Commit
•
c81fe7e
1
Parent(s):
7b7da48
Training in progress, step 8000
Browse files- {checkpoint-5000 → checkpoint-8000}/config.json +0 -0
- {checkpoint-5000 → checkpoint-8000}/optimizer.pt +1 -1
- {checkpoint-5000 → checkpoint-8000}/preprocessor_config.json +0 -0
- {checkpoint-5000 → checkpoint-8000}/pytorch_model.bin +1 -1
- {checkpoint-5000 → checkpoint-8000}/rng_state.pth +1 -1
- {checkpoint-5000 → checkpoint-8000}/scaler.pt +1 -1
- {checkpoint-5000 → checkpoint-8000}/scheduler.pt +1 -1
- {checkpoint-5000 → checkpoint-8000}/trainer_state.json +210 -3
- {checkpoint-5000 → checkpoint-8000}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-5000 → checkpoint-8000}/config.json
RENAMED
|
File without changes
|
{checkpoint-5000 → checkpoint-8000}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2490337809
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa4c9dd53d15d49879e66548349b7ba93af22cc90b50aaa0c548b3f0c7083e31
|
| 3 |
size 2490337809
|
{checkpoint-5000 → checkpoint-8000}/preprocessor_config.json
RENAMED
|
File without changes
|
{checkpoint-5000 → checkpoint-8000}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262063089
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e03974019e7bfaa10bfd153daa4001f4cabd730e7b038f7b98a07fecd285577
|
| 3 |
size 1262063089
|
{checkpoint-5000 → checkpoint-8000}/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 sha256:6c6ef44676e7224155f7e14d7b74145bb60e6f4e6c88ebd09fe8826554b4b1fc
|
| 3 |
size 14567
|
{checkpoint-5000 → checkpoint-8000}/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 sha256:403ba7f22569c4902b32046c993b89b828f741c88d8cb44a56e4afd0c94e4b39
|
| 3 |
size 559
|
{checkpoint-5000 → checkpoint-8000}/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 sha256:777f30eac54f0933d63aacbfb66ab44a18d7286a386bfd5f6e0c77c6b3ab9531
|
| 3 |
size 623
|
{checkpoint-5000 → checkpoint-8000}/trainer_state.json
RENAMED
|
@@ -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,
|
|
@@ -351,11 +351,218 @@
|
|
| 351 |
"eval_steps_per_second": 0.799,
|
| 352 |
"eval_wer": 0.12054297171344966,
|
| 353 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 354 |
}
|
| 355 |
],
|
| 356 |
"max_steps": 9600,
|
| 357 |
"num_train_epochs": 100,
|
| 358 |
-
"total_flos":
|
| 359 |
"trial_name": null,
|
| 360 |
"trial_params": null
|
| 361 |
}
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 83.33246753246753,
|
| 5 |
+
"global_step": 8000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 351 |
"eval_steps_per_second": 0.799,
|
| 352 |
"eval_wer": 0.12054297171344966,
|
| 353 |
"step": 5000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 53.12,
|
| 357 |
+
"learning_rate": 4.3974609374999994e-05,
|
| 358 |
+
"loss": 0.8275,
|
| 359 |
+
"step": 5100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 54.17,
|
| 363 |
+
"learning_rate": 4.2998046875e-05,
|
| 364 |
+
"loss": 0.8262,
|
| 365 |
+
"step": 5200
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 55.21,
|
| 369 |
+
"learning_rate": 4.2021484375e-05,
|
| 370 |
+
"loss": 0.8167,
|
| 371 |
+
"step": 5300
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 56.25,
|
| 375 |
+
"learning_rate": 4.1044921875e-05,
|
| 376 |
+
"loss": 0.8194,
|
| 377 |
+
"step": 5400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 57.29,
|
| 381 |
+
"learning_rate": 4.0068359375e-05,
|
| 382 |
+
"loss": 0.8192,
|
| 383 |
+
"step": 5500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 58.33,
|
| 387 |
+
"learning_rate": 3.9091796874999996e-05,
|
| 388 |
+
"loss": 0.8176,
|
| 389 |
+
"step": 5600
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 59.37,
|
| 393 |
+
"learning_rate": 3.8115234374999995e-05,
|
| 394 |
+
"loss": 0.8115,
|
| 395 |
+
"step": 5700
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 60.42,
|
| 399 |
+
"learning_rate": 3.7138671874999994e-05,
|
| 400 |
+
"loss": 0.8129,
|
| 401 |
+
"step": 5800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 61.46,
|
| 405 |
+
"learning_rate": 3.6162109375e-05,
|
| 406 |
+
"loss": 0.8052,
|
| 407 |
+
"step": 5900
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 62.5,
|
| 411 |
+
"learning_rate": 3.518554687499999e-05,
|
| 412 |
+
"loss": 0.8068,
|
| 413 |
+
"step": 6000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 62.5,
|
| 417 |
+
"eval_loss": 0.13501569628715515,
|
| 418 |
+
"eval_runtime": 207.5786,
|
| 419 |
+
"eval_samples_per_second": 24.304,
|
| 420 |
+
"eval_steps_per_second": 0.761,
|
| 421 |
+
"eval_wer": 0.11913406307575593,
|
| 422 |
+
"step": 6000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 63.54,
|
| 426 |
+
"learning_rate": 3.4208984375e-05,
|
| 427 |
+
"loss": 0.8004,
|
| 428 |
+
"step": 6100
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 64.58,
|
| 432 |
+
"learning_rate": 3.32421875e-05,
|
| 433 |
+
"loss": 0.7904,
|
| 434 |
+
"step": 6200
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 65.62,
|
| 438 |
+
"learning_rate": 3.2265625e-05,
|
| 439 |
+
"loss": 0.7947,
|
| 440 |
+
"step": 6300
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 66.66,
|
| 444 |
+
"learning_rate": 3.12890625e-05,
|
| 445 |
+
"loss": 0.7981,
|
| 446 |
+
"step": 6400
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 67.71,
|
| 450 |
+
"learning_rate": 3.0312499999999998e-05,
|
| 451 |
+
"loss": 0.8018,
|
| 452 |
+
"step": 6500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 68.75,
|
| 456 |
+
"learning_rate": 2.93359375e-05,
|
| 457 |
+
"loss": 0.7922,
|
| 458 |
+
"step": 6600
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 69.79,
|
| 462 |
+
"learning_rate": 2.8359374999999996e-05,
|
| 463 |
+
"loss": 0.796,
|
| 464 |
+
"step": 6700
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 70.83,
|
| 468 |
+
"learning_rate": 2.73828125e-05,
|
| 469 |
+
"loss": 0.7887,
|
| 470 |
+
"step": 6800
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 71.87,
|
| 474 |
+
"learning_rate": 2.6406249999999998e-05,
|
| 475 |
+
"loss": 0.7796,
|
| 476 |
+
"step": 6900
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 72.91,
|
| 480 |
+
"learning_rate": 2.5429687499999997e-05,
|
| 481 |
+
"loss": 0.7822,
|
| 482 |
+
"step": 7000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 72.91,
|
| 486 |
+
"eval_loss": 0.1346774846315384,
|
| 487 |
+
"eval_runtime": 195.6804,
|
| 488 |
+
"eval_samples_per_second": 25.782,
|
| 489 |
+
"eval_steps_per_second": 0.807,
|
| 490 |
+
"eval_wer": 0.11550341389400672,
|
| 491 |
+
"step": 7000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 73.96,
|
| 495 |
+
"learning_rate": 2.4453125e-05,
|
| 496 |
+
"loss": 0.7882,
|
| 497 |
+
"step": 7100
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 75.0,
|
| 501 |
+
"learning_rate": 2.34765625e-05,
|
| 502 |
+
"loss": 0.7821,
|
| 503 |
+
"step": 7200
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 76.04,
|
| 507 |
+
"learning_rate": 2.2499999999999998e-05,
|
| 508 |
+
"loss": 0.7814,
|
| 509 |
+
"step": 7300
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 77.08,
|
| 513 |
+
"learning_rate": 2.1523437499999997e-05,
|
| 514 |
+
"loss": 0.784,
|
| 515 |
+
"step": 7400
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 78.12,
|
| 519 |
+
"learning_rate": 2.0546875e-05,
|
| 520 |
+
"loss": 0.7772,
|
| 521 |
+
"step": 7500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 79.17,
|
| 525 |
+
"learning_rate": 1.95703125e-05,
|
| 526 |
+
"loss": 0.7785,
|
| 527 |
+
"step": 7600
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 80.21,
|
| 531 |
+
"learning_rate": 1.8593749999999998e-05,
|
| 532 |
+
"loss": 0.7731,
|
| 533 |
+
"step": 7700
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 81.25,
|
| 537 |
+
"learning_rate": 1.7617187499999997e-05,
|
| 538 |
+
"loss": 0.7726,
|
| 539 |
+
"step": 7800
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 82.29,
|
| 543 |
+
"learning_rate": 1.6640624999999996e-05,
|
| 544 |
+
"loss": 0.7765,
|
| 545 |
+
"step": 7900
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 83.33,
|
| 549 |
+
"learning_rate": 1.56640625e-05,
|
| 550 |
+
"loss": 0.7769,
|
| 551 |
+
"step": 8000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 83.33,
|
| 555 |
+
"eval_loss": 0.1320926398038864,
|
| 556 |
+
"eval_runtime": 197.3103,
|
| 557 |
+
"eval_samples_per_second": 25.569,
|
| 558 |
+
"eval_steps_per_second": 0.801,
|
| 559 |
+
"eval_wer": 0.11306491817492142,
|
| 560 |
+
"step": 8000
|
| 561 |
}
|
| 562 |
],
|
| 563 |
"max_steps": 9600,
|
| 564 |
"num_train_epochs": 100,
|
| 565 |
+
"total_flos": 1.2431184698047783e+20,
|
| 566 |
"trial_name": null,
|
| 567 |
"trial_params": null
|
| 568 |
}
|
{checkpoint-5000 → checkpoint-8000}/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 1262063089
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e03974019e7bfaa10bfd153daa4001f4cabd730e7b038f7b98a07fecd285577
|
| 3 |
size 1262063089
|