initial commit
Browse files- config.json +24 -0
- eval_results_mlm.txt +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +286 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"transformers_version": "4.2.2",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
eval_results_mlm.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
perplexity = 3.2958442552761893
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:246a786ed25d99de4a34223410c9ec6b85b1c83a9ea39023793d3551fd604788
|
| 3 |
+
size 438110325
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 3.0
|
| 2 |
+
train_runtime = 19825.6129
|
| 3 |
+
train_samples_per_second = 1.118
|
trainer_state.json
ADDED
|
@@ -0,0 +1,286 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 22170,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 4.8872350022553004e-05,
|
| 13 |
+
"loss": 1.7015,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"learning_rate": 4.7744700045106e-05,
|
| 19 |
+
"loss": 1.5752,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.2,
|
| 24 |
+
"learning_rate": 4.6617050067659e-05,
|
| 25 |
+
"loss": 1.5199,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.27,
|
| 30 |
+
"learning_rate": 4.5489400090211996e-05,
|
| 31 |
+
"loss": 1.4862,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.34,
|
| 36 |
+
"learning_rate": 4.4361750112765e-05,
|
| 37 |
+
"loss": 1.4695,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.41,
|
| 42 |
+
"learning_rate": 4.3234100135318e-05,
|
| 43 |
+
"loss": 1.44,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.47,
|
| 48 |
+
"learning_rate": 4.2106450157870994e-05,
|
| 49 |
+
"loss": 1.4353,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.54,
|
| 54 |
+
"learning_rate": 4.0978800180423996e-05,
|
| 55 |
+
"loss": 1.4165,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.61,
|
| 60 |
+
"learning_rate": 3.9851150202977e-05,
|
| 61 |
+
"loss": 1.4017,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.68,
|
| 66 |
+
"learning_rate": 3.872350022553e-05,
|
| 67 |
+
"loss": 1.3854,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.74,
|
| 72 |
+
"learning_rate": 3.7595850248083e-05,
|
| 73 |
+
"loss": 1.3809,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.81,
|
| 78 |
+
"learning_rate": 3.6468200270635996e-05,
|
| 79 |
+
"loss": 1.3731,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.88,
|
| 84 |
+
"learning_rate": 3.5340550293189e-05,
|
| 85 |
+
"loss": 1.3641,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.95,
|
| 90 |
+
"learning_rate": 3.4212900315742e-05,
|
| 91 |
+
"loss": 1.3546,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.01,
|
| 96 |
+
"learning_rate": 3.3085250338294994e-05,
|
| 97 |
+
"loss": 1.3382,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.08,
|
| 102 |
+
"learning_rate": 3.1957600360847996e-05,
|
| 103 |
+
"loss": 1.3303,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.15,
|
| 108 |
+
"learning_rate": 3.0829950383401e-05,
|
| 109 |
+
"loss": 1.3253,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.22,
|
| 114 |
+
"learning_rate": 2.9702300405953993e-05,
|
| 115 |
+
"loss": 1.3242,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.29,
|
| 120 |
+
"learning_rate": 2.8574650428506994e-05,
|
| 121 |
+
"loss": 1.307,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.35,
|
| 126 |
+
"learning_rate": 2.744700045105999e-05,
|
| 127 |
+
"loss": 1.3029,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.42,
|
| 132 |
+
"learning_rate": 2.631935047361299e-05,
|
| 133 |
+
"loss": 1.3085,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.49,
|
| 138 |
+
"learning_rate": 2.5191700496165993e-05,
|
| 139 |
+
"loss": 1.2841,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.56,
|
| 144 |
+
"learning_rate": 2.406405051871899e-05,
|
| 145 |
+
"loss": 1.2921,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.62,
|
| 150 |
+
"learning_rate": 2.293640054127199e-05,
|
| 151 |
+
"loss": 1.2855,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.69,
|
| 156 |
+
"learning_rate": 2.1808750563824988e-05,
|
| 157 |
+
"loss": 1.2759,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.76,
|
| 162 |
+
"learning_rate": 2.068110058637799e-05,
|
| 163 |
+
"loss": 1.26,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.83,
|
| 168 |
+
"learning_rate": 1.955345060893099e-05,
|
| 169 |
+
"loss": 1.2742,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.89,
|
| 174 |
+
"learning_rate": 1.842580063148399e-05,
|
| 175 |
+
"loss": 1.2761,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.96,
|
| 180 |
+
"learning_rate": 1.7298150654036988e-05,
|
| 181 |
+
"loss": 1.2549,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.03,
|
| 186 |
+
"learning_rate": 1.6170500676589986e-05,
|
| 187 |
+
"loss": 1.2552,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.1,
|
| 192 |
+
"learning_rate": 1.5042850699142988e-05,
|
| 193 |
+
"loss": 1.2356,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.17,
|
| 198 |
+
"learning_rate": 1.3915200721695986e-05,
|
| 199 |
+
"loss": 1.239,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.23,
|
| 204 |
+
"learning_rate": 1.2787550744248986e-05,
|
| 205 |
+
"loss": 1.2378,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.3,
|
| 210 |
+
"learning_rate": 1.1659900766801986e-05,
|
| 211 |
+
"loss": 1.2431,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.37,
|
| 216 |
+
"learning_rate": 1.0532250789354985e-05,
|
| 217 |
+
"loss": 1.2202,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.44,
|
| 222 |
+
"learning_rate": 9.404600811907985e-06,
|
| 223 |
+
"loss": 1.232,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.5,
|
| 228 |
+
"learning_rate": 8.276950834460983e-06,
|
| 229 |
+
"loss": 1.2274,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.57,
|
| 234 |
+
"learning_rate": 7.149300857013984e-06,
|
| 235 |
+
"loss": 1.2233,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.64,
|
| 240 |
+
"learning_rate": 6.021650879566982e-06,
|
| 241 |
+
"loss": 1.2234,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.71,
|
| 246 |
+
"learning_rate": 4.894000902119982e-06,
|
| 247 |
+
"loss": 1.2216,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.77,
|
| 252 |
+
"learning_rate": 3.7663509246729816e-06,
|
| 253 |
+
"loss": 1.2164,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.84,
|
| 258 |
+
"learning_rate": 2.638700947225981e-06,
|
| 259 |
+
"loss": 1.2203,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.91,
|
| 264 |
+
"learning_rate": 1.5110509697789808e-06,
|
| 265 |
+
"loss": 1.2105,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.98,
|
| 270 |
+
"learning_rate": 3.8340099233198017e-07,
|
| 271 |
+
"loss": 1.2186,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.0,
|
| 276 |
+
"step": 22170,
|
| 277 |
+
"train_runtime": 19825.6129,
|
| 278 |
+
"train_samples_per_second": 1.118
|
| 279 |
+
}
|
| 280 |
+
],
|
| 281 |
+
"max_steps": 22170,
|
| 282 |
+
"num_train_epochs": 3,
|
| 283 |
+
"total_flos": 59663810085304320,
|
| 284 |
+
"trial_name": null,
|
| 285 |
+
"trial_params": null
|
| 286 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:184e0deaf9afeeb27859ca3611b72eb15e23b15a7404a2290d003dc3cc87ecdd
|
| 3 |
+
size 1809
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|