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 767856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe7d367849eecb8dda941dfe4cc125baa244258d2522b6e8063b56df13f50a07
|
| 3 |
size 767856
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1601338
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70f8d29ab82dcf882a4c0f7f61e641a0d66fd875a85f9ec4fbc2838618655778
|
| 3 |
size 1601338
|
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:d8cfa92e786dc8058a98db4c8d65fae09ff5a09363959f173afe0900a72ea440
|
| 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:c5d2a6c6aafc669cea03b9634666f204de949a3d45ce2f48a07e7e3eaf18c715
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 7.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -381,6 +381,372 @@
|
|
| 381 |
"eval_samples_per_second": 45.352,
|
| 382 |
"eval_steps_per_second": 6.349,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -409,7 +775,7 @@
|
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 8,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 7.306600570678711,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.026897989375294196,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 381 |
"eval_samples_per_second": 45.352,
|
| 382 |
"eval_steps_per_second": 6.349,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.01371797458140004,
|
| 387 |
+
"grad_norm": 2.073488235473633,
|
| 388 |
+
"learning_rate": 0.0002668315918143169,
|
| 389 |
+
"loss": 6.6067,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.013986954475152982,
|
| 394 |
+
"grad_norm": 1.6959115266799927,
|
| 395 |
+
"learning_rate": 0.00026526016662852886,
|
| 396 |
+
"loss": 7.4615,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.014255934368905925,
|
| 401 |
+
"grad_norm": 1.1312484741210938,
|
| 402 |
+
"learning_rate": 0.00026365723046405023,
|
| 403 |
+
"loss": 7.562,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.014524914262658867,
|
| 408 |
+
"grad_norm": 0.8906031847000122,
|
| 409 |
+
"learning_rate": 0.0002620232215476231,
|
| 410 |
+
"loss": 7.8548,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.014793894156411809,
|
| 415 |
+
"grad_norm": 1.1955941915512085,
|
| 416 |
+
"learning_rate": 0.0002603585866009697,
|
| 417 |
+
"loss": 7.5388,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.01506287405016475,
|
| 422 |
+
"grad_norm": 1.6056780815124512,
|
| 423 |
+
"learning_rate": 0.00025866378071866334,
|
| 424 |
+
"loss": 6.7458,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.015331853943917692,
|
| 429 |
+
"grad_norm": 0.9653465151786804,
|
| 430 |
+
"learning_rate": 0.00025693926724370956,
|
| 431 |
+
"loss": 7.2338,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.015600833837670634,
|
| 436 |
+
"grad_norm": 1.055378794670105,
|
| 437 |
+
"learning_rate": 0.00025518551764087326,
|
| 438 |
+
"loss": 7.2497,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.015869813731423574,
|
| 443 |
+
"grad_norm": 0.982029378414154,
|
| 444 |
+
"learning_rate": 0.00025340301136778483,
|
| 445 |
+
"loss": 6.3055,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.016138793625176517,
|
| 450 |
+
"grad_norm": 1.4051647186279297,
|
| 451 |
+
"learning_rate": 0.00025159223574386114,
|
| 452 |
+
"loss": 6.7392,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.01640777351892946,
|
| 457 |
+
"grad_norm": 1.224535346031189,
|
| 458 |
+
"learning_rate": 0.0002497536858170772,
|
| 459 |
+
"loss": 6.2815,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.0166767534126824,
|
| 464 |
+
"grad_norm": 0.9965676069259644,
|
| 465 |
+
"learning_rate": 0.00024788786422862526,
|
| 466 |
+
"loss": 6.5987,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.016945733306435343,
|
| 471 |
+
"grad_norm": 0.7063784599304199,
|
| 472 |
+
"learning_rate": 0.00024599528107549745,
|
| 473 |
+
"loss": 6.5176,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.017214713200188286,
|
| 478 |
+
"grad_norm": 1.3905584812164307,
|
| 479 |
+
"learning_rate": 0.00024407645377103054,
|
| 480 |
+
"loss": 7.3527,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.017483693093941228,
|
| 485 |
+
"grad_norm": 0.6794236898422241,
|
| 486 |
+
"learning_rate": 0.00024213190690345018,
|
| 487 |
+
"loss": 7.1635,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.01775267298769417,
|
| 492 |
+
"grad_norm": 0.85134357213974,
|
| 493 |
+
"learning_rate": 0.00024016217209245374,
|
| 494 |
+
"loss": 6.9162,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.018021652881447112,
|
| 499 |
+
"grad_norm": 1.1831365823745728,
|
| 500 |
+
"learning_rate": 0.00023816778784387094,
|
| 501 |
+
"loss": 7.4826,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.018290632775200055,
|
| 506 |
+
"grad_norm": 0.7540268301963806,
|
| 507 |
+
"learning_rate": 0.0002361492994024415,
|
| 508 |
+
"loss": 7.5541,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.018559612668952997,
|
| 513 |
+
"grad_norm": 0.8305040597915649,
|
| 514 |
+
"learning_rate": 0.0002341072586027509,
|
| 515 |
+
"loss": 7.0236,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.01882859256270594,
|
| 520 |
+
"grad_norm": 0.8232185244560242,
|
| 521 |
+
"learning_rate": 0.00023204222371836405,
|
| 522 |
+
"loss": 7.256,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.01909757245645888,
|
| 527 |
+
"grad_norm": 0.8017435669898987,
|
| 528 |
+
"learning_rate": 0.00022995475930919905,
|
| 529 |
+
"loss": 7.2468,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.01936655235021182,
|
| 534 |
+
"grad_norm": 0.7299101948738098,
|
| 535 |
+
"learning_rate": 0.00022784543606718227,
|
| 536 |
+
"loss": 6.8815,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.019635532243964762,
|
| 541 |
+
"grad_norm": 0.9603165984153748,
|
| 542 |
+
"learning_rate": 0.00022571483066022657,
|
| 543 |
+
"loss": 7.1806,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.019904512137717705,
|
| 548 |
+
"grad_norm": 0.7412318587303162,
|
| 549 |
+
"learning_rate": 0.0002235635255745762,
|
| 550 |
+
"loss": 6.8687,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.020173492031470647,
|
| 555 |
+
"grad_norm": 1.5883235931396484,
|
| 556 |
+
"learning_rate": 0.00022139210895556104,
|
| 557 |
+
"loss": 6.6477,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.020173492031470647,
|
| 562 |
+
"eval_loss": 7.266612529754639,
|
| 563 |
+
"eval_runtime": 1.1026,
|
| 564 |
+
"eval_samples_per_second": 45.347,
|
| 565 |
+
"eval_steps_per_second": 6.349,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.02044247192522359,
|
| 570 |
+
"grad_norm": 0.874472975730896,
|
| 571 |
+
"learning_rate": 0.00021920117444680317,
|
| 572 |
+
"loss": 6.5988,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.02071145181897653,
|
| 577 |
+
"grad_norm": 1.0724687576293945,
|
| 578 |
+
"learning_rate": 0.00021699132102792097,
|
| 579 |
+
"loss": 7.0543,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.020980431712729473,
|
| 584 |
+
"grad_norm": 0.7699567079544067,
|
| 585 |
+
"learning_rate": 0.0002147631528507739,
|
| 586 |
+
"loss": 7.1625,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.021249411606482416,
|
| 591 |
+
"grad_norm": 0.622986912727356,
|
| 592 |
+
"learning_rate": 0.00021251727907429355,
|
| 593 |
+
"loss": 7.4872,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.021518391500235358,
|
| 598 |
+
"grad_norm": 0.9322075843811035,
|
| 599 |
+
"learning_rate": 0.0002102543136979454,
|
| 600 |
+
"loss": 7.0894,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.0217873713939883,
|
| 605 |
+
"grad_norm": 0.6225010752677917,
|
| 606 |
+
"learning_rate": 0.0002079748753938678,
|
| 607 |
+
"loss": 6.9691,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.022056351287741242,
|
| 612 |
+
"grad_norm": 0.9002844095230103,
|
| 613 |
+
"learning_rate": 0.0002056795873377331,
|
| 614 |
+
"loss": 6.5822,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.022325331181494185,
|
| 619 |
+
"grad_norm": 0.6348511576652527,
|
| 620 |
+
"learning_rate": 0.00020336907703837748,
|
| 621 |
+
"loss": 6.8699,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.022594311075247127,
|
| 626 |
+
"grad_norm": 0.5231301188468933,
|
| 627 |
+
"learning_rate": 0.00020104397616624645,
|
| 628 |
+
"loss": 6.8725,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.022863290969000066,
|
| 633 |
+
"grad_norm": 0.68709397315979,
|
| 634 |
+
"learning_rate": 0.00019870492038070252,
|
| 635 |
+
"loss": 6.7312,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.023132270862753008,
|
| 640 |
+
"grad_norm": 0.47030457854270935,
|
| 641 |
+
"learning_rate": 0.0001963525491562421,
|
| 642 |
+
"loss": 6.7572,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.02340125075650595,
|
| 647 |
+
"grad_norm": 0.7477748394012451,
|
| 648 |
+
"learning_rate": 0.0001939875056076697,
|
| 649 |
+
"loss": 7.014,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.023670230650258892,
|
| 654 |
+
"grad_norm": 0.9135372638702393,
|
| 655 |
+
"learning_rate": 0.00019161043631427666,
|
| 656 |
+
"loss": 6.8656,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.023939210544011835,
|
| 661 |
+
"grad_norm": 0.7729247212409973,
|
| 662 |
+
"learning_rate": 0.00018922199114307294,
|
| 663 |
+
"loss": 6.8811,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.024208190437764777,
|
| 668 |
+
"grad_norm": 0.8843768835067749,
|
| 669 |
+
"learning_rate": 0.00018682282307111987,
|
| 670 |
+
"loss": 6.8623,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.02447717033151772,
|
| 675 |
+
"grad_norm": 0.5804451107978821,
|
| 676 |
+
"learning_rate": 0.00018441358800701273,
|
| 677 |
+
"loss": 6.8921,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.02474615022527066,
|
| 682 |
+
"grad_norm": 0.9439037442207336,
|
| 683 |
+
"learning_rate": 0.00018199494461156203,
|
| 684 |
+
"loss": 7.4667,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.025015130119023603,
|
| 689 |
+
"grad_norm": 0.6652296185493469,
|
| 690 |
+
"learning_rate": 0.000179567554117722,
|
| 691 |
+
"loss": 7.1213,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.025284110012776546,
|
| 696 |
+
"grad_norm": 0.9313641786575317,
|
| 697 |
+
"learning_rate": 0.00017713208014981648,
|
| 698 |
+
"loss": 6.9055,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.025553089906529488,
|
| 703 |
+
"grad_norm": 0.5718141198158264,
|
| 704 |
+
"learning_rate": 0.00017468918854211007,
|
| 705 |
+
"loss": 7.4156,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.02582206980028243,
|
| 710 |
+
"grad_norm": 0.90057772397995,
|
| 711 |
+
"learning_rate": 0.00017223954715677627,
|
| 712 |
+
"loss": 7.0547,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.026091049694035372,
|
| 717 |
+
"grad_norm": 0.8088359236717224,
|
| 718 |
+
"learning_rate": 0.00016978382570131034,
|
| 719 |
+
"loss": 6.8638,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.02636002958778831,
|
| 724 |
+
"grad_norm": 0.7129319310188293,
|
| 725 |
+
"learning_rate": 0.00016732269554543794,
|
| 726 |
+
"loss": 7.0757,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.026629009481541253,
|
| 731 |
+
"grad_norm": 0.7212324142456055,
|
| 732 |
+
"learning_rate": 0.00016485682953756942,
|
| 733 |
+
"loss": 7.3563,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.026897989375294196,
|
| 738 |
+
"grad_norm": 1.3920371532440186,
|
| 739 |
+
"learning_rate": 0.00016238690182084986,
|
| 740 |
+
"loss": 7.3419,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.026897989375294196,
|
| 745 |
+
"eval_loss": 7.306600570678711,
|
| 746 |
+
"eval_runtime": 1.1005,
|
| 747 |
+
"eval_samples_per_second": 45.435,
|
| 748 |
+
"eval_steps_per_second": 6.361,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 87404486197248.0,
|
| 779 |
"train_batch_size": 8,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|