End of training
Browse files- README.md +5 -5
- all_results.json +11 -11
- eval_results.json +7 -7
- logs/events.out.tfevents.1675027212.serv-3333.4029993.2 +3 -0
- train_results.json +5 -5
- trainer_state.json +389 -2279
README.md
CHANGED
|
@@ -13,7 +13,7 @@ model-index:
|
|
| 13 |
name: Masked Language Modeling
|
| 14 |
type: fill-mask
|
| 15 |
dataset:
|
| 16 |
-
name: wikitext
|
| 17 |
type: wikitext
|
| 18 |
config: wikitext-103-raw-v1
|
| 19 |
split: validation
|
|
@@ -21,7 +21,7 @@ model-index:
|
|
| 21 |
metrics:
|
| 22 |
- name: Accuracy
|
| 23 |
type: accuracy
|
| 24 |
-
value: 0.
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -29,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 29 |
|
| 30 |
# mobilebert_sa_pre-training-complete
|
| 31 |
|
| 32 |
-
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the wikitext dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
-
- Loss: 1.
|
| 35 |
-
- Accuracy: 0.
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
| 13 |
name: Masked Language Modeling
|
| 14 |
type: fill-mask
|
| 15 |
dataset:
|
| 16 |
+
name: wikitext wikitext-103-raw-v1
|
| 17 |
type: wikitext
|
| 18 |
config: wikitext-103-raw-v1
|
| 19 |
split: validation
|
| 21 |
metrics:
|
| 22 |
- name: Accuracy
|
| 23 |
type: accuracy
|
| 24 |
+
value: 0.7161816392520737
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
|
| 30 |
# mobilebert_sa_pre-training-complete
|
| 31 |
|
| 32 |
+
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the wikitext wikitext-103-raw-v1 dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 1.3239
|
| 35 |
+
- Accuracy: 0.7162
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 479,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"perplexity":
|
| 10 |
-
"train_loss":
|
| 11 |
-
"train_runtime":
|
| 12 |
"train_samples": 228639,
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second":
|
| 15 |
}
|
| 1 |
{
|
| 2 |
+
"epoch": 41.99,
|
| 3 |
+
"eval_accuracy": 0.7161816392520737,
|
| 4 |
+
"eval_loss": 1.3238917589187622,
|
| 5 |
+
"eval_runtime": 1.539,
|
| 6 |
"eval_samples": 479,
|
| 7 |
+
"eval_samples_per_second": 311.239,
|
| 8 |
+
"eval_steps_per_second": 9.747,
|
| 9 |
+
"perplexity": 3.7580182561358457,
|
| 10 |
+
"train_loss": 1.4300982942708333,
|
| 11 |
+
"train_runtime": 103608.4476,
|
| 12 |
"train_samples": 228639,
|
| 13 |
+
"train_samples_per_second": 92.657,
|
| 14 |
+
"train_steps_per_second": 2.896
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 479,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"perplexity":
|
| 10 |
}
|
| 1 |
{
|
| 2 |
+
"epoch": 41.99,
|
| 3 |
+
"eval_accuracy": 0.7161816392520737,
|
| 4 |
+
"eval_loss": 1.3238917589187622,
|
| 5 |
+
"eval_runtime": 1.539,
|
| 6 |
"eval_samples": 479,
|
| 7 |
+
"eval_samples_per_second": 311.239,
|
| 8 |
+
"eval_steps_per_second": 9.747,
|
| 9 |
+
"perplexity": 3.7580182561358457
|
| 10 |
}
|
logs/events.out.tfevents.1675027212.serv-3333.4029993.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d9bb817d0bb9025eec140956e3d4adda688dd63d57b5c0d85a5a2c6065c492f
|
| 3 |
+
size 369
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 228639,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
| 1 |
{
|
| 2 |
+
"epoch": 41.99,
|
| 3 |
+
"train_loss": 1.4300982942708333,
|
| 4 |
+
"train_runtime": 103608.4476,
|
| 5 |
"train_samples": 228639,
|
| 6 |
+
"train_samples_per_second": 92.657,
|
| 7 |
+
"train_steps_per_second": 2.896
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "mobilebert_sa_pre-training-complete/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"global_step": 300000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
|
@@ -9,2537 +9,647 @@
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
-
"learning_rate": 4.
|
| 13 |
-
"loss":
|
| 14 |
-
"step":
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
-
"eval_accuracy": 0.
|
| 19 |
-
"eval_loss":
|
| 20 |
-
"eval_runtime":
|
| 21 |
-
"eval_samples_per_second":
|
| 22 |
-
"eval_steps_per_second":
|
| 23 |
-
"step":
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 2.0,
|
| 27 |
-
"learning_rate": 4.
|
| 28 |
-
"loss":
|
| 29 |
-
"step":
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 2.0,
|
| 33 |
-
"eval_accuracy": 0.
|
| 34 |
-
"eval_loss":
|
| 35 |
-
"eval_runtime":
|
| 36 |
-
"eval_samples_per_second":
|
| 37 |
-
"eval_steps_per_second":
|
| 38 |
-
"step":
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 3.0,
|
| 42 |
-
"learning_rate": 4.
|
| 43 |
-
"loss":
|
| 44 |
-
"step":
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 3.0,
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_loss":
|
| 50 |
-
"eval_runtime":
|
| 51 |
-
"eval_samples_per_second":
|
| 52 |
-
"eval_steps_per_second":
|
| 53 |
-
"step":
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 4.0,
|
| 57 |
-
"learning_rate": 4.
|
| 58 |
-
"loss":
|
| 59 |
-
"step":
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 4.0,
|
| 63 |
-
"eval_accuracy": 0.
|
| 64 |
-
"eval_loss":
|
| 65 |
-
"eval_runtime":
|
| 66 |
-
"eval_samples_per_second":
|
| 67 |
-
"eval_steps_per_second":
|
| 68 |
-
"step":
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 5.0,
|
| 72 |
-
"learning_rate": 4.
|
| 73 |
-
"loss":
|
| 74 |
-
"step":
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 5.0,
|
| 78 |
-
"eval_accuracy": 0.
|
| 79 |
-
"eval_loss":
|
| 80 |
-
"eval_runtime":
|
| 81 |
-
"eval_samples_per_second":
|
| 82 |
-
"eval_steps_per_second":
|
| 83 |
-
"step":
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 6.0,
|
| 87 |
-
"learning_rate": 4.
|
| 88 |
-
"loss":
|
| 89 |
-
"step":
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 6.0,
|
| 93 |
-
"eval_accuracy": 0.
|
| 94 |
-
"eval_loss":
|
| 95 |
-
"eval_runtime":
|
| 96 |
-
"eval_samples_per_second":
|
| 97 |
-
"eval_steps_per_second":
|
| 98 |
-
"step":
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 7.0,
|
| 102 |
-
"learning_rate": 4.
|
| 103 |
-
"loss":
|
| 104 |
-
"step":
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 7.0,
|
| 108 |
-
"eval_accuracy": 0.
|
| 109 |
-
"eval_loss":
|
| 110 |
-
"eval_runtime":
|
| 111 |
-
"eval_samples_per_second":
|
| 112 |
-
"eval_steps_per_second":
|
| 113 |
-
"step":
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 8.0,
|
| 117 |
-
"learning_rate": 4.
|
| 118 |
-
"loss":
|
| 119 |
-
"step":
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 8.0,
|
| 123 |
-
"eval_accuracy": 0.
|
| 124 |
-
"eval_loss":
|
| 125 |
-
"eval_runtime":
|
| 126 |
-
"eval_samples_per_second":
|
| 127 |
-
"eval_steps_per_second":
|
| 128 |
-
"step":
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 9.0,
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss":
|
| 134 |
-
"step":
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 9.0,
|
| 138 |
-
"eval_accuracy": 0.
|
| 139 |
-
"eval_loss":
|
| 140 |
-
"eval_runtime": 1.
|
| 141 |
-
"eval_samples_per_second":
|
| 142 |
-
"eval_steps_per_second":
|
| 143 |
-
"step":
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 10.0,
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss":
|
| 149 |
-
"step":
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 10.0,
|
| 153 |
-
"eval_accuracy": 0.
|
| 154 |
-
"eval_loss":
|
| 155 |
-
"eval_runtime":
|
| 156 |
-
"eval_samples_per_second":
|
| 157 |
-
"eval_steps_per_second":
|
| 158 |
-
"step":
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 11.0,
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss":
|
| 164 |
-
"step":
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 11.0,
|
| 168 |
-
"eval_accuracy": 0.
|
| 169 |
-
"eval_loss":
|
| 170 |
-
"eval_runtime":
|
| 171 |
-
"eval_samples_per_second":
|
| 172 |
-
"eval_steps_per_second":
|
| 173 |
-
"step":
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 12.0,
|
| 177 |
-
"learning_rate":
|
| 178 |
-
"loss":
|
| 179 |
-
"step":
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 12.0,
|
| 183 |
-
"eval_accuracy": 0.
|
| 184 |
-
"eval_loss":
|
| 185 |
-
"eval_runtime": 1.
|
| 186 |
-
"eval_samples_per_second":
|
| 187 |
-
"eval_steps_per_second":
|
| 188 |
-
"step":
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 13.0,
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss":
|
| 194 |
-
"step":
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 13.0,
|
| 198 |
-
"eval_accuracy": 0.
|
| 199 |
-
"eval_loss":
|
| 200 |
-
"eval_runtime":
|
| 201 |
-
"eval_samples_per_second":
|
| 202 |
-
"eval_steps_per_second":
|
| 203 |
-
"step":
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 14.0,
|
| 207 |
-
"learning_rate":
|
| 208 |
-
"loss":
|
| 209 |
-
"step":
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 14.0,
|
| 213 |
-
"eval_accuracy": 0.
|
| 214 |
-
"eval_loss":
|
| 215 |
-
"eval_runtime":
|
| 216 |
-
"eval_samples_per_second":
|
| 217 |
-
"eval_steps_per_second":
|
| 218 |
-
"step":
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 15.0,
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss":
|
| 224 |
-
"step":
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 15.0,
|
| 228 |
-
"eval_accuracy": 0.
|
| 229 |
-
"eval_loss":
|
| 230 |
-
"eval_runtime": 1.
|
| 231 |
-
"eval_samples_per_second":
|
| 232 |
-
"eval_steps_per_second":
|
| 233 |
-
"step":
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 16.0,
|
| 237 |
-
"learning_rate":
|
| 238 |
-
"loss":
|
| 239 |
-
"step":
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 16.0,
|
| 243 |
-
"eval_accuracy": 0.
|
| 244 |
-
"eval_loss":
|
| 245 |
-
"eval_runtime":
|
| 246 |
-
"eval_samples_per_second":
|
| 247 |
-
"eval_steps_per_second":
|
| 248 |
-
"step":
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 17.0,
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss":
|
| 254 |
-
"step":
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 17.0,
|
| 258 |
-
"eval_accuracy": 0.
|
| 259 |
-
"eval_loss":
|
| 260 |
-
"eval_runtime":
|
| 261 |
-
"eval_samples_per_second":
|
| 262 |
-
"eval_steps_per_second":
|
| 263 |
-
"step":
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 18.0,
|
| 267 |
-
"learning_rate":
|
| 268 |
-
"loss":
|
| 269 |
-
"step":
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 18.0,
|
| 273 |
-
"eval_accuracy": 0.
|
| 274 |
-
"eval_loss":
|
| 275 |
-
"eval_runtime":
|
| 276 |
-
"eval_samples_per_second":
|
| 277 |
-
"eval_steps_per_second":
|
| 278 |
-
"step":
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 19.0,
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss":
|
| 284 |
-
"step":
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 19.0,
|
| 288 |
-
"eval_accuracy": 0.
|
| 289 |
-
"eval_loss":
|
| 290 |
-
"eval_runtime":
|
| 291 |
-
"eval_samples_per_second":
|
| 292 |
-
"eval_steps_per_second":
|
| 293 |
-
"step":
|
| 294 |
},
|
| 295 |
{
|
| 296 |
"epoch": 20.0,
|
| 297 |
-
"learning_rate":
|
| 298 |
-
"loss":
|
| 299 |
-
"step":
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 20.0,
|
| 303 |
-
"eval_accuracy": 0.
|
| 304 |
-
"eval_loss":
|
| 305 |
-
"eval_runtime":
|
| 306 |
-
"eval_samples_per_second":
|
| 307 |
-
"eval_steps_per_second":
|
| 308 |
-
"step":
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 21.0,
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss":
|
| 314 |
-
"step":
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 21.0,
|
| 318 |
-
"eval_accuracy": 0.
|
| 319 |
-
"eval_loss":
|
| 320 |
-
"eval_runtime":
|
| 321 |
-
"eval_samples_per_second":
|
| 322 |
-
"eval_steps_per_second":
|
| 323 |
-
"step":
|
| 324 |
},
|
| 325 |
{
|
| 326 |
"epoch": 22.0,
|
| 327 |
-
"learning_rate":
|
| 328 |
-
"loss":
|
| 329 |
-
"step":
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"epoch": 22.0,
|
| 333 |
-
"eval_accuracy": 0.
|
| 334 |
-
"eval_loss":
|
| 335 |
-
"eval_runtime":
|
| 336 |
-
"eval_samples_per_second":
|
| 337 |
-
"eval_steps_per_second":
|
| 338 |
-
"step":
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 23.0,
|
| 342 |
-
"learning_rate":
|
| 343 |
-
"loss":
|
| 344 |
-
"step":
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 23.0,
|
| 348 |
-
"eval_accuracy": 0.
|
| 349 |
-
"eval_loss":
|
| 350 |
-
"eval_runtime":
|
| 351 |
-
"eval_samples_per_second":
|
| 352 |
-
"eval_steps_per_second":
|
| 353 |
-
"step":
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 24.0,
|
| 357 |
-
"learning_rate":
|
| 358 |
-
"loss":
|
| 359 |
-
"step":
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 24.0,
|
| 363 |
-
"eval_accuracy": 0.
|
| 364 |
-
"eval_loss":
|
| 365 |
-
"eval_runtime":
|
| 366 |
-
"eval_samples_per_second":
|
| 367 |
-
"eval_steps_per_second":
|
| 368 |
-
"step":
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 25.0,
|
| 372 |
-
"learning_rate":
|
| 373 |
-
"loss":
|
| 374 |
-
"step":
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 25.0,
|
| 378 |
-
"eval_accuracy": 0.
|
| 379 |
-
"eval_loss":
|
| 380 |
-
"eval_runtime":
|
| 381 |
-
"eval_samples_per_second":
|
| 382 |
-
"eval_steps_per_second":
|
| 383 |
-
"step":
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 26.0,
|
| 387 |
-
"learning_rate":
|
| 388 |
-
"loss":
|
| 389 |
-
"step":
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 26.0,
|
| 393 |
-
"eval_accuracy": 0.
|
| 394 |
-
"eval_loss":
|
| 395 |
-
"eval_runtime":
|
| 396 |
-
"eval_samples_per_second":
|
| 397 |
-
"eval_steps_per_second":
|
| 398 |
-
"step":
|
| 399 |
},
|
| 400 |
{
|
| 401 |
"epoch": 27.0,
|
| 402 |
-
"learning_rate":
|
| 403 |
-
"loss":
|
| 404 |
-
"step":
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 27.0,
|
| 408 |
-
"eval_accuracy": 0.
|
| 409 |
-
"eval_loss":
|
| 410 |
-
"eval_runtime":
|
| 411 |
-
"eval_samples_per_second":
|
| 412 |
-
"eval_steps_per_second":
|
| 413 |
-
"step":
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 28.0,
|
| 417 |
-
"learning_rate":
|
| 418 |
-
"loss":
|
| 419 |
-
"step":
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 28.0,
|
| 423 |
-
"eval_accuracy": 0.
|
| 424 |
-
"eval_loss":
|
| 425 |
-
"eval_runtime":
|
| 426 |
-
"eval_samples_per_second":
|
| 427 |
-
"eval_steps_per_second":
|
| 428 |
-
"step":
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 29.0,
|
| 432 |
-
"learning_rate":
|
| 433 |
-
"loss":
|
| 434 |
-
"step":
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 29.0,
|
| 438 |
-
"eval_accuracy": 0.
|
| 439 |
-
"eval_loss":
|
| 440 |
-
"eval_runtime":
|
| 441 |
-
"eval_samples_per_second":
|
| 442 |
-
"eval_steps_per_second":
|
| 443 |
-
"step":
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 30.0,
|
| 447 |
-
"learning_rate":
|
| 448 |
-
"loss":
|
| 449 |
-
"step":
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 30.0,
|
| 453 |
-
"eval_accuracy": 0.
|
| 454 |
-
"eval_loss":
|
| 455 |
-
"eval_runtime":
|
| 456 |
-
"eval_samples_per_second":
|
| 457 |
-
"eval_steps_per_second":
|
| 458 |
-
"step":
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 31.0,
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss":
|
| 464 |
-
"step":
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 31.0,
|
| 468 |
-
"eval_accuracy": 0.
|
| 469 |
-
"eval_loss":
|
| 470 |
-
"eval_runtime":
|
| 471 |
-
"eval_samples_per_second":
|
| 472 |
-
"eval_steps_per_second":
|
| 473 |
-
"step":
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 32.0,
|
| 477 |
-
"learning_rate":
|
| 478 |
-
"loss":
|
| 479 |
-
"step":
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 32.0,
|
| 483 |
-
"eval_accuracy": 0.
|
| 484 |
-
"eval_loss":
|
| 485 |
-
"eval_runtime":
|
| 486 |
-
"eval_samples_per_second":
|
| 487 |
-
"eval_steps_per_second":
|
| 488 |
-
"step":
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 33.0,
|
| 492 |
-
"learning_rate":
|
| 493 |
-
"loss":
|
| 494 |
-
"step":
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"epoch": 33.0,
|
| 498 |
-
"eval_accuracy": 0.
|
| 499 |
-
"eval_loss":
|
| 500 |
-
"eval_runtime":
|
| 501 |
-
"eval_samples_per_second":
|
| 502 |
-
"eval_steps_per_second":
|
| 503 |
-
"step":
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 34.0,
|
| 507 |
-
"learning_rate":
|
| 508 |
-
"loss":
|
| 509 |
-
"step":
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 34.0,
|
| 513 |
-
"eval_accuracy": 0.
|
| 514 |
-
"eval_loss":
|
| 515 |
-
"eval_runtime":
|
| 516 |
-
"eval_samples_per_second":
|
| 517 |
-
"eval_steps_per_second":
|
| 518 |
-
"step":
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 35.0,
|
| 522 |
-
"learning_rate":
|
| 523 |
-
"loss":
|
| 524 |
-
"step":
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 35.0,
|
| 528 |
-
"eval_accuracy": 0.
|
| 529 |
-
"eval_loss":
|
| 530 |
-
"eval_runtime":
|
| 531 |
-
"eval_samples_per_second":
|
| 532 |
-
"eval_steps_per_second":
|
| 533 |
-
"step":
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 36.0,
|
| 537 |
-
"learning_rate":
|
| 538 |
-
"loss":
|
| 539 |
-
"step":
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 36.0,
|
| 543 |
-
"eval_accuracy": 0.
|
| 544 |
-
"eval_loss":
|
| 545 |
-
"eval_runtime": 1.
|
| 546 |
-
"eval_samples_per_second":
|
| 547 |
-
"eval_steps_per_second":
|
| 548 |
-
"step":
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 37.0,
|
| 552 |
-
"learning_rate":
|
| 553 |
-
"loss":
|
| 554 |
-
"step":
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 37.0,
|
| 558 |
-
"eval_accuracy": 0.
|
| 559 |
-
"eval_loss":
|
| 560 |
-
"eval_runtime":
|
| 561 |
-
"eval_samples_per_second":
|
| 562 |
-
"eval_steps_per_second":
|
| 563 |
-
"step":
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 38.0,
|
| 567 |
-
"learning_rate":
|
| 568 |
-
"loss":
|
| 569 |
-
"step":
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 38.0,
|
| 573 |
-
"eval_accuracy": 0.
|
| 574 |
-
"eval_loss":
|
| 575 |
-
"eval_runtime":
|
| 576 |
-
"eval_samples_per_second":
|
| 577 |
-
"eval_steps_per_second":
|
| 578 |
-
"step":
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 39.0,
|
| 582 |
-
"learning_rate": 3.
|
| 583 |
-
"loss":
|
| 584 |
-
"step":
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 39.0,
|
| 588 |
-
"eval_accuracy": 0.
|
| 589 |
-
"eval_loss":
|
| 590 |
-
"eval_runtime":
|
| 591 |
-
"eval_samples_per_second":
|
| 592 |
-
"eval_steps_per_second":
|
| 593 |
-
"step":
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 40.0,
|
| 597 |
-
"learning_rate":
|
| 598 |
-
"loss":
|
| 599 |
-
"step":
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 40.0,
|
| 603 |
-
"eval_accuracy": 0.
|
| 604 |
-
"eval_loss":
|
| 605 |
-
"eval_runtime":
|
| 606 |
-
"eval_samples_per_second":
|
| 607 |
-
"eval_steps_per_second":
|
| 608 |
-
"step":
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 41.0,
|
| 612 |
-
"learning_rate":
|
| 613 |
-
"loss":
|
| 614 |
-
"step":
|
| 615 |
},
|
| 616 |
{
|
| 617 |
"epoch": 41.0,
|
| 618 |
-
"eval_accuracy": 0.
|
| 619 |
-
"eval_loss":
|
| 620 |
-
"eval_runtime":
|
| 621 |
-
"eval_samples_per_second":
|
| 622 |
-
"eval_steps_per_second":
|
| 623 |
-
"step":
|
| 624 |
},
|
| 625 |
{
|
| 626 |
-
"epoch":
|
| 627 |
-
"learning_rate":
|
| 628 |
-
"loss":
|
| 629 |
-
"step": 75054
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"epoch": 42.0,
|
| 633 |
-
"eval_accuracy": 0.6374992997591171,
|
| 634 |
-
"eval_loss": NaN,
|
| 635 |
-
"eval_runtime": 2.2992,
|
| 636 |
-
"eval_samples_per_second": 208.332,
|
| 637 |
-
"eval_steps_per_second": 1.74,
|
| 638 |
-
"step": 75054
|
| 639 |
-
},
|
| 640 |
-
{
|
| 641 |
-
"epoch": 43.0,
|
| 642 |
-
"learning_rate": 3.723324441480494e-05,
|
| 643 |
-
"loss": 0.0,
|
| 644 |
-
"step": 76841
|
| 645 |
-
},
|
| 646 |
-
{
|
| 647 |
-
"epoch": 43.0,
|
| 648 |
-
"eval_accuracy": 0.6292381720579646,
|
| 649 |
-
"eval_loss": NaN,
|
| 650 |
-
"eval_runtime": 2.3504,
|
| 651 |
-
"eval_samples_per_second": 203.794,
|
| 652 |
-
"eval_steps_per_second": 1.702,
|
| 653 |
-
"step": 76841
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 44.0,
|
| 657 |
-
"learning_rate": 3.69353117705902e-05,
|
| 658 |
-
"loss": 0.0,
|
| 659 |
-
"step": 78628
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 44.0,
|
| 663 |
-
"eval_accuracy": 0.6336636427076064,
|
| 664 |
-
"eval_loss": NaN,
|
| 665 |
-
"eval_runtime": 2.1818,
|
| 666 |
-
"eval_samples_per_second": 219.543,
|
| 667 |
-
"eval_steps_per_second": 1.833,
|
| 668 |
-
"step": 78628
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 45.0,
|
| 672 |
-
"learning_rate": 3.663737912637546e-05,
|
| 673 |
-
"loss": 0.0,
|
| 674 |
-
"step": 80415
|
| 675 |
-
},
|
| 676 |
-
{
|
| 677 |
-
"epoch": 45.0,
|
| 678 |
-
"eval_accuracy": 0.6451018731049335,
|
| 679 |
-
"eval_loss": NaN,
|
| 680 |
-
"eval_runtime": 2.2283,
|
| 681 |
-
"eval_samples_per_second": 214.958,
|
| 682 |
-
"eval_steps_per_second": 1.795,
|
| 683 |
-
"step": 80415
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 46.0,
|
| 687 |
-
"learning_rate": 3.6339446482160724e-05,
|
| 688 |
-
"loss": 0.0,
|
| 689 |
-
"step": 82202
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 46.0,
|
| 693 |
-
"eval_accuracy": 0.6376266844860229,
|
| 694 |
-
"eval_loss": NaN,
|
| 695 |
-
"eval_runtime": 2.9896,
|
| 696 |
-
"eval_samples_per_second": 160.224,
|
| 697 |
-
"eval_steps_per_second": 1.338,
|
| 698 |
-
"step": 82202
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 47.0,
|
| 702 |
-
"learning_rate": 3.6041513837945984e-05,
|
| 703 |
-
"loss": 0.0,
|
| 704 |
-
"step": 83989
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 47.0,
|
| 708 |
-
"eval_accuracy": 0.6354616290150793,
|
| 709 |
-
"eval_loss": NaN,
|
| 710 |
-
"eval_runtime": 2.3984,
|
| 711 |
-
"eval_samples_per_second": 199.716,
|
| 712 |
-
"eval_steps_per_second": 1.668,
|
| 713 |
-
"step": 83989
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 48.0,
|
| 717 |
-
"learning_rate": 3.5743581193731244e-05,
|
| 718 |
-
"loss": 0.0,
|
| 719 |
-
"step": 85776
|
| 720 |
-
},
|
| 721 |
-
{
|
| 722 |
-
"epoch": 48.0,
|
| 723 |
-
"eval_accuracy": 0.64114792031153,
|
| 724 |
-
"eval_loss": NaN,
|
| 725 |
-
"eval_runtime": 2.2,
|
| 726 |
-
"eval_samples_per_second": 217.728,
|
| 727 |
-
"eval_steps_per_second": 1.818,
|
| 728 |
-
"step": 85776
|
| 729 |
-
},
|
| 730 |
-
{
|
| 731 |
-
"epoch": 49.0,
|
| 732 |
-
"learning_rate": 3.544564854951651e-05,
|
| 733 |
-
"loss": 0.0,
|
| 734 |
-
"step": 87563
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 49.0,
|
| 738 |
-
"eval_accuracy": 0.6358090934764191,
|
| 739 |
-
"eval_loss": NaN,
|
| 740 |
-
"eval_runtime": 2.0902,
|
| 741 |
-
"eval_samples_per_second": 229.163,
|
| 742 |
-
"eval_steps_per_second": 1.914,
|
| 743 |
-
"step": 87563
|
| 744 |
-
},
|
| 745 |
-
{
|
| 746 |
-
"epoch": 50.0,
|
| 747 |
-
"learning_rate": 3.514771590530177e-05,
|
| 748 |
-
"loss": 0.0,
|
| 749 |
-
"step": 89350
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 50.0,
|
| 753 |
-
"eval_accuracy": 0.64278059785674,
|
| 754 |
-
"eval_loss": NaN,
|
| 755 |
-
"eval_runtime": 2.0804,
|
| 756 |
-
"eval_samples_per_second": 230.249,
|
| 757 |
-
"eval_steps_per_second": 1.923,
|
| 758 |
-
"step": 89350
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 51.0,
|
| 762 |
-
"learning_rate": 3.484978326108703e-05,
|
| 763 |
-
"loss": 0.0,
|
| 764 |
-
"step": 91137
|
| 765 |
-
},
|
| 766 |
-
{
|
| 767 |
-
"epoch": 51.0,
|
| 768 |
-
"eval_accuracy": 0.6421150697306759,
|
| 769 |
-
"eval_loss": NaN,
|
| 770 |
-
"eval_runtime": 2.0459,
|
| 771 |
-
"eval_samples_per_second": 234.122,
|
| 772 |
-
"eval_steps_per_second": 1.955,
|
| 773 |
-
"step": 91137
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 52.0,
|
| 777 |
-
"learning_rate": 3.4551850616872296e-05,
|
| 778 |
-
"loss": 0.004,
|
| 779 |
-
"step": 92924
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 52.0,
|
| 783 |
-
"eval_accuracy": 0.6352199471785989,
|
| 784 |
-
"eval_loss": NaN,
|
| 785 |
-
"eval_runtime": 1.9574,
|
| 786 |
-
"eval_samples_per_second": 244.709,
|
| 787 |
-
"eval_steps_per_second": 2.044,
|
| 788 |
-
"step": 92924
|
| 789 |
-
},
|
| 790 |
-
{
|
| 791 |
-
"epoch": 53.0,
|
| 792 |
-
"learning_rate": 3.4253917972657556e-05,
|
| 793 |
-
"loss": 0.0,
|
| 794 |
-
"step": 94711
|
| 795 |
-
},
|
| 796 |
-
{
|
| 797 |
-
"epoch": 53.0,
|
| 798 |
-
"eval_accuracy": 0.641116936275197,
|
| 799 |
-
"eval_loss": NaN,
|
| 800 |
-
"eval_runtime": 1.8623,
|
| 801 |
-
"eval_samples_per_second": 257.205,
|
| 802 |
-
"eval_steps_per_second": 2.148,
|
| 803 |
-
"step": 94711
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 54.0,
|
| 807 |
-
"learning_rate": 3.3955985328442816e-05,
|
| 808 |
-
"loss": 0.0,
|
| 809 |
-
"step": 96498
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 54.0,
|
| 813 |
-
"eval_accuracy": 0.6376506868516961,
|
| 814 |
-
"eval_loss": NaN,
|
| 815 |
-
"eval_runtime": 2.0734,
|
| 816 |
-
"eval_samples_per_second": 231.022,
|
| 817 |
-
"eval_steps_per_second": 1.929,
|
| 818 |
-
"step": 96498
|
| 819 |
-
},
|
| 820 |
-
{
|
| 821 |
-
"epoch": 55.0,
|
| 822 |
-
"learning_rate": 3.3658052684228076e-05,
|
| 823 |
-
"loss": 0.0,
|
| 824 |
-
"step": 98285
|
| 825 |
-
},
|
| 826 |
-
{
|
| 827 |
-
"epoch": 55.0,
|
| 828 |
-
"eval_accuracy": 0.6374884528175125,
|
| 829 |
-
"eval_loss": NaN,
|
| 830 |
-
"eval_runtime": 1.9769,
|
| 831 |
-
"eval_samples_per_second": 242.303,
|
| 832 |
-
"eval_steps_per_second": 2.023,
|
| 833 |
-
"step": 98285
|
| 834 |
-
},
|
| 835 |
-
{
|
| 836 |
-
"epoch": 56.0,
|
| 837 |
-
"learning_rate": 3.3360120040013336e-05,
|
| 838 |
-
"loss": 0.0,
|
| 839 |
-
"step": 100072
|
| 840 |
-
},
|
| 841 |
-
{
|
| 842 |
-
"epoch": 56.0,
|
| 843 |
-
"eval_accuracy": 0.6368413657439933,
|
| 844 |
-
"eval_loss": NaN,
|
| 845 |
-
"eval_runtime": 2.4635,
|
| 846 |
-
"eval_samples_per_second": 194.44,
|
| 847 |
-
"eval_steps_per_second": 1.624,
|
| 848 |
-
"step": 100072
|
| 849 |
-
},
|
| 850 |
-
{
|
| 851 |
-
"epoch": 57.0,
|
| 852 |
-
"learning_rate": 3.30621873957986e-05,
|
| 853 |
-
"loss": 0.0,
|
| 854 |
-
"step": 101859
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 57.0,
|
| 858 |
-
"eval_accuracy": 0.6364829030006979,
|
| 859 |
-
"eval_loss": NaN,
|
| 860 |
-
"eval_runtime": 2.4227,
|
| 861 |
-
"eval_samples_per_second": 197.715,
|
| 862 |
-
"eval_steps_per_second": 1.651,
|
| 863 |
-
"step": 101859
|
| 864 |
-
},
|
| 865 |
-
{
|
| 866 |
-
"epoch": 58.0,
|
| 867 |
-
"learning_rate": 3.276425475158386e-05,
|
| 868 |
-
"loss": 0.0,
|
| 869 |
-
"step": 103646
|
| 870 |
-
},
|
| 871 |
-
{
|
| 872 |
-
"epoch": 58.0,
|
| 873 |
-
"eval_accuracy": 0.6412562335406511,
|
| 874 |
-
"eval_loss": NaN,
|
| 875 |
-
"eval_runtime": 2.535,
|
| 876 |
-
"eval_samples_per_second": 188.957,
|
| 877 |
-
"eval_steps_per_second": 1.578,
|
| 878 |
-
"step": 103646
|
| 879 |
-
},
|
| 880 |
-
{
|
| 881 |
-
"epoch": 59.0,
|
| 882 |
-
"learning_rate": 3.246632210736912e-05,
|
| 883 |
-
"loss": 0.0,
|
| 884 |
-
"step": 105433
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"epoch": 59.0,
|
| 888 |
-
"eval_accuracy": 0.6347360495273153,
|
| 889 |
-
"eval_loss": NaN,
|
| 890 |
-
"eval_runtime": 2.3607,
|
| 891 |
-
"eval_samples_per_second": 202.908,
|
| 892 |
-
"eval_steps_per_second": 1.694,
|
| 893 |
-
"step": 105433
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"epoch": 60.0,
|
| 897 |
-
"learning_rate": 3.216838946315439e-05,
|
| 898 |
-
"loss": 0.0,
|
| 899 |
-
"step": 107220
|
| 900 |
-
},
|
| 901 |
-
{
|
| 902 |
-
"epoch": 60.0,
|
| 903 |
-
"eval_accuracy": 0.6407410498205791,
|
| 904 |
-
"eval_loss": NaN,
|
| 905 |
-
"eval_runtime": 2.469,
|
| 906 |
-
"eval_samples_per_second": 194.009,
|
| 907 |
-
"eval_steps_per_second": 1.62,
|
| 908 |
-
"step": 107220
|
| 909 |
-
},
|
| 910 |
-
{
|
| 911 |
-
"epoch": 61.0,
|
| 912 |
-
"learning_rate": 3.187045681893965e-05,
|
| 913 |
-
"loss": 0.0,
|
| 914 |
-
"step": 109007
|
| 915 |
-
},
|
| 916 |
-
{
|
| 917 |
-
"epoch": 61.0,
|
| 918 |
-
"eval_accuracy": 0.6394521622227202,
|
| 919 |
-
"eval_loss": NaN,
|
| 920 |
-
"eval_runtime": 2.4014,
|
| 921 |
-
"eval_samples_per_second": 199.465,
|
| 922 |
-
"eval_steps_per_second": 1.666,
|
| 923 |
-
"step": 109007
|
| 924 |
-
},
|
| 925 |
-
{
|
| 926 |
-
"epoch": 62.0,
|
| 927 |
-
"learning_rate": 3.157252417472491e-05,
|
| 928 |
-
"loss": 0.0,
|
| 929 |
-
"step": 110794
|
| 930 |
-
},
|
| 931 |
-
{
|
| 932 |
-
"epoch": 62.0,
|
| 933 |
-
"eval_accuracy": 0.6373080145210835,
|
| 934 |
-
"eval_loss": NaN,
|
| 935 |
-
"eval_runtime": 3.0171,
|
| 936 |
-
"eval_samples_per_second": 158.763,
|
| 937 |
-
"eval_steps_per_second": 1.326,
|
| 938 |
-
"step": 110794
|
| 939 |
-
},
|
| 940 |
-
{
|
| 941 |
-
"epoch": 63.0,
|
| 942 |
-
"learning_rate": 3.1274591530510175e-05,
|
| 943 |
-
"loss": 0.0,
|
| 944 |
-
"step": 112581
|
| 945 |
-
},
|
| 946 |
-
{
|
| 947 |
-
"epoch": 63.0,
|
| 948 |
-
"eval_accuracy": 0.6356097148176356,
|
| 949 |
-
"eval_loss": NaN,
|
| 950 |
-
"eval_runtime": 2.5297,
|
| 951 |
-
"eval_samples_per_second": 189.349,
|
| 952 |
-
"eval_steps_per_second": 1.581,
|
| 953 |
-
"step": 112581
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 64.0,
|
| 957 |
-
"learning_rate": 3.0976658886295434e-05,
|
| 958 |
-
"loss": 0.0,
|
| 959 |
-
"step": 114368
|
| 960 |
-
},
|
| 961 |
-
{
|
| 962 |
-
"epoch": 64.0,
|
| 963 |
-
"eval_accuracy": 0.6366671342404264,
|
| 964 |
-
"eval_loss": NaN,
|
| 965 |
-
"eval_runtime": 2.4813,
|
| 966 |
-
"eval_samples_per_second": 193.043,
|
| 967 |
-
"eval_steps_per_second": 1.612,
|
| 968 |
-
"step": 114368
|
| 969 |
-
},
|
| 970 |
-
{
|
| 971 |
-
"epoch": 65.0,
|
| 972 |
-
"learning_rate": 3.0678726242080694e-05,
|
| 973 |
-
"loss": 0.0,
|
| 974 |
-
"step": 116155
|
| 975 |
-
},
|
| 976 |
-
{
|
| 977 |
-
"epoch": 65.0,
|
| 978 |
-
"eval_accuracy": 0.6440701993138839,
|
| 979 |
-
"eval_loss": NaN,
|
| 980 |
-
"eval_runtime": 3.2092,
|
| 981 |
-
"eval_samples_per_second": 149.257,
|
| 982 |
-
"eval_steps_per_second": 1.246,
|
| 983 |
-
"step": 116155
|
| 984 |
-
},
|
| 985 |
-
{
|
| 986 |
-
"epoch": 66.0,
|
| 987 |
-
"learning_rate": 3.0380793597865957e-05,
|
| 988 |
-
"loss": 0.0017,
|
| 989 |
-
"step": 117942
|
| 990 |
-
},
|
| 991 |
-
{
|
| 992 |
-
"epoch": 66.0,
|
| 993 |
-
"eval_accuracy": 0.6379713046379714,
|
| 994 |
-
"eval_loss": NaN,
|
| 995 |
-
"eval_runtime": 2.5164,
|
| 996 |
-
"eval_samples_per_second": 190.349,
|
| 997 |
-
"eval_steps_per_second": 1.59,
|
| 998 |
-
"step": 117942
|
| 999 |
-
},
|
| 1000 |
-
{
|
| 1001 |
-
"epoch": 67.0,
|
| 1002 |
-
"learning_rate": 3.008286095365122e-05,
|
| 1003 |
-
"loss": 0.0,
|
| 1004 |
-
"step": 119729
|
| 1005 |
-
},
|
| 1006 |
-
{
|
| 1007 |
-
"epoch": 67.0,
|
| 1008 |
-
"eval_accuracy": 0.6348476780359295,
|
| 1009 |
-
"eval_loss": NaN,
|
| 1010 |
-
"eval_runtime": 2.4358,
|
| 1011 |
-
"eval_samples_per_second": 196.654,
|
| 1012 |
-
"eval_steps_per_second": 1.642,
|
| 1013 |
-
"step": 119729
|
| 1014 |
-
},
|
| 1015 |
-
{
|
| 1016 |
-
"epoch": 68.0,
|
| 1017 |
-
"learning_rate": 2.9784928309436484e-05,
|
| 1018 |
-
"loss": 0.0,
|
| 1019 |
-
"step": 121516
|
| 1020 |
-
},
|
| 1021 |
-
{
|
| 1022 |
-
"epoch": 68.0,
|
| 1023 |
-
"eval_accuracy": 0.6356471316782075,
|
| 1024 |
-
"eval_loss": NaN,
|
| 1025 |
-
"eval_runtime": 1.8438,
|
| 1026 |
-
"eval_samples_per_second": 259.796,
|
| 1027 |
-
"eval_steps_per_second": 2.169,
|
| 1028 |
-
"step": 121516
|
| 1029 |
-
},
|
| 1030 |
-
{
|
| 1031 |
-
"epoch": 69.0,
|
| 1032 |
-
"learning_rate": 2.948699566522174e-05,
|
| 1033 |
-
"loss": 0.0,
|
| 1034 |
-
"step": 123303
|
| 1035 |
-
},
|
| 1036 |
-
{
|
| 1037 |
-
"epoch": 69.0,
|
| 1038 |
-
"eval_accuracy": 0.6391043176626526,
|
| 1039 |
-
"eval_loss": NaN,
|
| 1040 |
-
"eval_runtime": 2.4179,
|
| 1041 |
-
"eval_samples_per_second": 198.106,
|
| 1042 |
-
"eval_steps_per_second": 1.654,
|
| 1043 |
-
"step": 123303
|
| 1044 |
-
},
|
| 1045 |
-
{
|
| 1046 |
-
"epoch": 70.0,
|
| 1047 |
-
"learning_rate": 2.9189063021007e-05,
|
| 1048 |
-
"loss": 0.0006,
|
| 1049 |
-
"step": 125090
|
| 1050 |
-
},
|
| 1051 |
-
{
|
| 1052 |
-
"epoch": 70.0,
|
| 1053 |
-
"eval_accuracy": 0.636170153182671,
|
| 1054 |
-
"eval_loss": NaN,
|
| 1055 |
-
"eval_runtime": 2.5589,
|
| 1056 |
-
"eval_samples_per_second": 187.19,
|
| 1057 |
-
"eval_steps_per_second": 1.563,
|
| 1058 |
-
"step": 125090
|
| 1059 |
-
},
|
| 1060 |
-
{
|
| 1061 |
-
"epoch": 71.0,
|
| 1062 |
-
"learning_rate": 2.8891130376792263e-05,
|
| 1063 |
-
"loss": 0.0,
|
| 1064 |
-
"step": 126877
|
| 1065 |
-
},
|
| 1066 |
-
{
|
| 1067 |
-
"epoch": 71.0,
|
| 1068 |
-
"eval_accuracy": 0.6387962677575724,
|
| 1069 |
-
"eval_loss": NaN,
|
| 1070 |
-
"eval_runtime": 2.2538,
|
| 1071 |
-
"eval_samples_per_second": 212.526,
|
| 1072 |
-
"eval_steps_per_second": 1.775,
|
| 1073 |
-
"step": 126877
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"epoch": 72.0,
|
| 1077 |
-
"learning_rate": 2.8593197732577526e-05,
|
| 1078 |
-
"loss": 0.0,
|
| 1079 |
-
"step": 128664
|
| 1080 |
-
},
|
| 1081 |
-
{
|
| 1082 |
-
"epoch": 72.0,
|
| 1083 |
-
"eval_accuracy": 0.6353993285750558,
|
| 1084 |
-
"eval_loss": NaN,
|
| 1085 |
-
"eval_runtime": 2.4543,
|
| 1086 |
-
"eval_samples_per_second": 195.171,
|
| 1087 |
-
"eval_steps_per_second": 1.63,
|
| 1088 |
-
"step": 128664
|
| 1089 |
-
},
|
| 1090 |
-
{
|
| 1091 |
-
"epoch": 73.0,
|
| 1092 |
-
"learning_rate": 2.8295265088362786e-05,
|
| 1093 |
-
"loss": 0.0,
|
| 1094 |
-
"step": 130451
|
| 1095 |
-
},
|
| 1096 |
-
{
|
| 1097 |
-
"epoch": 73.0,
|
| 1098 |
-
"eval_accuracy": 0.6361857774753318,
|
| 1099 |
-
"eval_loss": NaN,
|
| 1100 |
-
"eval_runtime": 2.4316,
|
| 1101 |
-
"eval_samples_per_second": 196.992,
|
| 1102 |
-
"eval_steps_per_second": 1.645,
|
| 1103 |
-
"step": 130451
|
| 1104 |
-
},
|
| 1105 |
-
{
|
| 1106 |
-
"epoch": 74.0,
|
| 1107 |
-
"learning_rate": 2.799733244414805e-05,
|
| 1108 |
-
"loss": 0.0013,
|
| 1109 |
-
"step": 132238
|
| 1110 |
-
},
|
| 1111 |
-
{
|
| 1112 |
-
"epoch": 74.0,
|
| 1113 |
-
"eval_accuracy": 0.6347066167290887,
|
| 1114 |
-
"eval_loss": NaN,
|
| 1115 |
-
"eval_runtime": 2.3647,
|
| 1116 |
-
"eval_samples_per_second": 202.564,
|
| 1117 |
-
"eval_steps_per_second": 1.692,
|
| 1118 |
-
"step": 132238
|
| 1119 |
-
},
|
| 1120 |
-
{
|
| 1121 |
-
"epoch": 75.0,
|
| 1122 |
-
"learning_rate": 2.7699399799933313e-05,
|
| 1123 |
-
"loss": 0.0,
|
| 1124 |
-
"step": 134025
|
| 1125 |
-
},
|
| 1126 |
-
{
|
| 1127 |
-
"epoch": 75.0,
|
| 1128 |
-
"eval_accuracy": 0.632699704554323,
|
| 1129 |
-
"eval_loss": NaN,
|
| 1130 |
-
"eval_runtime": 2.4813,
|
| 1131 |
-
"eval_samples_per_second": 193.045,
|
| 1132 |
-
"eval_steps_per_second": 1.612,
|
| 1133 |
-
"step": 134025
|
| 1134 |
-
},
|
| 1135 |
-
{
|
| 1136 |
-
"epoch": 76.0,
|
| 1137 |
-
"learning_rate": 2.7401467155718576e-05,
|
| 1138 |
-
"loss": 0.0,
|
| 1139 |
-
"step": 135812
|
| 1140 |
-
},
|
| 1141 |
-
{
|
| 1142 |
-
"epoch": 76.0,
|
| 1143 |
-
"eval_accuracy": 0.6382416594058293,
|
| 1144 |
-
"eval_loss": NaN,
|
| 1145 |
-
"eval_runtime": 2.3498,
|
| 1146 |
-
"eval_samples_per_second": 203.844,
|
| 1147 |
-
"eval_steps_per_second": 1.702,
|
| 1148 |
-
"step": 135812
|
| 1149 |
-
},
|
| 1150 |
-
{
|
| 1151 |
-
"epoch": 77.0,
|
| 1152 |
-
"learning_rate": 2.7103534511503836e-05,
|
| 1153 |
-
"loss": 0.0,
|
| 1154 |
-
"step": 137599
|
| 1155 |
-
},
|
| 1156 |
-
{
|
| 1157 |
-
"epoch": 77.0,
|
| 1158 |
-
"eval_accuracy": 0.6411355703960205,
|
| 1159 |
-
"eval_loss": NaN,
|
| 1160 |
-
"eval_runtime": 1.8611,
|
| 1161 |
-
"eval_samples_per_second": 257.378,
|
| 1162 |
-
"eval_steps_per_second": 2.149,
|
| 1163 |
-
"step": 137599
|
| 1164 |
-
},
|
| 1165 |
-
{
|
| 1166 |
-
"epoch": 78.0,
|
| 1167 |
-
"learning_rate": 2.68056018672891e-05,
|
| 1168 |
-
"loss": 0.0,
|
| 1169 |
-
"step": 139386
|
| 1170 |
-
},
|
| 1171 |
-
{
|
| 1172 |
-
"epoch": 78.0,
|
| 1173 |
-
"eval_accuracy": 0.640435869351532,
|
| 1174 |
-
"eval_loss": NaN,
|
| 1175 |
-
"eval_runtime": 2.2547,
|
| 1176 |
-
"eval_samples_per_second": 212.448,
|
| 1177 |
-
"eval_steps_per_second": 1.774,
|
| 1178 |
-
"step": 139386
|
| 1179 |
-
},
|
| 1180 |
-
{
|
| 1181 |
-
"epoch": 79.0,
|
| 1182 |
-
"learning_rate": 2.6507669223074362e-05,
|
| 1183 |
-
"loss": 0.0,
|
| 1184 |
-
"step": 141173
|
| 1185 |
-
},
|
| 1186 |
-
{
|
| 1187 |
-
"epoch": 79.0,
|
| 1188 |
-
"eval_accuracy": 0.6391697411777959,
|
| 1189 |
-
"eval_loss": NaN,
|
| 1190 |
-
"eval_runtime": 2.1542,
|
| 1191 |
-
"eval_samples_per_second": 222.352,
|
| 1192 |
-
"eval_steps_per_second": 1.857,
|
| 1193 |
-
"step": 141173
|
| 1194 |
-
},
|
| 1195 |
-
{
|
| 1196 |
-
"epoch": 80.0,
|
| 1197 |
-
"learning_rate": 2.6209736578859622e-05,
|
| 1198 |
-
"loss": 0.0,
|
| 1199 |
-
"step": 142960
|
| 1200 |
-
},
|
| 1201 |
-
{
|
| 1202 |
-
"epoch": 80.0,
|
| 1203 |
-
"eval_accuracy": 0.6403956068586798,
|
| 1204 |
-
"eval_loss": NaN,
|
| 1205 |
-
"eval_runtime": 2.2858,
|
| 1206 |
-
"eval_samples_per_second": 209.555,
|
| 1207 |
-
"eval_steps_per_second": 1.75,
|
| 1208 |
-
"step": 142960
|
| 1209 |
-
},
|
| 1210 |
-
{
|
| 1211 |
-
"epoch": 81.0,
|
| 1212 |
-
"learning_rate": 2.5911803934644885e-05,
|
| 1213 |
-
"loss": 0.0,
|
| 1214 |
-
"step": 144747
|
| 1215 |
-
},
|
| 1216 |
-
{
|
| 1217 |
-
"epoch": 81.0,
|
| 1218 |
-
"eval_accuracy": 0.6420577823455521,
|
| 1219 |
-
"eval_loss": NaN,
|
| 1220 |
-
"eval_runtime": 2.0194,
|
| 1221 |
-
"eval_samples_per_second": 237.198,
|
| 1222 |
-
"eval_steps_per_second": 1.981,
|
| 1223 |
-
"step": 144747
|
| 1224 |
-
},
|
| 1225 |
-
{
|
| 1226 |
-
"epoch": 82.0,
|
| 1227 |
-
"learning_rate": 2.5613871290430148e-05,
|
| 1228 |
-
"loss": 0.0,
|
| 1229 |
-
"step": 146534
|
| 1230 |
-
},
|
| 1231 |
-
{
|
| 1232 |
-
"epoch": 82.0,
|
| 1233 |
-
"eval_accuracy": 0.6363990538472242,
|
| 1234 |
-
"eval_loss": NaN,
|
| 1235 |
-
"eval_runtime": 2.2166,
|
| 1236 |
-
"eval_samples_per_second": 216.094,
|
| 1237 |
-
"eval_steps_per_second": 1.805,
|
| 1238 |
-
"step": 146534
|
| 1239 |
-
},
|
| 1240 |
-
{
|
| 1241 |
-
"epoch": 83.0,
|
| 1242 |
-
"learning_rate": 2.5315938646215408e-05,
|
| 1243 |
-
"loss": 0.0,
|
| 1244 |
-
"step": 148321
|
| 1245 |
-
},
|
| 1246 |
-
{
|
| 1247 |
-
"epoch": 83.0,
|
| 1248 |
-
"eval_accuracy": 0.6363839910439406,
|
| 1249 |
-
"eval_loss": NaN,
|
| 1250 |
-
"eval_runtime": 2.0538,
|
| 1251 |
-
"eval_samples_per_second": 233.223,
|
| 1252 |
-
"eval_steps_per_second": 1.948,
|
| 1253 |
-
"step": 148321
|
| 1254 |
-
},
|
| 1255 |
-
{
|
| 1256 |
-
"epoch": 84.0,
|
| 1257 |
-
"learning_rate": 2.5018006002000664e-05,
|
| 1258 |
-
"loss": 0.0,
|
| 1259 |
-
"step": 150108
|
| 1260 |
-
},
|
| 1261 |
-
{
|
| 1262 |
-
"epoch": 84.0,
|
| 1263 |
-
"eval_accuracy": 0.6370422337589449,
|
| 1264 |
-
"eval_loss": NaN,
|
| 1265 |
-
"eval_runtime": 1.9129,
|
| 1266 |
-
"eval_samples_per_second": 250.403,
|
| 1267 |
-
"eval_steps_per_second": 2.091,
|
| 1268 |
-
"step": 150108
|
| 1269 |
-
},
|
| 1270 |
-
{
|
| 1271 |
-
"epoch": 85.0,
|
| 1272 |
-
"learning_rate": 2.472007335778593e-05,
|
| 1273 |
-
"loss": 0.0,
|
| 1274 |
-
"step": 151895
|
| 1275 |
-
},
|
| 1276 |
-
{
|
| 1277 |
-
"epoch": 85.0,
|
| 1278 |
-
"eval_accuracy": 0.6357136919112145,
|
| 1279 |
-
"eval_loss": NaN,
|
| 1280 |
-
"eval_runtime": 1.9511,
|
| 1281 |
-
"eval_samples_per_second": 245.5,
|
| 1282 |
-
"eval_steps_per_second": 2.05,
|
| 1283 |
-
"step": 151895
|
| 1284 |
-
},
|
| 1285 |
-
{
|
| 1286 |
-
"epoch": 86.0,
|
| 1287 |
-
"learning_rate": 2.4422140713571194e-05,
|
| 1288 |
-
"loss": 0.0,
|
| 1289 |
-
"step": 153682
|
| 1290 |
-
},
|
| 1291 |
-
{
|
| 1292 |
-
"epoch": 86.0,
|
| 1293 |
-
"eval_accuracy": 0.6353468815697267,
|
| 1294 |
-
"eval_loss": NaN,
|
| 1295 |
-
"eval_runtime": 2.3614,
|
| 1296 |
-
"eval_samples_per_second": 202.845,
|
| 1297 |
-
"eval_steps_per_second": 1.694,
|
| 1298 |
-
"step": 153682
|
| 1299 |
-
},
|
| 1300 |
-
{
|
| 1301 |
-
"epoch": 87.0,
|
| 1302 |
-
"learning_rate": 2.412420806935645e-05,
|
| 1303 |
-
"loss": 0.0,
|
| 1304 |
-
"step": 155469
|
| 1305 |
-
},
|
| 1306 |
-
{
|
| 1307 |
-
"epoch": 87.0,
|
| 1308 |
-
"eval_accuracy": 0.6392810219998323,
|
| 1309 |
-
"eval_loss": NaN,
|
| 1310 |
-
"eval_runtime": 1.9531,
|
| 1311 |
-
"eval_samples_per_second": 245.249,
|
| 1312 |
-
"eval_steps_per_second": 2.048,
|
| 1313 |
-
"step": 155469
|
| 1314 |
-
},
|
| 1315 |
-
{
|
| 1316 |
-
"epoch": 88.0,
|
| 1317 |
-
"learning_rate": 2.3826275425141714e-05,
|
| 1318 |
-
"loss": 0.0,
|
| 1319 |
-
"step": 157256
|
| 1320 |
-
},
|
| 1321 |
-
{
|
| 1322 |
-
"epoch": 88.0,
|
| 1323 |
-
"eval_accuracy": 0.639685437438562,
|
| 1324 |
-
"eval_loss": NaN,
|
| 1325 |
-
"eval_runtime": 2.3006,
|
| 1326 |
-
"eval_samples_per_second": 208.209,
|
| 1327 |
-
"eval_steps_per_second": 1.739,
|
| 1328 |
-
"step": 157256
|
| 1329 |
-
},
|
| 1330 |
-
{
|
| 1331 |
-
"epoch": 89.0,
|
| 1332 |
-
"learning_rate": 2.3528342780926977e-05,
|
| 1333 |
-
"loss": 0.0006,
|
| 1334 |
-
"step": 159043
|
| 1335 |
-
},
|
| 1336 |
-
{
|
| 1337 |
-
"epoch": 89.0,
|
| 1338 |
-
"eval_accuracy": 0.639618138424821,
|
| 1339 |
-
"eval_loss": NaN,
|
| 1340 |
-
"eval_runtime": 2.0432,
|
| 1341 |
-
"eval_samples_per_second": 234.432,
|
| 1342 |
-
"eval_steps_per_second": 1.958,
|
| 1343 |
-
"step": 159043
|
| 1344 |
-
},
|
| 1345 |
-
{
|
| 1346 |
-
"epoch": 90.0,
|
| 1347 |
-
"learning_rate": 2.3230410136712237e-05,
|
| 1348 |
-
"loss": 0.0013,
|
| 1349 |
-
"step": 160830
|
| 1350 |
-
},
|
| 1351 |
-
{
|
| 1352 |
-
"epoch": 90.0,
|
| 1353 |
-
"eval_accuracy": 0.6378478767047344,
|
| 1354 |
-
"eval_loss": NaN,
|
| 1355 |
-
"eval_runtime": 2.1388,
|
| 1356 |
-
"eval_samples_per_second": 223.962,
|
| 1357 |
-
"eval_steps_per_second": 1.87,
|
| 1358 |
-
"step": 160830
|
| 1359 |
-
},
|
| 1360 |
-
{
|
| 1361 |
-
"epoch": 91.0,
|
| 1362 |
-
"learning_rate": 2.29324774924975e-05,
|
| 1363 |
-
"loss": 0.0,
|
| 1364 |
-
"step": 162617
|
| 1365 |
-
},
|
| 1366 |
-
{
|
| 1367 |
-
"epoch": 91.0,
|
| 1368 |
-
"eval_accuracy": 0.6385569271433793,
|
| 1369 |
-
"eval_loss": NaN,
|
| 1370 |
-
"eval_runtime": 1.9971,
|
| 1371 |
-
"eval_samples_per_second": 239.843,
|
| 1372 |
-
"eval_steps_per_second": 2.003,
|
| 1373 |
-
"step": 162617
|
| 1374 |
-
},
|
| 1375 |
-
{
|
| 1376 |
-
"epoch": 92.0,
|
| 1377 |
-
"learning_rate": 2.2634544848282763e-05,
|
| 1378 |
-
"loss": 0.0,
|
| 1379 |
-
"step": 164404
|
| 1380 |
-
},
|
| 1381 |
-
{
|
| 1382 |
-
"epoch": 92.0,
|
| 1383 |
-
"eval_accuracy": 0.6414956218149055,
|
| 1384 |
-
"eval_loss": NaN,
|
| 1385 |
-
"eval_runtime": 2.0014,
|
| 1386 |
-
"eval_samples_per_second": 239.331,
|
| 1387 |
-
"eval_steps_per_second": 1.999,
|
| 1388 |
-
"step": 164404
|
| 1389 |
-
},
|
| 1390 |
-
{
|
| 1391 |
-
"epoch": 93.0,
|
| 1392 |
-
"learning_rate": 2.2336612204068026e-05,
|
| 1393 |
-
"loss": 0.0,
|
| 1394 |
-
"step": 166191
|
| 1395 |
-
},
|
| 1396 |
-
{
|
| 1397 |
-
"epoch": 93.0,
|
| 1398 |
-
"eval_accuracy": 0.6342390696634239,
|
| 1399 |
-
"eval_loss": NaN,
|
| 1400 |
-
"eval_runtime": 1.987,
|
| 1401 |
-
"eval_samples_per_second": 241.063,
|
| 1402 |
-
"eval_steps_per_second": 2.013,
|
| 1403 |
-
"step": 166191
|
| 1404 |
-
},
|
| 1405 |
-
{
|
| 1406 |
-
"epoch": 94.0,
|
| 1407 |
-
"learning_rate": 2.2038679559853283e-05,
|
| 1408 |
-
"loss": 0.0,
|
| 1409 |
-
"step": 167978
|
| 1410 |
-
},
|
| 1411 |
-
{
|
| 1412 |
-
"epoch": 94.0,
|
| 1413 |
-
"eval_accuracy": 0.6355638270873869,
|
| 1414 |
-
"eval_loss": NaN,
|
| 1415 |
-
"eval_runtime": 1.9543,
|
| 1416 |
-
"eval_samples_per_second": 245.1,
|
| 1417 |
-
"eval_steps_per_second": 2.047,
|
| 1418 |
-
"step": 167978
|
| 1419 |
-
},
|
| 1420 |
-
{
|
| 1421 |
-
"epoch": 95.0,
|
| 1422 |
-
"learning_rate": 2.1740746915638546e-05,
|
| 1423 |
-
"loss": 0.0,
|
| 1424 |
-
"step": 169765
|
| 1425 |
-
},
|
| 1426 |
-
{
|
| 1427 |
-
"epoch": 95.0,
|
| 1428 |
-
"eval_accuracy": 0.6410132895072398,
|
| 1429 |
-
"eval_loss": NaN,
|
| 1430 |
-
"eval_runtime": 2.1422,
|
| 1431 |
-
"eval_samples_per_second": 223.599,
|
| 1432 |
-
"eval_steps_per_second": 1.867,
|
| 1433 |
-
"step": 169765
|
| 1434 |
-
},
|
| 1435 |
-
{
|
| 1436 |
-
"epoch": 96.0,
|
| 1437 |
-
"learning_rate": 2.144281427142381e-05,
|
| 1438 |
-
"loss": 0.0,
|
| 1439 |
-
"step": 171552
|
| 1440 |
-
},
|
| 1441 |
-
{
|
| 1442 |
-
"epoch": 96.0,
|
| 1443 |
-
"eval_accuracy": 0.6365928831605492,
|
| 1444 |
-
"eval_loss": NaN,
|
| 1445 |
-
"eval_runtime": 2.1461,
|
| 1446 |
-
"eval_samples_per_second": 223.199,
|
| 1447 |
-
"eval_steps_per_second": 1.864,
|
| 1448 |
-
"step": 171552
|
| 1449 |
-
},
|
| 1450 |
-
{
|
| 1451 |
-
"epoch": 97.0,
|
| 1452 |
-
"learning_rate": 2.114488162720907e-05,
|
| 1453 |
-
"loss": 0.0,
|
| 1454 |
-
"step": 173339
|
| 1455 |
-
},
|
| 1456 |
-
{
|
| 1457 |
-
"epoch": 97.0,
|
| 1458 |
-
"eval_accuracy": 0.6328623582197698,
|
| 1459 |
-
"eval_loss": NaN,
|
| 1460 |
-
"eval_runtime": 2.0065,
|
| 1461 |
-
"eval_samples_per_second": 238.72,
|
| 1462 |
-
"eval_steps_per_second": 1.993,
|
| 1463 |
-
"step": 173339
|
| 1464 |
-
},
|
| 1465 |
-
{
|
| 1466 |
-
"epoch": 98.0,
|
| 1467 |
-
"learning_rate": 2.0846948982994332e-05,
|
| 1468 |
-
"loss": 0.0013,
|
| 1469 |
-
"step": 175126
|
| 1470 |
-
},
|
| 1471 |
-
{
|
| 1472 |
-
"epoch": 98.0,
|
| 1473 |
-
"eval_accuracy": 0.635225093083606,
|
| 1474 |
-
"eval_loss": NaN,
|
| 1475 |
-
"eval_runtime": 2.2096,
|
| 1476 |
-
"eval_samples_per_second": 216.784,
|
| 1477 |
-
"eval_steps_per_second": 1.81,
|
| 1478 |
-
"step": 175126
|
| 1479 |
-
},
|
| 1480 |
-
{
|
| 1481 |
-
"epoch": 99.0,
|
| 1482 |
-
"learning_rate": 2.0549016338779595e-05,
|
| 1483 |
-
"loss": 0.0,
|
| 1484 |
-
"step": 176913
|
| 1485 |
-
},
|
| 1486 |
-
{
|
| 1487 |
-
"epoch": 99.0,
|
| 1488 |
-
"eval_accuracy": 0.633986562150056,
|
| 1489 |
-
"eval_loss": NaN,
|
| 1490 |
-
"eval_runtime": 2.7617,
|
| 1491 |
-
"eval_samples_per_second": 173.442,
|
| 1492 |
-
"eval_steps_per_second": 1.448,
|
| 1493 |
-
"step": 176913
|
| 1494 |
-
},
|
| 1495 |
-
{
|
| 1496 |
-
"epoch": 100.0,
|
| 1497 |
-
"learning_rate": 2.0251083694564855e-05,
|
| 1498 |
-
"loss": 0.0,
|
| 1499 |
-
"step": 178700
|
| 1500 |
-
},
|
| 1501 |
-
{
|
| 1502 |
-
"epoch": 100.0,
|
| 1503 |
-
"eval_accuracy": 0.6358424725822532,
|
| 1504 |
-
"eval_loss": NaN,
|
| 1505 |
-
"eval_runtime": 2.5626,
|
| 1506 |
-
"eval_samples_per_second": 186.922,
|
| 1507 |
-
"eval_steps_per_second": 1.561,
|
| 1508 |
-
"step": 178700
|
| 1509 |
-
},
|
| 1510 |
-
{
|
| 1511 |
-
"epoch": 101.0,
|
| 1512 |
-
"learning_rate": 1.995315105035012e-05,
|
| 1513 |
-
"loss": 0.0,
|
| 1514 |
-
"step": 180487
|
| 1515 |
-
},
|
| 1516 |
-
{
|
| 1517 |
-
"epoch": 101.0,
|
| 1518 |
-
"eval_accuracy": 0.6366913511247729,
|
| 1519 |
-
"eval_loss": NaN,
|
| 1520 |
-
"eval_runtime": 2.4375,
|
| 1521 |
-
"eval_samples_per_second": 196.515,
|
| 1522 |
-
"eval_steps_per_second": 1.641,
|
| 1523 |
-
"step": 180487
|
| 1524 |
-
},
|
| 1525 |
-
{
|
| 1526 |
-
"epoch": 102.0,
|
| 1527 |
-
"learning_rate": 1.9655218406135378e-05,
|
| 1528 |
-
"loss": 0.0006,
|
| 1529 |
-
"step": 182274
|
| 1530 |
-
},
|
| 1531 |
-
{
|
| 1532 |
-
"epoch": 102.0,
|
| 1533 |
-
"eval_accuracy": 0.6367565747003845,
|
| 1534 |
-
"eval_loss": NaN,
|
| 1535 |
-
"eval_runtime": 2.3509,
|
| 1536 |
-
"eval_samples_per_second": 203.749,
|
| 1537 |
-
"eval_steps_per_second": 1.701,
|
| 1538 |
-
"step": 182274
|
| 1539 |
-
},
|
| 1540 |
-
{
|
| 1541 |
-
"epoch": 103.0,
|
| 1542 |
-
"learning_rate": 1.935728576192064e-05,
|
| 1543 |
-
"loss": 0.0,
|
| 1544 |
-
"step": 184061
|
| 1545 |
-
},
|
| 1546 |
-
{
|
| 1547 |
-
"epoch": 103.0,
|
| 1548 |
-
"eval_accuracy": 0.6353013702468686,
|
| 1549 |
-
"eval_loss": NaN,
|
| 1550 |
-
"eval_runtime": 2.0088,
|
| 1551 |
-
"eval_samples_per_second": 238.45,
|
| 1552 |
-
"eval_steps_per_second": 1.991,
|
| 1553 |
-
"step": 184061
|
| 1554 |
-
},
|
| 1555 |
-
{
|
| 1556 |
-
"epoch": 104.0,
|
| 1557 |
-
"learning_rate": 1.90593531177059e-05,
|
| 1558 |
-
"loss": 0.0,
|
| 1559 |
-
"step": 185848
|
| 1560 |
-
},
|
| 1561 |
-
{
|
| 1562 |
-
"epoch": 104.0,
|
| 1563 |
-
"eval_accuracy": 0.6369532258970184,
|
| 1564 |
-
"eval_loss": NaN,
|
| 1565 |
-
"eval_runtime": 2.1758,
|
| 1566 |
-
"eval_samples_per_second": 220.149,
|
| 1567 |
-
"eval_steps_per_second": 1.838,
|
| 1568 |
-
"step": 185848
|
| 1569 |
-
},
|
| 1570 |
-
{
|
| 1571 |
-
"epoch": 105.0,
|
| 1572 |
-
"learning_rate": 1.8761420473491164e-05,
|
| 1573 |
-
"loss": 0.0,
|
| 1574 |
-
"step": 187635
|
| 1575 |
-
},
|
| 1576 |
-
{
|
| 1577 |
-
"epoch": 105.0,
|
| 1578 |
-
"eval_accuracy": 0.6333213286422694,
|
| 1579 |
-
"eval_loss": NaN,
|
| 1580 |
-
"eval_runtime": 2.3075,
|
| 1581 |
-
"eval_samples_per_second": 207.588,
|
| 1582 |
-
"eval_steps_per_second": 1.734,
|
| 1583 |
-
"step": 187635
|
| 1584 |
-
},
|
| 1585 |
-
{
|
| 1586 |
-
"epoch": 106.0,
|
| 1587 |
-
"learning_rate": 1.8463487829276428e-05,
|
| 1588 |
-
"loss": 0.0,
|
| 1589 |
-
"step": 189422
|
| 1590 |
-
},
|
| 1591 |
-
{
|
| 1592 |
-
"epoch": 106.0,
|
| 1593 |
-
"eval_accuracy": 0.6316263365222284,
|
| 1594 |
-
"eval_loss": NaN,
|
| 1595 |
-
"eval_runtime": 1.8744,
|
| 1596 |
-
"eval_samples_per_second": 255.55,
|
| 1597 |
-
"eval_steps_per_second": 2.134,
|
| 1598 |
-
"step": 189422
|
| 1599 |
-
},
|
| 1600 |
-
{
|
| 1601 |
-
"epoch": 107.0,
|
| 1602 |
-
"learning_rate": 1.8165555185061687e-05,
|
| 1603 |
-
"loss": 0.0006,
|
| 1604 |
-
"step": 191209
|
| 1605 |
-
},
|
| 1606 |
-
{
|
| 1607 |
-
"epoch": 107.0,
|
| 1608 |
-
"eval_accuracy": 0.6393596184961253,
|
| 1609 |
-
"eval_loss": NaN,
|
| 1610 |
-
"eval_runtime": 2.5091,
|
| 1611 |
-
"eval_samples_per_second": 190.907,
|
| 1612 |
-
"eval_steps_per_second": 1.594,
|
| 1613 |
-
"step": 191209
|
| 1614 |
-
},
|
| 1615 |
-
{
|
| 1616 |
-
"epoch": 108.0,
|
| 1617 |
-
"learning_rate": 1.786762254084695e-05,
|
| 1618 |
-
"loss": 0.0,
|
| 1619 |
-
"step": 192996
|
| 1620 |
-
},
|
| 1621 |
-
{
|
| 1622 |
-
"epoch": 108.0,
|
| 1623 |
-
"eval_accuracy": 0.6323443376514835,
|
| 1624 |
-
"eval_loss": NaN,
|
| 1625 |
-
"eval_runtime": 2.4565,
|
| 1626 |
-
"eval_samples_per_second": 194.993,
|
| 1627 |
-
"eval_steps_per_second": 1.628,
|
| 1628 |
-
"step": 192996
|
| 1629 |
-
},
|
| 1630 |
-
{
|
| 1631 |
-
"epoch": 109.0,
|
| 1632 |
-
"learning_rate": 1.756968989663221e-05,
|
| 1633 |
-
"loss": 0.0,
|
| 1634 |
-
"step": 194783
|
| 1635 |
-
},
|
| 1636 |
-
{
|
| 1637 |
-
"epoch": 109.0,
|
| 1638 |
-
"eval_accuracy": 0.6405684971827432,
|
| 1639 |
-
"eval_loss": NaN,
|
| 1640 |
-
"eval_runtime": 2.4473,
|
| 1641 |
-
"eval_samples_per_second": 195.727,
|
| 1642 |
-
"eval_steps_per_second": 1.634,
|
| 1643 |
-
"step": 194783
|
| 1644 |
-
},
|
| 1645 |
-
{
|
| 1646 |
-
"epoch": 110.0,
|
| 1647 |
-
"learning_rate": 1.7271757252417474e-05,
|
| 1648 |
-
"loss": 0.0012,
|
| 1649 |
-
"step": 196570
|
| 1650 |
-
},
|
| 1651 |
-
{
|
| 1652 |
-
"epoch": 110.0,
|
| 1653 |
-
"eval_accuracy": 0.6330752990851513,
|
| 1654 |
-
"eval_loss": NaN,
|
| 1655 |
-
"eval_runtime": 2.4244,
|
| 1656 |
-
"eval_samples_per_second": 197.575,
|
| 1657 |
-
"eval_steps_per_second": 1.65,
|
| 1658 |
-
"step": 196570
|
| 1659 |
-
},
|
| 1660 |
-
{
|
| 1661 |
-
"epoch": 111.0,
|
| 1662 |
-
"learning_rate": 1.6973824608202733e-05,
|
| 1663 |
-
"loss": 0.0,
|
| 1664 |
-
"step": 198357
|
| 1665 |
-
},
|
| 1666 |
-
{
|
| 1667 |
-
"epoch": 111.0,
|
| 1668 |
-
"eval_accuracy": 0.6397748592870544,
|
| 1669 |
-
"eval_loss": NaN,
|
| 1670 |
-
"eval_runtime": 2.4021,
|
| 1671 |
-
"eval_samples_per_second": 199.407,
|
| 1672 |
-
"eval_steps_per_second": 1.665,
|
| 1673 |
-
"step": 198357
|
| 1674 |
-
},
|
| 1675 |
-
{
|
| 1676 |
-
"epoch": 112.0,
|
| 1677 |
-
"learning_rate": 1.6675891963987997e-05,
|
| 1678 |
-
"loss": 0.0,
|
| 1679 |
-
"step": 200144
|
| 1680 |
-
},
|
| 1681 |
-
{
|
| 1682 |
-
"epoch": 112.0,
|
| 1683 |
-
"eval_accuracy": 0.640183902890303,
|
| 1684 |
-
"eval_loss": NaN,
|
| 1685 |
-
"eval_runtime": 2.4547,
|
| 1686 |
-
"eval_samples_per_second": 195.14,
|
| 1687 |
-
"eval_steps_per_second": 1.63,
|
| 1688 |
-
"step": 200144
|
| 1689 |
-
},
|
| 1690 |
-
{
|
| 1691 |
-
"epoch": 113.0,
|
| 1692 |
-
"learning_rate": 1.637795931977326e-05,
|
| 1693 |
-
"loss": 0.0,
|
| 1694 |
-
"step": 201931
|
| 1695 |
-
},
|
| 1696 |
-
{
|
| 1697 |
-
"epoch": 113.0,
|
| 1698 |
-
"eval_accuracy": 0.6345416867743492,
|
| 1699 |
-
"eval_loss": NaN,
|
| 1700 |
-
"eval_runtime": 2.4355,
|
| 1701 |
-
"eval_samples_per_second": 196.673,
|
| 1702 |
-
"eval_steps_per_second": 1.642,
|
| 1703 |
-
"step": 201931
|
| 1704 |
-
},
|
| 1705 |
-
{
|
| 1706 |
-
"epoch": 114.0,
|
| 1707 |
-
"learning_rate": 1.608002667555852e-05,
|
| 1708 |
-
"loss": 0.0,
|
| 1709 |
-
"step": 203718
|
| 1710 |
-
},
|
| 1711 |
-
{
|
| 1712 |
-
"epoch": 114.0,
|
| 1713 |
-
"eval_accuracy": 0.6416126303918804,
|
| 1714 |
-
"eval_loss": NaN,
|
| 1715 |
-
"eval_runtime": 1.881,
|
| 1716 |
-
"eval_samples_per_second": 254.65,
|
| 1717 |
-
"eval_steps_per_second": 2.127,
|
| 1718 |
-
"step": 203718
|
| 1719 |
-
},
|
| 1720 |
-
{
|
| 1721 |
-
"epoch": 115.0,
|
| 1722 |
-
"learning_rate": 1.5782094031343783e-05,
|
| 1723 |
-
"loss": 0.0,
|
| 1724 |
-
"step": 205505
|
| 1725 |
-
},
|
| 1726 |
-
{
|
| 1727 |
-
"epoch": 115.0,
|
| 1728 |
-
"eval_accuracy": 0.635246810870771,
|
| 1729 |
-
"eval_loss": NaN,
|
| 1730 |
-
"eval_runtime": 2.3521,
|
| 1731 |
-
"eval_samples_per_second": 203.648,
|
| 1732 |
-
"eval_steps_per_second": 1.701,
|
| 1733 |
-
"step": 205505
|
| 1734 |
-
},
|
| 1735 |
-
{
|
| 1736 |
-
"epoch": 116.0,
|
| 1737 |
-
"learning_rate": 1.5484161387129043e-05,
|
| 1738 |
-
"loss": 0.0,
|
| 1739 |
-
"step": 207292
|
| 1740 |
-
},
|
| 1741 |
-
{
|
| 1742 |
-
"epoch": 116.0,
|
| 1743 |
-
"eval_accuracy": 0.635686274509804,
|
| 1744 |
-
"eval_loss": NaN,
|
| 1745 |
-
"eval_runtime": 2.3117,
|
| 1746 |
-
"eval_samples_per_second": 207.209,
|
| 1747 |
-
"eval_steps_per_second": 1.73,
|
| 1748 |
-
"step": 207292
|
| 1749 |
-
},
|
| 1750 |
-
{
|
| 1751 |
-
"epoch": 117.0,
|
| 1752 |
-
"learning_rate": 1.5186228742914304e-05,
|
| 1753 |
-
"loss": 0.0032,
|
| 1754 |
-
"step": 209079
|
| 1755 |
-
},
|
| 1756 |
-
{
|
| 1757 |
-
"epoch": 117.0,
|
| 1758 |
-
"eval_accuracy": 0.6358383124351314,
|
| 1759 |
-
"eval_loss": NaN,
|
| 1760 |
-
"eval_runtime": 2.4352,
|
| 1761 |
-
"eval_samples_per_second": 196.698,
|
| 1762 |
-
"eval_steps_per_second": 1.643,
|
| 1763 |
-
"step": 209079
|
| 1764 |
-
},
|
| 1765 |
-
{
|
| 1766 |
-
"epoch": 118.0,
|
| 1767 |
-
"learning_rate": 1.4888296098699567e-05,
|
| 1768 |
-
"loss": 0.0013,
|
| 1769 |
-
"step": 210866
|
| 1770 |
-
},
|
| 1771 |
-
{
|
| 1772 |
-
"epoch": 118.0,
|
| 1773 |
-
"eval_accuracy": 0.6405930899426493,
|
| 1774 |
-
"eval_loss": NaN,
|
| 1775 |
-
"eval_runtime": 2.2861,
|
| 1776 |
-
"eval_samples_per_second": 209.529,
|
| 1777 |
-
"eval_steps_per_second": 1.75,
|
| 1778 |
-
"step": 210866
|
| 1779 |
-
},
|
| 1780 |
-
{
|
| 1781 |
-
"epoch": 119.0,
|
| 1782 |
-
"learning_rate": 1.4590363454484829e-05,
|
| 1783 |
-
"loss": 0.0,
|
| 1784 |
-
"step": 212653
|
| 1785 |
-
},
|
| 1786 |
-
{
|
| 1787 |
-
"epoch": 119.0,
|
| 1788 |
-
"eval_accuracy": 0.6353956511992827,
|
| 1789 |
-
"eval_loss": NaN,
|
| 1790 |
-
"eval_runtime": 2.3549,
|
| 1791 |
-
"eval_samples_per_second": 203.406,
|
| 1792 |
-
"eval_steps_per_second": 1.699,
|
| 1793 |
-
"step": 212653
|
| 1794 |
-
},
|
| 1795 |
-
{
|
| 1796 |
-
"epoch": 120.0,
|
| 1797 |
-
"learning_rate": 1.429243081027009e-05,
|
| 1798 |
-
"loss": 0.0,
|
| 1799 |
-
"step": 214440
|
| 1800 |
-
},
|
| 1801 |
-
{
|
| 1802 |
-
"epoch": 120.0,
|
| 1803 |
-
"eval_accuracy": 0.6345421474450066,
|
| 1804 |
-
"eval_loss": NaN,
|
| 1805 |
-
"eval_runtime": 2.4547,
|
| 1806 |
-
"eval_samples_per_second": 195.139,
|
| 1807 |
-
"eval_steps_per_second": 1.63,
|
| 1808 |
-
"step": 214440
|
| 1809 |
-
},
|
| 1810 |
-
{
|
| 1811 |
-
"epoch": 121.0,
|
| 1812 |
-
"learning_rate": 1.3994498166055354e-05,
|
| 1813 |
-
"loss": 0.0,
|
| 1814 |
-
"step": 216227
|
| 1815 |
-
},
|
| 1816 |
-
{
|
| 1817 |
-
"epoch": 121.0,
|
| 1818 |
-
"eval_accuracy": 0.6432686391856368,
|
| 1819 |
-
"eval_loss": NaN,
|
| 1820 |
-
"eval_runtime": 2.5342,
|
| 1821 |
-
"eval_samples_per_second": 189.015,
|
| 1822 |
-
"eval_steps_per_second": 1.578,
|
| 1823 |
-
"step": 216227
|
| 1824 |
-
},
|
| 1825 |
-
{
|
| 1826 |
-
"epoch": 122.0,
|
| 1827 |
-
"learning_rate": 1.3696565521840615e-05,
|
| 1828 |
-
"loss": 0.0,
|
| 1829 |
-
"step": 218014
|
| 1830 |
-
},
|
| 1831 |
-
{
|
| 1832 |
-
"epoch": 122.0,
|
| 1833 |
-
"eval_accuracy": 0.6326222917132008,
|
| 1834 |
-
"eval_loss": NaN,
|
| 1835 |
-
"eval_runtime": 2.3651,
|
| 1836 |
-
"eval_samples_per_second": 202.525,
|
| 1837 |
-
"eval_steps_per_second": 1.691,
|
| 1838 |
-
"step": 218014
|
| 1839 |
-
},
|
| 1840 |
-
{
|
| 1841 |
-
"epoch": 123.0,
|
| 1842 |
-
"learning_rate": 1.3398632877625875e-05,
|
| 1843 |
-
"loss": 0.0,
|
| 1844 |
-
"step": 219801
|
| 1845 |
-
},
|
| 1846 |
-
{
|
| 1847 |
-
"epoch": 123.0,
|
| 1848 |
-
"eval_accuracy": 0.6357796872798985,
|
| 1849 |
-
"eval_loss": NaN,
|
| 1850 |
-
"eval_runtime": 2.4594,
|
| 1851 |
-
"eval_samples_per_second": 194.763,
|
| 1852 |
-
"eval_steps_per_second": 1.626,
|
| 1853 |
-
"step": 219801
|
| 1854 |
-
},
|
| 1855 |
-
{
|
| 1856 |
-
"epoch": 124.0,
|
| 1857 |
-
"learning_rate": 1.3100700233411136e-05,
|
| 1858 |
-
"loss": 0.0,
|
| 1859 |
-
"step": 221588
|
| 1860 |
-
},
|
| 1861 |
-
{
|
| 1862 |
-
"epoch": 124.0,
|
| 1863 |
-
"eval_accuracy": 0.6409228526575466,
|
| 1864 |
-
"eval_loss": NaN,
|
| 1865 |
-
"eval_runtime": 2.4398,
|
| 1866 |
-
"eval_samples_per_second": 196.326,
|
| 1867 |
-
"eval_steps_per_second": 1.639,
|
| 1868 |
-
"step": 221588
|
| 1869 |
-
},
|
| 1870 |
-
{
|
| 1871 |
-
"epoch": 125.0,
|
| 1872 |
-
"learning_rate": 1.28027675891964e-05,
|
| 1873 |
-
"loss": 0.0,
|
| 1874 |
-
"step": 223375
|
| 1875 |
-
},
|
| 1876 |
-
{
|
| 1877 |
-
"epoch": 125.0,
|
| 1878 |
-
"eval_accuracy": 0.6404630806155583,
|
| 1879 |
-
"eval_loss": NaN,
|
| 1880 |
-
"eval_runtime": 3.34,
|
| 1881 |
-
"eval_samples_per_second": 143.413,
|
| 1882 |
-
"eval_steps_per_second": 1.198,
|
| 1883 |
-
"step": 223375
|
| 1884 |
-
},
|
| 1885 |
-
{
|
| 1886 |
-
"epoch": 126.0,
|
| 1887 |
-
"learning_rate": 1.2504834944981661e-05,
|
| 1888 |
-
"loss": 0.0,
|
| 1889 |
-
"step": 225162
|
| 1890 |
-
},
|
| 1891 |
-
{
|
| 1892 |
-
"epoch": 126.0,
|
| 1893 |
-
"eval_accuracy": 0.637574502616336,
|
| 1894 |
-
"eval_loss": NaN,
|
| 1895 |
-
"eval_runtime": 2.7328,
|
| 1896 |
-
"eval_samples_per_second": 175.276,
|
| 1897 |
-
"eval_steps_per_second": 1.464,
|
| 1898 |
-
"step": 225162
|
| 1899 |
-
},
|
| 1900 |
-
{
|
| 1901 |
-
"epoch": 127.0,
|
| 1902 |
-
"learning_rate": 1.2206902300766923e-05,
|
| 1903 |
-
"loss": 0.0,
|
| 1904 |
-
"step": 226949
|
| 1905 |
-
},
|
| 1906 |
-
{
|
| 1907 |
-
"epoch": 127.0,
|
| 1908 |
-
"eval_accuracy": 0.63958607925068,
|
| 1909 |
-
"eval_loss": NaN,
|
| 1910 |
-
"eval_runtime": 2.3572,
|
| 1911 |
-
"eval_samples_per_second": 203.207,
|
| 1912 |
-
"eval_steps_per_second": 1.697,
|
| 1913 |
-
"step": 226949
|
| 1914 |
-
},
|
| 1915 |
-
{
|
| 1916 |
-
"epoch": 128.0,
|
| 1917 |
-
"learning_rate": 1.1908969656552186e-05,
|
| 1918 |
-
"loss": 0.0,
|
| 1919 |
-
"step": 228736
|
| 1920 |
-
},
|
| 1921 |
-
{
|
| 1922 |
-
"epoch": 128.0,
|
| 1923 |
-
"eval_accuracy": 0.6355922615680507,
|
| 1924 |
-
"eval_loss": NaN,
|
| 1925 |
-
"eval_runtime": 2.0355,
|
| 1926 |
-
"eval_samples_per_second": 235.321,
|
| 1927 |
-
"eval_steps_per_second": 1.965,
|
| 1928 |
-
"step": 228736
|
| 1929 |
-
},
|
| 1930 |
-
{
|
| 1931 |
-
"epoch": 129.0,
|
| 1932 |
-
"learning_rate": 1.1611037012337446e-05,
|
| 1933 |
-
"loss": 0.0,
|
| 1934 |
-
"step": 230523
|
| 1935 |
-
},
|
| 1936 |
-
{
|
| 1937 |
-
"epoch": 129.0,
|
| 1938 |
-
"eval_accuracy": 0.6431967398686892,
|
| 1939 |
-
"eval_loss": NaN,
|
| 1940 |
-
"eval_runtime": 2.3821,
|
| 1941 |
-
"eval_samples_per_second": 201.084,
|
| 1942 |
-
"eval_steps_per_second": 1.679,
|
| 1943 |
-
"step": 230523
|
| 1944 |
-
},
|
| 1945 |
-
{
|
| 1946 |
-
"epoch": 130.0,
|
| 1947 |
-
"learning_rate": 1.1313104368122709e-05,
|
| 1948 |
-
"loss": 0.0,
|
| 1949 |
-
"step": 232310
|
| 1950 |
-
},
|
| 1951 |
-
{
|
| 1952 |
-
"epoch": 130.0,
|
| 1953 |
-
"eval_accuracy": 0.6384714590108781,
|
| 1954 |
-
"eval_loss": NaN,
|
| 1955 |
-
"eval_runtime": 2.3962,
|
| 1956 |
-
"eval_samples_per_second": 199.899,
|
| 1957 |
-
"eval_steps_per_second": 1.669,
|
| 1958 |
-
"step": 232310
|
| 1959 |
-
},
|
| 1960 |
-
{
|
| 1961 |
-
"epoch": 131.0,
|
| 1962 |
-
"learning_rate": 1.101517172390797e-05,
|
| 1963 |
-
"loss": 0.0,
|
| 1964 |
-
"step": 234097
|
| 1965 |
-
},
|
| 1966 |
-
{
|
| 1967 |
-
"epoch": 131.0,
|
| 1968 |
-
"eval_accuracy": 0.6337281095644365,
|
| 1969 |
-
"eval_loss": NaN,
|
| 1970 |
-
"eval_runtime": 1.8635,
|
| 1971 |
-
"eval_samples_per_second": 257.042,
|
| 1972 |
-
"eval_steps_per_second": 2.146,
|
| 1973 |
-
"step": 234097
|
| 1974 |
-
},
|
| 1975 |
-
{
|
| 1976 |
-
"epoch": 132.0,
|
| 1977 |
-
"learning_rate": 1.0717239079693232e-05,
|
| 1978 |
-
"loss": 0.0,
|
| 1979 |
-
"step": 235884
|
| 1980 |
-
},
|
| 1981 |
-
{
|
| 1982 |
-
"epoch": 132.0,
|
| 1983 |
-
"eval_accuracy": 0.6389531480810502,
|
| 1984 |
-
"eval_loss": NaN,
|
| 1985 |
-
"eval_runtime": 2.3837,
|
| 1986 |
-
"eval_samples_per_second": 200.947,
|
| 1987 |
-
"eval_steps_per_second": 1.678,
|
| 1988 |
-
"step": 235884
|
| 1989 |
-
},
|
| 1990 |
-
{
|
| 1991 |
-
"epoch": 133.0,
|
| 1992 |
-
"learning_rate": 1.0419306435478493e-05,
|
| 1993 |
-
"loss": 0.0,
|
| 1994 |
-
"step": 237671
|
| 1995 |
-
},
|
| 1996 |
-
{
|
| 1997 |
-
"epoch": 133.0,
|
| 1998 |
-
"eval_accuracy": 0.636236112669734,
|
| 1999 |
-
"eval_loss": NaN,
|
| 2000 |
-
"eval_runtime": 2.4808,
|
| 2001 |
-
"eval_samples_per_second": 193.082,
|
| 2002 |
-
"eval_steps_per_second": 1.612,
|
| 2003 |
-
"step": 237671
|
| 2004 |
-
},
|
| 2005 |
-
{
|
| 2006 |
-
"epoch": 134.0,
|
| 2007 |
-
"learning_rate": 1.0121373791263755e-05,
|
| 2008 |
-
"loss": 0.0,
|
| 2009 |
-
"step": 239458
|
| 2010 |
-
},
|
| 2011 |
-
{
|
| 2012 |
-
"epoch": 134.0,
|
| 2013 |
-
"eval_accuracy": 0.6331533837934105,
|
| 2014 |
-
"eval_loss": NaN,
|
| 2015 |
-
"eval_runtime": 1.8767,
|
| 2016 |
-
"eval_samples_per_second": 255.23,
|
| 2017 |
-
"eval_steps_per_second": 2.131,
|
| 2018 |
-
"step": 239458
|
| 2019 |
-
},
|
| 2020 |
-
{
|
| 2021 |
-
"epoch": 135.0,
|
| 2022 |
-
"learning_rate": 9.823441147049018e-06,
|
| 2023 |
-
"loss": 0.0,
|
| 2024 |
-
"step": 241245
|
| 2025 |
-
},
|
| 2026 |
-
{
|
| 2027 |
-
"epoch": 135.0,
|
| 2028 |
-
"eval_accuracy": 0.636656406748746,
|
| 2029 |
-
"eval_loss": NaN,
|
| 2030 |
-
"eval_runtime": 2.2751,
|
| 2031 |
-
"eval_samples_per_second": 210.541,
|
| 2032 |
-
"eval_steps_per_second": 1.758,
|
| 2033 |
-
"step": 241245
|
| 2034 |
-
},
|
| 2035 |
-
{
|
| 2036 |
-
"epoch": 136.0,
|
| 2037 |
-
"learning_rate": 9.525508502834278e-06,
|
| 2038 |
-
"loss": 0.0016,
|
| 2039 |
-
"step": 243032
|
| 2040 |
-
},
|
| 2041 |
-
{
|
| 2042 |
-
"epoch": 136.0,
|
| 2043 |
-
"eval_accuracy": 0.6333677196308585,
|
| 2044 |
-
"eval_loss": NaN,
|
| 2045 |
-
"eval_runtime": 2.3276,
|
| 2046 |
-
"eval_samples_per_second": 205.787,
|
| 2047 |
-
"eval_steps_per_second": 1.718,
|
| 2048 |
-
"step": 243032
|
| 2049 |
-
},
|
| 2050 |
-
{
|
| 2051 |
-
"epoch": 137.0,
|
| 2052 |
-
"learning_rate": 9.227575858619541e-06,
|
| 2053 |
-
"loss": 0.0,
|
| 2054 |
-
"step": 244819
|
| 2055 |
-
},
|
| 2056 |
-
{
|
| 2057 |
-
"epoch": 137.0,
|
| 2058 |
-
"eval_accuracy": 0.6411590941060628,
|
| 2059 |
-
"eval_loss": NaN,
|
| 2060 |
-
"eval_runtime": 2.7102,
|
| 2061 |
-
"eval_samples_per_second": 176.741,
|
| 2062 |
-
"eval_steps_per_second": 1.476,
|
| 2063 |
-
"step": 244819
|
| 2064 |
-
},
|
| 2065 |
-
{
|
| 2066 |
-
"epoch": 138.0,
|
| 2067 |
-
"learning_rate": 8.929643214404802e-06,
|
| 2068 |
-
"loss": 0.0,
|
| 2069 |
-
"step": 246606
|
| 2070 |
-
},
|
| 2071 |
-
{
|
| 2072 |
-
"epoch": 138.0,
|
| 2073 |
-
"eval_accuracy": 0.63665891972111,
|
| 2074 |
-
"eval_loss": NaN,
|
| 2075 |
-
"eval_runtime": 2.397,
|
| 2076 |
-
"eval_samples_per_second": 199.829,
|
| 2077 |
-
"eval_steps_per_second": 1.669,
|
| 2078 |
-
"step": 246606
|
| 2079 |
-
},
|
| 2080 |
-
{
|
| 2081 |
-
"epoch": 139.0,
|
| 2082 |
-
"learning_rate": 8.631710570190064e-06,
|
| 2083 |
-
"loss": 0.0,
|
| 2084 |
-
"step": 248393
|
| 2085 |
-
},
|
| 2086 |
-
{
|
| 2087 |
-
"epoch": 139.0,
|
| 2088 |
-
"eval_accuracy": 0.637815760763141,
|
| 2089 |
-
"eval_loss": NaN,
|
| 2090 |
-
"eval_runtime": 2.2977,
|
| 2091 |
-
"eval_samples_per_second": 208.473,
|
| 2092 |
-
"eval_steps_per_second": 1.741,
|
| 2093 |
-
"step": 248393
|
| 2094 |
-
},
|
| 2095 |
-
{
|
| 2096 |
-
"epoch": 140.0,
|
| 2097 |
-
"learning_rate": 8.333777925975325e-06,
|
| 2098 |
-
"loss": 0.0,
|
| 2099 |
-
"step": 250180
|
| 2100 |
-
},
|
| 2101 |
-
{
|
| 2102 |
-
"epoch": 140.0,
|
| 2103 |
-
"eval_accuracy": 0.6389793548752514,
|
| 2104 |
-
"eval_loss": NaN,
|
| 2105 |
-
"eval_runtime": 2.4084,
|
| 2106 |
-
"eval_samples_per_second": 198.888,
|
| 2107 |
-
"eval_steps_per_second": 1.661,
|
| 2108 |
-
"step": 250180
|
| 2109 |
-
},
|
| 2110 |
-
{
|
| 2111 |
-
"epoch": 141.0,
|
| 2112 |
-
"learning_rate": 8.035845281760587e-06,
|
| 2113 |
-
"loss": 0.0,
|
| 2114 |
-
"step": 251967
|
| 2115 |
-
},
|
| 2116 |
-
{
|
| 2117 |
-
"epoch": 141.0,
|
| 2118 |
-
"eval_accuracy": 0.6375586326994916,
|
| 2119 |
-
"eval_loss": NaN,
|
| 2120 |
-
"eval_runtime": 2.1944,
|
| 2121 |
-
"eval_samples_per_second": 218.284,
|
| 2122 |
-
"eval_steps_per_second": 1.823,
|
| 2123 |
-
"step": 251967
|
| 2124 |
-
},
|
| 2125 |
-
{
|
| 2126 |
-
"epoch": 142.0,
|
| 2127 |
-
"learning_rate": 7.73791263754585e-06,
|
| 2128 |
-
"loss": 0.0,
|
| 2129 |
-
"step": 253754
|
| 2130 |
-
},
|
| 2131 |
-
{
|
| 2132 |
-
"epoch": 142.0,
|
| 2133 |
-
"eval_accuracy": 0.6363045444268596,
|
| 2134 |
-
"eval_loss": NaN,
|
| 2135 |
-
"eval_runtime": 1.9755,
|
| 2136 |
-
"eval_samples_per_second": 242.476,
|
| 2137 |
-
"eval_steps_per_second": 2.025,
|
| 2138 |
-
"step": 253754
|
| 2139 |
-
},
|
| 2140 |
-
{
|
| 2141 |
-
"epoch": 143.0,
|
| 2142 |
-
"learning_rate": 7.43997999333111e-06,
|
| 2143 |
-
"loss": 0.0033,
|
| 2144 |
-
"step": 255541
|
| 2145 |
-
},
|
| 2146 |
-
{
|
| 2147 |
-
"epoch": 143.0,
|
| 2148 |
-
"eval_accuracy": 0.642540373190528,
|
| 2149 |
-
"eval_loss": NaN,
|
| 2150 |
-
"eval_runtime": 1.9855,
|
| 2151 |
-
"eval_samples_per_second": 241.25,
|
| 2152 |
-
"eval_steps_per_second": 2.015,
|
| 2153 |
-
"step": 255541
|
| 2154 |
-
},
|
| 2155 |
-
{
|
| 2156 |
-
"epoch": 144.0,
|
| 2157 |
-
"learning_rate": 7.142047349116372e-06,
|
| 2158 |
-
"loss": 0.0,
|
| 2159 |
-
"step": 257328
|
| 2160 |
-
},
|
| 2161 |
-
{
|
| 2162 |
-
"epoch": 144.0,
|
| 2163 |
-
"eval_accuracy": 0.6360186889423758,
|
| 2164 |
-
"eval_loss": NaN,
|
| 2165 |
-
"eval_runtime": 1.9778,
|
| 2166 |
-
"eval_samples_per_second": 242.187,
|
| 2167 |
-
"eval_steps_per_second": 2.022,
|
| 2168 |
-
"step": 257328
|
| 2169 |
-
},
|
| 2170 |
-
{
|
| 2171 |
-
"epoch": 145.0,
|
| 2172 |
-
"learning_rate": 6.844114704901635e-06,
|
| 2173 |
-
"loss": 0.0,
|
| 2174 |
-
"step": 259115
|
| 2175 |
-
},
|
| 2176 |
-
{
|
| 2177 |
-
"epoch": 145.0,
|
| 2178 |
-
"eval_accuracy": 0.6377054679637706,
|
| 2179 |
-
"eval_loss": NaN,
|
| 2180 |
-
"eval_runtime": 1.9561,
|
| 2181 |
-
"eval_samples_per_second": 244.876,
|
| 2182 |
-
"eval_steps_per_second": 2.045,
|
| 2183 |
-
"step": 259115
|
| 2184 |
-
},
|
| 2185 |
-
{
|
| 2186 |
-
"epoch": 146.0,
|
| 2187 |
-
"learning_rate": 6.546182060686896e-06,
|
| 2188 |
-
"loss": 0.0,
|
| 2189 |
-
"step": 260902
|
| 2190 |
-
},
|
| 2191 |
-
{
|
| 2192 |
-
"epoch": 146.0,
|
| 2193 |
-
"eval_accuracy": 0.630178854426081,
|
| 2194 |
-
"eval_loss": NaN,
|
| 2195 |
-
"eval_runtime": 2.1068,
|
| 2196 |
-
"eval_samples_per_second": 227.357,
|
| 2197 |
-
"eval_steps_per_second": 1.899,
|
| 2198 |
-
"step": 260902
|
| 2199 |
-
},
|
| 2200 |
-
{
|
| 2201 |
-
"epoch": 147.0,
|
| 2202 |
-
"learning_rate": 6.248249416472158e-06,
|
| 2203 |
-
"loss": 0.0,
|
| 2204 |
-
"step": 262689
|
| 2205 |
-
},
|
| 2206 |
-
{
|
| 2207 |
-
"epoch": 147.0,
|
| 2208 |
-
"eval_accuracy": 0.6320312280603219,
|
| 2209 |
-
"eval_loss": NaN,
|
| 2210 |
-
"eval_runtime": 2.051,
|
| 2211 |
-
"eval_samples_per_second": 233.54,
|
| 2212 |
-
"eval_steps_per_second": 1.95,
|
| 2213 |
-
"step": 262689
|
| 2214 |
-
},
|
| 2215 |
-
{
|
| 2216 |
-
"epoch": 148.0,
|
| 2217 |
-
"learning_rate": 5.950316772257419e-06,
|
| 2218 |
-
"loss": 0.0,
|
| 2219 |
-
"step": 264476
|
| 2220 |
-
},
|
| 2221 |
-
{
|
| 2222 |
-
"epoch": 148.0,
|
| 2223 |
-
"eval_accuracy": 0.6358165946266633,
|
| 2224 |
-
"eval_loss": NaN,
|
| 2225 |
-
"eval_runtime": 2.0868,
|
| 2226 |
-
"eval_samples_per_second": 229.54,
|
| 2227 |
-
"eval_steps_per_second": 1.917,
|
| 2228 |
-
"step": 264476
|
| 2229 |
-
},
|
| 2230 |
-
{
|
| 2231 |
-
"epoch": 149.0,
|
| 2232 |
-
"learning_rate": 5.6523841280426815e-06,
|
| 2233 |
-
"loss": 0.0,
|
| 2234 |
-
"step": 266263
|
| 2235 |
-
},
|
| 2236 |
-
{
|
| 2237 |
-
"epoch": 149.0,
|
| 2238 |
-
"eval_accuracy": 0.6381050924242848,
|
| 2239 |
-
"eval_loss": NaN,
|
| 2240 |
-
"eval_runtime": 2.0799,
|
| 2241 |
-
"eval_samples_per_second": 230.305,
|
| 2242 |
-
"eval_steps_per_second": 1.923,
|
| 2243 |
-
"step": 266263
|
| 2244 |
-
},
|
| 2245 |
-
{
|
| 2246 |
-
"epoch": 150.0,
|
| 2247 |
-
"learning_rate": 5.354451483827943e-06,
|
| 2248 |
-
"loss": 0.0,
|
| 2249 |
-
"step": 268050
|
| 2250 |
-
},
|
| 2251 |
-
{
|
| 2252 |
-
"epoch": 150.0,
|
| 2253 |
-
"eval_accuracy": 0.6414367457934395,
|
| 2254 |
-
"eval_loss": NaN,
|
| 2255 |
-
"eval_runtime": 2.0658,
|
| 2256 |
-
"eval_samples_per_second": 231.876,
|
| 2257 |
-
"eval_steps_per_second": 1.936,
|
| 2258 |
-
"step": 268050
|
| 2259 |
-
},
|
| 2260 |
-
{
|
| 2261 |
-
"epoch": 151.0,
|
| 2262 |
-
"learning_rate": 5.0565188396132045e-06,
|
| 2263 |
-
"loss": 0.0,
|
| 2264 |
-
"step": 269837
|
| 2265 |
-
},
|
| 2266 |
-
{
|
| 2267 |
-
"epoch": 151.0,
|
| 2268 |
-
"eval_accuracy": 0.640085841757497,
|
| 2269 |
-
"eval_loss": NaN,
|
| 2270 |
-
"eval_runtime": 2.0508,
|
| 2271 |
-
"eval_samples_per_second": 233.571,
|
| 2272 |
-
"eval_steps_per_second": 1.95,
|
| 2273 |
-
"step": 269837
|
| 2274 |
-
},
|
| 2275 |
-
{
|
| 2276 |
-
"epoch": 152.0,
|
| 2277 |
-
"learning_rate": 4.758586195398467e-06,
|
| 2278 |
-
"loss": 0.0012,
|
| 2279 |
-
"step": 271624
|
| 2280 |
-
},
|
| 2281 |
-
{
|
| 2282 |
-
"epoch": 152.0,
|
| 2283 |
-
"eval_accuracy": 0.6415057319841915,
|
| 2284 |
-
"eval_loss": NaN,
|
| 2285 |
-
"eval_runtime": 2.0208,
|
| 2286 |
-
"eval_samples_per_second": 237.04,
|
| 2287 |
-
"eval_steps_per_second": 1.979,
|
| 2288 |
-
"step": 271624
|
| 2289 |
-
},
|
| 2290 |
-
{
|
| 2291 |
-
"epoch": 153.0,
|
| 2292 |
-
"learning_rate": 4.4606535511837275e-06,
|
| 2293 |
-
"loss": 0.0,
|
| 2294 |
-
"step": 273411
|
| 2295 |
-
},
|
| 2296 |
-
{
|
| 2297 |
-
"epoch": 153.0,
|
| 2298 |
-
"eval_accuracy": 0.6424933908445805,
|
| 2299 |
-
"eval_loss": NaN,
|
| 2300 |
-
"eval_runtime": 2.1125,
|
| 2301 |
-
"eval_samples_per_second": 226.742,
|
| 2302 |
-
"eval_steps_per_second": 1.893,
|
| 2303 |
-
"step": 273411
|
| 2304 |
-
},
|
| 2305 |
-
{
|
| 2306 |
-
"epoch": 154.0,
|
| 2307 |
-
"learning_rate": 4.16272090696899e-06,
|
| 2308 |
-
"loss": 0.0,
|
| 2309 |
-
"step": 275198
|
| 2310 |
-
},
|
| 2311 |
-
{
|
| 2312 |
-
"epoch": 154.0,
|
| 2313 |
-
"eval_accuracy": 0.6366794508365293,
|
| 2314 |
-
"eval_loss": NaN,
|
| 2315 |
-
"eval_runtime": 2.1748,
|
| 2316 |
-
"eval_samples_per_second": 220.247,
|
| 2317 |
-
"eval_steps_per_second": 1.839,
|
| 2318 |
-
"step": 275198
|
| 2319 |
-
},
|
| 2320 |
-
{
|
| 2321 |
-
"epoch": 155.0,
|
| 2322 |
-
"learning_rate": 3.864788262754251e-06,
|
| 2323 |
-
"loss": 0.0,
|
| 2324 |
-
"step": 276985
|
| 2325 |
-
},
|
| 2326 |
-
{
|
| 2327 |
-
"epoch": 155.0,
|
| 2328 |
-
"eval_accuracy": 0.6356290122761572,
|
| 2329 |
-
"eval_loss": NaN,
|
| 2330 |
-
"eval_runtime": 2.0784,
|
| 2331 |
-
"eval_samples_per_second": 230.462,
|
| 2332 |
-
"eval_steps_per_second": 1.925,
|
| 2333 |
-
"step": 276985
|
| 2334 |
-
},
|
| 2335 |
-
{
|
| 2336 |
-
"epoch": 156.0,
|
| 2337 |
-
"learning_rate": 3.5668556185395137e-06,
|
| 2338 |
-
"loss": 0.0,
|
| 2339 |
-
"step": 278772
|
| 2340 |
-
},
|
| 2341 |
-
{
|
| 2342 |
-
"epoch": 156.0,
|
| 2343 |
-
"eval_accuracy": 0.6411258795934324,
|
| 2344 |
-
"eval_loss": NaN,
|
| 2345 |
-
"eval_runtime": 2.0969,
|
| 2346 |
-
"eval_samples_per_second": 228.428,
|
| 2347 |
-
"eval_steps_per_second": 1.908,
|
| 2348 |
-
"step": 278772
|
| 2349 |
-
},
|
| 2350 |
-
{
|
| 2351 |
-
"epoch": 157.0,
|
| 2352 |
-
"learning_rate": 3.268922974324775e-06,
|
| 2353 |
-
"loss": 0.0,
|
| 2354 |
-
"step": 280559
|
| 2355 |
-
},
|
| 2356 |
-
{
|
| 2357 |
-
"epoch": 157.0,
|
| 2358 |
-
"eval_accuracy": 0.6343390602592582,
|
| 2359 |
-
"eval_loss": NaN,
|
| 2360 |
-
"eval_runtime": 2.0784,
|
| 2361 |
-
"eval_samples_per_second": 230.468,
|
| 2362 |
-
"eval_steps_per_second": 1.925,
|
| 2363 |
-
"step": 280559
|
| 2364 |
-
},
|
| 2365 |
-
{
|
| 2366 |
-
"epoch": 158.0,
|
| 2367 |
-
"learning_rate": 2.9709903301100367e-06,
|
| 2368 |
-
"loss": 0.0007,
|
| 2369 |
-
"step": 282346
|
| 2370 |
-
},
|
| 2371 |
-
{
|
| 2372 |
-
"epoch": 158.0,
|
| 2373 |
-
"eval_accuracy": 0.6368964554842311,
|
| 2374 |
-
"eval_loss": NaN,
|
| 2375 |
-
"eval_runtime": 2.0391,
|
| 2376 |
-
"eval_samples_per_second": 234.912,
|
| 2377 |
-
"eval_steps_per_second": 1.962,
|
| 2378 |
-
"step": 282346
|
| 2379 |
-
},
|
| 2380 |
-
{
|
| 2381 |
-
"epoch": 159.0,
|
| 2382 |
-
"learning_rate": 2.6730576858952986e-06,
|
| 2383 |
-
"loss": 0.0,
|
| 2384 |
-
"step": 284133
|
| 2385 |
-
},
|
| 2386 |
-
{
|
| 2387 |
-
"epoch": 159.0,
|
| 2388 |
-
"eval_accuracy": 0.636098163643511,
|
| 2389 |
-
"eval_loss": NaN,
|
| 2390 |
-
"eval_runtime": 2.1494,
|
| 2391 |
-
"eval_samples_per_second": 222.857,
|
| 2392 |
-
"eval_steps_per_second": 1.861,
|
| 2393 |
-
"step": 284133
|
| 2394 |
-
},
|
| 2395 |
-
{
|
| 2396 |
-
"epoch": 160.0,
|
| 2397 |
-
"learning_rate": 2.3751250416805605e-06,
|
| 2398 |
-
"loss": 0.0013,
|
| 2399 |
-
"step": 285920
|
| 2400 |
-
},
|
| 2401 |
-
{
|
| 2402 |
-
"epoch": 160.0,
|
| 2403 |
-
"eval_accuracy": 0.6396206236631768,
|
| 2404 |
-
"eval_loss": NaN,
|
| 2405 |
-
"eval_runtime": 2.0359,
|
| 2406 |
-
"eval_samples_per_second": 235.272,
|
| 2407 |
-
"eval_steps_per_second": 1.965,
|
| 2408 |
-
"step": 285920
|
| 2409 |
-
},
|
| 2410 |
-
{
|
| 2411 |
-
"epoch": 161.0,
|
| 2412 |
-
"learning_rate": 2.077192397465822e-06,
|
| 2413 |
-
"loss": 0.0008,
|
| 2414 |
-
"step": 287707
|
| 2415 |
-
},
|
| 2416 |
-
{
|
| 2417 |
-
"epoch": 161.0,
|
| 2418 |
-
"eval_accuracy": 0.6381123797738906,
|
| 2419 |
-
"eval_loss": NaN,
|
| 2420 |
-
"eval_runtime": 2.4553,
|
| 2421 |
-
"eval_samples_per_second": 195.089,
|
| 2422 |
-
"eval_steps_per_second": 1.629,
|
| 2423 |
-
"step": 287707
|
| 2424 |
-
},
|
| 2425 |
-
{
|
| 2426 |
-
"epoch": 162.0,
|
| 2427 |
-
"learning_rate": 1.779259753251084e-06,
|
| 2428 |
-
"loss": 0.0,
|
| 2429 |
-
"step": 289494
|
| 2430 |
-
},
|
| 2431 |
-
{
|
| 2432 |
-
"epoch": 162.0,
|
| 2433 |
-
"eval_accuracy": 0.6351684010294282,
|
| 2434 |
-
"eval_loss": NaN,
|
| 2435 |
-
"eval_runtime": 2.0507,
|
| 2436 |
-
"eval_samples_per_second": 233.583,
|
| 2437 |
-
"eval_steps_per_second": 1.951,
|
| 2438 |
-
"step": 289494
|
| 2439 |
-
},
|
| 2440 |
-
{
|
| 2441 |
-
"epoch": 163.0,
|
| 2442 |
-
"learning_rate": 1.4813271090363454e-06,
|
| 2443 |
-
"loss": 0.0,
|
| 2444 |
-
"step": 291281
|
| 2445 |
-
},
|
| 2446 |
-
{
|
| 2447 |
-
"epoch": 163.0,
|
| 2448 |
-
"eval_accuracy": 0.6370490792387252,
|
| 2449 |
-
"eval_loss": NaN,
|
| 2450 |
-
"eval_runtime": 2.0888,
|
| 2451 |
-
"eval_samples_per_second": 229.314,
|
| 2452 |
-
"eval_steps_per_second": 1.915,
|
| 2453 |
-
"step": 291281
|
| 2454 |
-
},
|
| 2455 |
-
{
|
| 2456 |
-
"epoch": 164.0,
|
| 2457 |
-
"learning_rate": 1.1833944648216071e-06,
|
| 2458 |
-
"loss": 0.0,
|
| 2459 |
-
"step": 293068
|
| 2460 |
-
},
|
| 2461 |
-
{
|
| 2462 |
-
"epoch": 164.0,
|
| 2463 |
-
"eval_accuracy": 0.6399250601196801,
|
| 2464 |
-
"eval_loss": NaN,
|
| 2465 |
-
"eval_runtime": 2.061,
|
| 2466 |
-
"eval_samples_per_second": 232.411,
|
| 2467 |
-
"eval_steps_per_second": 1.941,
|
| 2468 |
-
"step": 293068
|
| 2469 |
-
},
|
| 2470 |
-
{
|
| 2471 |
-
"epoch": 165.0,
|
| 2472 |
-
"learning_rate": 8.854618206068691e-07,
|
| 2473 |
-
"loss": 0.0031,
|
| 2474 |
-
"step": 294855
|
| 2475 |
-
},
|
| 2476 |
-
{
|
| 2477 |
-
"epoch": 165.0,
|
| 2478 |
-
"eval_accuracy": 0.6401486145381321,
|
| 2479 |
-
"eval_loss": NaN,
|
| 2480 |
-
"eval_runtime": 2.2403,
|
| 2481 |
-
"eval_samples_per_second": 213.812,
|
| 2482 |
-
"eval_steps_per_second": 1.785,
|
| 2483 |
-
"step": 294855
|
| 2484 |
-
},
|
| 2485 |
-
{
|
| 2486 |
-
"epoch": 166.0,
|
| 2487 |
-
"learning_rate": 5.875291763921307e-07,
|
| 2488 |
-
"loss": 0.0,
|
| 2489 |
-
"step": 296642
|
| 2490 |
-
},
|
| 2491 |
-
{
|
| 2492 |
-
"epoch": 166.0,
|
| 2493 |
-
"eval_accuracy": 0.6357598978288633,
|
| 2494 |
-
"eval_loss": NaN,
|
| 2495 |
-
"eval_runtime": 2.2206,
|
| 2496 |
-
"eval_samples_per_second": 215.711,
|
| 2497 |
-
"eval_steps_per_second": 1.801,
|
| 2498 |
-
"step": 296642
|
| 2499 |
-
},
|
| 2500 |
-
{
|
| 2501 |
-
"epoch": 167.0,
|
| 2502 |
-
"learning_rate": 2.895965321773925e-07,
|
| 2503 |
-
"loss": 0.0,
|
| 2504 |
-
"step": 298429
|
| 2505 |
-
},
|
| 2506 |
-
{
|
| 2507 |
-
"epoch": 167.0,
|
| 2508 |
-
"eval_accuracy": 0.6389859154929578,
|
| 2509 |
-
"eval_loss": NaN,
|
| 2510 |
-
"eval_runtime": 2.2354,
|
| 2511 |
-
"eval_samples_per_second": 214.281,
|
| 2512 |
-
"eval_steps_per_second": 1.789,
|
| 2513 |
-
"step": 298429
|
| 2514 |
-
},
|
| 2515 |
-
{
|
| 2516 |
-
"epoch": 167.88,
|
| 2517 |
-
"learning_rate": 2.7675891963987998e-08,
|
| 2518 |
-
"loss": 0.0,
|
| 2519 |
"step": 300000
|
| 2520 |
},
|
| 2521 |
{
|
| 2522 |
-
"epoch":
|
| 2523 |
-
"eval_accuracy": 0.
|
| 2524 |
-
"eval_loss":
|
| 2525 |
-
"eval_runtime":
|
| 2526 |
-
"eval_samples_per_second":
|
| 2527 |
-
"eval_steps_per_second":
|
| 2528 |
"step": 300000
|
| 2529 |
},
|
| 2530 |
{
|
| 2531 |
-
"epoch":
|
| 2532 |
"step": 300000,
|
| 2533 |
-
"total_flos":
|
| 2534 |
-
"train_loss":
|
| 2535 |
-
"train_runtime":
|
| 2536 |
-
"train_samples_per_second":
|
| 2537 |
-
"train_steps_per_second":
|
| 2538 |
}
|
| 2539 |
],
|
| 2540 |
"max_steps": 300000,
|
| 2541 |
-
"num_train_epochs":
|
| 2542 |
-
"total_flos":
|
| 2543 |
"trial_name": null,
|
| 2544 |
"trial_params": null
|
| 2545 |
}
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3073620796203613,
|
| 3 |
+
"best_model_checkpoint": "mobilebert_sa_pre-training-complete/checkpoint-300000",
|
| 4 |
+
"epoch": 41.98740377886634,
|
| 5 |
"global_step": 300000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 4.882544181393798e-05,
|
| 13 |
+
"loss": 1.6028,
|
| 14 |
+
"step": 7145
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.6935334549025108,
|
| 19 |
+
"eval_loss": 1.4525387287139893,
|
| 20 |
+
"eval_runtime": 1.4716,
|
| 21 |
+
"eval_samples_per_second": 325.49,
|
| 22 |
+
"eval_steps_per_second": 10.193,
|
| 23 |
+
"step": 7145
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 4.763421140380127e-05,
|
| 28 |
+
"loss": 1.5524,
|
| 29 |
+
"step": 14290
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.6992782005371531,
|
| 34 |
+
"eval_loss": 1.437490463256836,
|
| 35 |
+
"eval_runtime": 1.5211,
|
| 36 |
+
"eval_samples_per_second": 314.9,
|
| 37 |
+
"eval_steps_per_second": 9.861,
|
| 38 |
+
"step": 14290
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 4.6442980993664556e-05,
|
| 43 |
+
"loss": 1.5323,
|
| 44 |
+
"step": 21435
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.6993441976976554,
|
| 49 |
+
"eval_loss": 1.4193694591522217,
|
| 50 |
+
"eval_runtime": 1.4759,
|
| 51 |
+
"eval_samples_per_second": 324.542,
|
| 52 |
+
"eval_steps_per_second": 10.163,
|
| 53 |
+
"step": 21435
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 4.0,
|
| 57 |
+
"learning_rate": 4.5251750583527844e-05,
|
| 58 |
+
"loss": 1.5191,
|
| 59 |
+
"step": 28580
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 4.0,
|
| 63 |
+
"eval_accuracy": 0.7026513032777716,
|
| 64 |
+
"eval_loss": 1.4109910726547241,
|
| 65 |
+
"eval_runtime": 1.4968,
|
| 66 |
+
"eval_samples_per_second": 320.019,
|
| 67 |
+
"eval_steps_per_second": 10.021,
|
| 68 |
+
"step": 28580
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 5.0,
|
| 72 |
+
"learning_rate": 4.406052017339113e-05,
|
| 73 |
+
"loss": 1.5025,
|
| 74 |
+
"step": 35725
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 5.0,
|
| 78 |
+
"eval_accuracy": 0.7013675690761931,
|
| 79 |
+
"eval_loss": 1.4167572259902954,
|
| 80 |
+
"eval_runtime": 1.4782,
|
| 81 |
+
"eval_samples_per_second": 324.039,
|
| 82 |
+
"eval_steps_per_second": 10.147,
|
| 83 |
+
"step": 35725
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 6.0,
|
| 87 |
+
"learning_rate": 4.286928976325442e-05,
|
| 88 |
+
"loss": 1.4902,
|
| 89 |
+
"step": 42870
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 6.0,
|
| 93 |
+
"eval_accuracy": 0.7011720396863318,
|
| 94 |
+
"eval_loss": 1.3931331634521484,
|
| 95 |
+
"eval_runtime": 1.4734,
|
| 96 |
+
"eval_samples_per_second": 325.107,
|
| 97 |
+
"eval_steps_per_second": 10.181,
|
| 98 |
+
"step": 42870
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 7.0,
|
| 102 |
+
"learning_rate": 4.167805935311771e-05,
|
| 103 |
+
"loss": 1.4813,
|
| 104 |
+
"step": 50015
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 7.0,
|
| 108 |
+
"eval_accuracy": 0.7056545531078995,
|
| 109 |
+
"eval_loss": 1.3738043308258057,
|
| 110 |
+
"eval_runtime": 1.4644,
|
| 111 |
+
"eval_samples_per_second": 327.106,
|
| 112 |
+
"eval_steps_per_second": 10.243,
|
| 113 |
+
"step": 50015
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 8.0,
|
| 117 |
+
"learning_rate": 4.0486828942981e-05,
|
| 118 |
+
"loss": 1.4751,
|
| 119 |
+
"step": 57160
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 8.0,
|
| 123 |
+
"eval_accuracy": 0.6995995407320283,
|
| 124 |
+
"eval_loss": 1.4237422943115234,
|
| 125 |
+
"eval_runtime": 1.459,
|
| 126 |
+
"eval_samples_per_second": 328.317,
|
| 127 |
+
"eval_steps_per_second": 10.281,
|
| 128 |
+
"step": 57160
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 9.0,
|
| 132 |
+
"learning_rate": 3.929559853284429e-05,
|
| 133 |
+
"loss": 1.4689,
|
| 134 |
+
"step": 64305
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 9.0,
|
| 138 |
+
"eval_accuracy": 0.704691011235955,
|
| 139 |
+
"eval_loss": 1.3969331979751587,
|
| 140 |
+
"eval_runtime": 1.6056,
|
| 141 |
+
"eval_samples_per_second": 298.322,
|
| 142 |
+
"eval_steps_per_second": 9.342,
|
| 143 |
+
"step": 64305
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 10.0,
|
| 147 |
+
"learning_rate": 3.8104368122707576e-05,
|
| 148 |
+
"loss": 1.4626,
|
| 149 |
+
"step": 71450
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 10.0,
|
| 153 |
+
"eval_accuracy": 0.7067709060449532,
|
| 154 |
+
"eval_loss": 1.391621470451355,
|
| 155 |
+
"eval_runtime": 1.4719,
|
| 156 |
+
"eval_samples_per_second": 325.421,
|
| 157 |
+
"eval_steps_per_second": 10.191,
|
| 158 |
+
"step": 71450
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 11.0,
|
| 162 |
+
"learning_rate": 3.691313771257086e-05,
|
| 163 |
+
"loss": 1.4566,
|
| 164 |
+
"step": 78595
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 11.0,
|
| 168 |
+
"eval_accuracy": 0.7071985535088711,
|
| 169 |
+
"eval_loss": 1.3686023950576782,
|
| 170 |
+
"eval_runtime": 1.4629,
|
| 171 |
+
"eval_samples_per_second": 327.432,
|
| 172 |
+
"eval_steps_per_second": 10.254,
|
| 173 |
+
"step": 78595
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 12.0,
|
| 177 |
+
"learning_rate": 3.572190730243415e-05,
|
| 178 |
+
"loss": 1.451,
|
| 179 |
+
"step": 85740
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 12.0,
|
| 183 |
+
"eval_accuracy": 0.7060222091689743,
|
| 184 |
+
"eval_loss": 1.3811498880386353,
|
| 185 |
+
"eval_runtime": 1.4641,
|
| 186 |
+
"eval_samples_per_second": 327.173,
|
| 187 |
+
"eval_steps_per_second": 10.246,
|
| 188 |
+
"step": 85740
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 13.0,
|
| 192 |
+
"learning_rate": 3.453067689229744e-05,
|
| 193 |
+
"loss": 1.4478,
|
| 194 |
+
"step": 92885
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 13.0,
|
| 198 |
+
"eval_accuracy": 0.7091579355840124,
|
| 199 |
+
"eval_loss": 1.3597520589828491,
|
| 200 |
+
"eval_runtime": 1.4632,
|
| 201 |
+
"eval_samples_per_second": 327.355,
|
| 202 |
+
"eval_steps_per_second": 10.251,
|
| 203 |
+
"step": 92885
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 14.0,
|
| 207 |
+
"learning_rate": 3.3339446482160726e-05,
|
| 208 |
+
"loss": 1.4441,
|
| 209 |
+
"step": 100030
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 14.0,
|
| 213 |
+
"eval_accuracy": 0.7054075191330094,
|
| 214 |
+
"eval_loss": 1.3789618015289307,
|
| 215 |
+
"eval_runtime": 1.4621,
|
| 216 |
+
"eval_samples_per_second": 327.608,
|
| 217 |
+
"eval_steps_per_second": 10.259,
|
| 218 |
+
"step": 100030
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 15.0,
|
| 222 |
+
"learning_rate": 3.214821607202401e-05,
|
| 223 |
+
"loss": 1.4379,
|
| 224 |
+
"step": 107175
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 15.0,
|
| 228 |
+
"eval_accuracy": 0.7065809145017066,
|
| 229 |
+
"eval_loss": 1.379388451576233,
|
| 230 |
+
"eval_runtime": 1.5875,
|
| 231 |
+
"eval_samples_per_second": 301.725,
|
| 232 |
+
"eval_steps_per_second": 9.449,
|
| 233 |
+
"step": 107175
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 16.0,
|
| 237 |
+
"learning_rate": 3.09569856618873e-05,
|
| 238 |
+
"loss": 1.4353,
|
| 239 |
+
"step": 114320
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 16.0,
|
| 243 |
+
"eval_accuracy": 0.710198236648509,
|
| 244 |
+
"eval_loss": 1.3609341382980347,
|
| 245 |
+
"eval_runtime": 1.4593,
|
| 246 |
+
"eval_samples_per_second": 328.244,
|
| 247 |
+
"eval_steps_per_second": 10.279,
|
| 248 |
+
"step": 114320
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 17.0,
|
| 252 |
+
"learning_rate": 2.976575525175058e-05,
|
| 253 |
+
"loss": 1.43,
|
| 254 |
+
"step": 121465
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 17.0,
|
| 258 |
+
"eval_accuracy": 0.7083252258512857,
|
| 259 |
+
"eval_loss": 1.3685261011123657,
|
| 260 |
+
"eval_runtime": 1.4875,
|
| 261 |
+
"eval_samples_per_second": 322.019,
|
| 262 |
+
"eval_steps_per_second": 10.084,
|
| 263 |
+
"step": 121465
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 18.0,
|
| 267 |
+
"learning_rate": 2.857452484161387e-05,
|
| 268 |
+
"loss": 1.4278,
|
| 269 |
+
"step": 128610
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 18.0,
|
| 273 |
+
"eval_accuracy": 0.7036037555518075,
|
| 274 |
+
"eval_loss": 1.3953258991241455,
|
| 275 |
+
"eval_runtime": 1.4616,
|
| 276 |
+
"eval_samples_per_second": 327.715,
|
| 277 |
+
"eval_steps_per_second": 10.262,
|
| 278 |
+
"step": 128610
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 19.0,
|
| 282 |
+
"learning_rate": 2.7383294431477156e-05,
|
| 283 |
+
"loss": 1.4219,
|
| 284 |
+
"step": 135755
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 19.0,
|
| 288 |
+
"eval_accuracy": 0.7085320020194088,
|
| 289 |
+
"eval_loss": 1.3756214380264282,
|
| 290 |
+
"eval_runtime": 1.4616,
|
| 291 |
+
"eval_samples_per_second": 327.73,
|
| 292 |
+
"eval_steps_per_second": 10.263,
|
| 293 |
+
"step": 135755
|
| 294 |
},
|
| 295 |
{
|
| 296 |
"epoch": 20.0,
|
| 297 |
+
"learning_rate": 2.6192064021340444e-05,
|
| 298 |
+
"loss": 1.4197,
|
| 299 |
+
"step": 142900
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 20.0,
|
| 303 |
+
"eval_accuracy": 0.7089573167311684,
|
| 304 |
+
"eval_loss": 1.3597127199172974,
|
| 305 |
+
"eval_runtime": 1.4718,
|
| 306 |
+
"eval_samples_per_second": 325.445,
|
| 307 |
+
"eval_steps_per_second": 10.191,
|
| 308 |
+
"step": 142900
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 21.0,
|
| 312 |
+
"learning_rate": 2.5000833611203735e-05,
|
| 313 |
+
"loss": 1.4169,
|
| 314 |
+
"step": 150045
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 21.0,
|
| 318 |
+
"eval_accuracy": 0.7060544426179265,
|
| 319 |
+
"eval_loss": 1.367296576499939,
|
| 320 |
+
"eval_runtime": 1.4625,
|
| 321 |
+
"eval_samples_per_second": 327.518,
|
| 322 |
+
"eval_steps_per_second": 10.256,
|
| 323 |
+
"step": 150045
|
| 324 |
},
|
| 325 |
{
|
| 326 |
"epoch": 22.0,
|
| 327 |
+
"learning_rate": 2.3809603201067022e-05,
|
| 328 |
+
"loss": 1.4146,
|
| 329 |
+
"step": 157190
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"epoch": 22.0,
|
| 333 |
+
"eval_accuracy": 0.707288269036104,
|
| 334 |
+
"eval_loss": 1.3753403425216675,
|
| 335 |
+
"eval_runtime": 1.4573,
|
| 336 |
+
"eval_samples_per_second": 328.688,
|
| 337 |
+
"eval_steps_per_second": 10.293,
|
| 338 |
+
"step": 157190
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 23.0,
|
| 342 |
+
"learning_rate": 2.2618372790930313e-05,
|
| 343 |
+
"loss": 1.4109,
|
| 344 |
+
"step": 164335
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 23.0,
|
| 348 |
+
"eval_accuracy": 0.7081938623386121,
|
| 349 |
+
"eval_loss": 1.3696134090423584,
|
| 350 |
+
"eval_runtime": 1.4581,
|
| 351 |
+
"eval_samples_per_second": 328.502,
|
| 352 |
+
"eval_steps_per_second": 10.287,
|
| 353 |
+
"step": 164335
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 24.0,
|
| 357 |
+
"learning_rate": 2.14271423807936e-05,
|
| 358 |
+
"loss": 1.4073,
|
| 359 |
+
"step": 171480
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 24.0,
|
| 363 |
+
"eval_accuracy": 0.7092472511981956,
|
| 364 |
+
"eval_loss": 1.356264352798462,
|
| 365 |
+
"eval_runtime": 1.4561,
|
| 366 |
+
"eval_samples_per_second": 328.957,
|
| 367 |
+
"eval_steps_per_second": 10.301,
|
| 368 |
+
"step": 171480
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 25.0,
|
| 372 |
+
"learning_rate": 2.0235911970656888e-05,
|
| 373 |
+
"loss": 1.4054,
|
| 374 |
+
"step": 178625
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 25.0,
|
| 378 |
+
"eval_accuracy": 0.7103286516069584,
|
| 379 |
+
"eval_loss": 1.371171474456787,
|
| 380 |
+
"eval_runtime": 1.475,
|
| 381 |
+
"eval_samples_per_second": 324.736,
|
| 382 |
+
"eval_steps_per_second": 10.169,
|
| 383 |
+
"step": 178625
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 26.0,
|
| 387 |
+
"learning_rate": 1.9044681560520176e-05,
|
| 388 |
+
"loss": 1.402,
|
| 389 |
+
"step": 185770
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 26.0,
|
| 393 |
+
"eval_accuracy": 0.7112762628520339,
|
| 394 |
+
"eval_loss": 1.3528329133987427,
|
| 395 |
+
"eval_runtime": 1.467,
|
| 396 |
+
"eval_samples_per_second": 326.525,
|
| 397 |
+
"eval_steps_per_second": 10.225,
|
| 398 |
+
"step": 185770
|
| 399 |
},
|
| 400 |
{
|
| 401 |
"epoch": 27.0,
|
| 402 |
+
"learning_rate": 1.7853451150383463e-05,
|
| 403 |
+
"loss": 1.4001,
|
| 404 |
+
"step": 192915
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 27.0,
|
| 408 |
+
"eval_accuracy": 0.712307605886979,
|
| 409 |
+
"eval_loss": 1.336666226387024,
|
| 410 |
+
"eval_runtime": 1.4596,
|
| 411 |
+
"eval_samples_per_second": 328.179,
|
| 412 |
+
"eval_steps_per_second": 10.277,
|
| 413 |
+
"step": 192915
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 28.0,
|
| 417 |
+
"learning_rate": 1.666222074024675e-05,
|
| 418 |
+
"loss": 1.397,
|
| 419 |
+
"step": 200060
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 28.0,
|
| 423 |
+
"eval_accuracy": 0.7117655307810966,
|
| 424 |
+
"eval_loss": 1.3508223295211792,
|
| 425 |
+
"eval_runtime": 1.458,
|
| 426 |
+
"eval_samples_per_second": 328.539,
|
| 427 |
+
"eval_steps_per_second": 10.288,
|
| 428 |
+
"step": 200060
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 29.0,
|
| 432 |
+
"learning_rate": 1.5470990330110038e-05,
|
| 433 |
+
"loss": 1.3955,
|
| 434 |
+
"step": 207205
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 29.0,
|
| 438 |
+
"eval_accuracy": 0.7116529947185077,
|
| 439 |
+
"eval_loss": 1.3571882247924805,
|
| 440 |
+
"eval_runtime": 1.6349,
|
| 441 |
+
"eval_samples_per_second": 292.987,
|
| 442 |
+
"eval_steps_per_second": 9.175,
|
| 443 |
+
"step": 207205
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 30.0,
|
| 447 |
+
"learning_rate": 1.4279759919973326e-05,
|
| 448 |
+
"loss": 1.3937,
|
| 449 |
+
"step": 214350
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 30.0,
|
| 453 |
+
"eval_accuracy": 0.7095319458838688,
|
| 454 |
+
"eval_loss": 1.356575846672058,
|
| 455 |
+
"eval_runtime": 1.4657,
|
| 456 |
+
"eval_samples_per_second": 326.804,
|
| 457 |
+
"eval_steps_per_second": 10.234,
|
| 458 |
+
"step": 214350
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 31.0,
|
| 462 |
+
"learning_rate": 1.3088529509836615e-05,
|
| 463 |
+
"loss": 1.3901,
|
| 464 |
+
"step": 221495
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 31.0,
|
| 468 |
+
"eval_accuracy": 0.7116992819935238,
|
| 469 |
+
"eval_loss": 1.3515229225158691,
|
| 470 |
+
"eval_runtime": 1.461,
|
| 471 |
+
"eval_samples_per_second": 327.859,
|
| 472 |
+
"eval_steps_per_second": 10.267,
|
| 473 |
+
"step": 221495
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 32.0,
|
| 477 |
+
"learning_rate": 1.18972990996999e-05,
|
| 478 |
+
"loss": 1.3874,
|
| 479 |
+
"step": 228640
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 32.0,
|
| 483 |
+
"eval_accuracy": 0.7118393529493795,
|
| 484 |
+
"eval_loss": 1.3445274829864502,
|
| 485 |
+
"eval_runtime": 1.4728,
|
| 486 |
+
"eval_samples_per_second": 325.229,
|
| 487 |
+
"eval_steps_per_second": 10.185,
|
| 488 |
+
"step": 228640
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 33.0,
|
| 492 |
+
"learning_rate": 1.0706068689563188e-05,
|
| 493 |
+
"loss": 1.386,
|
| 494 |
+
"step": 235785
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"epoch": 33.0,
|
| 498 |
+
"eval_accuracy": 0.7097090095131505,
|
| 499 |
+
"eval_loss": 1.361108660697937,
|
| 500 |
+
"eval_runtime": 1.4621,
|
| 501 |
+
"eval_samples_per_second": 327.607,
|
| 502 |
+
"eval_steps_per_second": 10.259,
|
| 503 |
+
"step": 235785
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 34.0,
|
| 507 |
+
"learning_rate": 9.514838279426476e-06,
|
| 508 |
+
"loss": 1.3833,
|
| 509 |
+
"step": 242930
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 34.0,
|
| 513 |
+
"eval_accuracy": 0.7086746246959827,
|
| 514 |
+
"eval_loss": 1.350243091583252,
|
| 515 |
+
"eval_runtime": 1.4812,
|
| 516 |
+
"eval_samples_per_second": 323.387,
|
| 517 |
+
"eval_steps_per_second": 10.127,
|
| 518 |
+
"step": 242930
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 35.0,
|
| 522 |
+
"learning_rate": 8.323607869289763e-06,
|
| 523 |
+
"loss": 1.3822,
|
| 524 |
+
"step": 250075
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 35.0,
|
| 528 |
+
"eval_accuracy": 0.7108018854610629,
|
| 529 |
+
"eval_loss": 1.3657063245773315,
|
| 530 |
+
"eval_runtime": 1.4712,
|
| 531 |
+
"eval_samples_per_second": 325.58,
|
| 532 |
+
"eval_steps_per_second": 10.196,
|
| 533 |
+
"step": 250075
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 36.0,
|
| 537 |
+
"learning_rate": 7.132377459153051e-06,
|
| 538 |
+
"loss": 1.3797,
|
| 539 |
+
"step": 257220
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 36.0,
|
| 543 |
+
"eval_accuracy": 0.7107789319595755,
|
| 544 |
+
"eval_loss": 1.3575541973114014,
|
| 545 |
+
"eval_runtime": 1.4667,
|
| 546 |
+
"eval_samples_per_second": 326.589,
|
| 547 |
+
"eval_steps_per_second": 10.227,
|
| 548 |
+
"step": 257220
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 37.0,
|
| 552 |
+
"learning_rate": 5.941147049016339e-06,
|
| 553 |
+
"loss": 1.3793,
|
| 554 |
+
"step": 264365
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 37.0,
|
| 558 |
+
"eval_accuracy": 0.710604865960802,
|
| 559 |
+
"eval_loss": 1.3471879959106445,
|
| 560 |
+
"eval_runtime": 1.4747,
|
| 561 |
+
"eval_samples_per_second": 324.802,
|
| 562 |
+
"eval_steps_per_second": 10.171,
|
| 563 |
+
"step": 264365
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 38.0,
|
| 567 |
+
"learning_rate": 4.749916638879627e-06,
|
| 568 |
+
"loss": 1.3763,
|
| 569 |
+
"step": 271510
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 38.0,
|
| 573 |
+
"eval_accuracy": 0.7155870445344129,
|
| 574 |
+
"eval_loss": 1.3322880268096924,
|
| 575 |
+
"eval_runtime": 1.4923,
|
| 576 |
+
"eval_samples_per_second": 320.979,
|
| 577 |
+
"eval_steps_per_second": 10.052,
|
| 578 |
+
"step": 271510
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 39.0,
|
| 582 |
+
"learning_rate": 3.5586862287429143e-06,
|
| 583 |
+
"loss": 1.3762,
|
| 584 |
+
"step": 278655
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 39.0,
|
| 588 |
+
"eval_accuracy": 0.7144579664629017,
|
| 589 |
+
"eval_loss": 1.3325406312942505,
|
| 590 |
+
"eval_runtime": 1.6301,
|
| 591 |
+
"eval_samples_per_second": 293.852,
|
| 592 |
+
"eval_steps_per_second": 9.202,
|
| 593 |
+
"step": 278655
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 40.0,
|
| 597 |
+
"learning_rate": 2.3674558186062022e-06,
|
| 598 |
+
"loss": 1.3748,
|
| 599 |
+
"step": 285800
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 40.0,
|
| 603 |
+
"eval_accuracy": 0.7138002117109589,
|
| 604 |
+
"eval_loss": 1.3242748975753784,
|
| 605 |
+
"eval_runtime": 1.4707,
|
| 606 |
+
"eval_samples_per_second": 325.685,
|
| 607 |
+
"eval_steps_per_second": 10.199,
|
| 608 |
+
"step": 285800
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 41.0,
|
| 612 |
+
"learning_rate": 1.17622540846949e-06,
|
| 613 |
+
"loss": 1.3733,
|
| 614 |
+
"step": 292945
|
| 615 |
},
|
| 616 |
{
|
| 617 |
"epoch": 41.0,
|
| 618 |
+
"eval_accuracy": 0.7170023313951855,
|
| 619 |
+
"eval_loss": 1.3217717409133911,
|
| 620 |
+
"eval_runtime": 1.459,
|
| 621 |
+
"eval_samples_per_second": 328.301,
|
| 622 |
+
"eval_steps_per_second": 10.281,
|
| 623 |
+
"step": 292945
|
| 624 |
},
|
| 625 |
{
|
| 626 |
+
"epoch": 41.99,
|
| 627 |
+
"learning_rate": 0.0,
|
| 628 |
+
"loss": 1.3722,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 629 |
"step": 300000
|
| 630 |
},
|
| 631 |
{
|
| 632 |
+
"epoch": 41.99,
|
| 633 |
+
"eval_accuracy": 0.7186174960946218,
|
| 634 |
+
"eval_loss": 1.3073620796203613,
|
| 635 |
+
"eval_runtime": 1.4662,
|
| 636 |
+
"eval_samples_per_second": 326.688,
|
| 637 |
+
"eval_steps_per_second": 10.23,
|
| 638 |
"step": 300000
|
| 639 |
},
|
| 640 |
{
|
| 641 |
+
"epoch": 41.99,
|
| 642 |
"step": 300000,
|
| 643 |
+
"total_flos": 9.562938924439962e+17,
|
| 644 |
+
"train_loss": 1.4300982942708333,
|
| 645 |
+
"train_runtime": 103608.4476,
|
| 646 |
+
"train_samples_per_second": 92.657,
|
| 647 |
+
"train_steps_per_second": 2.896
|
| 648 |
}
|
| 649 |
],
|
| 650 |
"max_steps": 300000,
|
| 651 |
+
"num_train_epochs": 42,
|
| 652 |
+
"total_flos": 9.562938924439962e+17,
|
| 653 |
"trial_name": null,
|
| 654 |
"trial_params": null
|
| 655 |
}
|