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 159967880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2021a800c1854eac01ff271d37861087fde777f7fb257333d3dbbdfc394f1ade
|
| 3 |
size 159967880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 320194002
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d001862fae1d42de07fce4846c70af826ffed8a047504c0927eb15e54f340e9d
|
| 3 |
size 320194002
|
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 sha256:57d7fa21a7bb45a179b6712aafbea04906d6e951da49ca512e829f67e9530edf
|
| 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": 0.
|
| 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": 3.846,
|
| 382 |
"eval_steps_per_second": 0.538,
|
| 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": 0.011105372570455074,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.4069175991861648,
|
| 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": 3.846,
|
| 382 |
"eval_steps_per_second": 0.538,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.20752797558494404,
|
| 387 |
+
"grad_norm": 0.7120374441146851,
|
| 388 |
+
"learning_rate": 0.0002668315918143169,
|
| 389 |
+
"loss": 0.096,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.2115971515768057,
|
| 394 |
+
"grad_norm": 0.3248690366744995,
|
| 395 |
+
"learning_rate": 0.00026526016662852886,
|
| 396 |
+
"loss": 0.0389,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.21566632756866735,
|
| 401 |
+
"grad_norm": 0.3197277784347534,
|
| 402 |
+
"learning_rate": 0.00026365723046405023,
|
| 403 |
+
"loss": 0.0302,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.21973550356052898,
|
| 408 |
+
"grad_norm": 0.14361833035945892,
|
| 409 |
+
"learning_rate": 0.0002620232215476231,
|
| 410 |
+
"loss": 0.0137,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.22380467955239064,
|
| 415 |
+
"grad_norm": 0.17876560986042023,
|
| 416 |
+
"learning_rate": 0.0002603585866009697,
|
| 417 |
+
"loss": 0.036,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.2278738555442523,
|
| 422 |
+
"grad_norm": 0.07787288725376129,
|
| 423 |
+
"learning_rate": 0.00025866378071866334,
|
| 424 |
+
"loss": 0.0154,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.23194303153611392,
|
| 429 |
+
"grad_norm": 0.11396508663892746,
|
| 430 |
+
"learning_rate": 0.00025693926724370956,
|
| 431 |
+
"loss": 0.0188,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.23601220752797558,
|
| 436 |
+
"grad_norm": 0.10331092029809952,
|
| 437 |
+
"learning_rate": 0.00025518551764087326,
|
| 438 |
+
"loss": 0.0184,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.24008138351983724,
|
| 443 |
+
"grad_norm": 0.07832586020231247,
|
| 444 |
+
"learning_rate": 0.00025340301136778483,
|
| 445 |
+
"loss": 0.0126,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.2441505595116989,
|
| 450 |
+
"grad_norm": 0.038063760846853256,
|
| 451 |
+
"learning_rate": 0.00025159223574386114,
|
| 452 |
+
"loss": 0.0064,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.24821973550356052,
|
| 457 |
+
"grad_norm": 0.04389215260744095,
|
| 458 |
+
"learning_rate": 0.0002497536858170772,
|
| 459 |
+
"loss": 0.0035,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.25228891149542215,
|
| 464 |
+
"grad_norm": 0.033812519162893295,
|
| 465 |
+
"learning_rate": 0.00024788786422862526,
|
| 466 |
+
"loss": 0.0029,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.25635808748728384,
|
| 471 |
+
"grad_norm": 0.05039115995168686,
|
| 472 |
+
"learning_rate": 0.00024599528107549745,
|
| 473 |
+
"loss": 0.0049,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.26042726347914547,
|
| 478 |
+
"grad_norm": 0.04454028606414795,
|
| 479 |
+
"learning_rate": 0.00024407645377103054,
|
| 480 |
+
"loss": 0.003,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.2644964394710071,
|
| 485 |
+
"grad_norm": 0.03696225956082344,
|
| 486 |
+
"learning_rate": 0.00024213190690345018,
|
| 487 |
+
"loss": 0.0022,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.2685656154628688,
|
| 492 |
+
"grad_norm": 0.05542654171586037,
|
| 493 |
+
"learning_rate": 0.00024016217209245374,
|
| 494 |
+
"loss": 0.0021,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.2726347914547304,
|
| 499 |
+
"grad_norm": 0.013826167210936546,
|
| 500 |
+
"learning_rate": 0.00023816778784387094,
|
| 501 |
+
"loss": 0.0008,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.2767039674465921,
|
| 506 |
+
"grad_norm": 0.023703791201114655,
|
| 507 |
+
"learning_rate": 0.0002361492994024415,
|
| 508 |
+
"loss": 0.0022,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.2807731434384537,
|
| 513 |
+
"grad_norm": 0.08458836376667023,
|
| 514 |
+
"learning_rate": 0.0002341072586027509,
|
| 515 |
+
"loss": 0.0164,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.28484231943031535,
|
| 520 |
+
"grad_norm": 0.7300925850868225,
|
| 521 |
+
"learning_rate": 0.00023204222371836405,
|
| 522 |
+
"loss": 0.0927,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.28891149542217703,
|
| 527 |
+
"grad_norm": 0.5981572270393372,
|
| 528 |
+
"learning_rate": 0.00022995475930919905,
|
| 529 |
+
"loss": 0.1194,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.29298067141403866,
|
| 534 |
+
"grad_norm": 0.5619075298309326,
|
| 535 |
+
"learning_rate": 0.00022784543606718227,
|
| 536 |
+
"loss": 0.0957,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.2970498474059003,
|
| 541 |
+
"grad_norm": 0.33565792441368103,
|
| 542 |
+
"learning_rate": 0.00022571483066022657,
|
| 543 |
+
"loss": 0.0656,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.301119023397762,
|
| 548 |
+
"grad_norm": 0.46171268820762634,
|
| 549 |
+
"learning_rate": 0.0002235635255745762,
|
| 550 |
+
"loss": 0.0598,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.3051881993896236,
|
| 555 |
+
"grad_norm": 0.45766952633857727,
|
| 556 |
+
"learning_rate": 0.00022139210895556104,
|
| 557 |
+
"loss": 0.0685,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.3051881993896236,
|
| 562 |
+
"eval_loss": 0.025676894932985306,
|
| 563 |
+
"eval_runtime": 13.0016,
|
| 564 |
+
"eval_samples_per_second": 3.846,
|
| 565 |
+
"eval_steps_per_second": 0.538,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.30925737538148523,
|
| 570 |
+
"grad_norm": 0.5149214863777161,
|
| 571 |
+
"learning_rate": 0.00021920117444680317,
|
| 572 |
+
"loss": 0.0755,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.3133265513733469,
|
| 577 |
+
"grad_norm": 0.3870311975479126,
|
| 578 |
+
"learning_rate": 0.00021699132102792097,
|
| 579 |
+
"loss": 0.0534,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.31739572736520855,
|
| 584 |
+
"grad_norm": 0.33499646186828613,
|
| 585 |
+
"learning_rate": 0.0002147631528507739,
|
| 586 |
+
"loss": 0.0599,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.3214649033570702,
|
| 591 |
+
"grad_norm": 0.29793283343315125,
|
| 592 |
+
"learning_rate": 0.00021251727907429355,
|
| 593 |
+
"loss": 0.0375,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.32553407934893186,
|
| 598 |
+
"grad_norm": 0.2961036264896393,
|
| 599 |
+
"learning_rate": 0.0002102543136979454,
|
| 600 |
+
"loss": 0.0398,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.3296032553407935,
|
| 605 |
+
"grad_norm": 0.3199717104434967,
|
| 606 |
+
"learning_rate": 0.0002079748753938678,
|
| 607 |
+
"loss": 0.0375,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.3336724313326551,
|
| 612 |
+
"grad_norm": 0.30673283338546753,
|
| 613 |
+
"learning_rate": 0.0002056795873377331,
|
| 614 |
+
"loss": 0.0474,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.3377416073245168,
|
| 619 |
+
"grad_norm": 0.35638052225112915,
|
| 620 |
+
"learning_rate": 0.00020336907703837748,
|
| 621 |
+
"loss": 0.0364,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.34181078331637843,
|
| 626 |
+
"grad_norm": 0.541354775428772,
|
| 627 |
+
"learning_rate": 0.00020104397616624645,
|
| 628 |
+
"loss": 0.0596,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.34587995930824006,
|
| 633 |
+
"grad_norm": 0.23636458814144135,
|
| 634 |
+
"learning_rate": 0.00019870492038070252,
|
| 635 |
+
"loss": 0.0285,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.34994913530010174,
|
| 640 |
+
"grad_norm": 0.25946715474128723,
|
| 641 |
+
"learning_rate": 0.0001963525491562421,
|
| 642 |
+
"loss": 0.0334,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.3540183112919634,
|
| 647 |
+
"grad_norm": 0.3717379868030548,
|
| 648 |
+
"learning_rate": 0.0001939875056076697,
|
| 649 |
+
"loss": 0.0823,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.358087487283825,
|
| 654 |
+
"grad_norm": 0.6748691201210022,
|
| 655 |
+
"learning_rate": 0.00019161043631427666,
|
| 656 |
+
"loss": 0.072,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.3621566632756867,
|
| 661 |
+
"grad_norm": 0.42658162117004395,
|
| 662 |
+
"learning_rate": 0.00018922199114307294,
|
| 663 |
+
"loss": 0.0462,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.3662258392675483,
|
| 668 |
+
"grad_norm": 0.42387211322784424,
|
| 669 |
+
"learning_rate": 0.00018682282307111987,
|
| 670 |
+
"loss": 0.1011,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.37029501525940994,
|
| 675 |
+
"grad_norm": 0.29736894369125366,
|
| 676 |
+
"learning_rate": 0.00018441358800701273,
|
| 677 |
+
"loss": 0.0411,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.3743641912512716,
|
| 682 |
+
"grad_norm": 0.2868631184101105,
|
| 683 |
+
"learning_rate": 0.00018199494461156203,
|
| 684 |
+
"loss": 0.0671,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.37843336724313326,
|
| 689 |
+
"grad_norm": 0.4251483082771301,
|
| 690 |
+
"learning_rate": 0.000179567554117722,
|
| 691 |
+
"loss": 0.1333,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.38250254323499494,
|
| 696 |
+
"grad_norm": 0.3550730049610138,
|
| 697 |
+
"learning_rate": 0.00017713208014981648,
|
| 698 |
+
"loss": 0.0863,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.38657171922685657,
|
| 703 |
+
"grad_norm": 0.28326889872550964,
|
| 704 |
+
"learning_rate": 0.00017468918854211007,
|
| 705 |
+
"loss": 0.0795,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.3906408952187182,
|
| 710 |
+
"grad_norm": 0.3059619963169098,
|
| 711 |
+
"learning_rate": 0.00017223954715677627,
|
| 712 |
+
"loss": 0.1373,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.3947100712105799,
|
| 717 |
+
"grad_norm": 0.3868827819824219,
|
| 718 |
+
"learning_rate": 0.00016978382570131034,
|
| 719 |
+
"loss": 0.1411,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.3987792472024415,
|
| 724 |
+
"grad_norm": 0.35499969124794006,
|
| 725 |
+
"learning_rate": 0.00016732269554543794,
|
| 726 |
+
"loss": 0.1811,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.40284842319430314,
|
| 731 |
+
"grad_norm": 0.793555736541748,
|
| 732 |
+
"learning_rate": 0.00016485682953756942,
|
| 733 |
+
"loss": 0.4984,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.4069175991861648,
|
| 738 |
+
"grad_norm": 1.1363798379898071,
|
| 739 |
+
"learning_rate": 0.00016238690182084986,
|
| 740 |
+
"loss": 0.742,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.4069175991861648,
|
| 745 |
+
"eval_loss": 0.011105372570455074,
|
| 746 |
+
"eval_runtime": 12.9997,
|
| 747 |
+
"eval_samples_per_second": 3.846,
|
| 748 |
+
"eval_steps_per_second": 0.538,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 2.7563955529659187e+17,
|
| 779 |
"train_batch_size": 8,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|