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 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ea216a6ff6464bbb0071a4dc4b359572bae47a60a2f2f00f228a94770528d49
|
| 3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335922386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9592e26f32696e693546933ea978dfb6689742a5db4ee2a46b07daabd50f774
|
| 3 |
size 335922386
|
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 sha256:04cb58c7c22b9c64173b11c368e5d7c1be618464957b34eeda2626a0f059931b
|
| 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 sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 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": 3.51,
|
| 374 |
"eval_steps_per_second": 1.78,
|
| 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": 2,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.135526418685913,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.6006006006006006,
|
| 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": 3.51,
|
| 374 |
"eval_steps_per_second": 1.78,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.3063063063063063,
|
| 379 |
+
"grad_norm": 2.467716932296753,
|
| 380 |
+
"learning_rate": 0.00010495837546732224,
|
| 381 |
+
"loss": 1.3141,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.3123123123123123,
|
| 386 |
+
"grad_norm": 2.7195961475372314,
|
| 387 |
+
"learning_rate": 0.00010165339447663587,
|
| 388 |
+
"loss": 1.1358,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.3183183183183183,
|
| 393 |
+
"grad_norm": 2.4302902221679688,
|
| 394 |
+
"learning_rate": 9.834660552336415e-05,
|
| 395 |
+
"loss": 1.2766,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.32432432432432434,
|
| 400 |
+
"grad_norm": 2.4811532497406006,
|
| 401 |
+
"learning_rate": 9.504162453267777e-05,
|
| 402 |
+
"loss": 1.2285,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.3303303303303303,
|
| 407 |
+
"grad_norm": 2.6031277179718018,
|
| 408 |
+
"learning_rate": 9.174206545276677e-05,
|
| 409 |
+
"loss": 1.2114,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.33633633633633636,
|
| 414 |
+
"grad_norm": 3.0436697006225586,
|
| 415 |
+
"learning_rate": 8.845153630304139e-05,
|
| 416 |
+
"loss": 1.457,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.34234234234234234,
|
| 421 |
+
"grad_norm": 2.756425619125366,
|
| 422 |
+
"learning_rate": 8.517363522881579e-05,
|
| 423 |
+
"loss": 1.2442,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.3483483483483483,
|
| 428 |
+
"grad_norm": 2.9140679836273193,
|
| 429 |
+
"learning_rate": 8.191194656678904e-05,
|
| 430 |
+
"loss": 1.127,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.35435435435435436,
|
| 435 |
+
"grad_norm": 2.6434483528137207,
|
| 436 |
+
"learning_rate": 7.867003692562534e-05,
|
| 437 |
+
"loss": 1.0603,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.36036036036036034,
|
| 442 |
+
"grad_norm": 5.660317897796631,
|
| 443 |
+
"learning_rate": 7.54514512859201e-05,
|
| 444 |
+
"loss": 1.048,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.3663663663663664,
|
| 449 |
+
"grad_norm": 2.662621021270752,
|
| 450 |
+
"learning_rate": 7.225970912381556e-05,
|
| 451 |
+
"loss": 0.9771,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.37237237237237236,
|
| 456 |
+
"grad_norm": 3.0631654262542725,
|
| 457 |
+
"learning_rate": 6.909830056250527e-05,
|
| 458 |
+
"loss": 1.4288,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.3783783783783784,
|
| 463 |
+
"grad_norm": 2.566416025161743,
|
| 464 |
+
"learning_rate": 6.59706825558357e-05,
|
| 465 |
+
"loss": 0.9023,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.3843843843843844,
|
| 470 |
+
"grad_norm": 2.502877712249756,
|
| 471 |
+
"learning_rate": 6.28802751081779e-05,
|
| 472 |
+
"loss": 0.8202,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.39039039039039036,
|
| 477 |
+
"grad_norm": 3.319624662399292,
|
| 478 |
+
"learning_rate": 5.983045753470308e-05,
|
| 479 |
+
"loss": 1.045,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.3963963963963964,
|
| 484 |
+
"grad_norm": 2.7986936569213867,
|
| 485 |
+
"learning_rate": 5.6824564766150726e-05,
|
| 486 |
+
"loss": 1.295,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.4024024024024024,
|
| 491 |
+
"grad_norm": 3.08010196685791,
|
| 492 |
+
"learning_rate": 5.386588370213124e-05,
|
| 493 |
+
"loss": 1.0989,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.4084084084084084,
|
| 498 |
+
"grad_norm": 3.931140899658203,
|
| 499 |
+
"learning_rate": 5.095764961694922e-05,
|
| 500 |
+
"loss": 0.8769,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.4144144144144144,
|
| 505 |
+
"grad_norm": 4.616240978240967,
|
| 506 |
+
"learning_rate": 4.810304262187852e-05,
|
| 507 |
+
"loss": 1.3225,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.42042042042042044,
|
| 512 |
+
"grad_norm": 3.139350652694702,
|
| 513 |
+
"learning_rate": 4.530518418775733e-05,
|
| 514 |
+
"loss": 1.1953,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.4264264264264264,
|
| 519 |
+
"grad_norm": 3.0971598625183105,
|
| 520 |
+
"learning_rate": 4.256713373170564e-05,
|
| 521 |
+
"loss": 0.9564,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.43243243243243246,
|
| 526 |
+
"grad_norm": 4.219956874847412,
|
| 527 |
+
"learning_rate": 3.9891885271697496e-05,
|
| 528 |
+
"loss": 0.9444,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.43843843843843844,
|
| 533 |
+
"grad_norm": 3.592334747314453,
|
| 534 |
+
"learning_rate": 3.7282364152646297e-05,
|
| 535 |
+
"loss": 1.1826,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.4444444444444444,
|
| 540 |
+
"grad_norm": 4.302462577819824,
|
| 541 |
+
"learning_rate": 3.4741423847583134e-05,
|
| 542 |
+
"loss": 1.0087,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.45045045045045046,
|
| 547 |
+
"grad_norm": 2.8837406635284424,
|
| 548 |
+
"learning_rate": 3.227184283742591e-05,
|
| 549 |
+
"loss": 0.9843,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.45645645645645644,
|
| 554 |
+
"grad_norm": 2.9115164279937744,
|
| 555 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 556 |
+
"loss": 1.013,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.4624624624624625,
|
| 561 |
+
"grad_norm": 2.647456645965576,
|
| 562 |
+
"learning_rate": 2.7557479520891104e-05,
|
| 563 |
+
"loss": 0.9615,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.46846846846846846,
|
| 568 |
+
"grad_norm": 2.5124423503875732,
|
| 569 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 570 |
+
"loss": 0.697,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.4744744744744745,
|
| 575 |
+
"grad_norm": 4.744019508361816,
|
| 576 |
+
"learning_rate": 2.315988891431412e-05,
|
| 577 |
+
"loss": 1.0931,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.4804804804804805,
|
| 582 |
+
"grad_norm": 3.7033681869506836,
|
| 583 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 584 |
+
"loss": 1.0538,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.4864864864864865,
|
| 589 |
+
"grad_norm": 3.1618974208831787,
|
| 590 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 591 |
+
"loss": 0.7846,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.4924924924924925,
|
| 596 |
+
"grad_norm": 3.4100112915039062,
|
| 597 |
+
"learning_rate": 1.7199116885197995e-05,
|
| 598 |
+
"loss": 1.1595,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.4984984984984985,
|
| 603 |
+
"grad_norm": 2.8490142822265625,
|
| 604 |
+
"learning_rate": 1.5390474757906446e-05,
|
| 605 |
+
"loss": 1.3412,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.5045045045045045,
|
| 610 |
+
"grad_norm": 1.9056596755981445,
|
| 611 |
+
"learning_rate": 1.3674351904242611e-05,
|
| 612 |
+
"loss": 1.2043,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.5105105105105106,
|
| 617 |
+
"grad_norm": 2.0238497257232666,
|
| 618 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 619 |
+
"loss": 1.1433,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.5165165165165165,
|
| 624 |
+
"grad_norm": 2.10072922706604,
|
| 625 |
+
"learning_rate": 1.0527067017923654e-05,
|
| 626 |
+
"loss": 1.2434,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.5225225225225225,
|
| 631 |
+
"grad_norm": 2.534837484359741,
|
| 632 |
+
"learning_rate": 9.09934649508375e-06,
|
| 633 |
+
"loss": 1.176,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.5285285285285285,
|
| 638 |
+
"grad_norm": 2.2539825439453125,
|
| 639 |
+
"learning_rate": 7.771024502261526e-06,
|
| 640 |
+
"loss": 1.2467,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.5345345345345346,
|
| 645 |
+
"grad_norm": 2.548096179962158,
|
| 646 |
+
"learning_rate": 6.543553540053926e-06,
|
| 647 |
+
"loss": 1.3314,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.5405405405405406,
|
| 652 |
+
"grad_norm": 2.4377360343933105,
|
| 653 |
+
"learning_rate": 5.418275829936537e-06,
|
| 654 |
+
"loss": 1.2026,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.5465465465465466,
|
| 659 |
+
"grad_norm": 2.1080400943756104,
|
| 660 |
+
"learning_rate": 4.3964218465642355e-06,
|
| 661 |
+
"loss": 1.1876,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.5525525525525525,
|
| 666 |
+
"grad_norm": 2.250770330429077,
|
| 667 |
+
"learning_rate": 3.4791089722651436e-06,
|
| 668 |
+
"loss": 1.2981,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.5585585585585585,
|
| 673 |
+
"grad_norm": 2.5565848350524902,
|
| 674 |
+
"learning_rate": 2.667340275199426e-06,
|
| 675 |
+
"loss": 1.031,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.5645645645645646,
|
| 680 |
+
"grad_norm": 2.642076015472412,
|
| 681 |
+
"learning_rate": 1.9620034125190644e-06,
|
| 682 |
+
"loss": 1.1568,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.5705705705705706,
|
| 687 |
+
"grad_norm": 2.3764145374298096,
|
| 688 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 689 |
+
"loss": 1.2446,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.5765765765765766,
|
| 694 |
+
"grad_norm": 2.5050697326660156,
|
| 695 |
+
"learning_rate": 8.735930673024806e-07,
|
| 696 |
+
"loss": 1.0928,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.5825825825825826,
|
| 701 |
+
"grad_norm": 2.3315417766571045,
|
| 702 |
+
"learning_rate": 4.917097454988584e-07,
|
| 703 |
+
"loss": 1.0785,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.5885885885885885,
|
| 708 |
+
"grad_norm": 1.9666122198104858,
|
| 709 |
+
"learning_rate": 2.1863727812254653e-07,
|
| 710 |
+
"loss": 0.9106,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.5945945945945946,
|
| 715 |
+
"grad_norm": 2.5268125534057617,
|
| 716 |
+
"learning_rate": 5.467426590739511e-08,
|
| 717 |
+
"loss": 1.2624,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.6006006006006006,
|
| 722 |
+
"grad_norm": 2.017895460128784,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 0.8749,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.6006006006006006,
|
| 729 |
+
"eval_loss": 1.135526418685913,
|
| 730 |
+
"eval_runtime": 20.2206,
|
| 731 |
+
"eval_samples_per_second": 3.511,
|
| 732 |
+
"eval_steps_per_second": 1.78,
|
| 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": 1.483774567120896e+17,
|
| 763 |
"train_batch_size": 2,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|