update model
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +602 -5
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 455,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
-
"perplexity": 5.
|
| 9 |
-
"train_loss": 1.
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 9572,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second":
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"eval_loss": 1.7010221481323242,
|
| 4 |
+
"eval_runtime": 34.7991,
|
| 5 |
"eval_samples": 455,
|
| 6 |
+
"eval_samples_per_second": 13.075,
|
| 7 |
+
"eval_steps_per_second": 1.638,
|
| 8 |
+
"perplexity": 5.479545437358641,
|
| 9 |
+
"train_loss": 1.0414019944791026,
|
| 10 |
+
"train_runtime": 23906.9056,
|
| 11 |
"train_samples": 9572,
|
| 12 |
+
"train_samples_per_second": 4.805,
|
| 13 |
+
"train_steps_per_second": 2.402
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 455,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
-
"perplexity": 5.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"eval_loss": 1.7010221481323242,
|
| 4 |
+
"eval_runtime": 34.7991,
|
| 5 |
"eval_samples": 455,
|
| 6 |
+
"eval_samples_per_second": 13.075,
|
| 7 |
+
"eval_steps_per_second": 1.638,
|
| 8 |
+
"perplexity": 5.479545437358641
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510435963
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f2d41238a98adcd748d7db02b0080e34378e845a398f3d85ed71d96942e129e
|
| 3 |
size 510435963
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 1.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 9572,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"train_loss": 1.0414019944791026,
|
| 4 |
+
"train_runtime": 23906.9056,
|
| 5 |
"train_samples": 9572,
|
| 6 |
+
"train_samples_per_second": 4.805,
|
| 7 |
+
"train_steps_per_second": 2.402
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -207,11 +207,608 @@
|
|
| 207 |
"train_runtime": 8429.8505,
|
| 208 |
"train_samples_per_second": 3.406,
|
| 209 |
"train_steps_per_second": 1.703
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 210 |
}
|
| 211 |
],
|
| 212 |
-
"max_steps":
|
| 213 |
-
"num_train_epochs":
|
| 214 |
-
"total_flos":
|
| 215 |
"trial_name": null,
|
| 216 |
"trial_params": null
|
| 217 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.0,
|
| 5 |
+
"global_step": 57432,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 207 |
"train_runtime": 8429.8505,
|
| 208 |
"train_samples_per_second": 3.406,
|
| 209 |
"train_steps_per_second": 1.703
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.03,
|
| 213 |
+
"learning_rate": 4.987811672934949e-05,
|
| 214 |
+
"loss": 1.5627,
|
| 215 |
+
"step": 14500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.13,
|
| 219 |
+
"learning_rate": 4.944368992895947e-05,
|
| 220 |
+
"loss": 1.5686,
|
| 221 |
+
"step": 15000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 3.24,
|
| 225 |
+
"learning_rate": 4.900839253377908e-05,
|
| 226 |
+
"loss": 1.5776,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.34,
|
| 231 |
+
"learning_rate": 4.85730951385987e-05,
|
| 232 |
+
"loss": 1.5699,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.45,
|
| 237 |
+
"learning_rate": 4.8137797743418304e-05,
|
| 238 |
+
"loss": 1.5476,
|
| 239 |
+
"step": 16500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.55,
|
| 243 |
+
"learning_rate": 4.770250034823792e-05,
|
| 244 |
+
"loss": 1.5448,
|
| 245 |
+
"step": 17000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.66,
|
| 249 |
+
"learning_rate": 4.726720295305753e-05,
|
| 250 |
+
"loss": 1.5656,
|
| 251 |
+
"step": 17500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.76,
|
| 255 |
+
"learning_rate": 4.683277615266751e-05,
|
| 256 |
+
"loss": 1.5694,
|
| 257 |
+
"step": 18000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.87,
|
| 261 |
+
"learning_rate": 4.6397478757487115e-05,
|
| 262 |
+
"loss": 1.542,
|
| 263 |
+
"step": 18500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.97,
|
| 267 |
+
"learning_rate": 4.596218136230673e-05,
|
| 268 |
+
"loss": 1.5474,
|
| 269 |
+
"step": 19000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.0,
|
| 273 |
+
"eval_loss": 1.5994045734405518,
|
| 274 |
+
"eval_runtime": 39.2637,
|
| 275 |
+
"eval_samples_per_second": 11.588,
|
| 276 |
+
"eval_steps_per_second": 1.452,
|
| 277 |
+
"step": 19144
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 4.07,
|
| 281 |
+
"learning_rate": 4.552688396712634e-05,
|
| 282 |
+
"loss": 1.5336,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.18,
|
| 287 |
+
"learning_rate": 4.5091586571945955e-05,
|
| 288 |
+
"loss": 1.5259,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 4.28,
|
| 293 |
+
"learning_rate": 4.465628917676557e-05,
|
| 294 |
+
"loss": 1.495,
|
| 295 |
+
"step": 20500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 4.39,
|
| 299 |
+
"learning_rate": 4.422099178158518e-05,
|
| 300 |
+
"loss": 1.5003,
|
| 301 |
+
"step": 21000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 4.49,
|
| 305 |
+
"learning_rate": 4.378656498119515e-05,
|
| 306 |
+
"loss": 1.4912,
|
| 307 |
+
"step": 21500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 4.6,
|
| 311 |
+
"learning_rate": 4.3351267586014767e-05,
|
| 312 |
+
"loss": 1.491,
|
| 313 |
+
"step": 22000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 4.7,
|
| 317 |
+
"learning_rate": 4.291597019083438e-05,
|
| 318 |
+
"loss": 1.4888,
|
| 319 |
+
"step": 22500
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 4.81,
|
| 323 |
+
"learning_rate": 4.2480672795653994e-05,
|
| 324 |
+
"loss": 1.5098,
|
| 325 |
+
"step": 23000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.91,
|
| 329 |
+
"learning_rate": 4.2046245995263964e-05,
|
| 330 |
+
"loss": 1.5011,
|
| 331 |
+
"step": 23500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 5.0,
|
| 335 |
+
"eval_loss": 1.5889110565185547,
|
| 336 |
+
"eval_runtime": 42.2475,
|
| 337 |
+
"eval_samples_per_second": 10.77,
|
| 338 |
+
"eval_steps_per_second": 1.349,
|
| 339 |
+
"step": 23930
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 5.01,
|
| 343 |
+
"learning_rate": 4.161094860008358e-05,
|
| 344 |
+
"loss": 1.4888,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 5.12,
|
| 349 |
+
"learning_rate": 4.117565120490319e-05,
|
| 350 |
+
"loss": 1.4664,
|
| 351 |
+
"step": 24500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 5.22,
|
| 355 |
+
"learning_rate": 4.0740353809722805e-05,
|
| 356 |
+
"loss": 1.455,
|
| 357 |
+
"step": 25000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 5.33,
|
| 361 |
+
"learning_rate": 4.030505641454242e-05,
|
| 362 |
+
"loss": 1.4491,
|
| 363 |
+
"step": 25500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 5.43,
|
| 367 |
+
"learning_rate": 3.986975901936203e-05,
|
| 368 |
+
"loss": 1.4543,
|
| 369 |
+
"step": 26000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 5.54,
|
| 373 |
+
"learning_rate": 3.9435332218972e-05,
|
| 374 |
+
"loss": 1.4588,
|
| 375 |
+
"step": 26500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 5.64,
|
| 379 |
+
"learning_rate": 3.9000034823791616e-05,
|
| 380 |
+
"loss": 1.446,
|
| 381 |
+
"step": 27000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 5.75,
|
| 385 |
+
"learning_rate": 3.856473742861123e-05,
|
| 386 |
+
"loss": 1.4386,
|
| 387 |
+
"step": 27500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 5.85,
|
| 391 |
+
"learning_rate": 3.812944003343084e-05,
|
| 392 |
+
"loss": 1.4473,
|
| 393 |
+
"step": 28000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 5.95,
|
| 397 |
+
"learning_rate": 3.7694142638250456e-05,
|
| 398 |
+
"loss": 1.4724,
|
| 399 |
+
"step": 28500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 6.0,
|
| 403 |
+
"eval_loss": 1.5893619060516357,
|
| 404 |
+
"eval_runtime": 39.6175,
|
| 405 |
+
"eval_samples_per_second": 11.485,
|
| 406 |
+
"eval_steps_per_second": 1.439,
|
| 407 |
+
"step": 28716
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 6.06,
|
| 411 |
+
"learning_rate": 3.725884524307007e-05,
|
| 412 |
+
"loss": 1.4439,
|
| 413 |
+
"step": 29000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 6.16,
|
| 417 |
+
"learning_rate": 3.6823547847889676e-05,
|
| 418 |
+
"loss": 1.4021,
|
| 419 |
+
"step": 29500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 6.27,
|
| 423 |
+
"learning_rate": 3.6388250452709297e-05,
|
| 424 |
+
"loss": 1.4147,
|
| 425 |
+
"step": 30000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 6.37,
|
| 429 |
+
"learning_rate": 3.595382365231927e-05,
|
| 430 |
+
"loss": 1.4157,
|
| 431 |
+
"step": 30500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 6.48,
|
| 435 |
+
"learning_rate": 3.551852625713888e-05,
|
| 436 |
+
"loss": 1.417,
|
| 437 |
+
"step": 31000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 6.58,
|
| 441 |
+
"learning_rate": 3.508322886195849e-05,
|
| 442 |
+
"loss": 1.4094,
|
| 443 |
+
"step": 31500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 6.69,
|
| 447 |
+
"learning_rate": 3.464793146677811e-05,
|
| 448 |
+
"loss": 1.4209,
|
| 449 |
+
"step": 32000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 6.79,
|
| 453 |
+
"learning_rate": 3.4212634071597714e-05,
|
| 454 |
+
"loss": 1.415,
|
| 455 |
+
"step": 32500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 6.9,
|
| 459 |
+
"learning_rate": 3.377907786599805e-05,
|
| 460 |
+
"loss": 1.4128,
|
| 461 |
+
"step": 33000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 7.0,
|
| 465 |
+
"learning_rate": 3.334378047081766e-05,
|
| 466 |
+
"loss": 1.414,
|
| 467 |
+
"step": 33500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 7.0,
|
| 471 |
+
"eval_loss": 1.5933945178985596,
|
| 472 |
+
"eval_runtime": 39.5291,
|
| 473 |
+
"eval_samples_per_second": 11.51,
|
| 474 |
+
"eval_steps_per_second": 1.442,
|
| 475 |
+
"step": 33502
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 7.1,
|
| 479 |
+
"learning_rate": 3.2908483075637276e-05,
|
| 480 |
+
"loss": 1.358,
|
| 481 |
+
"step": 34000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 7.21,
|
| 485 |
+
"learning_rate": 3.247318568045689e-05,
|
| 486 |
+
"loss": 1.3821,
|
| 487 |
+
"step": 34500
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 7.31,
|
| 491 |
+
"learning_rate": 3.20378882852765e-05,
|
| 492 |
+
"loss": 1.377,
|
| 493 |
+
"step": 35000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 7.42,
|
| 497 |
+
"learning_rate": 3.1602590890096116e-05,
|
| 498 |
+
"loss": 1.3772,
|
| 499 |
+
"step": 35500
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.52,
|
| 503 |
+
"learning_rate": 3.116729349491573e-05,
|
| 504 |
+
"loss": 1.3777,
|
| 505 |
+
"step": 36000
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 7.63,
|
| 509 |
+
"learning_rate": 3.0731996099735337e-05,
|
| 510 |
+
"loss": 1.3672,
|
| 511 |
+
"step": 36500
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 7.73,
|
| 515 |
+
"learning_rate": 3.0298439894135678e-05,
|
| 516 |
+
"loss": 1.3949,
|
| 517 |
+
"step": 37000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 7.84,
|
| 521 |
+
"learning_rate": 2.9864013093745645e-05,
|
| 522 |
+
"loss": 1.3626,
|
| 523 |
+
"step": 37500
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 7.94,
|
| 527 |
+
"learning_rate": 2.9428715698565262e-05,
|
| 528 |
+
"loss": 1.3939,
|
| 529 |
+
"step": 38000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 8.0,
|
| 533 |
+
"eval_loss": 1.6080235242843628,
|
| 534 |
+
"eval_runtime": 39.1335,
|
| 535 |
+
"eval_samples_per_second": 11.627,
|
| 536 |
+
"eval_steps_per_second": 1.457,
|
| 537 |
+
"step": 38288
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 8.04,
|
| 541 |
+
"learning_rate": 2.8993418303384872e-05,
|
| 542 |
+
"loss": 1.3667,
|
| 543 |
+
"step": 38500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 8.15,
|
| 547 |
+
"learning_rate": 2.855812090820449e-05,
|
| 548 |
+
"loss": 1.336,
|
| 549 |
+
"step": 39000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 8.25,
|
| 553 |
+
"learning_rate": 2.81228235130241e-05,
|
| 554 |
+
"loss": 1.3212,
|
| 555 |
+
"step": 39500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 8.36,
|
| 559 |
+
"learning_rate": 2.768752611784371e-05,
|
| 560 |
+
"loss": 1.3235,
|
| 561 |
+
"step": 40000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 8.46,
|
| 565 |
+
"learning_rate": 2.7252228722663326e-05,
|
| 566 |
+
"loss": 1.3649,
|
| 567 |
+
"step": 40500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 8.57,
|
| 571 |
+
"learning_rate": 2.6816931327482936e-05,
|
| 572 |
+
"loss": 1.3423,
|
| 573 |
+
"step": 41000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 8.67,
|
| 577 |
+
"learning_rate": 2.6381633932302553e-05,
|
| 578 |
+
"loss": 1.3396,
|
| 579 |
+
"step": 41500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 8.78,
|
| 583 |
+
"learning_rate": 2.5946336537122163e-05,
|
| 584 |
+
"loss": 1.3528,
|
| 585 |
+
"step": 42000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 8.88,
|
| 589 |
+
"learning_rate": 2.5511909736732137e-05,
|
| 590 |
+
"loss": 1.3488,
|
| 591 |
+
"step": 42500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 8.98,
|
| 595 |
+
"learning_rate": 2.5076612341551747e-05,
|
| 596 |
+
"loss": 1.3448,
|
| 597 |
+
"step": 43000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 9.0,
|
| 601 |
+
"eval_loss": 1.626845121383667,
|
| 602 |
+
"eval_runtime": 39.7529,
|
| 603 |
+
"eval_samples_per_second": 11.446,
|
| 604 |
+
"eval_steps_per_second": 1.434,
|
| 605 |
+
"step": 43074
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 9.09,
|
| 609 |
+
"learning_rate": 2.4641314946371364e-05,
|
| 610 |
+
"loss": 1.3208,
|
| 611 |
+
"step": 43500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 9.19,
|
| 615 |
+
"learning_rate": 2.4206017551190974e-05,
|
| 616 |
+
"loss": 1.3107,
|
| 617 |
+
"step": 44000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 9.3,
|
| 621 |
+
"learning_rate": 2.377159075080095e-05,
|
| 622 |
+
"loss": 1.3029,
|
| 623 |
+
"step": 44500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 9.4,
|
| 627 |
+
"learning_rate": 2.3336293355620562e-05,
|
| 628 |
+
"loss": 1.3034,
|
| 629 |
+
"step": 45000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 9.51,
|
| 633 |
+
"learning_rate": 2.2900995960440175e-05,
|
| 634 |
+
"loss": 1.3041,
|
| 635 |
+
"step": 45500
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 9.61,
|
| 639 |
+
"learning_rate": 2.2466569160050146e-05,
|
| 640 |
+
"loss": 1.3025,
|
| 641 |
+
"step": 46000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 9.72,
|
| 645 |
+
"learning_rate": 2.203127176486976e-05,
|
| 646 |
+
"loss": 1.3186,
|
| 647 |
+
"step": 46500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 9.82,
|
| 651 |
+
"learning_rate": 2.1595974369689373e-05,
|
| 652 |
+
"loss": 1.3185,
|
| 653 |
+
"step": 47000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 9.92,
|
| 657 |
+
"learning_rate": 2.1160676974508987e-05,
|
| 658 |
+
"loss": 1.3227,
|
| 659 |
+
"step": 47500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 10.0,
|
| 663 |
+
"eval_loss": 1.6497271060943604,
|
| 664 |
+
"eval_runtime": 39.0443,
|
| 665 |
+
"eval_samples_per_second": 11.653,
|
| 666 |
+
"eval_steps_per_second": 1.46,
|
| 667 |
+
"step": 47860
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 10.03,
|
| 671 |
+
"learning_rate": 2.07253795793286e-05,
|
| 672 |
+
"loss": 1.3038,
|
| 673 |
+
"step": 48000
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 10.13,
|
| 677 |
+
"learning_rate": 2.029008218414821e-05,
|
| 678 |
+
"loss": 1.2825,
|
| 679 |
+
"step": 48500
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 10.24,
|
| 683 |
+
"learning_rate": 1.9854784788967824e-05,
|
| 684 |
+
"loss": 1.2657,
|
| 685 |
+
"step": 49000
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 10.34,
|
| 689 |
+
"learning_rate": 1.9419487393787437e-05,
|
| 690 |
+
"loss": 1.2851,
|
| 691 |
+
"step": 49500
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 10.45,
|
| 695 |
+
"learning_rate": 1.898418999860705e-05,
|
| 696 |
+
"loss": 1.294,
|
| 697 |
+
"step": 50000
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 10.55,
|
| 701 |
+
"learning_rate": 1.8549763198217025e-05,
|
| 702 |
+
"loss": 1.2857,
|
| 703 |
+
"step": 50500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 10.66,
|
| 707 |
+
"learning_rate": 1.8114465803036635e-05,
|
| 708 |
+
"loss": 1.2665,
|
| 709 |
+
"step": 51000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 10.76,
|
| 713 |
+
"learning_rate": 1.7679168407856248e-05,
|
| 714 |
+
"loss": 1.273,
|
| 715 |
+
"step": 51500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 10.87,
|
| 719 |
+
"learning_rate": 1.724387101267586e-05,
|
| 720 |
+
"loss": 1.2838,
|
| 721 |
+
"step": 52000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 10.97,
|
| 725 |
+
"learning_rate": 1.6809444212285836e-05,
|
| 726 |
+
"loss": 1.2873,
|
| 727 |
+
"step": 52500
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 11.0,
|
| 731 |
+
"eval_loss": 1.673952341079712,
|
| 732 |
+
"eval_runtime": 38.6787,
|
| 733 |
+
"eval_samples_per_second": 11.764,
|
| 734 |
+
"eval_steps_per_second": 1.474,
|
| 735 |
+
"step": 52646
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 11.07,
|
| 739 |
+
"learning_rate": 1.637414681710545e-05,
|
| 740 |
+
"loss": 1.2753,
|
| 741 |
+
"step": 53000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 11.18,
|
| 745 |
+
"learning_rate": 1.593884942192506e-05,
|
| 746 |
+
"loss": 1.2625,
|
| 747 |
+
"step": 53500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 11.28,
|
| 751 |
+
"learning_rate": 1.5503552026744673e-05,
|
| 752 |
+
"loss": 1.2471,
|
| 753 |
+
"step": 54000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 11.39,
|
| 757 |
+
"learning_rate": 1.5068254631564285e-05,
|
| 758 |
+
"loss": 1.2523,
|
| 759 |
+
"step": 54500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 11.49,
|
| 763 |
+
"learning_rate": 1.463382783117426e-05,
|
| 764 |
+
"loss": 1.2534,
|
| 765 |
+
"step": 55000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 11.6,
|
| 769 |
+
"learning_rate": 1.4199401030784231e-05,
|
| 770 |
+
"loss": 1.2606,
|
| 771 |
+
"step": 55500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 11.7,
|
| 775 |
+
"learning_rate": 1.3764103635603845e-05,
|
| 776 |
+
"loss": 1.244,
|
| 777 |
+
"step": 56000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 11.81,
|
| 781 |
+
"learning_rate": 1.332967683521382e-05,
|
| 782 |
+
"loss": 1.2577,
|
| 783 |
+
"step": 56500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 11.91,
|
| 787 |
+
"learning_rate": 1.2894379440033432e-05,
|
| 788 |
+
"loss": 1.2671,
|
| 789 |
+
"step": 57000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 12.0,
|
| 793 |
+
"eval_loss": 1.7010221481323242,
|
| 794 |
+
"eval_runtime": 38.3243,
|
| 795 |
+
"eval_samples_per_second": 11.872,
|
| 796 |
+
"eval_steps_per_second": 1.487,
|
| 797 |
+
"step": 57432
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 12.0,
|
| 801 |
+
"step": 57432,
|
| 802 |
+
"total_flos": 6.0026095927296e+16,
|
| 803 |
+
"train_loss": 1.0414019944791026,
|
| 804 |
+
"train_runtime": 23906.9056,
|
| 805 |
+
"train_samples_per_second": 4.805,
|
| 806 |
+
"train_steps_per_second": 2.402
|
| 807 |
}
|
| 808 |
],
|
| 809 |
+
"max_steps": 57432,
|
| 810 |
+
"num_train_epochs": 12,
|
| 811 |
+
"total_flos": 6.0026095927296e+16,
|
| 812 |
"trial_name": null,
|
| 813 |
"trial_params": null
|
| 814 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2671
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c53e7fa950a52eaad61b7c8a110974066f4a67ab2333e62df9941b90476f3148
|
| 3 |
size 2671
|