Training in progress, step 100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 140815952
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba2b2ffcdfe4e53884a9e8b4b7f9d039bdbf366d6f4070b60af9a1eb1c2950fe
|
| 3 |
size 140815952
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 71878612
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4c6b7417693f53702b7a1dc0d824175d9b86cdf2a77631bf9393fa64eeed014
|
| 3 |
size 71878612
|
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:d615d15cea818dabfcf735a8bc847e17cb572710ee44540d46fa4abc586854b8
|
| 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 sha256:2cdd5e1998f1139b3d2606fc1207245b65164fdf9041e6fa58bd90acc8d38fa5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -373,6 +373,364 @@
|
|
| 373 |
"eval_samples_per_second": 13.735,
|
| 374 |
"eval_steps_per_second": 1.717,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -396,12 +754,12 @@
|
|
| 396 |
"should_evaluate": false,
|
| 397 |
"should_log": false,
|
| 398 |
"should_save": true,
|
| 399 |
-
"should_training_stop":
|
| 400 |
},
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.25296375155448914,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.013832693571255663,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 373 |
"eval_samples_per_second": 13.735,
|
| 374 |
"eval_steps_per_second": 1.717,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.007054673721340388,
|
| 379 |
+
"grad_norm": 0.17172540724277496,
|
| 380 |
+
"learning_rate": 7.65e-06,
|
| 381 |
+
"loss": 0.2737,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.007193000657052945,
|
| 386 |
+
"grad_norm": 0.18842163681983948,
|
| 387 |
+
"learning_rate": 7.8e-06,
|
| 388 |
+
"loss": 0.2943,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.007331327592765501,
|
| 393 |
+
"grad_norm": 0.18067596852779388,
|
| 394 |
+
"learning_rate": 7.95e-06,
|
| 395 |
+
"loss": 0.308,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.007469654528478058,
|
| 400 |
+
"grad_norm": 0.16696469485759735,
|
| 401 |
+
"learning_rate": 8.1e-06,
|
| 402 |
+
"loss": 0.2641,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.0076079814641906145,
|
| 407 |
+
"grad_norm": 0.15525111556053162,
|
| 408 |
+
"learning_rate": 8.25e-06,
|
| 409 |
+
"loss": 0.2417,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.007746308399903171,
|
| 414 |
+
"grad_norm": 0.17325535416603088,
|
| 415 |
+
"learning_rate": 8.400000000000001e-06,
|
| 416 |
+
"loss": 0.3275,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.007884635335615727,
|
| 421 |
+
"grad_norm": 0.1737009733915329,
|
| 422 |
+
"learning_rate": 8.55e-06,
|
| 423 |
+
"loss": 0.3544,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.008022962271328284,
|
| 428 |
+
"grad_norm": 0.16440212726593018,
|
| 429 |
+
"learning_rate": 8.7e-06,
|
| 430 |
+
"loss": 0.3049,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.008161289207040841,
|
| 435 |
+
"grad_norm": 0.15149055421352386,
|
| 436 |
+
"learning_rate": 8.85e-06,
|
| 437 |
+
"loss": 0.2669,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.008299616142753397,
|
| 442 |
+
"grad_norm": 0.15021531283855438,
|
| 443 |
+
"learning_rate": 9e-06,
|
| 444 |
+
"loss": 0.2852,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.008437943078465954,
|
| 449 |
+
"grad_norm": 0.14351071417331696,
|
| 450 |
+
"learning_rate": 9.15e-06,
|
| 451 |
+
"loss": 0.2018,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.008576270014178511,
|
| 456 |
+
"grad_norm": 0.12986423075199127,
|
| 457 |
+
"learning_rate": 9.3e-06,
|
| 458 |
+
"loss": 0.2416,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.008714596949891068,
|
| 463 |
+
"grad_norm": 0.1482655256986618,
|
| 464 |
+
"learning_rate": 9.450000000000001e-06,
|
| 465 |
+
"loss": 0.2492,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.008852923885603624,
|
| 470 |
+
"grad_norm": 0.14514705538749695,
|
| 471 |
+
"learning_rate": 9.600000000000001e-06,
|
| 472 |
+
"loss": 0.2925,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.008991250821316181,
|
| 477 |
+
"grad_norm": 0.15891727805137634,
|
| 478 |
+
"learning_rate": 9.75e-06,
|
| 479 |
+
"loss": 0.234,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.009129577757028738,
|
| 484 |
+
"grad_norm": 0.12783700227737427,
|
| 485 |
+
"learning_rate": 9.9e-06,
|
| 486 |
+
"loss": 0.2144,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.009267904692741294,
|
| 491 |
+
"grad_norm": 0.11698262393474579,
|
| 492 |
+
"learning_rate": 1.005e-05,
|
| 493 |
+
"loss": 0.2107,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.00940623162845385,
|
| 498 |
+
"grad_norm": 0.14814496040344238,
|
| 499 |
+
"learning_rate": 1.02e-05,
|
| 500 |
+
"loss": 0.296,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.009544558564166408,
|
| 505 |
+
"grad_norm": 0.1301187127828598,
|
| 506 |
+
"learning_rate": 1.035e-05,
|
| 507 |
+
"loss": 0.1869,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.009682885499878963,
|
| 512 |
+
"grad_norm": 0.17036621272563934,
|
| 513 |
+
"learning_rate": 1.05e-05,
|
| 514 |
+
"loss": 0.3304,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.00982121243559152,
|
| 519 |
+
"grad_norm": 0.12910433113574982,
|
| 520 |
+
"learning_rate": 1.065e-05,
|
| 521 |
+
"loss": 0.2495,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.009959539371304078,
|
| 526 |
+
"grad_norm": 0.14236624538898468,
|
| 527 |
+
"learning_rate": 1.08e-05,
|
| 528 |
+
"loss": 0.2275,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.010097866307016633,
|
| 533 |
+
"grad_norm": 0.15861648321151733,
|
| 534 |
+
"learning_rate": 1.095e-05,
|
| 535 |
+
"loss": 0.3031,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.01023619324272919,
|
| 540 |
+
"grad_norm": 0.1290421336889267,
|
| 541 |
+
"learning_rate": 1.11e-05,
|
| 542 |
+
"loss": 0.2598,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.010374520178441747,
|
| 547 |
+
"grad_norm": 0.13748377561569214,
|
| 548 |
+
"learning_rate": 1.125e-05,
|
| 549 |
+
"loss": 0.2692,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.010512847114154303,
|
| 554 |
+
"grad_norm": 0.1323186159133911,
|
| 555 |
+
"learning_rate": 1.1400000000000001e-05,
|
| 556 |
+
"loss": 0.2333,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.01065117404986686,
|
| 561 |
+
"grad_norm": 0.14683866500854492,
|
| 562 |
+
"learning_rate": 1.1550000000000001e-05,
|
| 563 |
+
"loss": 0.2783,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.010789500985579417,
|
| 568 |
+
"grad_norm": 0.14012585580348969,
|
| 569 |
+
"learning_rate": 1.1700000000000001e-05,
|
| 570 |
+
"loss": 0.3069,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.010927827921291974,
|
| 575 |
+
"grad_norm": 0.14110729098320007,
|
| 576 |
+
"learning_rate": 1.185e-05,
|
| 577 |
+
"loss": 0.3,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.01106615485700453,
|
| 582 |
+
"grad_norm": 0.15559019148349762,
|
| 583 |
+
"learning_rate": 1.2e-05,
|
| 584 |
+
"loss": 0.3066,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.011204481792717087,
|
| 589 |
+
"grad_norm": 0.11998707801103592,
|
| 590 |
+
"learning_rate": 1.215e-05,
|
| 591 |
+
"loss": 0.2358,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.011342808728429644,
|
| 596 |
+
"grad_norm": 0.1280561089515686,
|
| 597 |
+
"learning_rate": 1.2299999999999999e-05,
|
| 598 |
+
"loss": 0.2721,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.0114811356641422,
|
| 603 |
+
"grad_norm": 0.14386573433876038,
|
| 604 |
+
"learning_rate": 1.245e-05,
|
| 605 |
+
"loss": 0.2976,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.011619462599854757,
|
| 610 |
+
"grad_norm": 0.1161927729845047,
|
| 611 |
+
"learning_rate": 1.26e-05,
|
| 612 |
+
"loss": 0.2059,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.011757789535567314,
|
| 617 |
+
"grad_norm": 0.1201709434390068,
|
| 618 |
+
"learning_rate": 1.275e-05,
|
| 619 |
+
"loss": 0.2446,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.01189611647127987,
|
| 624 |
+
"grad_norm": 0.1458764672279358,
|
| 625 |
+
"learning_rate": 1.29e-05,
|
| 626 |
+
"loss": 0.2376,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.012034443406992426,
|
| 631 |
+
"grad_norm": 0.13553838431835175,
|
| 632 |
+
"learning_rate": 1.305e-05,
|
| 633 |
+
"loss": 0.2875,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.012172770342704984,
|
| 638 |
+
"grad_norm": 0.13249175250530243,
|
| 639 |
+
"learning_rate": 1.32e-05,
|
| 640 |
+
"loss": 0.2974,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.012311097278417539,
|
| 645 |
+
"grad_norm": 0.15065519511699677,
|
| 646 |
+
"learning_rate": 1.3350000000000001e-05,
|
| 647 |
+
"loss": 0.2945,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.012449424214130096,
|
| 652 |
+
"grad_norm": 0.1529104858636856,
|
| 653 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 654 |
+
"loss": 0.2972,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.012587751149842653,
|
| 659 |
+
"grad_norm": 0.1217237114906311,
|
| 660 |
+
"learning_rate": 1.3650000000000001e-05,
|
| 661 |
+
"loss": 0.2322,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.01272607808555521,
|
| 666 |
+
"grad_norm": 0.13060763478279114,
|
| 667 |
+
"learning_rate": 1.3800000000000002e-05,
|
| 668 |
+
"loss": 0.2931,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.012864405021267766,
|
| 673 |
+
"grad_norm": 0.1278468370437622,
|
| 674 |
+
"learning_rate": 1.395e-05,
|
| 675 |
+
"loss": 0.245,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.013002731956980323,
|
| 680 |
+
"grad_norm": 0.11934634298086166,
|
| 681 |
+
"learning_rate": 1.4099999999999999e-05,
|
| 682 |
+
"loss": 0.2238,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.01314105889269288,
|
| 687 |
+
"grad_norm": 0.13119642436504364,
|
| 688 |
+
"learning_rate": 1.4249999999999999e-05,
|
| 689 |
+
"loss": 0.2394,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.013279385828405436,
|
| 694 |
+
"grad_norm": 0.13287314772605896,
|
| 695 |
+
"learning_rate": 1.44e-05,
|
| 696 |
+
"loss": 0.2134,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.013417712764117993,
|
| 701 |
+
"grad_norm": 0.13096174597740173,
|
| 702 |
+
"learning_rate": 1.455e-05,
|
| 703 |
+
"loss": 0.2449,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.01355603969983055,
|
| 708 |
+
"grad_norm": 0.1295308768749237,
|
| 709 |
+
"learning_rate": 1.47e-05,
|
| 710 |
+
"loss": 0.2517,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.013694366635543105,
|
| 715 |
+
"grad_norm": 0.1313454955816269,
|
| 716 |
+
"learning_rate": 1.485e-05,
|
| 717 |
+
"loss": 0.2596,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.013832693571255663,
|
| 722 |
+
"grad_norm": 0.12004859000444412,
|
| 723 |
+
"learning_rate": 1.5e-05,
|
| 724 |
+
"loss": 0.2258,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.013832693571255663,
|
| 729 |
+
"eval_loss": 0.25296375155448914,
|
| 730 |
+
"eval_runtime": 873.1576,
|
| 731 |
+
"eval_samples_per_second": 13.945,
|
| 732 |
+
"eval_steps_per_second": 1.743,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 754 |
"should_evaluate": false,
|
| 755 |
"should_log": false,
|
| 756 |
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
},
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 3.0372935956955136e+16,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|