Upload 11 files

README.md

@@ -1,6 +1,6 @@
 ---
-library_name: transformers
-tags: []
+library_name: peft
+base_model: HuggingFaceH4/zephyr-7b-beta
 ---
 
 # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -199,3 +199,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 
 
+### Framework versions
+
+- PEFT 0.8.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d847eb69a109a3e1cd845266fa98a2f461b1fed3970bc724941001827ac6c987
+size 83945296

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0dcf4353783649e62ad9299f6e0b30f9ad36ff6f3c404c698af35adb47d101f
+size 42545748

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf06c45b970b1b34ce67cb8828e0263cbda8e0df2dbecb2fed56e0fe0cd196eb
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8302adb20f41877642052256f1e499f9f7b40f090024c7b3f17e305006028513
+size 1064

special_tokens_map.json

@@ -18,7 +18,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -37,15 +37,12 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "max_length": 1024,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
   "truncation_side": "left",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": true
 }

trainer_state.json

@@ -0,0 +1,1341 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.036697247706422,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019919156561236823,
+      "loss": 2.1538,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019835812809934576,
+      "loss": 2.1787,
+      "step": 2
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001975246905863233,
+      "loss": 1.769,
+      "step": 3
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019669125307330082,
+      "loss": 1.4897,
+      "step": 4
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019585781556027837,
+      "loss": 1.3456,
+      "step": 5
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001950243780472559,
+      "loss": 1.3128,
+      "step": 6
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019419094053423346,
+      "loss": 1.1232,
+      "step": 7
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000193357503021211,
+      "loss": 1.0925,
+      "step": 8
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019252406550818854,
+      "loss": 0.9432,
+      "step": 9
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019169062799516607,
+      "loss": 1.1487,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001908571904821436,
+      "loss": 0.8783,
+      "step": 11
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019002375296912116,
+      "loss": 1.0987,
+      "step": 12
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00018919031545609868,
+      "loss": 1.1263,
+      "step": 13
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00018835687794307624,
+      "loss": 1.0026,
+      "step": 14
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018752344043005377,
+      "loss": 0.9925,
+      "step": 15
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018669000291703133,
+      "loss": 0.9272,
+      "step": 16
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00018585656540400885,
+      "loss": 1.1142,
+      "step": 17
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00018502312789098638,
+      "loss": 0.8863,
+      "step": 18
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001841896903779639,
+      "loss": 1.4011,
+      "step": 19
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00018335625286494147,
+      "loss": 1.1558,
+      "step": 20
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.000182522815351919,
+      "loss": 1.1528,
+      "step": 21
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00018168937783889655,
+      "loss": 0.9246,
+      "step": 22
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00018085594032587408,
+      "loss": 0.8869,
+      "step": 23
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00018002250281285164,
+      "loss": 0.9948,
+      "step": 24
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00017918906529982914,
+      "loss": 1.1422,
+      "step": 25
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0001783556277868067,
+      "loss": 1.0643,
+      "step": 26
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00017752219027378422,
+      "loss": 1.0188,
+      "step": 27
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00017668875276076178,
+      "loss": 1.2852,
+      "step": 28
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0001758553152477393,
+      "loss": 1.1224,
+      "step": 29
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00017502187773471686,
+      "loss": 0.9911,
+      "step": 30
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0001741884402216944,
+      "loss": 1.0483,
+      "step": 31
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00017335500270867192,
+      "loss": 1.0113,
+      "step": 32
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00017252156519564945,
+      "loss": 0.9042,
+      "step": 33
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.000171688127682627,
+      "loss": 0.747,
+      "step": 34
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017085469016960453,
+      "loss": 1.0973,
+      "step": 35
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001700212526565821,
+      "loss": 1.2896,
+      "step": 36
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00016918781514355962,
+      "loss": 0.7344,
+      "step": 37
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00016835437763053717,
+      "loss": 1.1291,
+      "step": 38
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001675209401175147,
+      "loss": 0.9825,
+      "step": 39
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00016668750260449223,
+      "loss": 1.1524,
+      "step": 40
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016585406509146976,
+      "loss": 0.8895,
+      "step": 41
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016502062757844731,
+      "loss": 0.8906,
+      "step": 42
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016418719006542484,
+      "loss": 0.9501,
+      "step": 43
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0001633537525524024,
+      "loss": 1.215,
+      "step": 44
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00016252031503937993,
+      "loss": 1.1934,
+      "step": 45
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016168687752635748,
+      "loss": 1.138,
+      "step": 46
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.000160853440013335,
+      "loss": 1.147,
+      "step": 47
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016002000250031254,
+      "loss": 1.1176,
+      "step": 48
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015918656498729007,
+      "loss": 1.2923,
+      "step": 49
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015835312747426763,
+      "loss": 0.6327,
+      "step": 50
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015751968996124515,
+      "loss": 1.1538,
+      "step": 51
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001566862524482227,
+      "loss": 0.9916,
+      "step": 52
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015585281493520024,
+      "loss": 1.088,
+      "step": 53
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015501937742217777,
+      "loss": 1.1032,
+      "step": 54
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00015418593990915532,
+      "loss": 0.9807,
+      "step": 55
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00015335250239613285,
+      "loss": 0.992,
+      "step": 56
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001525190648831104,
+      "loss": 0.8244,
+      "step": 57
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00015168562737008794,
+      "loss": 0.6069,
+      "step": 58
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0001508521898570655,
+      "loss": 0.5618,
+      "step": 59
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00015001875234404302,
+      "loss": 0.7973,
+      "step": 60
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00014918531483102055,
+      "loss": 0.7905,
+      "step": 61
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00014835187731799808,
+      "loss": 0.557,
+      "step": 62
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00014751843980497563,
+      "loss": 0.5413,
+      "step": 63
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00014668500229195316,
+      "loss": 0.5814,
+      "step": 64
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00014585156477893072,
+      "loss": 0.4426,
+      "step": 65
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00014501812726590825,
+      "loss": 0.962,
+      "step": 66
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0001441846897528858,
+      "loss": 0.6668,
+      "step": 67
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00014335125223986333,
+      "loss": 0.5324,
+      "step": 68
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00014251781472684086,
+      "loss": 0.5355,
+      "step": 69
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0001416843772138184,
+      "loss": 0.8187,
+      "step": 70
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014085093970079594,
+      "loss": 0.8092,
+      "step": 71
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00014001750218777347,
+      "loss": 0.5255,
+      "step": 72
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013918406467475103,
+      "loss": 0.4591,
+      "step": 73
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013835062716172856,
+      "loss": 0.9451,
+      "step": 74
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00013751718964870611,
+      "loss": 1.0429,
+      "step": 75
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00013668375213568364,
+      "loss": 0.9241,
+      "step": 76
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00013585031462266117,
+      "loss": 0.8724,
+      "step": 77
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0001350168771096387,
+      "loss": 0.5596,
+      "step": 78
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00013418343959661626,
+      "loss": 0.8192,
+      "step": 79
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00013335000208359378,
+      "loss": 0.9415,
+      "step": 80
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00013251656457057134,
+      "loss": 0.739,
+      "step": 81
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00013168312705754887,
+      "loss": 0.8788,
+      "step": 82
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0001308496895445264,
+      "loss": 0.6318,
+      "step": 83
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00013001625203150393,
+      "loss": 0.5367,
+      "step": 84
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00012918281451848148,
+      "loss": 0.7263,
+      "step": 85
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.000128349377005459,
+      "loss": 0.9614,
+      "step": 86
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00012751593949243657,
+      "loss": 0.8175,
+      "step": 87
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0001266825019794141,
+      "loss": 0.7122,
+      "step": 88
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00012584906446639165,
+      "loss": 0.5881,
+      "step": 89
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00012501562695336918,
+      "loss": 0.7257,
+      "step": 90
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001241821894403467,
+      "loss": 0.7989,
+      "step": 91
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00012334875192732424,
+      "loss": 0.6186,
+      "step": 92
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.0001225153144143018,
+      "loss": 0.3911,
+      "step": 93
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00012168187690127932,
+      "loss": 0.5717,
+      "step": 94
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00012084843938825688,
+      "loss": 0.6305,
+      "step": 95
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0001200150018752344,
+      "loss": 0.6012,
+      "step": 96
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00011918156436221195,
+      "loss": 0.7495,
+      "step": 97
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00011834812684918948,
+      "loss": 0.7502,
+      "step": 98
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00011751468933616703,
+      "loss": 0.85,
+      "step": 99
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00011668125182314456,
+      "loss": 0.604,
+      "step": 100
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0001158478143101221,
+      "loss": 0.9405,
+      "step": 101
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00011501437679709966,
+      "loss": 0.4737,
+      "step": 102
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00011418093928407719,
+      "loss": 0.8025,
+      "step": 103
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00011334750177105473,
+      "loss": 0.7759,
+      "step": 104
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00011251406425803226,
+      "loss": 0.7529,
+      "step": 105
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00011168062674500981,
+      "loss": 0.6858,
+      "step": 106
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00011084718923198733,
+      "loss": 0.8112,
+      "step": 107
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00011001375171896489,
+      "loss": 0.6097,
+      "step": 108
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00010918031420594241,
+      "loss": 0.7296,
+      "step": 109
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.00010834687669291996,
+      "loss": 0.5612,
+      "step": 110
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.00010751343917989749,
+      "loss": 0.4,
+      "step": 111
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00010668000166687504,
+      "loss": 0.3471,
+      "step": 112
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00010584656415385257,
+      "loss": 0.5078,
+      "step": 113
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00010501312664083011,
+      "loss": 0.2617,
+      "step": 114
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00010417968912780764,
+      "loss": 0.4909,
+      "step": 115
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0001033462516147852,
+      "loss": 0.4184,
+      "step": 116
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00010251281410176273,
+      "loss": 0.2669,
+      "step": 117
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.00010167937658874027,
+      "loss": 0.3185,
+      "step": 118
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.0001008459390757178,
+      "loss": 0.4198,
+      "step": 119
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.00010001250156269535,
+      "loss": 0.3946,
+      "step": 120
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 9.917906404967288e-05,
+      "loss": 0.3378,
+      "step": 121
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 9.834562653665041e-05,
+      "loss": 0.287,
+      "step": 122
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 9.751218902362795e-05,
+      "loss": 0.2577,
+      "step": 123
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 9.66787515106055e-05,
+      "loss": 0.3326,
+      "step": 124
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 9.584531399758304e-05,
+      "loss": 0.3724,
+      "step": 125
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 9.501187648456058e-05,
+      "loss": 0.1924,
+      "step": 126
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 9.417843897153812e-05,
+      "loss": 0.2683,
+      "step": 127
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 9.334500145851566e-05,
+      "loss": 0.368,
+      "step": 128
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 9.251156394549319e-05,
+      "loss": 0.3479,
+      "step": 129
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 9.167812643247073e-05,
+      "loss": 0.4842,
+      "step": 130
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 9.084468891944828e-05,
+      "loss": 0.404,
+      "step": 131
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 9.001125140642582e-05,
+      "loss": 0.5347,
+      "step": 132
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.917781389340335e-05,
+      "loss": 0.1655,
+      "step": 133
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 8.834437638038089e-05,
+      "loss": 0.3897,
+      "step": 134
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.751093886735843e-05,
+      "loss": 0.4423,
+      "step": 135
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.667750135433596e-05,
+      "loss": 0.5997,
+      "step": 136
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 8.58440638413135e-05,
+      "loss": 0.4646,
+      "step": 137
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 8.501062632829104e-05,
+      "loss": 0.3572,
+      "step": 138
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 8.417718881526859e-05,
+      "loss": 0.1949,
+      "step": 139
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 8.334375130224612e-05,
+      "loss": 0.2445,
+      "step": 140
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 8.251031378922366e-05,
+      "loss": 0.1282,
+      "step": 141
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.16768762762012e-05,
+      "loss": 0.3019,
+      "step": 142
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.084343876317874e-05,
+      "loss": 0.5425,
+      "step": 143
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 8.001000125015627e-05,
+      "loss": 0.2889,
+      "step": 144
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 7.917656373713381e-05,
+      "loss": 0.5389,
+      "step": 145
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 7.834312622411136e-05,
+      "loss": 0.3105,
+      "step": 146
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 7.750968871108888e-05,
+      "loss": 0.2775,
+      "step": 147
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 7.667625119806643e-05,
+      "loss": 0.2566,
+      "step": 148
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 7.584281368504397e-05,
+      "loss": 0.4733,
+      "step": 149
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 7.500937617202151e-05,
+      "loss": 0.5824,
+      "step": 150
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 7.417593865899904e-05,
+      "loss": 0.4396,
+      "step": 151
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 7.334250114597658e-05,
+      "loss": 0.3624,
+      "step": 152
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.250906363295412e-05,
+      "loss": 0.3028,
+      "step": 153
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 7.167562611993167e-05,
+      "loss": 0.4637,
+      "step": 154
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 7.08421886069092e-05,
+      "loss": 0.4665,
+      "step": 155
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 7.000875109388674e-05,
+      "loss": 0.395,
+      "step": 156
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 6.917531358086428e-05,
+      "loss": 0.349,
+      "step": 157
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 6.834187606784182e-05,
+      "loss": 0.308,
+      "step": 158
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 6.750843855481935e-05,
+      "loss": 0.3379,
+      "step": 159
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 6.667500104179689e-05,
+      "loss": 0.3393,
+      "step": 160
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 6.584156352877443e-05,
+      "loss": 0.265,
+      "step": 161
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 6.500812601575196e-05,
+      "loss": 0.3515,
+      "step": 162
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 6.41746885027295e-05,
+      "loss": 0.3806,
+      "step": 163
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 6.334125098970705e-05,
+      "loss": 0.1495,
+      "step": 164
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 6.250781347668459e-05,
+      "loss": 0.1339,
+      "step": 165
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 6.167437596366212e-05,
+      "loss": 0.1661,
+      "step": 166
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 6.084093845063966e-05,
+      "loss": 0.1169,
+      "step": 167
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 6.00075009376172e-05,
+      "loss": 0.1587,
+      "step": 168
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 5.917406342459474e-05,
+      "loss": 0.1224,
+      "step": 169
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 5.834062591157228e-05,
+      "loss": 0.1495,
+      "step": 170
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 5.750718839854983e-05,
+      "loss": 0.1137,
+      "step": 171
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 5.6673750885527365e-05,
+      "loss": 0.1997,
+      "step": 172
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 5.584031337250491e-05,
+      "loss": 0.1012,
+      "step": 173
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 5.500687585948244e-05,
+      "loss": 0.0897,
+      "step": 174
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 5.417343834645998e-05,
+      "loss": 0.0843,
+      "step": 175
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 5.334000083343752e-05,
+      "loss": 0.1603,
+      "step": 176
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 5.2506563320415056e-05,
+      "loss": 0.1169,
+      "step": 177
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 5.16731258073926e-05,
+      "loss": 0.0993,
+      "step": 178
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 5.0839688294370134e-05,
+      "loss": 0.1018,
+      "step": 179
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 5.0006250781347676e-05,
+      "loss": 0.1279,
+      "step": 180
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 4.9172813268325205e-05,
+      "loss": 0.27,
+      "step": 181
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 4.833937575530275e-05,
+      "loss": 0.2169,
+      "step": 182
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 4.750593824228029e-05,
+      "loss": 0.0919,
+      "step": 183
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 4.667250072925783e-05,
+      "loss": 0.1618,
+      "step": 184
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 4.583906321623537e-05,
+      "loss": 0.0735,
+      "step": 185
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 4.500562570321291e-05,
+      "loss": 0.0924,
+      "step": 186
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 4.4172188190190444e-05,
+      "loss": 0.1398,
+      "step": 187
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 4.333875067716798e-05,
+      "loss": 0.3616,
+      "step": 188
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 4.250531316414552e-05,
+      "loss": 0.2796,
+      "step": 189
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 4.167187565112306e-05,
+      "loss": 0.1794,
+      "step": 190
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 4.08384381381006e-05,
+      "loss": 0.2183,
+      "step": 191
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 4.0005000625078135e-05,
+      "loss": 0.2381,
+      "step": 192
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 3.917156311205568e-05,
+      "loss": 0.1094,
+      "step": 193
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 3.833812559903321e-05,
+      "loss": 0.1113,
+      "step": 194
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 3.7504688086010755e-05,
+      "loss": 0.1681,
+      "step": 195
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 3.667125057298829e-05,
+      "loss": 0.1226,
+      "step": 196
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 3.583781305996583e-05,
+      "loss": 0.2821,
+      "step": 197
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 3.500437554694337e-05,
+      "loss": 0.1742,
+      "step": 198
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 3.417093803392091e-05,
+      "loss": 0.289,
+      "step": 199
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 3.3337500520898446e-05,
+      "loss": 0.2191,
+      "step": 200
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 3.250406300787598e-05,
+      "loss": 0.1286,
+      "step": 201
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 3.1670625494853524e-05,
+      "loss": 0.2275,
+      "step": 202
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 3.083718798183106e-05,
+      "loss": 0.0647,
+      "step": 203
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 3.00037504688086e-05,
+      "loss": 0.0477,
+      "step": 204
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 2.917031295578614e-05,
+      "loss": 0.2203,
+      "step": 205
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 2.8336875442763683e-05,
+      "loss": 0.2017,
+      "step": 206
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 2.750343792974122e-05,
+      "loss": 0.1703,
+      "step": 207
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 2.667000041671876e-05,
+      "loss": 0.2045,
+      "step": 208
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 2.58365629036963e-05,
+      "loss": 0.0735,
+      "step": 209
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 2.5003125390673838e-05,
+      "loss": 0.143,
+      "step": 210
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 2.4169687877651373e-05,
+      "loss": 0.0957,
+      "step": 211
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 2.3336250364628916e-05,
+      "loss": 0.1068,
+      "step": 212
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 2.2502812851606454e-05,
+      "loss": 0.0779,
+      "step": 213
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 2.166937533858399e-05,
+      "loss": 0.1485,
+      "step": 214
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 2.083593782556153e-05,
+      "loss": 0.1665,
+      "step": 215
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 2.0002500312539068e-05,
+      "loss": 0.1002,
+      "step": 216
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 1.9169062799516606e-05,
+      "loss": 0.0731,
+      "step": 217
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.8335625286494145e-05,
+      "loss": 0.2159,
+      "step": 218
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 1.7502187773471684e-05,
+      "loss": 0.1446,
+      "step": 219
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 1.6668750260449223e-05,
+      "loss": 0.0548,
+      "step": 220
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 20,
+  "total_flos": 1.3658971558649856e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10cfd8ac7249b8abeb2bceefc2d27974994b55b14acfc08d30d5cdb9efb4510
+size 4728