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 50624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7abe2422a0995616bf17d085c9084821d9ef6028586d94c0f2756ec0b713fbf8
|
| 3 |
size 50624
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118090
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82ffcfbea78f3e6a85dc8887d2a9cc3ea352d2e9baed6ee77ad3e59a43ed37e6
|
| 3 |
size 118090
|
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 sha256:1532fcda08409d1eee43e4ac1a56b777d52d2c75477bbd2f451ae7c444979d2a
|
| 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": 11.
|
| 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": 60.803,
|
| 374 |
"eval_steps_per_second": 30.401,
|
| 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": 11.747422218322754,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.5037783375314862,
|
| 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": 60.803,
|
| 374 |
"eval_steps_per_second": 30.401,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.25692695214105793,
|
| 379 |
+
"grad_norm": 0.12329468876123428,
|
| 380 |
+
"learning_rate": 0.00010495837546732224,
|
| 381 |
+
"loss": 11.7644,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.2619647355163728,
|
| 386 |
+
"grad_norm": 0.19282935559749603,
|
| 387 |
+
"learning_rate": 0.00010165339447663587,
|
| 388 |
+
"loss": 11.7626,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.26700251889168763,
|
| 393 |
+
"grad_norm": 0.13012297451496124,
|
| 394 |
+
"learning_rate": 9.834660552336415e-05,
|
| 395 |
+
"loss": 11.7701,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.27204030226700254,
|
| 400 |
+
"grad_norm": 0.1542385220527649,
|
| 401 |
+
"learning_rate": 9.504162453267777e-05,
|
| 402 |
+
"loss": 11.748,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.2770780856423174,
|
| 407 |
+
"grad_norm": 0.13558229804039001,
|
| 408 |
+
"learning_rate": 9.174206545276677e-05,
|
| 409 |
+
"loss": 11.7566,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.28211586901763225,
|
| 414 |
+
"grad_norm": 0.1677481085062027,
|
| 415 |
+
"learning_rate": 8.845153630304139e-05,
|
| 416 |
+
"loss": 11.7563,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.2871536523929471,
|
| 421 |
+
"grad_norm": 0.20597466826438904,
|
| 422 |
+
"learning_rate": 8.517363522881579e-05,
|
| 423 |
+
"loss": 11.7526,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.29219143576826195,
|
| 428 |
+
"grad_norm": 0.17000000178813934,
|
| 429 |
+
"learning_rate": 8.191194656678904e-05,
|
| 430 |
+
"loss": 11.7474,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.2972292191435768,
|
| 435 |
+
"grad_norm": 0.2849511206150055,
|
| 436 |
+
"learning_rate": 7.867003692562534e-05,
|
| 437 |
+
"loss": 11.7591,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.3022670025188917,
|
| 442 |
+
"grad_norm": 0.19527281820774078,
|
| 443 |
+
"learning_rate": 7.54514512859201e-05,
|
| 444 |
+
"loss": 11.7456,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.30730478589420657,
|
| 449 |
+
"grad_norm": 0.25237226486206055,
|
| 450 |
+
"learning_rate": 7.225970912381556e-05,
|
| 451 |
+
"loss": 11.7602,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.3123425692695214,
|
| 456 |
+
"grad_norm": 0.24200652539730072,
|
| 457 |
+
"learning_rate": 6.909830056250527e-05,
|
| 458 |
+
"loss": 11.7528,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.31738035264483627,
|
| 463 |
+
"grad_norm": 0.19608649611473083,
|
| 464 |
+
"learning_rate": 6.59706825558357e-05,
|
| 465 |
+
"loss": 11.7477,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.3224181360201511,
|
| 470 |
+
"grad_norm": 0.2160205841064453,
|
| 471 |
+
"learning_rate": 6.28802751081779e-05,
|
| 472 |
+
"loss": 11.7498,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.327455919395466,
|
| 477 |
+
"grad_norm": 0.3006030321121216,
|
| 478 |
+
"learning_rate": 5.983045753470308e-05,
|
| 479 |
+
"loss": 11.7526,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.33249370277078083,
|
| 484 |
+
"grad_norm": 0.2874875068664551,
|
| 485 |
+
"learning_rate": 5.6824564766150726e-05,
|
| 486 |
+
"loss": 11.7516,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.33753148614609574,
|
| 491 |
+
"grad_norm": 0.34401634335517883,
|
| 492 |
+
"learning_rate": 5.386588370213124e-05,
|
| 493 |
+
"loss": 11.7539,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.3425692695214106,
|
| 498 |
+
"grad_norm": 0.33066168427467346,
|
| 499 |
+
"learning_rate": 5.095764961694922e-05,
|
| 500 |
+
"loss": 11.752,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.34760705289672544,
|
| 505 |
+
"grad_norm": 0.29201266169548035,
|
| 506 |
+
"learning_rate": 4.810304262187852e-05,
|
| 507 |
+
"loss": 11.743,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.3526448362720403,
|
| 512 |
+
"grad_norm": 0.34607893228530884,
|
| 513 |
+
"learning_rate": 4.530518418775733e-05,
|
| 514 |
+
"loss": 11.7538,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.35768261964735515,
|
| 519 |
+
"grad_norm": 0.2541449964046478,
|
| 520 |
+
"learning_rate": 4.256713373170564e-05,
|
| 521 |
+
"loss": 11.7628,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.36272040302267,
|
| 526 |
+
"grad_norm": 0.29604771733283997,
|
| 527 |
+
"learning_rate": 3.9891885271697496e-05,
|
| 528 |
+
"loss": 11.7578,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.3677581863979849,
|
| 533 |
+
"grad_norm": 0.3188517093658447,
|
| 534 |
+
"learning_rate": 3.7282364152646297e-05,
|
| 535 |
+
"loss": 11.7621,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.37279596977329976,
|
| 540 |
+
"grad_norm": 0.24045149981975555,
|
| 541 |
+
"learning_rate": 3.4741423847583134e-05,
|
| 542 |
+
"loss": 11.7587,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.3778337531486146,
|
| 547 |
+
"grad_norm": 0.27738526463508606,
|
| 548 |
+
"learning_rate": 3.227184283742591e-05,
|
| 549 |
+
"loss": 11.7587,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.38287153652392947,
|
| 554 |
+
"grad_norm": 0.20490190386772156,
|
| 555 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 556 |
+
"loss": 11.736,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.3879093198992443,
|
| 561 |
+
"grad_norm": 0.34930336475372314,
|
| 562 |
+
"learning_rate": 2.7557479520891104e-05,
|
| 563 |
+
"loss": 11.7466,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.3929471032745592,
|
| 568 |
+
"grad_norm": 0.3548698425292969,
|
| 569 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 570 |
+
"loss": 11.748,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.3979848866498741,
|
| 575 |
+
"grad_norm": 0.22995570302009583,
|
| 576 |
+
"learning_rate": 2.315988891431412e-05,
|
| 577 |
+
"loss": 11.7384,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.40302267002518893,
|
| 582 |
+
"grad_norm": 0.39114826917648315,
|
| 583 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 584 |
+
"loss": 11.7427,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.4080604534005038,
|
| 589 |
+
"grad_norm": 0.3221098482608795,
|
| 590 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 591 |
+
"loss": 11.7438,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.41309823677581864,
|
| 596 |
+
"grad_norm": 0.5230813026428223,
|
| 597 |
+
"learning_rate": 1.7199116885197995e-05,
|
| 598 |
+
"loss": 11.7491,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.4181360201511335,
|
| 603 |
+
"grad_norm": 0.5868245363235474,
|
| 604 |
+
"learning_rate": 1.5390474757906446e-05,
|
| 605 |
+
"loss": 11.7492,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.42317380352644834,
|
| 610 |
+
"grad_norm": 0.7091190218925476,
|
| 611 |
+
"learning_rate": 1.3674351904242611e-05,
|
| 612 |
+
"loss": 11.7395,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.4282115869017632,
|
| 617 |
+
"grad_norm": 0.34904906153678894,
|
| 618 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 619 |
+
"loss": 11.7469,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.4332493702770781,
|
| 624 |
+
"grad_norm": 0.497840017080307,
|
| 625 |
+
"learning_rate": 1.0527067017923654e-05,
|
| 626 |
+
"loss": 11.7541,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.43828715365239296,
|
| 631 |
+
"grad_norm": 0.6534344553947449,
|
| 632 |
+
"learning_rate": 9.09934649508375e-06,
|
| 633 |
+
"loss": 11.7602,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.4433249370277078,
|
| 638 |
+
"grad_norm": 0.6424288749694824,
|
| 639 |
+
"learning_rate": 7.771024502261526e-06,
|
| 640 |
+
"loss": 11.7518,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.44836272040302266,
|
| 645 |
+
"grad_norm": 0.6290802955627441,
|
| 646 |
+
"learning_rate": 6.543553540053926e-06,
|
| 647 |
+
"loss": 11.7363,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.4534005037783375,
|
| 652 |
+
"grad_norm": 0.6020405292510986,
|
| 653 |
+
"learning_rate": 5.418275829936537e-06,
|
| 654 |
+
"loss": 11.7478,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.45843828715365237,
|
| 659 |
+
"grad_norm": 0.5933429002761841,
|
| 660 |
+
"learning_rate": 4.3964218465642355e-06,
|
| 661 |
+
"loss": 11.7431,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.4634760705289673,
|
| 666 |
+
"grad_norm": 0.7595274448394775,
|
| 667 |
+
"learning_rate": 3.4791089722651436e-06,
|
| 668 |
+
"loss": 11.746,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.46851385390428213,
|
| 673 |
+
"grad_norm": 0.7738293409347534,
|
| 674 |
+
"learning_rate": 2.667340275199426e-06,
|
| 675 |
+
"loss": 11.7478,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.473551637279597,
|
| 680 |
+
"grad_norm": 0.6566546559333801,
|
| 681 |
+
"learning_rate": 1.9620034125190644e-06,
|
| 682 |
+
"loss": 11.7331,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.47858942065491183,
|
| 687 |
+
"grad_norm": 0.790342390537262,
|
| 688 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 689 |
+
"loss": 11.7377,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.4836272040302267,
|
| 694 |
+
"grad_norm": 0.7581157684326172,
|
| 695 |
+
"learning_rate": 8.735930673024806e-07,
|
| 696 |
+
"loss": 11.7515,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.48866498740554154,
|
| 701 |
+
"grad_norm": 0.8844296932220459,
|
| 702 |
+
"learning_rate": 4.917097454988584e-07,
|
| 703 |
+
"loss": 11.715,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.49370277078085645,
|
| 708 |
+
"grad_norm": 0.9089491963386536,
|
| 709 |
+
"learning_rate": 2.1863727812254653e-07,
|
| 710 |
+
"loss": 11.7192,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.4987405541561713,
|
| 715 |
+
"grad_norm": 0.14338494837284088,
|
| 716 |
+
"learning_rate": 5.467426590739511e-08,
|
| 717 |
+
"loss": 11.7708,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.5037783375314862,
|
| 722 |
+
"grad_norm": 0.16467101871967316,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 11.7612,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.5037783375314862,
|
| 729 |
+
"eval_loss": 11.747422218322754,
|
| 730 |
+
"eval_runtime": 1.3803,
|
| 731 |
+
"eval_samples_per_second": 60.857,
|
| 732 |
+
"eval_steps_per_second": 30.429,
|
| 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": 40740008755200.0,
|
| 763 |
"train_batch_size": 2,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|