Commit
•
a5ea3ed
1
Parent(s):
0c23640
Training in progress, step 600
Browse files- {checkpoint-300 → checkpoint-600}/config.json +0 -0
- {checkpoint-300 → checkpoint-600}/optimizer.pt +1 -1
- {checkpoint-300 → checkpoint-600}/preprocessor_config.json +0 -0
- {checkpoint-300 → checkpoint-600}/pytorch_model.bin +1 -1
- {checkpoint-300 → checkpoint-600}/rng_state.pth +1 -1
- {checkpoint-300 → checkpoint-600}/scaler.pt +1 -1
- {checkpoint-300 → checkpoint-600}/scheduler.pt +1 -1
- {checkpoint-300 → checkpoint-600}/trainer_state.json +210 -3
- {checkpoint-300 → checkpoint-600}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-300 → checkpoint-600}/config.json
RENAMED
|
File without changes
|
{checkpoint-300 → checkpoint-600}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2490346001
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87b571a9150b8daa615fd79bd19594823cd3a5916dff123175f2b5acd3aae34f
|
| 3 |
size 2490346001
|
{checkpoint-300 → checkpoint-600}/preprocessor_config.json
RENAMED
|
File without changes
|
{checkpoint-300 → checkpoint-600}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262067185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8516ba404c3005619dab698e95eba4925ba995d7c93b7c12a9a3ec6e076a633a
|
| 3 |
size 1262067185
|
{checkpoint-300 → checkpoint-600}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4efb8c99e93bf6a9e0eaf10d4bc56f851a7d3bcdc654e07f6bc1aa10347070e6
|
| 3 |
size 14567
|
{checkpoint-300 → checkpoint-600}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd9adbb7bf7a7b94e5da4d383115b816c16f892b14cb7df333d0775ae0f262ae
|
| 3 |
size 559
|
{checkpoint-300 → checkpoint-600}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1234d8c3176806f7e4a5e539c9c83abb170bf548c7ebf7edff51815795c496ed
|
| 3 |
size 623
|
{checkpoint-300 → checkpoint-600}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -213,11 +213,218 @@
|
|
| 213 |
"eval_steps_per_second": 1.116,
|
| 214 |
"eval_wer": 1.0,
|
| 215 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 216 |
}
|
| 217 |
],
|
| 218 |
"max_steps": 6501,
|
| 219 |
"num_train_epochs": 3,
|
| 220 |
-
"total_flos":
|
| 221 |
"trial_name": null,
|
| 222 |
"trial_params": null
|
| 223 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2768166089965398,
|
| 5 |
+
"global_step": 600,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 213 |
"eval_steps_per_second": 1.116,
|
| 214 |
"eval_wer": 1.0,
|
| 215 |
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.14,
|
| 219 |
+
"learning_rate": 7.29866562009419e-05,
|
| 220 |
+
"loss": 2.9984,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.15,
|
| 225 |
+
"learning_rate": 7.286891679748822e-05,
|
| 226 |
+
"loss": 3.0006,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.15,
|
| 231 |
+
"learning_rate": 7.275117739403453e-05,
|
| 232 |
+
"loss": 3.029,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.16,
|
| 237 |
+
"learning_rate": 7.263343799058085e-05,
|
| 238 |
+
"loss": 3.158,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.16,
|
| 243 |
+
"learning_rate": 7.252747252747252e-05,
|
| 244 |
+
"loss": 3.4909,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.17,
|
| 249 |
+
"learning_rate": 7.240973312401883e-05,
|
| 250 |
+
"loss": 3.001,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.17,
|
| 255 |
+
"learning_rate": 7.229199372056515e-05,
|
| 256 |
+
"loss": 2.9925,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.18,
|
| 261 |
+
"learning_rate": 7.217425431711145e-05,
|
| 262 |
+
"loss": 3.0009,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.18,
|
| 267 |
+
"learning_rate": 7.205651491365776e-05,
|
| 268 |
+
"loss": 3.1263,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.18,
|
| 273 |
+
"learning_rate": 7.195054945054944e-05,
|
| 274 |
+
"loss": 3.421,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18,
|
| 279 |
+
"eval_loss": 3.0357792377471924,
|
| 280 |
+
"eval_runtime": 130.0328,
|
| 281 |
+
"eval_samples_per_second": 35.529,
|
| 282 |
+
"eval_steps_per_second": 1.115,
|
| 283 |
+
"eval_wer": 1.0,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.19,
|
| 288 |
+
"learning_rate": 7.183281004709575e-05,
|
| 289 |
+
"loss": 3.0018,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.19,
|
| 294 |
+
"learning_rate": 7.171507064364207e-05,
|
| 295 |
+
"loss": 2.9947,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2,
|
| 300 |
+
"learning_rate": 7.159733124018838e-05,
|
| 301 |
+
"loss": 2.9935,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.2,
|
| 306 |
+
"learning_rate": 7.147959183673469e-05,
|
| 307 |
+
"loss": 3.0818,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.21,
|
| 312 |
+
"learning_rate": 7.137362637362637e-05,
|
| 313 |
+
"loss": 3.3386,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.21,
|
| 318 |
+
"learning_rate": 7.125588697017268e-05,
|
| 319 |
+
"loss": 3.0803,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.22,
|
| 324 |
+
"learning_rate": 7.1138147566719e-05,
|
| 325 |
+
"loss": 3.1655,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.22,
|
| 330 |
+
"learning_rate": 7.10204081632653e-05,
|
| 331 |
+
"loss": 3.0899,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.23,
|
| 336 |
+
"learning_rate": 7.090266875981161e-05,
|
| 337 |
+
"loss": 3.1638,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.23,
|
| 342 |
+
"learning_rate": 7.079670329670328e-05,
|
| 343 |
+
"loss": 3.3518,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.23,
|
| 348 |
+
"eval_loss": 2.9412434101104736,
|
| 349 |
+
"eval_runtime": 130.1575,
|
| 350 |
+
"eval_samples_per_second": 35.495,
|
| 351 |
+
"eval_steps_per_second": 1.114,
|
| 352 |
+
"eval_wer": 1.0,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.24,
|
| 357 |
+
"learning_rate": 7.06789638932496e-05,
|
| 358 |
+
"loss": 2.9352,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.24,
|
| 363 |
+
"learning_rate": 7.056122448979591e-05,
|
| 364 |
+
"loss": 2.9405,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.24,
|
| 369 |
+
"learning_rate": 7.044348508634222e-05,
|
| 370 |
+
"loss": 2.9125,
|
| 371 |
+
"step": 530
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.25,
|
| 375 |
+
"learning_rate": 7.032574568288854e-05,
|
| 376 |
+
"loss": 2.9401,
|
| 377 |
+
"step": 540
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.25,
|
| 381 |
+
"learning_rate": 7.021978021978021e-05,
|
| 382 |
+
"loss": 3.1443,
|
| 383 |
+
"step": 550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.26,
|
| 387 |
+
"learning_rate": 7.010204081632653e-05,
|
| 388 |
+
"loss": 2.7692,
|
| 389 |
+
"step": 560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.26,
|
| 393 |
+
"learning_rate": 6.998430141287284e-05,
|
| 394 |
+
"loss": 2.7574,
|
| 395 |
+
"step": 570
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.27,
|
| 399 |
+
"learning_rate": 6.986656200941914e-05,
|
| 400 |
+
"loss": 2.706,
|
| 401 |
+
"step": 580
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.27,
|
| 405 |
+
"learning_rate": 6.974882260596545e-05,
|
| 406 |
+
"loss": 2.7155,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.28,
|
| 411 |
+
"learning_rate": 6.964285714285713e-05,
|
| 412 |
+
"loss": 2.8747,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.28,
|
| 417 |
+
"eval_loss": 2.5006003379821777,
|
| 418 |
+
"eval_runtime": 129.3111,
|
| 419 |
+
"eval_samples_per_second": 35.728,
|
| 420 |
+
"eval_steps_per_second": 1.121,
|
| 421 |
+
"eval_wer": 1.0,
|
| 422 |
+
"step": 600
|
| 423 |
}
|
| 424 |
],
|
| 425 |
"max_steps": 6501,
|
| 426 |
"num_train_epochs": 3,
|
| 427 |
+
"total_flos": 1.1344329626225234e+19,
|
| 428 |
"trial_name": null,
|
| 429 |
"trial_params": null
|
| 430 |
}
|
{checkpoint-300 → checkpoint-600}/training_args.bin
RENAMED
|
File without changes
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262067185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8516ba404c3005619dab698e95eba4925ba995d7c93b7c12a9a3ec6e076a633a
|
| 3 |
size 1262067185
|