05,
+ "loss": 0.4921,
"step": 853
},
{
- "epoch": 17.28,
- "learning_rate": 9.107142857142857e-05,
- "loss": 1.1138,
+ "epoch": 9.65,
+ "learning_rate": 7.869318181818182e-05,
+ "loss": 0.4969,
"step": 854
},
{
- "epoch": 17.3,
- "learning_rate": 9.094387755102042e-05,
- "loss": 1.1025,
+ "epoch": 9.66,
+ "learning_rate": 7.855113636363637e-05,
+ "loss": 0.5045,
"step": 855
},
{
- "epoch": 17.32,
- "learning_rate": 9.081632653061225e-05,
- "loss": 1.0968,
+ "epoch": 9.67,
+ "learning_rate": 7.840909090909091e-05,
+ "loss": 0.5207,
"step": 856
},
{
- "epoch": 17.34,
- "learning_rate": 9.068877551020408e-05,
- "loss": 1.1683,
+ "epoch": 9.68,
+ "learning_rate": 7.826704545454546e-05,
+ "loss": 0.5098,
"step": 857
},
{
- "epoch": 17.36,
- "learning_rate": 9.056122448979592e-05,
- "loss": 1.0975,
+ "epoch": 9.69,
+ "learning_rate": 7.8125e-05,
+ "loss": 0.5005,
"step": 858
},
{
- "epoch": 17.38,
- "learning_rate": 9.043367346938775e-05,
- "loss": 1.1274,
+ "epoch": 9.7,
+ "learning_rate": 7.798295454545455e-05,
+ "loss": 0.5028,
"step": 859
},
{
- "epoch": 17.4,
- "learning_rate": 9.030612244897958e-05,
- "loss": 1.0916,
+ "epoch": 9.72,
+ "learning_rate": 7.784090909090909e-05,
+ "loss": 0.5067,
"step": 860
},
{
- "epoch": 17.42,
- "learning_rate": 9.017857142857143e-05,
- "loss": 1.0912,
+ "epoch": 9.73,
+ "learning_rate": 7.769886363636364e-05,
+ "loss": 0.484,
"step": 861
},
{
- "epoch": 17.44,
- "learning_rate": 9.005102040816327e-05,
- "loss": 1.0875,
+ "epoch": 9.74,
+ "learning_rate": 7.755681818181818e-05,
+ "loss": 0.5029,
"step": 862
},
{
- "epoch": 17.46,
- "learning_rate": 8.99234693877551e-05,
- "loss": 1.05,
+ "epoch": 9.75,
+ "learning_rate": 7.741477272727273e-05,
+ "loss": 0.5077,
"step": 863
},
{
- "epoch": 17.48,
- "learning_rate": 8.979591836734695e-05,
- "loss": 1.1418,
+ "epoch": 9.76,
+ "learning_rate": 7.727272727272727e-05,
+ "loss": 0.5091,
"step": 864
},
{
- "epoch": 17.5,
- "learning_rate": 8.966836734693878e-05,
- "loss": 1.0609,
+ "epoch": 9.77,
+ "learning_rate": 7.713068181818183e-05,
+ "loss": 0.4781,
"step": 865
},
{
- "epoch": 17.52,
- "learning_rate": 8.954081632653062e-05,
- "loss": 1.1611,
+ "epoch": 9.78,
+ "learning_rate": 7.698863636363636e-05,
+ "loss": 0.5124,
"step": 866
},
{
- "epoch": 17.54,
- "learning_rate": 8.941326530612245e-05,
- "loss": 1.1065,
+ "epoch": 9.79,
+ "learning_rate": 7.684659090909091e-05,
+ "loss": 0.4859,
"step": 867
},
{
- "epoch": 17.56,
- "learning_rate": 8.92857142857143e-05,
- "loss": 1.1611,
+ "epoch": 9.81,
+ "learning_rate": 7.670454545454547e-05,
+ "loss": 0.4872,
"step": 868
},
{
- "epoch": 17.58,
- "learning_rate": 8.915816326530613e-05,
- "loss": 1.1398,
+ "epoch": 9.82,
+ "learning_rate": 7.65625e-05,
+ "loss": 0.4675,
"step": 869
},
{
- "epoch": 17.6,
- "learning_rate": 8.903061224489796e-05,
- "loss": 1.1055,
+ "epoch": 9.83,
+ "learning_rate": 7.642045454545454e-05,
+ "loss": 0.5056,
"step": 870
},
{
- "epoch": 17.62,
- "learning_rate": 8.89030612244898e-05,
- "loss": 1.1314,
+ "epoch": 9.84,
+ "learning_rate": 7.62784090909091e-05,
+ "loss": 0.4868,
"step": 871
},
{
- "epoch": 17.64,
- "learning_rate": 8.877551020408164e-05,
- "loss": 1.1084,
+ "epoch": 9.85,
+ "learning_rate": 7.613636363636363e-05,
+ "loss": 0.4907,
"step": 872
},
{
- "epoch": 17.66,
- "learning_rate": 8.864795918367348e-05,
- "loss": 1.1254,
+ "epoch": 9.86,
+ "learning_rate": 7.599431818181818e-05,
+ "loss": 0.474,
"step": 873
},
{
- "epoch": 17.68,
- "learning_rate": 8.852040816326531e-05,
- "loss": 1.142,
+ "epoch": 9.87,
+ "learning_rate": 7.585227272727274e-05,
+ "loss": 0.4813,
"step": 874
},
{
- "epoch": 17.7,
- "learning_rate": 8.839285714285714e-05,
- "loss": 1.1371,
+ "epoch": 9.89,
+ "learning_rate": 7.571022727272727e-05,
+ "loss": 0.4838,
"step": 875
},
{
- "epoch": 17.72,
- "learning_rate": 8.826530612244899e-05,
- "loss": 1.1092,
+ "epoch": 9.9,
+ "learning_rate": 7.556818181818183e-05,
+ "loss": 0.4935,
"step": 876
},
{
- "epoch": 17.75,
- "learning_rate": 8.813775510204082e-05,
- "loss": 1.161,
+ "epoch": 9.91,
+ "learning_rate": 7.542613636363637e-05,
+ "loss": 0.4884,
"step": 877
},
{
- "epoch": 17.77,
- "learning_rate": 8.801020408163265e-05,
- "loss": 1.1044,
+ "epoch": 9.92,
+ "learning_rate": 7.52840909090909e-05,
+ "loss": 0.4797,
"step": 878
},
{
- "epoch": 17.79,
- "learning_rate": 8.788265306122449e-05,
- "loss": 1.117,
+ "epoch": 9.93,
+ "learning_rate": 7.514204545454546e-05,
+ "loss": 0.479,
"step": 879
},
{
- "epoch": 17.81,
- "learning_rate": 8.775510204081632e-05,
- "loss": 1.1262,
+ "epoch": 9.94,
+ "learning_rate": 7.500000000000001e-05,
+ "loss": 0.4727,
"step": 880
},
{
- "epoch": 17.83,
- "learning_rate": 8.762755102040817e-05,
- "loss": 1.0829,
+ "epoch": 9.95,
+ "learning_rate": 7.485795454545454e-05,
+ "loss": 0.4758,
"step": 881
},
{
- "epoch": 17.85,
- "learning_rate": 8.75e-05,
- "loss": 1.1393,
+ "epoch": 9.96,
+ "learning_rate": 7.47159090909091e-05,
+ "loss": 0.482,
"step": 882
},
{
- "epoch": 17.87,
- "learning_rate": 8.737244897959183e-05,
- "loss": 1.1781,
+ "epoch": 9.98,
+ "learning_rate": 7.457386363636364e-05,
+ "loss": 0.4951,
"step": 883
},
{
- "epoch": 17.89,
- "learning_rate": 8.724489795918367e-05,
- "loss": 1.1582,
+ "epoch": 9.99,
+ "learning_rate": 7.443181818181817e-05,
+ "loss": 0.4823,
"step": 884
},
{
- "epoch": 17.91,
- "learning_rate": 8.711734693877552e-05,
- "loss": 1.1469,
+ "epoch": 10.0,
+ "learning_rate": 7.428977272727273e-05,
+ "loss": 0.4638,
"step": 885
},
{
- "epoch": 17.93,
- "learning_rate": 8.698979591836735e-05,
- "loss": 1.1494,
+ "epoch": 10.01,
+ "learning_rate": 7.414772727272728e-05,
+ "loss": 0.4715,
"step": 886
},
{
- "epoch": 17.95,
- "learning_rate": 8.68622448979592e-05,
- "loss": 1.1251,
+ "epoch": 10.02,
+ "learning_rate": 7.400568181818182e-05,
+ "loss": 0.461,
"step": 887
},
{
- "epoch": 17.97,
- "learning_rate": 8.673469387755102e-05,
- "loss": 1.1624,
+ "epoch": 10.03,
+ "learning_rate": 7.386363636363637e-05,
+ "loss": 0.4429,
"step": 888
},
{
- "epoch": 17.99,
- "learning_rate": 8.660714285714287e-05,
- "loss": 1.0842,
+ "epoch": 10.04,
+ "learning_rate": 7.372159090909091e-05,
+ "loss": 0.4403,
"step": 889
},
{
- "epoch": 18.01,
- "learning_rate": 8.64795918367347e-05,
- "loss": 1.1944,
+ "epoch": 10.05,
+ "learning_rate": 7.357954545454546e-05,
+ "loss": 0.4519,
"step": 890
},
{
- "epoch": 18.03,
- "learning_rate": 8.635204081632653e-05,
- "loss": 1.0642,
+ "epoch": 10.07,
+ "learning_rate": 7.34375e-05,
+ "loss": 0.4611,
"step": 891
},
{
- "epoch": 18.05,
- "learning_rate": 8.622448979591838e-05,
- "loss": 1.0459,
+ "epoch": 10.08,
+ "learning_rate": 7.329545454545455e-05,
+ "loss": 0.4543,
"step": 892
},
{
- "epoch": 18.07,
- "learning_rate": 8.60969387755102e-05,
- "loss": 1.0941,
+ "epoch": 10.09,
+ "learning_rate": 7.315340909090909e-05,
+ "loss": 0.4528,
"step": 893
},
{
- "epoch": 18.09,
- "learning_rate": 8.596938775510205e-05,
- "loss": 1.0457,
+ "epoch": 10.1,
+ "learning_rate": 7.301136363636364e-05,
+ "loss": 0.4586,
"step": 894
},
{
- "epoch": 18.11,
- "learning_rate": 8.584183673469388e-05,
- "loss": 1.1033,
+ "epoch": 10.11,
+ "learning_rate": 7.286931818181818e-05,
+ "loss": 0.4418,
"step": 895
},
{
- "epoch": 18.13,
- "learning_rate": 8.571428571428571e-05,
- "loss": 1.0756,
+ "epoch": 10.12,
+ "learning_rate": 7.272727272727273e-05,
+ "loss": 0.4435,
"step": 896
},
{
- "epoch": 18.15,
- "learning_rate": 8.558673469387756e-05,
- "loss": 1.0615,
+ "epoch": 10.13,
+ "learning_rate": 7.258522727272727e-05,
+ "loss": 0.44,
"step": 897
},
{
- "epoch": 18.17,
- "learning_rate": 8.545918367346939e-05,
- "loss": 1.0828,
+ "epoch": 10.15,
+ "learning_rate": 7.244318181818183e-05,
+ "loss": 0.4589,
"step": 898
},
{
- "epoch": 18.19,
- "learning_rate": 8.533163265306123e-05,
- "loss": 1.1158,
+ "epoch": 10.16,
+ "learning_rate": 7.230113636363636e-05,
+ "loss": 0.4597,
"step": 899
},
{
- "epoch": 18.21,
- "learning_rate": 8.520408163265306e-05,
- "loss": 1.0133,
+ "epoch": 10.17,
+ "learning_rate": 7.215909090909091e-05,
+ "loss": 0.4479,
"step": 900
}
],
"logging_steps": 1,
- "max_steps": 1568,
- "num_train_epochs": 32,
+ "max_steps": 1408,
+ "num_train_epochs": 16,
"save_steps": 100,
- "total_flos": 1.3323843726343987e+18,
+ "total_flos": 1.227986631604562e+18,
"trial_name": null,
"trial_params": null
}
diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin
index db23e07d097c18532e52f58a70eb72d22e39c8c1..ee7ddb867f05d9a969f71467a8eb88994865cf51 100644
--- a/checkpoint-900/training_args.bin
+++ b/checkpoint-900/training_args.bin
@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
-oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
+oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
size 4155
diff --git a/runs/Sep07_21-11-43_ThanhHa/events.out.tfevents.1694095915.ThanhHa.394731.0 b/runs/Sep07_21-11-43_ThanhHa/events.out.tfevents.1694095915.ThanhHa.394731.0
new file mode 100644
index 0000000000000000000000000000000000000000..ce803b244499d000f6f744c31af2b7cb7f2cc5c1
--- /dev/null
+++ b/runs/Sep07_21-11-43_ThanhHa/events.out.tfevents.1694095915.ThanhHa.394731.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8dad27dbe334a581ee472196ecf556186455fd7c690be38598bc5204a7e336e
+size 5116
diff --git a/runs/Sep07_22-33-24_ThanhHa/events.out.tfevents.1694100814.ThanhHa.395502.0 b/runs/Sep07_22-33-24_ThanhHa/events.out.tfevents.1694100814.ThanhHa.395502.0
new file mode 100644
index 0000000000000000000000000000000000000000..2748866b8ad3129f0bc47e506541af1618637c3c
--- /dev/null
+++ b/runs/Sep07_22-33-24_ThanhHa/events.out.tfevents.1694100814.ThanhHa.395502.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87710e6aaeb17305070659ecc60eaf6bfd088ebccd3ca76cf841c30caf34b61
+size 225837