Upload folder using huggingface_hub
Browse files- config.json +41 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +22 -0
- trainer_state.json +264 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2ForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"pad_token_id": 50256,
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.41.0.dev0",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50257
|
| 41 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03ad4d3c36b30ea779ce2a00be7ffea543c41572d0e3c85cfa80ecb86bcb186b
|
| 3 |
+
size 497780432
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22181c35a2f8a8976a47fd4240afc4ac392c92eb5f56689cfcf47c47112670b6
|
| 3 |
+
size 995655418
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:274edf35094f5a78c0709426ae762cb9979cfeff651d6a83a2f34d3ddd22a79f
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07cf3914a0923df4c893345ef16e6e0f0c85968dbc9f712fc0f0f27a9e6563bc
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
+
"clean_up_tokenization_spaces": true,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"model_max_length": 1024,
|
| 19 |
+
"pad_token": "<|endoftext|>",
|
| 20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
+
"unk_token": "<|endoftext|>"
|
| 22 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,264 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.932811944543192,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 16500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08887308922858159,
|
| 13 |
+
"grad_norm": 20.37746810913086,
|
| 14 |
+
"learning_rate": 4.851878184619031e-05,
|
| 15 |
+
"loss": 0.6617,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.17774617845716317,
|
| 20 |
+
"grad_norm": 8.832418441772461,
|
| 21 |
+
"learning_rate": 4.703756369238061e-05,
|
| 22 |
+
"loss": 0.5007,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.26661926768574473,
|
| 27 |
+
"grad_norm": 112.71693420410156,
|
| 28 |
+
"learning_rate": 4.555634553857092e-05,
|
| 29 |
+
"loss": 0.4867,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.35549235691432635,
|
| 34 |
+
"grad_norm": 0.7494603991508484,
|
| 35 |
+
"learning_rate": 4.407512738476123e-05,
|
| 36 |
+
"loss": 0.5113,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4443654461429079,
|
| 41 |
+
"grad_norm": 0.5181692838668823,
|
| 42 |
+
"learning_rate": 4.259390923095153e-05,
|
| 43 |
+
"loss": 0.557,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5332385353714895,
|
| 48 |
+
"grad_norm": 0.8127353191375732,
|
| 49 |
+
"learning_rate": 4.1112691077141844e-05,
|
| 50 |
+
"loss": 0.4746,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6221116246000711,
|
| 55 |
+
"grad_norm": 52.21469497680664,
|
| 56 |
+
"learning_rate": 3.9631472923332156e-05,
|
| 57 |
+
"loss": 0.4848,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7109847138286527,
|
| 62 |
+
"grad_norm": 3.922440767288208,
|
| 63 |
+
"learning_rate": 3.815025476952246e-05,
|
| 64 |
+
"loss": 0.4689,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7998578030572343,
|
| 69 |
+
"grad_norm": 39.936492919921875,
|
| 70 |
+
"learning_rate": 3.6669036615712765e-05,
|
| 71 |
+
"loss": 0.4724,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8887308922858158,
|
| 76 |
+
"grad_norm": 3.033518075942993,
|
| 77 |
+
"learning_rate": 3.518781846190307e-05,
|
| 78 |
+
"loss": 0.4384,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.9776039815143974,
|
| 83 |
+
"grad_norm": 8.464579582214355,
|
| 84 |
+
"learning_rate": 3.370660030809338e-05,
|
| 85 |
+
"loss": 0.4534,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.066477070742979,
|
| 90 |
+
"grad_norm": 0.24204222857952118,
|
| 91 |
+
"learning_rate": 3.2225382154283686e-05,
|
| 92 |
+
"loss": 0.3978,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.1553501599715605,
|
| 97 |
+
"grad_norm": 0.057052597403526306,
|
| 98 |
+
"learning_rate": 3.074416400047399e-05,
|
| 99 |
+
"loss": 0.3852,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.2442232492001422,
|
| 104 |
+
"grad_norm": 0.15880955755710602,
|
| 105 |
+
"learning_rate": 2.92629458466643e-05,
|
| 106 |
+
"loss": 0.3915,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.3330963384287238,
|
| 111 |
+
"grad_norm": 0.09902948141098022,
|
| 112 |
+
"learning_rate": 2.7781727692854603e-05,
|
| 113 |
+
"loss": 0.3785,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.4219694276573054,
|
| 118 |
+
"grad_norm": 0.15144290030002594,
|
| 119 |
+
"learning_rate": 2.6300509539044908e-05,
|
| 120 |
+
"loss": 0.3587,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.510842516885887,
|
| 125 |
+
"grad_norm": 0.22604715824127197,
|
| 126 |
+
"learning_rate": 2.481929138523522e-05,
|
| 127 |
+
"loss": 0.3811,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.5997156061144686,
|
| 132 |
+
"grad_norm": 14.215106964111328,
|
| 133 |
+
"learning_rate": 2.3338073231425524e-05,
|
| 134 |
+
"loss": 0.3591,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.68858869534305,
|
| 139 |
+
"grad_norm": 0.2168210744857788,
|
| 140 |
+
"learning_rate": 2.1856855077615832e-05,
|
| 141 |
+
"loss": 0.37,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.7774617845716318,
|
| 146 |
+
"grad_norm": 0.15380479395389557,
|
| 147 |
+
"learning_rate": 2.0375636923806137e-05,
|
| 148 |
+
"loss": 0.3492,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.8663348738002132,
|
| 153 |
+
"grad_norm": 0.09666112810373306,
|
| 154 |
+
"learning_rate": 1.889441876999645e-05,
|
| 155 |
+
"loss": 0.3922,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.9552079630287948,
|
| 160 |
+
"grad_norm": 0.7467890381813049,
|
| 161 |
+
"learning_rate": 1.7413200616186753e-05,
|
| 162 |
+
"loss": 0.3786,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.0440810522573765,
|
| 167 |
+
"grad_norm": 1.9722317457199097,
|
| 168 |
+
"learning_rate": 1.593198246237706e-05,
|
| 169 |
+
"loss": 0.3258,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.132954141485958,
|
| 174 |
+
"grad_norm": 0.07470700144767761,
|
| 175 |
+
"learning_rate": 1.4450764308567366e-05,
|
| 176 |
+
"loss": 0.2807,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.2218272307145397,
|
| 181 |
+
"grad_norm": 0.11256339401006699,
|
| 182 |
+
"learning_rate": 1.2969546154757672e-05,
|
| 183 |
+
"loss": 0.2751,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.310700319943121,
|
| 188 |
+
"grad_norm": 0.010098825208842754,
|
| 189 |
+
"learning_rate": 1.148832800094798e-05,
|
| 190 |
+
"loss": 0.2385,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.399573409171703,
|
| 195 |
+
"grad_norm": 0.15252766013145447,
|
| 196 |
+
"learning_rate": 1.0007109847138287e-05,
|
| 197 |
+
"loss": 0.2379,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.4884464984002843,
|
| 202 |
+
"grad_norm": 17.05082130432129,
|
| 203 |
+
"learning_rate": 8.525891693328595e-06,
|
| 204 |
+
"loss": 0.2706,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.5773195876288657,
|
| 209 |
+
"grad_norm": 0.11130794882774353,
|
| 210 |
+
"learning_rate": 7.0446735395189e-06,
|
| 211 |
+
"loss": 0.2591,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.6661926768574475,
|
| 216 |
+
"grad_norm": 74.68379974365234,
|
| 217 |
+
"learning_rate": 5.5634553857092076e-06,
|
| 218 |
+
"loss": 0.3314,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.7550657660860294,
|
| 223 |
+
"grad_norm": 15.91612434387207,
|
| 224 |
+
"learning_rate": 4.082237231899514e-06,
|
| 225 |
+
"loss": 0.2514,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.8439388553146108,
|
| 230 |
+
"grad_norm": 39.0718994140625,
|
| 231 |
+
"learning_rate": 2.601019078089821e-06,
|
| 232 |
+
"loss": 0.2358,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.932811944543192,
|
| 237 |
+
"grad_norm": 0.09988761693239212,
|
| 238 |
+
"learning_rate": 1.119800924280128e-06,
|
| 239 |
+
"loss": 0.2359,
|
| 240 |
+
"step": 16500
|
| 241 |
+
}
|
| 242 |
+
],
|
| 243 |
+
"logging_steps": 500,
|
| 244 |
+
"max_steps": 16878,
|
| 245 |
+
"num_input_tokens_seen": 0,
|
| 246 |
+
"num_train_epochs": 3,
|
| 247 |
+
"save_steps": 500,
|
| 248 |
+
"stateful_callbacks": {
|
| 249 |
+
"TrainerControl": {
|
| 250 |
+
"args": {
|
| 251 |
+
"should_epoch_stop": false,
|
| 252 |
+
"should_evaluate": false,
|
| 253 |
+
"should_log": false,
|
| 254 |
+
"should_save": true,
|
| 255 |
+
"should_training_stop": false
|
| 256 |
+
},
|
| 257 |
+
"attributes": {}
|
| 258 |
+
}
|
| 259 |
+
},
|
| 260 |
+
"total_flos": 4794112531464192.0,
|
| 261 |
+
"train_batch_size": 4,
|
| 262 |
+
"trial_name": null,
|
| 263 |
+
"trial_params": null
|
| 264 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:decd70813cd1d25be95943523f9ca0fe7732aafbad87e520c71e254d1c50ae26
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|