Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f91dc90f8a962de8a6f5d1f41852f156640af3d323856255e77ff35217bdb85f
+oid sha256:3a1c094e2b04c46c936a656de7835e85dbcf14183993b0c8bbe0411df903641f
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30dc0fc034e8e9d69cafd1f35008e0eec7c67338d72086921b094e81428d1919
+oid sha256:c1a989b37f527b2146802ecf1b0048cb62f261e022e387637a7fbfd210017c65
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c5f8ae8f35749de87d2bd30935015b688486235dbb0f9456f760d9020e6969
+oid sha256:c1e600d3f88008e73276d99a5b1120d15a4881ba5b50d66a82ac22c9b9e451d1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f6a4bc06789ee291aef58cb4310eddbcbfcda6bb9367569ae98777fc564406
+oid sha256:7a5239f249d81d8bfa06ef3de4b500e1ac939798a7dbf67fabb6fdf26f4f0286
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33fc9c99d6c6914158d280cc7ea9921d8a41ab7b750ccff6664687352e5ce95
+oid sha256:4d3fb3c75839ecf6ed308f90b9c2940bd609f26e633ef816e3b4989d2302e7d3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2a7fd3c6d658555e61566a198ddf405855c17c7c224c221ab28f490366dfaf
+oid sha256:fdd14640f5eeb90ec4e386c79cd20d4ed3e7b6616d7a4070b600d64580c4eace
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2043055295944214,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12876227265411236,
+  "best_metric": 1.1305104494094849,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2575245453082247,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 12.308,
       "eval_steps_per_second": 3.2,
       "step": 25
+    },
+    {
+      "epoch": 0.13391276356027684,
+      "grad_norm": 0.6668666005134583,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 1.4982,
+      "step": 26
+    },
+    {
+      "epoch": 0.13906325446644133,
+      "grad_norm": 0.6831625699996948,
+      "learning_rate": 7.75e-05,
+      "loss": 1.3068,
+      "step": 27
+    },
+    {
+      "epoch": 0.14421374537260584,
+      "grad_norm": 0.654782772064209,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 1.3077,
+      "step": 28
+    },
+    {
+      "epoch": 0.14936423627877032,
+      "grad_norm": 0.6191349625587463,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 1.3137,
+      "step": 29
+    },
+    {
+      "epoch": 0.1545147271849348,
+      "grad_norm": 0.6687305569648743,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 1.1626,
+      "step": 30
+    },
+    {
+      "epoch": 0.15966521809109932,
+      "grad_norm": 0.7296125888824463,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 1.1292,
+      "step": 31
+    },
+    {
+      "epoch": 0.1648157089972638,
+      "grad_norm": 0.7525869607925415,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 1.0622,
+      "step": 32
+    },
+    {
+      "epoch": 0.1699661999034283,
+      "grad_norm": 0.7842842936515808,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 1.0998,
+      "step": 33
+    },
+    {
+      "epoch": 0.1751166908095928,
+      "grad_norm": 0.7670237421989441,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 1.0795,
+      "step": 34
+    },
+    {
+      "epoch": 0.18026718171575729,
+      "grad_norm": 0.8848092555999756,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 1.0421,
+      "step": 35
+    },
+    {
+      "epoch": 0.18541767262192177,
+      "grad_norm": 0.9541935324668884,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.9614,
+      "step": 36
+    },
+    {
+      "epoch": 0.19056816352808628,
+      "grad_norm": 0.9986409544944763,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.9052,
+      "step": 37
+    },
+    {
+      "epoch": 0.19571865443425077,
+      "grad_norm": 0.7817866206169128,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 1.4343,
+      "step": 38
+    },
+    {
+      "epoch": 0.20086914534041525,
+      "grad_norm": 0.632110059261322,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.3297,
+      "step": 39
+    },
+    {
+      "epoch": 0.20601963624657976,
+      "grad_norm": 0.5873474478721619,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 1.225,
+      "step": 40
+    },
+    {
+      "epoch": 0.21117012715274425,
+      "grad_norm": 0.5888330936431885,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 1.2015,
+      "step": 41
+    },
+    {
+      "epoch": 0.21632061805890873,
+      "grad_norm": 0.6649183034896851,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.1975,
+      "step": 42
+    },
+    {
+      "epoch": 0.22147110896507324,
+      "grad_norm": 0.7081603407859802,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 1.1672,
+      "step": 43
+    },
+    {
+      "epoch": 0.22662159987123773,
+      "grad_norm": 0.7628908753395081,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 1.1333,
+      "step": 44
+    },
+    {
+      "epoch": 0.2317720907774022,
+      "grad_norm": 0.699059009552002,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1043,
+      "step": 45
+    },
+    {
+      "epoch": 0.23692258168356672,
+      "grad_norm": 0.7549357414245605,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 1.0802,
+      "step": 46
+    },
+    {
+      "epoch": 0.2420730725897312,
+      "grad_norm": 0.7739465236663818,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 1.0429,
+      "step": 47
+    },
+    {
+      "epoch": 0.2472235634958957,
+      "grad_norm": 0.8181856274604797,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8891,
+      "step": 48
+    },
+    {
+      "epoch": 0.2523740544020602,
+      "grad_norm": 0.9725480079650879,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.9871,
+      "step": 49
+    },
+    {
+      "epoch": 0.2575245453082247,
+      "grad_norm": 1.2461752891540527,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.8804,
+      "step": 50
+    },
+    {
+      "epoch": 0.2575245453082247,
+      "eval_loss": 1.1305104494094849,
+      "eval_runtime": 4.0432,
+      "eval_samples_per_second": 12.366,
+      "eval_steps_per_second": 3.215,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null