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 59933632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67d309fa6e2c94fffe94ae5c1cd751e2ada96235fa3d071d1689b2e21d23d296
|
| 3 |
size 59933632
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 31822948
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:775941da2bb8107c743563010ab389f5fe85396250d257676da1631fbdb583bf
|
| 3 |
size 31822948
|
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:dc63c4ae4209ae91b32565233a68dff2eab23003d43a2606f84870ca2b9bfc27
|
| 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 sha256:2b25db9d6c32183ddaa93d558dc84ffdbd4eb525849b91eaf9054a35b57bdb2d
|
| 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": 7.452,
|
| 374 |
"eval_steps_per_second": 7.452,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -401,7 +759,7 @@
|
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 1,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5930299162864685,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.7326007326007326,
|
| 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": 7.452,
|
| 374 |
"eval_steps_per_second": 7.452,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.37362637362637363,
|
| 379 |
+
"grad_norm": 0.2964664399623871,
|
| 380 |
+
"learning_rate": 0.0002922130265250764,
|
| 381 |
+
"loss": 0.6552,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.38095238095238093,
|
| 386 |
+
"grad_norm": 0.3150418996810913,
|
| 387 |
+
"learning_rate": 0.00029183206888705004,
|
| 388 |
+
"loss": 0.6041,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.3882783882783883,
|
| 393 |
+
"grad_norm": 0.2626626491546631,
|
| 394 |
+
"learning_rate": 0.00029144227423011555,
|
| 395 |
+
"loss": 0.6236,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.3956043956043956,
|
| 400 |
+
"grad_norm": 0.31966981291770935,
|
| 401 |
+
"learning_rate": 0.0002910436668409013,
|
| 402 |
+
"loss": 0.6936,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.40293040293040294,
|
| 407 |
+
"grad_norm": 0.3115909695625305,
|
| 408 |
+
"learning_rate": 0.00029063627155512375,
|
| 409 |
+
"loss": 0.5992,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.41025641025641024,
|
| 414 |
+
"grad_norm": 0.29618480801582336,
|
| 415 |
+
"learning_rate": 0.0002902201137560397,
|
| 416 |
+
"loss": 0.5781,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.4175824175824176,
|
| 421 |
+
"grad_norm": 0.2827432453632355,
|
| 422 |
+
"learning_rate": 0.0002897952193728652,
|
| 423 |
+
"loss": 0.5961,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.4249084249084249,
|
| 428 |
+
"grad_norm": 0.30941715836524963,
|
| 429 |
+
"learning_rate": 0.00028936161487915955,
|
| 430 |
+
"loss": 0.6069,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.43223443223443225,
|
| 435 |
+
"grad_norm": 0.34647953510284424,
|
| 436 |
+
"learning_rate": 0.00028891932729117615,
|
| 437 |
+
"loss": 0.6544,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.43956043956043955,
|
| 442 |
+
"grad_norm": 0.34131157398223877,
|
| 443 |
+
"learning_rate": 0.0002884683841661791,
|
| 444 |
+
"loss": 0.5973,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.4468864468864469,
|
| 449 |
+
"grad_norm": 0.3378750681877136,
|
| 450 |
+
"learning_rate": 0.00028800881360072615,
|
| 451 |
+
"loss": 0.5805,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.4542124542124542,
|
| 456 |
+
"grad_norm": 0.3864741027355194,
|
| 457 |
+
"learning_rate": 0.0002875406442289183,
|
| 458 |
+
"loss": 0.5829,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.46153846153846156,
|
| 463 |
+
"grad_norm": 0.31040650606155396,
|
| 464 |
+
"learning_rate": 0.0002870639052206155,
|
| 465 |
+
"loss": 0.5408,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.46886446886446886,
|
| 470 |
+
"grad_norm": 0.3510590195655823,
|
| 471 |
+
"learning_rate": 0.0002865786262796193,
|
| 472 |
+
"loss": 0.5623,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.47619047619047616,
|
| 477 |
+
"grad_norm": 0.34330350160598755,
|
| 478 |
+
"learning_rate": 0.00028608483764182215,
|
| 479 |
+
"loss": 0.5304,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.4835164835164835,
|
| 484 |
+
"grad_norm": 0.3788071274757385,
|
| 485 |
+
"learning_rate": 0.0002855825700733235,
|
| 486 |
+
"loss": 0.4966,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.4908424908424908,
|
| 491 |
+
"grad_norm": 0.38324546813964844,
|
| 492 |
+
"learning_rate": 0.00028507185486851275,
|
| 493 |
+
"loss": 0.44,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.4981684981684982,
|
| 498 |
+
"grad_norm": 0.4564480185508728,
|
| 499 |
+
"learning_rate": 0.0002845527238481195,
|
| 500 |
+
"loss": 0.4097,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.5054945054945055,
|
| 505 |
+
"grad_norm": 0.238909512758255,
|
| 506 |
+
"learning_rate": 0.0002840252093572311,
|
| 507 |
+
"loss": 0.6646,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.5128205128205128,
|
| 512 |
+
"grad_norm": 0.2642434239387512,
|
| 513 |
+
"learning_rate": 0.000283489344263277,
|
| 514 |
+
"loss": 0.6419,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.5201465201465202,
|
| 519 |
+
"grad_norm": 0.2626118063926697,
|
| 520 |
+
"learning_rate": 0.00028294516195398125,
|
| 521 |
+
"loss": 0.6318,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.5274725274725275,
|
| 526 |
+
"grad_norm": 0.23919053375720978,
|
| 527 |
+
"learning_rate": 0.00028239269633528204,
|
| 528 |
+
"loss": 0.6266,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.5347985347985348,
|
| 533 |
+
"grad_norm": 0.25669869780540466,
|
| 534 |
+
"learning_rate": 0.000281831981829219,
|
| 535 |
+
"loss": 0.6594,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.5421245421245421,
|
| 540 |
+
"grad_norm": 0.21138758957386017,
|
| 541 |
+
"learning_rate": 0.00028126305337178905,
|
| 542 |
+
"loss": 0.5986,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.5494505494505495,
|
| 547 |
+
"grad_norm": 0.24748112261295319,
|
| 548 |
+
"learning_rate": 0.0002806859464107689,
|
| 549 |
+
"loss": 0.6108,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.5567765567765568,
|
| 554 |
+
"grad_norm": 0.23385199904441833,
|
| 555 |
+
"learning_rate": 0.00028010069690350716,
|
| 556 |
+
"loss": 0.6049,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.5641025641025641,
|
| 561 |
+
"grad_norm": 0.2671392560005188,
|
| 562 |
+
"learning_rate": 0.00027950734131468346,
|
| 563 |
+
"loss": 0.6324,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.5714285714285714,
|
| 568 |
+
"grad_norm": 0.20720772445201874,
|
| 569 |
+
"learning_rate": 0.00027890591661403676,
|
| 570 |
+
"loss": 0.538,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.5787545787545788,
|
| 575 |
+
"grad_norm": 0.26165518164634705,
|
| 576 |
+
"learning_rate": 0.00027829646027406174,
|
| 577 |
+
"loss": 0.6713,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.5860805860805861,
|
| 582 |
+
"grad_norm": 0.285157173871994,
|
| 583 |
+
"learning_rate": 0.00027767901026767416,
|
| 584 |
+
"loss": 0.7407,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.5934065934065934,
|
| 589 |
+
"grad_norm": 0.24118804931640625,
|
| 590 |
+
"learning_rate": 0.00027705360506584484,
|
| 591 |
+
"loss": 0.6414,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.6007326007326007,
|
| 596 |
+
"grad_norm": 0.2540411651134491,
|
| 597 |
+
"learning_rate": 0.00027642028363520255,
|
| 598 |
+
"loss": 0.6584,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.608058608058608,
|
| 603 |
+
"grad_norm": 0.2713707685470581,
|
| 604 |
+
"learning_rate": 0.0002757790854356066,
|
| 605 |
+
"loss": 0.6356,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.6153846153846154,
|
| 610 |
+
"grad_norm": 0.25061967968940735,
|
| 611 |
+
"learning_rate": 0.0002751300504176876,
|
| 612 |
+
"loss": 0.5919,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.6227106227106227,
|
| 617 |
+
"grad_norm": 0.2813633382320404,
|
| 618 |
+
"learning_rate": 0.0002744732190203589,
|
| 619 |
+
"loss": 0.6507,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.63003663003663,
|
| 624 |
+
"grad_norm": 0.36446070671081543,
|
| 625 |
+
"learning_rate": 0.00027380863216829645,
|
| 626 |
+
"loss": 0.6146,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.6373626373626373,
|
| 631 |
+
"grad_norm": 0.2936757802963257,
|
| 632 |
+
"learning_rate": 0.00027313633126938936,
|
| 633 |
+
"loss": 0.5807,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.6446886446886447,
|
| 638 |
+
"grad_norm": 0.32543811202049255,
|
| 639 |
+
"learning_rate": 0.0002724563582121598,
|
| 640 |
+
"loss": 0.633,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.652014652014652,
|
| 645 |
+
"grad_norm": 0.26980024576187134,
|
| 646 |
+
"learning_rate": 0.0002717687553631531,
|
| 647 |
+
"loss": 0.5771,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.6593406593406593,
|
| 652 |
+
"grad_norm": 0.3081660568714142,
|
| 653 |
+
"learning_rate": 0.0002710735655642978,
|
| 654 |
+
"loss": 0.5795,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.6666666666666666,
|
| 659 |
+
"grad_norm": 0.30959567427635193,
|
| 660 |
+
"learning_rate": 0.0002703708321302367,
|
| 661 |
+
"loss": 0.5278,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.673992673992674,
|
| 666 |
+
"grad_norm": 0.30625343322753906,
|
| 667 |
+
"learning_rate": 0.0002696605988456279,
|
| 668 |
+
"loss": 0.5816,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.6813186813186813,
|
| 673 |
+
"grad_norm": 0.31666725873947144,
|
| 674 |
+
"learning_rate": 0.00026894290996241677,
|
| 675 |
+
"loss": 0.5393,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.6886446886446886,
|
| 680 |
+
"grad_norm": 0.31827884912490845,
|
| 681 |
+
"learning_rate": 0.0002682178101970788,
|
| 682 |
+
"loss": 0.5869,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.6959706959706959,
|
| 687 |
+
"grad_norm": 0.3418588936328888,
|
| 688 |
+
"learning_rate": 0.00026748534472783355,
|
| 689 |
+
"loss": 0.5939,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.7032967032967034,
|
| 694 |
+
"grad_norm": 0.35669511556625366,
|
| 695 |
+
"learning_rate": 0.00026674555919182943,
|
| 696 |
+
"loss": 0.6145,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.7106227106227107,
|
| 701 |
+
"grad_norm": 0.3676556348800659,
|
| 702 |
+
"learning_rate": 0.00026599849968230084,
|
| 703 |
+
"loss": 0.5306,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.717948717948718,
|
| 708 |
+
"grad_norm": 0.3910490870475769,
|
| 709 |
+
"learning_rate": 0.00026524421274569556,
|
| 710 |
+
"loss": 0.6035,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.7252747252747253,
|
| 715 |
+
"grad_norm": 0.3907155394554138,
|
| 716 |
+
"learning_rate": 0.00026448274537877527,
|
| 717 |
+
"loss": 0.5149,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.7326007326007326,
|
| 722 |
+
"grad_norm": 0.3669157326221466,
|
| 723 |
+
"learning_rate": 0.0002637141450256868,
|
| 724 |
+
"loss": 0.4153,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.7326007326007326,
|
| 729 |
+
"eval_loss": 0.5930299162864685,
|
| 730 |
+
"eval_runtime": 73.3788,
|
| 731 |
+
"eval_samples_per_second": 7.454,
|
| 732 |
+
"eval_steps_per_second": 7.454,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 1.4114926620573696e+16,
|
| 763 |
"train_batch_size": 1,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|