Training in progress, step 75, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134218
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e35230ecd7c380235c5a9416e893dbd0ee9b06f3874238dfc6829bb93c50f0e
|
| 3 |
size 134218
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -381,6 +381,189 @@
|
|
| 381 |
"eval_samples_per_second": 241.976,
|
| 382 |
"eval_steps_per_second": 120.988,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -395,12 +578,12 @@
|
|
| 395 |
"should_evaluate": false,
|
| 396 |
"should_log": false,
|
| 397 |
"should_save": true,
|
| 398 |
-
"should_training_stop":
|
| 399 |
},
|
| 400 |
"attributes": {}
|
| 401 |
}
|
| 402 |
},
|
| 403 |
-
"total_flos":
|
| 404 |
"train_batch_size": 2,
|
| 405 |
"trial_name": null,
|
| 406 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.01914425193835551,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 75,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 381 |
"eval_samples_per_second": 241.976,
|
| 382 |
"eval_steps_per_second": 120.988,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.013018091318081746,
|
| 387 |
+
"grad_norm": NaN,
|
| 388 |
+
"learning_rate": 2.500000000000001e-05,
|
| 389 |
+
"loss": 0.0,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.013273348010593152,
|
| 394 |
+
"grad_norm": NaN,
|
| 395 |
+
"learning_rate": 2.3135019582658802e-05,
|
| 396 |
+
"loss": 0.0,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.01352860470310456,
|
| 401 |
+
"grad_norm": NaN,
|
| 402 |
+
"learning_rate": 2.132117818244771e-05,
|
| 403 |
+
"loss": 0.0,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.013783861395615967,
|
| 408 |
+
"grad_norm": NaN,
|
| 409 |
+
"learning_rate": 1.9561928549563968e-05,
|
| 410 |
+
"loss": 0.0,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.014039118088127373,
|
| 415 |
+
"grad_norm": NaN,
|
| 416 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 417 |
+
"loss": 0.0,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.01429437478063878,
|
| 422 |
+
"grad_norm": NaN,
|
| 423 |
+
"learning_rate": 1.622048961921699e-05,
|
| 424 |
+
"loss": 0.0,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.014549631473150186,
|
| 429 |
+
"grad_norm": NaN,
|
| 430 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 431 |
+
"loss": 0.0,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.014804888165661594,
|
| 436 |
+
"grad_norm": NaN,
|
| 437 |
+
"learning_rate": 1.3136133159493802e-05,
|
| 438 |
+
"loss": 0.0,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.015060144858173,
|
| 443 |
+
"grad_norm": NaN,
|
| 444 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 445 |
+
"loss": 0.0,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.015315401550684407,
|
| 450 |
+
"grad_norm": NaN,
|
| 451 |
+
"learning_rate": 1.0332332985438248e-05,
|
| 452 |
+
"loss": 0.0,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.015570658243195814,
|
| 457 |
+
"grad_norm": NaN,
|
| 458 |
+
"learning_rate": 9.042397785550405e-06,
|
| 459 |
+
"loss": 0.0,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.01582591493570722,
|
| 464 |
+
"grad_norm": NaN,
|
| 465 |
+
"learning_rate": 7.830427709355725e-06,
|
| 466 |
+
"loss": 0.0,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.016081171628218628,
|
| 471 |
+
"grad_norm": NaN,
|
| 472 |
+
"learning_rate": 6.698729810778065e-06,
|
| 473 |
+
"loss": 0.0,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.016336428320730033,
|
| 478 |
+
"grad_norm": NaN,
|
| 479 |
+
"learning_rate": 5.649458341088915e-06,
|
| 480 |
+
"loss": 0.0,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.01659168501324144,
|
| 485 |
+
"grad_norm": NaN,
|
| 486 |
+
"learning_rate": 4.684610648167503e-06,
|
| 487 |
+
"loss": 0.0,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.01684694170575285,
|
| 492 |
+
"grad_norm": NaN,
|
| 493 |
+
"learning_rate": 3.8060233744356633e-06,
|
| 494 |
+
"loss": 0.0,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.017102198398264254,
|
| 499 |
+
"grad_norm": NaN,
|
| 500 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 501 |
+
"loss": 0.0,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.017357455090775662,
|
| 506 |
+
"grad_norm": NaN,
|
| 507 |
+
"learning_rate": 2.314152462588659e-06,
|
| 508 |
+
"loss": 0.0,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.017612711783287067,
|
| 513 |
+
"grad_norm": NaN,
|
| 514 |
+
"learning_rate": 1.70370868554659e-06,
|
| 515 |
+
"loss": 0.0,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.017867968475798475,
|
| 520 |
+
"grad_norm": NaN,
|
| 521 |
+
"learning_rate": 1.1851996440033319e-06,
|
| 522 |
+
"loss": 0.0,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.018123225168309883,
|
| 527 |
+
"grad_norm": NaN,
|
| 528 |
+
"learning_rate": 7.596123493895991e-07,
|
| 529 |
+
"loss": 0.0,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.018378481860821288,
|
| 534 |
+
"grad_norm": NaN,
|
| 535 |
+
"learning_rate": 4.277569313094809e-07,
|
| 536 |
+
"loss": 0.0,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.018633738553332696,
|
| 541 |
+
"grad_norm": NaN,
|
| 542 |
+
"learning_rate": 1.9026509541272275e-07,
|
| 543 |
+
"loss": 0.0,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.0188889952458441,
|
| 548 |
+
"grad_norm": NaN,
|
| 549 |
+
"learning_rate": 4.7588920907110094e-08,
|
| 550 |
+
"loss": 0.0,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.01914425193835551,
|
| 555 |
+
"grad_norm": NaN,
|
| 556 |
+
"learning_rate": 0.0,
|
| 557 |
+
"loss": 0.0,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.01914425193835551,
|
| 562 |
+
"eval_loss": NaN,
|
| 563 |
+
"eval_runtime": 13.5282,
|
| 564 |
+
"eval_samples_per_second": 243.935,
|
| 565 |
+
"eval_steps_per_second": 121.968,
|
| 566 |
+
"step": 75
|
| 567 |
}
|
| 568 |
],
|
| 569 |
"logging_steps": 1,
|
|
|
|
| 578 |
"should_evaluate": false,
|
| 579 |
"should_log": false,
|
| 580 |
"should_save": true,
|
| 581 |
+
"should_training_stop": true
|
| 582 |
},
|
| 583 |
"attributes": {}
|
| 584 |
}
|
| 585 |
},
|
| 586 |
+
"total_flos": 15578077593600.0,
|
| 587 |
"train_batch_size": 2,
|
| 588 |
"trial_name": null,
|
| 589 |
"trial_params": null
|