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 1157746040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4943b5432191f4bd1d8e776c584ac18938ecbc7dd7c5abf90535e27f52748065
|
| 3 |
size 1157746040
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 588699796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:869c796352468e6d3b898f828dff95fe0aaaf5dfc7bb2a0a2ba2e348c36d11de
|
| 3 |
size 588699796
|
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 sha256:18228cd45feb2ff78b15c28b71c8b1c30d50eba6bc85861e1b43cf34c6e2d689
|
| 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:a5f2068254def458b7bc10b909f0d55b265dc2a0afb1369a10fd37948299a71a
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 3.
|
| 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": 4.251,
|
| 374 |
"eval_steps_per_second": 1.069,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -401,7 +759,7 @@
|
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 4,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 3.0592901706695557,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.25806451612903225,
|
| 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": 4.251,
|
| 374 |
"eval_steps_per_second": 1.069,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.13161290322580646,
|
| 379 |
+
"grad_norm": 1.2032880783081055,
|
| 380 |
+
"learning_rate": 7.897e-05,
|
| 381 |
+
"loss": 2.8811,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.13419354838709677,
|
| 386 |
+
"grad_norm": 0.9579372406005859,
|
| 387 |
+
"learning_rate": 7.843999999999999e-05,
|
| 388 |
+
"loss": 2.9946,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.1367741935483871,
|
| 393 |
+
"grad_norm": 0.7830987572669983,
|
| 394 |
+
"learning_rate": 7.790999999999999e-05,
|
| 395 |
+
"loss": 2.8823,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.1393548387096774,
|
| 400 |
+
"grad_norm": 0.6758972406387329,
|
| 401 |
+
"learning_rate": 7.738e-05,
|
| 402 |
+
"loss": 2.9346,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.14193548387096774,
|
| 407 |
+
"grad_norm": 0.6744924187660217,
|
| 408 |
+
"learning_rate": 7.685e-05,
|
| 409 |
+
"loss": 2.8026,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.14451612903225808,
|
| 414 |
+
"grad_norm": 0.6925913691520691,
|
| 415 |
+
"learning_rate": 7.632e-05,
|
| 416 |
+
"loss": 2.9121,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.14709677419354839,
|
| 421 |
+
"grad_norm": 0.6952354311943054,
|
| 422 |
+
"learning_rate": 7.578999999999999e-05,
|
| 423 |
+
"loss": 2.9217,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.14967741935483872,
|
| 428 |
+
"grad_norm": 0.6015385985374451,
|
| 429 |
+
"learning_rate": 7.526e-05,
|
| 430 |
+
"loss": 2.911,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.15225806451612903,
|
| 435 |
+
"grad_norm": 0.6113649606704712,
|
| 436 |
+
"learning_rate": 7.473e-05,
|
| 437 |
+
"loss": 2.8453,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.15483870967741936,
|
| 442 |
+
"grad_norm": 0.6024471521377563,
|
| 443 |
+
"learning_rate": 7.419999999999999e-05,
|
| 444 |
+
"loss": 2.7338,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.15741935483870967,
|
| 449 |
+
"grad_norm": 0.6171099543571472,
|
| 450 |
+
"learning_rate": 7.367e-05,
|
| 451 |
+
"loss": 2.7157,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.16,
|
| 456 |
+
"grad_norm": 0.6734641790390015,
|
| 457 |
+
"learning_rate": 7.314e-05,
|
| 458 |
+
"loss": 3.0369,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.1625806451612903,
|
| 463 |
+
"grad_norm": 0.6411603689193726,
|
| 464 |
+
"learning_rate": 7.261e-05,
|
| 465 |
+
"loss": 2.9175,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.16516129032258065,
|
| 470 |
+
"grad_norm": 0.6401498913764954,
|
| 471 |
+
"learning_rate": 7.208e-05,
|
| 472 |
+
"loss": 2.9601,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.16774193548387098,
|
| 477 |
+
"grad_norm": 0.6685578227043152,
|
| 478 |
+
"learning_rate": 7.154999999999999e-05,
|
| 479 |
+
"loss": 2.9055,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.1703225806451613,
|
| 484 |
+
"grad_norm": 0.6739301681518555,
|
| 485 |
+
"learning_rate": 7.102e-05,
|
| 486 |
+
"loss": 2.8973,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.17290322580645162,
|
| 491 |
+
"grad_norm": 0.6716254353523254,
|
| 492 |
+
"learning_rate": 7.049e-05,
|
| 493 |
+
"loss": 2.8507,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.17548387096774193,
|
| 498 |
+
"grad_norm": 0.6408494710922241,
|
| 499 |
+
"learning_rate": 6.996e-05,
|
| 500 |
+
"loss": 2.8232,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.17806451612903226,
|
| 505 |
+
"grad_norm": 0.6635752320289612,
|
| 506 |
+
"learning_rate": 6.943e-05,
|
| 507 |
+
"loss": 3.088,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.18064516129032257,
|
| 512 |
+
"grad_norm": 0.710978090763092,
|
| 513 |
+
"learning_rate": 6.89e-05,
|
| 514 |
+
"loss": 2.8905,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.1832258064516129,
|
| 519 |
+
"grad_norm": 0.7735083103179932,
|
| 520 |
+
"learning_rate": 6.837e-05,
|
| 521 |
+
"loss": 2.9583,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.18580645161290324,
|
| 526 |
+
"grad_norm": 0.7552114725112915,
|
| 527 |
+
"learning_rate": 6.784e-05,
|
| 528 |
+
"loss": 2.8666,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.18838709677419355,
|
| 533 |
+
"grad_norm": 0.8119356036186218,
|
| 534 |
+
"learning_rate": 6.730999999999999e-05,
|
| 535 |
+
"loss": 3.0893,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.19096774193548388,
|
| 540 |
+
"grad_norm": 0.7227278351783752,
|
| 541 |
+
"learning_rate": 6.678e-05,
|
| 542 |
+
"loss": 2.9174,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.1935483870967742,
|
| 547 |
+
"grad_norm": 0.7297806143760681,
|
| 548 |
+
"learning_rate": 6.625e-05,
|
| 549 |
+
"loss": 2.9618,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.19612903225806452,
|
| 554 |
+
"grad_norm": 0.7950009107589722,
|
| 555 |
+
"learning_rate": 6.572e-05,
|
| 556 |
+
"loss": 2.8738,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.19870967741935483,
|
| 561 |
+
"grad_norm": 0.7869434952735901,
|
| 562 |
+
"learning_rate": 6.519e-05,
|
| 563 |
+
"loss": 2.7843,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.20129032258064516,
|
| 568 |
+
"grad_norm": 0.8707318902015686,
|
| 569 |
+
"learning_rate": 6.466e-05,
|
| 570 |
+
"loss": 3.1622,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.20387096774193547,
|
| 575 |
+
"grad_norm": 0.8520801663398743,
|
| 576 |
+
"learning_rate": 6.413e-05,
|
| 577 |
+
"loss": 3.0377,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.2064516129032258,
|
| 582 |
+
"grad_norm": 0.9687163233757019,
|
| 583 |
+
"learning_rate": 6.359999999999999e-05,
|
| 584 |
+
"loss": 3.0816,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.20903225806451614,
|
| 589 |
+
"grad_norm": 0.8639389872550964,
|
| 590 |
+
"learning_rate": 6.306999999999999e-05,
|
| 591 |
+
"loss": 2.8825,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.21161290322580645,
|
| 596 |
+
"grad_norm": 1.042325735092163,
|
| 597 |
+
"learning_rate": 6.254000000000001e-05,
|
| 598 |
+
"loss": 2.9446,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.21419354838709678,
|
| 603 |
+
"grad_norm": 0.9391971230506897,
|
| 604 |
+
"learning_rate": 6.201e-05,
|
| 605 |
+
"loss": 3.0544,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.2167741935483871,
|
| 610 |
+
"grad_norm": 1.0379990339279175,
|
| 611 |
+
"learning_rate": 6.148e-05,
|
| 612 |
+
"loss": 3.1278,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.21935483870967742,
|
| 617 |
+
"grad_norm": 1.0052063465118408,
|
| 618 |
+
"learning_rate": 6.095e-05,
|
| 619 |
+
"loss": 3.0154,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.22193548387096773,
|
| 624 |
+
"grad_norm": 1.1294814348220825,
|
| 625 |
+
"learning_rate": 6.0419999999999994e-05,
|
| 626 |
+
"loss": 2.9711,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.22451612903225807,
|
| 631 |
+
"grad_norm": 1.1187207698822021,
|
| 632 |
+
"learning_rate": 5.988999999999999e-05,
|
| 633 |
+
"loss": 2.7353,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.2270967741935484,
|
| 638 |
+
"grad_norm": 1.1556931734085083,
|
| 639 |
+
"learning_rate": 5.9359999999999994e-05,
|
| 640 |
+
"loss": 3.0027,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.2296774193548387,
|
| 645 |
+
"grad_norm": 1.4021755456924438,
|
| 646 |
+
"learning_rate": 5.8830000000000004e-05,
|
| 647 |
+
"loss": 2.9716,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.23225806451612904,
|
| 652 |
+
"grad_norm": 1.32869291305542,
|
| 653 |
+
"learning_rate": 5.83e-05,
|
| 654 |
+
"loss": 3.2768,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.23483870967741935,
|
| 659 |
+
"grad_norm": 1.6008881330490112,
|
| 660 |
+
"learning_rate": 5.777e-05,
|
| 661 |
+
"loss": 3.2203,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.23741935483870968,
|
| 666 |
+
"grad_norm": 1.739267349243164,
|
| 667 |
+
"learning_rate": 5.7239999999999994e-05,
|
| 668 |
+
"loss": 3.0869,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.24,
|
| 673 |
+
"grad_norm": 1.6709328889846802,
|
| 674 |
+
"learning_rate": 5.671e-05,
|
| 675 |
+
"loss": 3.1174,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.24258064516129033,
|
| 680 |
+
"grad_norm": 2.5117313861846924,
|
| 681 |
+
"learning_rate": 5.6179999999999994e-05,
|
| 682 |
+
"loss": 3.2951,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.24516129032258063,
|
| 687 |
+
"grad_norm": 2.1630053520202637,
|
| 688 |
+
"learning_rate": 5.5650000000000004e-05,
|
| 689 |
+
"loss": 3.3658,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.24774193548387097,
|
| 694 |
+
"grad_norm": 2.027144193649292,
|
| 695 |
+
"learning_rate": 5.512e-05,
|
| 696 |
+
"loss": 3.3735,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.2503225806451613,
|
| 701 |
+
"grad_norm": 2.5083370208740234,
|
| 702 |
+
"learning_rate": 5.459e-05,
|
| 703 |
+
"loss": 2.9347,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.25290322580645164,
|
| 708 |
+
"grad_norm": 2.995940685272217,
|
| 709 |
+
"learning_rate": 5.406e-05,
|
| 710 |
+
"loss": 3.5815,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.25548387096774194,
|
| 715 |
+
"grad_norm": 3.9194164276123047,
|
| 716 |
+
"learning_rate": 5.353e-05,
|
| 717 |
+
"loss": 3.3064,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.25806451612903225,
|
| 722 |
+
"grad_norm": 7.003715991973877,
|
| 723 |
+
"learning_rate": 5.2999999999999994e-05,
|
| 724 |
+
"loss": 3.744,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.25806451612903225,
|
| 729 |
+
"eval_loss": 3.0592901706695557,
|
| 730 |
+
"eval_runtime": 38.3187,
|
| 731 |
+
"eval_samples_per_second": 4.254,
|
| 732 |
+
"eval_steps_per_second": 1.07,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 8.417511821279232e+16,
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|