Commit
•
20dc6a2
1
Parent(s):
785fa00
Upload 7 files
Browse files- config.json +26 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- trainer_state.json +338 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-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": 514,
|
| 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 |
+
"transformers_version": "4.2.0",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 50265
|
| 26 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:364848f7afac7d956411814349fe1332043cb862917ca4bf3c301f984f6c48bf
|
| 3 |
+
size 997295237
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b174f46acc5c43e5500fdbb0af4b14fa4b3bfcac54c4727a7311159883c7db17
|
| 3 |
+
size 498675829
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9586a772d89848bcaf1d99ed76cc38192ad21b41d939b3c6b26fe92fba6bb9d9
|
| 3 |
+
size 627
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,338 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.973293768545994,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 8e-08,
|
| 13 |
+
"loss": 0.6853,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 1.6e-07,
|
| 19 |
+
"loss": 0.6856,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.18,
|
| 24 |
+
"learning_rate": 2.4e-07,
|
| 25 |
+
"loss": 0.6901,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 3.2e-07,
|
| 31 |
+
"loss": 0.6933,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.3,
|
| 36 |
+
"learning_rate": 4e-07,
|
| 37 |
+
"loss": 0.6836,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.36,
|
| 42 |
+
"learning_rate": 4.8e-07,
|
| 43 |
+
"loss": 0.6823,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.42,
|
| 48 |
+
"learning_rate": 5.6e-07,
|
| 49 |
+
"loss": 0.6894,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.47,
|
| 54 |
+
"learning_rate": 6.4e-07,
|
| 55 |
+
"loss": 0.6857,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.53,
|
| 60 |
+
"learning_rate": 7.2e-07,
|
| 61 |
+
"loss": 0.6775,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.59,
|
| 66 |
+
"learning_rate": 8e-07,
|
| 67 |
+
"loss": 0.6846,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.65,
|
| 72 |
+
"learning_rate": 8.799999999999999e-07,
|
| 73 |
+
"loss": 0.68,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.71,
|
| 78 |
+
"learning_rate": 9.6e-07,
|
| 79 |
+
"loss": 0.6751,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.77,
|
| 84 |
+
"learning_rate": 1.04e-06,
|
| 85 |
+
"loss": 0.6803,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.83,
|
| 90 |
+
"learning_rate": 1.12e-06,
|
| 91 |
+
"loss": 0.6812,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.89,
|
| 96 |
+
"learning_rate": 1.2e-06,
|
| 97 |
+
"loss": 0.6866,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.95,
|
| 102 |
+
"learning_rate": 1.28e-06,
|
| 103 |
+
"loss": 0.667,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.0,
|
| 108 |
+
"eval_accuracy": 0.5742942050520059,
|
| 109 |
+
"eval_f1": 0.364794714487966,
|
| 110 |
+
"eval_loss": 0.6554083824157715,
|
| 111 |
+
"eval_precision": 0.28714710252600295,
|
| 112 |
+
"eval_recall": 0.5,
|
| 113 |
+
"eval_runtime": 10.606,
|
| 114 |
+
"eval_samples_per_second": 253.819,
|
| 115 |
+
"step": 168
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.01,
|
| 119 |
+
"learning_rate": 1.3600000000000001e-06,
|
| 120 |
+
"loss": 0.6922,
|
| 121 |
+
"step": 170
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.07,
|
| 125 |
+
"learning_rate": 1.44e-06,
|
| 126 |
+
"loss": 0.64,
|
| 127 |
+
"step": 180
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.13,
|
| 131 |
+
"learning_rate": 1.5199999999999998e-06,
|
| 132 |
+
"loss": 0.5834,
|
| 133 |
+
"step": 190
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.19,
|
| 137 |
+
"learning_rate": 1.6e-06,
|
| 138 |
+
"loss": 0.4636,
|
| 139 |
+
"step": 200
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.25,
|
| 143 |
+
"learning_rate": 1.6799999999999998e-06,
|
| 144 |
+
"loss": 0.3717,
|
| 145 |
+
"step": 210
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.31,
|
| 149 |
+
"learning_rate": 1.7599999999999999e-06,
|
| 150 |
+
"loss": 0.3508,
|
| 151 |
+
"step": 220
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.37,
|
| 155 |
+
"learning_rate": 1.84e-06,
|
| 156 |
+
"loss": 0.2926,
|
| 157 |
+
"step": 230
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.43,
|
| 161 |
+
"learning_rate": 1.92e-06,
|
| 162 |
+
"loss": 0.2967,
|
| 163 |
+
"step": 240
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.49,
|
| 167 |
+
"learning_rate": 2e-06,
|
| 168 |
+
"loss": 0.2973,
|
| 169 |
+
"step": 250
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.55,
|
| 173 |
+
"learning_rate": 2.08e-06,
|
| 174 |
+
"loss": 0.2747,
|
| 175 |
+
"step": 260
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.61,
|
| 179 |
+
"learning_rate": 2.16e-06,
|
| 180 |
+
"loss": 0.3057,
|
| 181 |
+
"step": 270
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.66,
|
| 185 |
+
"learning_rate": 2.24e-06,
|
| 186 |
+
"loss": 0.284,
|
| 187 |
+
"step": 280
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.72,
|
| 191 |
+
"learning_rate": 2.32e-06,
|
| 192 |
+
"loss": 0.3063,
|
| 193 |
+
"step": 290
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.78,
|
| 197 |
+
"learning_rate": 2.4e-06,
|
| 198 |
+
"loss": 0.2705,
|
| 199 |
+
"step": 300
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.84,
|
| 203 |
+
"learning_rate": 2.48e-06,
|
| 204 |
+
"loss": 0.2598,
|
| 205 |
+
"step": 310
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.9,
|
| 209 |
+
"learning_rate": 2.56e-06,
|
| 210 |
+
"loss": 0.246,
|
| 211 |
+
"step": 320
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.96,
|
| 215 |
+
"learning_rate": 2.64e-06,
|
| 216 |
+
"loss": 0.2556,
|
| 217 |
+
"step": 330
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.0,
|
| 221 |
+
"eval_accuracy": 0.8904160475482912,
|
| 222 |
+
"eval_f1": 0.8873658539006881,
|
| 223 |
+
"eval_loss": 0.27534565329551697,
|
| 224 |
+
"eval_precision": 0.889704946803928,
|
| 225 |
+
"eval_recall": 0.885514947090843,
|
| 226 |
+
"eval_runtime": 10.6052,
|
| 227 |
+
"eval_samples_per_second": 253.837,
|
| 228 |
+
"step": 336
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.02,
|
| 232 |
+
"learning_rate": 2.7200000000000002e-06,
|
| 233 |
+
"loss": 0.2643,
|
| 234 |
+
"step": 340
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.08,
|
| 238 |
+
"learning_rate": 2.8e-06,
|
| 239 |
+
"loss": 0.2734,
|
| 240 |
+
"step": 350
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.14,
|
| 244 |
+
"learning_rate": 2.88e-06,
|
| 245 |
+
"loss": 0.2294,
|
| 246 |
+
"step": 360
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.2,
|
| 250 |
+
"learning_rate": 2.96e-06,
|
| 251 |
+
"loss": 0.2289,
|
| 252 |
+
"step": 370
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.26,
|
| 256 |
+
"learning_rate": 3.0399999999999997e-06,
|
| 257 |
+
"loss": 0.2494,
|
| 258 |
+
"step": 380
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.32,
|
| 262 |
+
"learning_rate": 3.1199999999999998e-06,
|
| 263 |
+
"loss": 0.222,
|
| 264 |
+
"step": 390
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.38,
|
| 268 |
+
"learning_rate": 3.2e-06,
|
| 269 |
+
"loss": 0.2603,
|
| 270 |
+
"step": 400
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.44,
|
| 274 |
+
"learning_rate": 3.2799999999999995e-06,
|
| 275 |
+
"loss": 0.265,
|
| 276 |
+
"step": 410
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.5,
|
| 280 |
+
"learning_rate": 3.3599999999999996e-06,
|
| 281 |
+
"loss": 0.2482,
|
| 282 |
+
"step": 420
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.56,
|
| 286 |
+
"learning_rate": 3.4399999999999997e-06,
|
| 287 |
+
"loss": 0.2623,
|
| 288 |
+
"step": 430
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.62,
|
| 292 |
+
"learning_rate": 3.5199999999999998e-06,
|
| 293 |
+
"loss": 0.2411,
|
| 294 |
+
"step": 440
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.68,
|
| 298 |
+
"learning_rate": 3.6e-06,
|
| 299 |
+
"loss": 0.2331,
|
| 300 |
+
"step": 450
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.74,
|
| 304 |
+
"learning_rate": 3.68e-06,
|
| 305 |
+
"loss": 0.2301,
|
| 306 |
+
"step": 460
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.8,
|
| 310 |
+
"learning_rate": 3.7599999999999996e-06,
|
| 311 |
+
"loss": 0.2105,
|
| 312 |
+
"step": 470
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.85,
|
| 316 |
+
"learning_rate": 3.84e-06,
|
| 317 |
+
"loss": 0.2282,
|
| 318 |
+
"step": 480
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.91,
|
| 322 |
+
"learning_rate": 3.92e-06,
|
| 323 |
+
"loss": 0.2357,
|
| 324 |
+
"step": 490
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.97,
|
| 328 |
+
"learning_rate": 4e-06,
|
| 329 |
+
"loss": 0.2191,
|
| 330 |
+
"step": 500
|
| 331 |
+
}
|
| 332 |
+
],
|
| 333 |
+
"max_steps": 840,
|
| 334 |
+
"num_train_epochs": 5,
|
| 335 |
+
"total_flos": 7162006012003440,
|
| 336 |
+
"trial_name": null,
|
| 337 |
+
"trial_params": null
|
| 338 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0610fae7ebb570e011518dad70d2d9c1edbf0618d38fa8150e7256db44a16b24
|
| 3 |
+
size 2107
|