Commit
·
962e35f
1
Parent(s):
29aa50a
Training in progress, step 2000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +254 -5
- pytorch_model.bin +1 -1
- runs/Jan28_23-19-38_gpu07.cyverse.org/events.out.tfevents.1674973221.gpu07.cyverse.org.79624.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12347192855
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46124b4c921f12dd4bf47335e9d76a44f1413ead1fdc2eb7bac5d8c91d14785d
|
| 3 |
size 12347192855
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6173655480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e3bce729d0a5aa88b97e2208db0eac5024f1cb7d8c05fa4291f05c5ffb546b6
|
| 3 |
size 6173655480
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6450fb70c9f637c8cf70a85044894a9aa53e7fb40b60415f65080b1848d744f8
|
| 3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73fb9353e9395a668a7a368e6a41451629f20384989decfcc02ea7b20b2db3e5
|
| 3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55371a8ee3a1d4bb4b0f9e4ee704a9718614f62f69f56fa1c068056dd8b6df67
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-arabic-24h/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -255,11 +255,260 @@
|
|
| 255 |
"eval_steps_per_second": 0.148,
|
| 256 |
"eval_wer": 0.4409728815314771,
|
| 257 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 258 |
}
|
| 259 |
],
|
| 260 |
"max_steps": 5000,
|
| 261 |
"num_train_epochs": 9,
|
| 262 |
-
"total_flos":
|
| 263 |
"trial_name": null,
|
| 264 |
"trial_params": null
|
| 265 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.42719787333206743,
|
| 3 |
+
"best_model_checkpoint": "/storage/elsayedissa/whisper-large-v2-arabic-24h/checkpoint-2000",
|
| 4 |
+
"epoch": 3.5650623885918002,
|
| 5 |
+
"global_step": 2000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 255 |
"eval_steps_per_second": 0.148,
|
| 256 |
"eval_wer": 0.4409728815314771,
|
| 257 |
"step": 1000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.83,
|
| 261 |
+
"learning_rate": 8.844444444444445e-06,
|
| 262 |
+
"loss": 0.1597,
|
| 263 |
+
"step": 1025
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.87,
|
| 267 |
+
"learning_rate": 8.788888888888891e-06,
|
| 268 |
+
"loss": 0.1524,
|
| 269 |
+
"step": 1050
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.92,
|
| 273 |
+
"learning_rate": 8.733333333333333e-06,
|
| 274 |
+
"loss": 0.1527,
|
| 275 |
+
"step": 1075
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.96,
|
| 279 |
+
"learning_rate": 8.677777777777779e-06,
|
| 280 |
+
"loss": 0.151,
|
| 281 |
+
"step": 1100
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.01,
|
| 285 |
+
"learning_rate": 8.622222222222223e-06,
|
| 286 |
+
"loss": 0.158,
|
| 287 |
+
"step": 1125
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.05,
|
| 291 |
+
"learning_rate": 8.566666666666667e-06,
|
| 292 |
+
"loss": 0.0797,
|
| 293 |
+
"step": 1150
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.09,
|
| 297 |
+
"learning_rate": 8.511111111111113e-06,
|
| 298 |
+
"loss": 0.1002,
|
| 299 |
+
"step": 1175
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.14,
|
| 303 |
+
"learning_rate": 8.455555555555555e-06,
|
| 304 |
+
"loss": 0.096,
|
| 305 |
+
"step": 1200
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.18,
|
| 309 |
+
"learning_rate": 8.400000000000001e-06,
|
| 310 |
+
"loss": 0.098,
|
| 311 |
+
"step": 1225
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.23,
|
| 315 |
+
"learning_rate": 8.344444444444445e-06,
|
| 316 |
+
"loss": 0.0927,
|
| 317 |
+
"step": 1250
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.27,
|
| 321 |
+
"learning_rate": 8.288888888888889e-06,
|
| 322 |
+
"loss": 0.1003,
|
| 323 |
+
"step": 1275
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.32,
|
| 327 |
+
"learning_rate": 8.233333333333335e-06,
|
| 328 |
+
"loss": 0.0885,
|
| 329 |
+
"step": 1300
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.36,
|
| 333 |
+
"learning_rate": 8.177777777777779e-06,
|
| 334 |
+
"loss": 0.1033,
|
| 335 |
+
"step": 1325
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.41,
|
| 339 |
+
"learning_rate": 8.122222222222223e-06,
|
| 340 |
+
"loss": 0.0914,
|
| 341 |
+
"step": 1350
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.45,
|
| 345 |
+
"learning_rate": 8.066666666666667e-06,
|
| 346 |
+
"loss": 0.1049,
|
| 347 |
+
"step": 1375
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.5,
|
| 351 |
+
"learning_rate": 8.011111111111113e-06,
|
| 352 |
+
"loss": 0.0889,
|
| 353 |
+
"step": 1400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.54,
|
| 357 |
+
"learning_rate": 7.955555555555557e-06,
|
| 358 |
+
"loss": 0.0989,
|
| 359 |
+
"step": 1425
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.58,
|
| 363 |
+
"learning_rate": 7.9e-06,
|
| 364 |
+
"loss": 0.0952,
|
| 365 |
+
"step": 1450
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.63,
|
| 369 |
+
"learning_rate": 7.844444444444446e-06,
|
| 370 |
+
"loss": 0.1034,
|
| 371 |
+
"step": 1475
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.67,
|
| 375 |
+
"learning_rate": 7.788888888888889e-06,
|
| 376 |
+
"loss": 0.0906,
|
| 377 |
+
"step": 1500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.72,
|
| 381 |
+
"learning_rate": 7.733333333333334e-06,
|
| 382 |
+
"loss": 0.0946,
|
| 383 |
+
"step": 1525
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.76,
|
| 387 |
+
"learning_rate": 7.677777777777778e-06,
|
| 388 |
+
"loss": 0.0865,
|
| 389 |
+
"step": 1550
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.81,
|
| 393 |
+
"learning_rate": 7.622222222222223e-06,
|
| 394 |
+
"loss": 0.105,
|
| 395 |
+
"step": 1575
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.85,
|
| 399 |
+
"learning_rate": 7.566666666666667e-06,
|
| 400 |
+
"loss": 0.0891,
|
| 401 |
+
"step": 1600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.9,
|
| 405 |
+
"learning_rate": 7.511111111111111e-06,
|
| 406 |
+
"loss": 0.1019,
|
| 407 |
+
"step": 1625
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.94,
|
| 411 |
+
"learning_rate": 7.455555555555556e-06,
|
| 412 |
+
"loss": 0.09,
|
| 413 |
+
"step": 1650
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.99,
|
| 417 |
+
"learning_rate": 7.4e-06,
|
| 418 |
+
"loss": 0.0941,
|
| 419 |
+
"step": 1675
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.03,
|
| 423 |
+
"learning_rate": 7.344444444444445e-06,
|
| 424 |
+
"loss": 0.0618,
|
| 425 |
+
"step": 1700
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.07,
|
| 429 |
+
"learning_rate": 7.28888888888889e-06,
|
| 430 |
+
"loss": 0.0489,
|
| 431 |
+
"step": 1725
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.12,
|
| 435 |
+
"learning_rate": 7.233333333333334e-06,
|
| 436 |
+
"loss": 0.0523,
|
| 437 |
+
"step": 1750
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.16,
|
| 441 |
+
"learning_rate": 7.177777777777778e-06,
|
| 442 |
+
"loss": 0.056,
|
| 443 |
+
"step": 1775
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.21,
|
| 447 |
+
"learning_rate": 7.122222222222222e-06,
|
| 448 |
+
"loss": 0.0544,
|
| 449 |
+
"step": 1800
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.25,
|
| 453 |
+
"learning_rate": 7.066666666666667e-06,
|
| 454 |
+
"loss": 0.0535,
|
| 455 |
+
"step": 1825
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.3,
|
| 459 |
+
"learning_rate": 7.011111111111112e-06,
|
| 460 |
+
"loss": 0.0548,
|
| 461 |
+
"step": 1850
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.34,
|
| 465 |
+
"learning_rate": 6.955555555555557e-06,
|
| 466 |
+
"loss": 0.0566,
|
| 467 |
+
"step": 1875
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.39,
|
| 471 |
+
"learning_rate": 6.9e-06,
|
| 472 |
+
"loss": 0.0563,
|
| 473 |
+
"step": 1900
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.43,
|
| 477 |
+
"learning_rate": 6.844444444444445e-06,
|
| 478 |
+
"loss": 0.0566,
|
| 479 |
+
"step": 1925
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.48,
|
| 483 |
+
"learning_rate": 6.788888888888889e-06,
|
| 484 |
+
"loss": 0.0588,
|
| 485 |
+
"step": 1950
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.52,
|
| 489 |
+
"learning_rate": 6.733333333333334e-06,
|
| 490 |
+
"loss": 0.0555,
|
| 491 |
+
"step": 1975
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 3.57,
|
| 495 |
+
"learning_rate": 6.677777777777779e-06,
|
| 496 |
+
"loss": 0.0587,
|
| 497 |
+
"step": 2000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 3.57,
|
| 501 |
+
"eval_loss": 0.23366238176822662,
|
| 502 |
+
"eval_runtime": 4445.0678,
|
| 503 |
+
"eval_samples_per_second": 2.348,
|
| 504 |
+
"eval_steps_per_second": 0.147,
|
| 505 |
+
"eval_wer": 0.42719787333206743,
|
| 506 |
+
"step": 2000
|
| 507 |
}
|
| 508 |
],
|
| 509 |
"max_steps": 5000,
|
| 510 |
"num_train_epochs": 9,
|
| 511 |
+
"total_flos": 2.122725154885632e+20,
|
| 512 |
"trial_name": null,
|
| 513 |
"trial_params": null
|
| 514 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6173655480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e3bce729d0a5aa88b97e2208db0eac5024f1cb7d8c05fa4291f05c5ffb546b6
|
| 3 |
size 6173655480
|
runs/Jan28_23-19-38_gpu07.cyverse.org/events.out.tfevents.1674973221.gpu07.cyverse.org.79624.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a4e7be97529d4d330c452ac014f467e347887004f00a52765249d37330791c
|
| 3 |
+
size 17594
|