update all
Browse files- added_tokens.json +1 -0
- bpe.codes +0 -0
- config.json +27 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +323 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<mask>": 64000}
|
bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "vinai/phobert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 258,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 23 |
+
"transformers_version": "4.3.2",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 64001
|
| 27 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 256, "name_or_path": "vinai/phobert-base"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 5.0
|
| 2 |
+
train_runtime = 8275.4395
|
| 3 |
+
train_samples_per_second = 1.217
|
trainer_state.json
ADDED
|
@@ -0,0 +1,323 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 10075,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 9.8014888337469e-06,
|
| 13 |
+
"loss": 0.2058,
|
| 14 |
+
"step": 200
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 9.602977667493797e-06,
|
| 19 |
+
"loss": 0.1586,
|
| 20 |
+
"step": 400
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.3,
|
| 24 |
+
"learning_rate": 9.404466501240696e-06,
|
| 25 |
+
"loss": 0.1283,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.4,
|
| 30 |
+
"learning_rate": 9.205955334987593e-06,
|
| 31 |
+
"loss": 0.1288,
|
| 32 |
+
"step": 800
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.5,
|
| 36 |
+
"learning_rate": 9.007444168734492e-06,
|
| 37 |
+
"loss": 0.1259,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.6,
|
| 42 |
+
"learning_rate": 8.80893300248139e-06,
|
| 43 |
+
"loss": 0.1196,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.69,
|
| 48 |
+
"learning_rate": 8.610421836228289e-06,
|
| 49 |
+
"loss": 0.125,
|
| 50 |
+
"step": 1400
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.79,
|
| 54 |
+
"learning_rate": 8.411910669975186e-06,
|
| 55 |
+
"loss": 0.1152,
|
| 56 |
+
"step": 1600
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.89,
|
| 60 |
+
"learning_rate": 8.213399503722085e-06,
|
| 61 |
+
"loss": 0.1141,
|
| 62 |
+
"step": 1800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.99,
|
| 66 |
+
"learning_rate": 8.014888337468984e-06,
|
| 67 |
+
"loss": 0.1088,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.09,
|
| 72 |
+
"learning_rate": 7.816377171215881e-06,
|
| 73 |
+
"loss": 0.0938,
|
| 74 |
+
"step": 2200
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.19,
|
| 78 |
+
"learning_rate": 7.6178660049627794e-06,
|
| 79 |
+
"loss": 0.0882,
|
| 80 |
+
"step": 2400
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.29,
|
| 84 |
+
"learning_rate": 7.4193548387096784e-06,
|
| 85 |
+
"loss": 0.0908,
|
| 86 |
+
"step": 2600
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.39,
|
| 90 |
+
"learning_rate": 7.220843672456577e-06,
|
| 91 |
+
"loss": 0.0982,
|
| 92 |
+
"step": 2800
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.49,
|
| 96 |
+
"learning_rate": 7.022332506203474e-06,
|
| 97 |
+
"loss": 0.0938,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.59,
|
| 102 |
+
"learning_rate": 6.823821339950373e-06,
|
| 103 |
+
"loss": 0.0997,
|
| 104 |
+
"step": 3200
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.69,
|
| 108 |
+
"learning_rate": 6.625310173697271e-06,
|
| 109 |
+
"loss": 0.0903,
|
| 110 |
+
"step": 3400
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.79,
|
| 114 |
+
"learning_rate": 6.426799007444169e-06,
|
| 115 |
+
"loss": 0.1015,
|
| 116 |
+
"step": 3600
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.89,
|
| 120 |
+
"learning_rate": 6.228287841191067e-06,
|
| 121 |
+
"loss": 0.0719,
|
| 122 |
+
"step": 3800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.99,
|
| 126 |
+
"learning_rate": 6.029776674937966e-06,
|
| 127 |
+
"loss": 0.0874,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.08,
|
| 132 |
+
"learning_rate": 5.831265508684864e-06,
|
| 133 |
+
"loss": 0.0783,
|
| 134 |
+
"step": 4200
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.18,
|
| 138 |
+
"learning_rate": 5.632754342431762e-06,
|
| 139 |
+
"loss": 0.0737,
|
| 140 |
+
"step": 4400
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.28,
|
| 144 |
+
"learning_rate": 5.434243176178661e-06,
|
| 145 |
+
"loss": 0.0657,
|
| 146 |
+
"step": 4600
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.38,
|
| 150 |
+
"learning_rate": 5.235732009925558e-06,
|
| 151 |
+
"loss": 0.0754,
|
| 152 |
+
"step": 4800
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.48,
|
| 156 |
+
"learning_rate": 5.037220843672457e-06,
|
| 157 |
+
"loss": 0.0734,
|
| 158 |
+
"step": 5000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.58,
|
| 162 |
+
"learning_rate": 4.838709677419355e-06,
|
| 163 |
+
"loss": 0.081,
|
| 164 |
+
"step": 5200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.68,
|
| 168 |
+
"learning_rate": 4.640198511166253e-06,
|
| 169 |
+
"loss": 0.0701,
|
| 170 |
+
"step": 5400
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.78,
|
| 174 |
+
"learning_rate": 4.4416873449131515e-06,
|
| 175 |
+
"loss": 0.0781,
|
| 176 |
+
"step": 5600
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.88,
|
| 180 |
+
"learning_rate": 4.24317617866005e-06,
|
| 181 |
+
"loss": 0.074,
|
| 182 |
+
"step": 5800
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.98,
|
| 186 |
+
"learning_rate": 4.044665012406948e-06,
|
| 187 |
+
"loss": 0.0722,
|
| 188 |
+
"step": 6000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.08,
|
| 192 |
+
"learning_rate": 3.846153846153847e-06,
|
| 193 |
+
"loss": 0.0551,
|
| 194 |
+
"step": 6200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.18,
|
| 198 |
+
"learning_rate": 3.6476426799007445e-06,
|
| 199 |
+
"loss": 0.0526,
|
| 200 |
+
"step": 6400
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.28,
|
| 204 |
+
"learning_rate": 3.4491315136476427e-06,
|
| 205 |
+
"loss": 0.0645,
|
| 206 |
+
"step": 6600
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.37,
|
| 210 |
+
"learning_rate": 3.2506203473945412e-06,
|
| 211 |
+
"loss": 0.064,
|
| 212 |
+
"step": 6800
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.47,
|
| 216 |
+
"learning_rate": 3.0521091811414394e-06,
|
| 217 |
+
"loss": 0.0569,
|
| 218 |
+
"step": 7000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.57,
|
| 222 |
+
"learning_rate": 2.8535980148883375e-06,
|
| 223 |
+
"loss": 0.066,
|
| 224 |
+
"step": 7200
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.67,
|
| 228 |
+
"learning_rate": 2.655086848635236e-06,
|
| 229 |
+
"loss": 0.0616,
|
| 230 |
+
"step": 7400
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.77,
|
| 234 |
+
"learning_rate": 2.4565756823821343e-06,
|
| 235 |
+
"loss": 0.0622,
|
| 236 |
+
"step": 7600
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.87,
|
| 240 |
+
"learning_rate": 2.2580645161290324e-06,
|
| 241 |
+
"loss": 0.0561,
|
| 242 |
+
"step": 7800
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.97,
|
| 246 |
+
"learning_rate": 2.0595533498759305e-06,
|
| 247 |
+
"loss": 0.0544,
|
| 248 |
+
"step": 8000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.07,
|
| 252 |
+
"learning_rate": 1.861042183622829e-06,
|
| 253 |
+
"loss": 0.0541,
|
| 254 |
+
"step": 8200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.17,
|
| 258 |
+
"learning_rate": 1.662531017369727e-06,
|
| 259 |
+
"loss": 0.0532,
|
| 260 |
+
"step": 8400
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.27,
|
| 264 |
+
"learning_rate": 1.4640198511166254e-06,
|
| 265 |
+
"loss": 0.046,
|
| 266 |
+
"step": 8600
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.37,
|
| 270 |
+
"learning_rate": 1.2655086848635238e-06,
|
| 271 |
+
"loss": 0.0522,
|
| 272 |
+
"step": 8800
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 4.47,
|
| 276 |
+
"learning_rate": 1.066997518610422e-06,
|
| 277 |
+
"loss": 0.0575,
|
| 278 |
+
"step": 9000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.57,
|
| 282 |
+
"learning_rate": 8.684863523573202e-07,
|
| 283 |
+
"loss": 0.0534,
|
| 284 |
+
"step": 9200
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.67,
|
| 288 |
+
"learning_rate": 6.699751861042183e-07,
|
| 289 |
+
"loss": 0.0466,
|
| 290 |
+
"step": 9400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.76,
|
| 294 |
+
"learning_rate": 4.714640198511167e-07,
|
| 295 |
+
"loss": 0.0485,
|
| 296 |
+
"step": 9600
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.86,
|
| 300 |
+
"learning_rate": 2.7295285359801494e-07,
|
| 301 |
+
"loss": 0.0624,
|
| 302 |
+
"step": 9800
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.96,
|
| 306 |
+
"learning_rate": 7.444168734491315e-08,
|
| 307 |
+
"loss": 0.0436,
|
| 308 |
+
"step": 10000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 5.0,
|
| 312 |
+
"step": 10075,
|
| 313 |
+
"total_flos": 66843438723916800,
|
| 314 |
+
"train_runtime": 8275.4395,
|
| 315 |
+
"train_samples_per_second": 1.217
|
| 316 |
+
}
|
| 317 |
+
],
|
| 318 |
+
"max_steps": 10075,
|
| 319 |
+
"num_train_epochs": 5,
|
| 320 |
+
"total_flos": 66843438723916800,
|
| 321 |
+
"trial_name": null,
|
| 322 |
+
"trial_params": null
|
| 323 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|