Edison
commited on
Commit
•
abff96a
1
Parent(s):
56a45a6
Model save
Browse files- .gitignore +1 -0
- config.json +24 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- trainer_state.json +305 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForMaskedLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"qa_dropout": 0.1,
|
| 18 |
+
"seq_classif_dropout": 0.2,
|
| 19 |
+
"sinusoidal_pos_embds": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.30.2",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a89317cbaa443606c792e797e7d08103e6632157c5f521f6ec65c9a38d0b32fb
|
| 3 |
+
size 267978033
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 7660,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 1.9878163251157847e-05,
|
| 13 |
+
"loss": 2.5054,
|
| 14 |
+
"step": 383
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 2.3042960166931152,
|
| 19 |
+
"eval_runtime": 6.5074,
|
| 20 |
+
"eval_samples_per_second": 941.694,
|
| 21 |
+
"eval_steps_per_second": 14.752,
|
| 22 |
+
"step": 383
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"learning_rate": 1.9513096703453338e-05,
|
| 27 |
+
"loss": 2.3885,
|
| 28 |
+
"step": 766
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_loss": 2.2446680068969727,
|
| 33 |
+
"eval_runtime": 6.5762,
|
| 34 |
+
"eval_samples_per_second": 931.841,
|
| 35 |
+
"eval_steps_per_second": 14.598,
|
| 36 |
+
"step": 766
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"learning_rate": 1.8913786142751957e-05,
|
| 41 |
+
"loss": 2.3418,
|
| 42 |
+
"step": 1149
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 2.231914758682251,
|
| 47 |
+
"eval_runtime": 6.5679,
|
| 48 |
+
"eval_samples_per_second": 933.023,
|
| 49 |
+
"eval_steps_per_second": 14.617,
|
| 50 |
+
"step": 1149
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 1.809498858405589e-05,
|
| 55 |
+
"loss": 2.3045,
|
| 56 |
+
"step": 1532
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_loss": 2.188257932662964,
|
| 61 |
+
"eval_runtime": 6.6128,
|
| 62 |
+
"eval_samples_per_second": 926.691,
|
| 63 |
+
"eval_steps_per_second": 14.517,
|
| 64 |
+
"step": 1532
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"learning_rate": 1.7076865540693534e-05,
|
| 69 |
+
"loss": 2.2772,
|
| 70 |
+
"step": 1915
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 5.0,
|
| 74 |
+
"eval_loss": 2.189318895339966,
|
| 75 |
+
"eval_runtime": 6.8537,
|
| 76 |
+
"eval_samples_per_second": 894.11,
|
| 77 |
+
"eval_steps_per_second": 14.007,
|
| 78 |
+
"step": 1915
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"learning_rate": 1.588448658094913e-05,
|
| 83 |
+
"loss": 2.2543,
|
| 84 |
+
"step": 2298
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"eval_loss": 2.168344736099243,
|
| 89 |
+
"eval_runtime": 6.7894,
|
| 90 |
+
"eval_samples_per_second": 902.58,
|
| 91 |
+
"eval_steps_per_second": 14.14,
|
| 92 |
+
"step": 2298
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"learning_rate": 1.4547212032090465e-05,
|
| 97 |
+
"loss": 2.2308,
|
| 98 |
+
"step": 2681
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 7.0,
|
| 102 |
+
"eval_loss": 2.1453945636749268,
|
| 103 |
+
"eval_runtime": 6.5512,
|
| 104 |
+
"eval_samples_per_second": 935.407,
|
| 105 |
+
"eval_steps_per_second": 14.654,
|
| 106 |
+
"step": 2681
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 8.0,
|
| 110 |
+
"learning_rate": 1.3097970031670223e-05,
|
| 111 |
+
"loss": 2.2139,
|
| 112 |
+
"step": 3064
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 8.0,
|
| 116 |
+
"eval_loss": 2.1402783393859863,
|
| 117 |
+
"eval_runtime": 6.5858,
|
| 118 |
+
"eval_samples_per_second": 930.487,
|
| 119 |
+
"eval_steps_per_second": 14.577,
|
| 120 |
+
"step": 3064
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.0,
|
| 124 |
+
"learning_rate": 1.1572445727497194e-05,
|
| 125 |
+
"loss": 2.2008,
|
| 126 |
+
"step": 3447
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 9.0,
|
| 130 |
+
"eval_loss": 2.11649489402771,
|
| 131 |
+
"eval_runtime": 6.5807,
|
| 132 |
+
"eval_samples_per_second": 931.208,
|
| 133 |
+
"eval_steps_per_second": 14.588,
|
| 134 |
+
"step": 3447
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.0,
|
| 138 |
+
"learning_rate": 1.0008202590865013e-05,
|
| 139 |
+
"loss": 2.1937,
|
| 140 |
+
"step": 3830
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 10.0,
|
| 144 |
+
"eval_loss": 2.1280927658081055,
|
| 145 |
+
"eval_runtime": 6.6743,
|
| 146 |
+
"eval_samples_per_second": 918.143,
|
| 147 |
+
"eval_steps_per_second": 14.383,
|
| 148 |
+
"step": 3830
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 11.0,
|
| 152 |
+
"learning_rate": 8.443757479222894e-06,
|
| 153 |
+
"loss": 2.1778,
|
| 154 |
+
"step": 4213
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 11.0,
|
| 158 |
+
"eval_loss": 2.1188840866088867,
|
| 159 |
+
"eval_runtime": 6.8275,
|
| 160 |
+
"eval_samples_per_second": 897.543,
|
| 161 |
+
"eval_steps_per_second": 14.061,
|
| 162 |
+
"step": 4213
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 12.0,
|
| 166 |
+
"learning_rate": 6.917632223315125e-06,
|
| 167 |
+
"loss": 2.1742,
|
| 168 |
+
"step": 4596
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 12.0,
|
| 172 |
+
"eval_loss": 2.121837854385376,
|
| 173 |
+
"eval_runtime": 6.6231,
|
| 174 |
+
"eval_samples_per_second": 925.24,
|
| 175 |
+
"eval_steps_per_second": 14.495,
|
| 176 |
+
"step": 4596
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"learning_rate": 5.467405091861484e-06,
|
| 181 |
+
"loss": 2.1611,
|
| 182 |
+
"step": 4979
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.0,
|
| 186 |
+
"eval_loss": 2.099580764770508,
|
| 187 |
+
"eval_runtime": 6.7959,
|
| 188 |
+
"eval_samples_per_second": 901.723,
|
| 189 |
+
"eval_steps_per_second": 14.126,
|
| 190 |
+
"step": 4979
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 14.0,
|
| 194 |
+
"learning_rate": 4.12878548986627e-06,
|
| 195 |
+
"loss": 2.1562,
|
| 196 |
+
"step": 5362
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 14.0,
|
| 200 |
+
"eval_loss": 2.099181890487671,
|
| 201 |
+
"eval_runtime": 6.8991,
|
| 202 |
+
"eval_samples_per_second": 888.236,
|
| 203 |
+
"eval_steps_per_second": 13.915,
|
| 204 |
+
"step": 5362
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 15.0,
|
| 208 |
+
"learning_rate": 2.934734674554366e-06,
|
| 209 |
+
"loss": 2.1508,
|
| 210 |
+
"step": 5745
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 15.0,
|
| 214 |
+
"eval_loss": 2.1012661457061768,
|
| 215 |
+
"eval_runtime": 6.8384,
|
| 216 |
+
"eval_samples_per_second": 896.11,
|
| 217 |
+
"eval_steps_per_second": 14.038,
|
| 218 |
+
"step": 5745
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 16.0,
|
| 222 |
+
"learning_rate": 1.9146541398261966e-06,
|
| 223 |
+
"loss": 2.1469,
|
| 224 |
+
"step": 6128
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 16.0,
|
| 228 |
+
"eval_loss": 2.094507932662964,
|
| 229 |
+
"eval_runtime": 6.7332,
|
| 230 |
+
"eval_samples_per_second": 910.114,
|
| 231 |
+
"eval_steps_per_second": 14.258,
|
| 232 |
+
"step": 6128
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 17.0,
|
| 236 |
+
"learning_rate": 1.0936616538999777e-06,
|
| 237 |
+
"loss": 2.1437,
|
| 238 |
+
"step": 6511
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 17.0,
|
| 242 |
+
"eval_loss": 2.089902639389038,
|
| 243 |
+
"eval_runtime": 6.6174,
|
| 244 |
+
"eval_samples_per_second": 926.05,
|
| 245 |
+
"eval_steps_per_second": 14.507,
|
| 246 |
+
"step": 6511
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"learning_rate": 4.919727764970517e-07,
|
| 251 |
+
"loss": 2.1436,
|
| 252 |
+
"step": 6894
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 18.0,
|
| 256 |
+
"eval_loss": 2.082735061645508,
|
| 257 |
+
"eval_runtime": 6.5958,
|
| 258 |
+
"eval_samples_per_second": 929.079,
|
| 259 |
+
"eval_steps_per_second": 14.555,
|
| 260 |
+
"step": 6894
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"learning_rate": 1.2440308466997952e-07,
|
| 265 |
+
"loss": 2.1443,
|
| 266 |
+
"step": 7277
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 19.0,
|
| 270 |
+
"eval_loss": 2.0934832096099854,
|
| 271 |
+
"eval_runtime": 6.5708,
|
| 272 |
+
"eval_samples_per_second": 932.611,
|
| 273 |
+
"eval_steps_per_second": 14.61,
|
| 274 |
+
"step": 7277
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 20.0,
|
| 278 |
+
"learning_rate": 3.3641254104654906e-12,
|
| 279 |
+
"loss": 2.1389,
|
| 280 |
+
"step": 7660
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 20.0,
|
| 284 |
+
"eval_loss": 2.0939252376556396,
|
| 285 |
+
"eval_runtime": 6.5634,
|
| 286 |
+
"eval_samples_per_second": 933.664,
|
| 287 |
+
"eval_steps_per_second": 14.627,
|
| 288 |
+
"step": 7660
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 20.0,
|
| 292 |
+
"step": 7660,
|
| 293 |
+
"total_flos": 3.24907393591296e+16,
|
| 294 |
+
"train_loss": 2.2224227227990374,
|
| 295 |
+
"train_runtime": 2024.9575,
|
| 296 |
+
"train_samples_per_second": 242.079,
|
| 297 |
+
"train_steps_per_second": 3.783
|
| 298 |
+
}
|
| 299 |
+
],
|
| 300 |
+
"max_steps": 7660,
|
| 301 |
+
"num_train_epochs": 20,
|
| 302 |
+
"total_flos": 3.24907393591296e+16,
|
| 303 |
+
"trial_name": null,
|
| 304 |
+
"trial_params": null
|
| 305 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f22f3ba3cfdb66236e9081453736abb889b17f53bcda49a5ac42b9bde37995a1
|
| 3 |
+
size 4027
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|