Training in progress, step 100, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13587864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18fc12de5654e0323293b5dd1ac28814fb994a9658fb252a535bc41258c43b46
|
| 3 |
size 13587864
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27273018
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d024d96a36897f201c8fa7589476419b4311211f4a208ffc2d9a459bb98de426
|
| 3 |
size 27273018
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0e862751a4e0db817da07bf59527ac4af8750f08140f75db069d784ab7ae078
|
| 3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5b2961bbcc1830d54960d6ae6bf069daa40b1ae66346ee47b349dc68099d8ee
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d9faa3e71f84c7c46366efe1c0a99a95347d103fa5203e0f64b50cc02d8b031
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:831873b8ec47d858edb49aabcab94a7eded7500ba341e5a8727949745145665c
|
| 3 |
size 15024
|
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:f5153517b1f7cd2d77a0f7948024c5ad6d674c6b3cf70e1337dc0d8c2248ef01
|
| 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": 173.489,
|
| 382 |
"eval_steps_per_second": 45.107,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -409,7 +775,7 @@
|
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 1,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.14205443859100342,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.2997236922212336,
|
| 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": 173.489,
|
| 382 |
"eval_steps_per_second": 45.107,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.1528590830328291,
|
| 387 |
+
"grad_norm": 4.228235721588135,
|
| 388 |
+
"learning_rate": 0.0002984781941052967,
|
| 389 |
+
"loss": 1.0819,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.15585631995504146,
|
| 394 |
+
"grad_norm": 3.424924612045288,
|
| 395 |
+
"learning_rate": 0.0002983786296793692,
|
| 396 |
+
"loss": 0.5749,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.15885355687725378,
|
| 401 |
+
"grad_norm": 3.9904696941375732,
|
| 402 |
+
"learning_rate": 0.00029827593027084546,
|
| 403 |
+
"loss": 0.5831,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.16185079379946612,
|
| 408 |
+
"grad_norm": 2.694119930267334,
|
| 409 |
+
"learning_rate": 0.00029817009829361196,
|
| 410 |
+
"loss": 0.4457,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.16484803072167845,
|
| 415 |
+
"grad_norm": 1.2387803792953491,
|
| 416 |
+
"learning_rate": 0.00029806113623518407,
|
| 417 |
+
"loss": 0.3431,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.1678452676438908,
|
| 422 |
+
"grad_norm": 1.6821039915084839,
|
| 423 |
+
"learning_rate": 0.0002979490466566481,
|
| 424 |
+
"loss": 0.3905,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.17084250456610311,
|
| 429 |
+
"grad_norm": 0.6684949994087219,
|
| 430 |
+
"learning_rate": 0.00029783383219260037,
|
| 431 |
+
"loss": 0.3056,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.17383974148831546,
|
| 436 |
+
"grad_norm": 0.7967026233673096,
|
| 437 |
+
"learning_rate": 0.0002977154955510861,
|
| 438 |
+
"loss": 0.3333,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.17683697841052778,
|
| 443 |
+
"grad_norm": 0.5187807083129883,
|
| 444 |
+
"learning_rate": 0.0002975940395135351,
|
| 445 |
+
"loss": 0.2867,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.17983421533274013,
|
| 450 |
+
"grad_norm": 7.2272138595581055,
|
| 451 |
+
"learning_rate": 0.00029746946693469693,
|
| 452 |
+
"loss": 1.0056,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.18283145225495245,
|
| 457 |
+
"grad_norm": 8.9348726272583,
|
| 458 |
+
"learning_rate": 0.00029734178074257325,
|
| 459 |
+
"loss": 0.7786,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.1858286891771648,
|
| 464 |
+
"grad_norm": 8.19704532623291,
|
| 465 |
+
"learning_rate": 0.0002972109839383494,
|
| 466 |
+
"loss": 0.3928,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.18882592609937715,
|
| 471 |
+
"grad_norm": 4.3927483558654785,
|
| 472 |
+
"learning_rate": 0.00029707707959632386,
|
| 473 |
+
"loss": 0.7528,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.19182316302158947,
|
| 478 |
+
"grad_norm": 2.271043539047241,
|
| 479 |
+
"learning_rate": 0.0002969400708638358,
|
| 480 |
+
"loss": 0.4877,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.19482039994380182,
|
| 485 |
+
"grad_norm": 1.3864595890045166,
|
| 486 |
+
"learning_rate": 0.000296799960961191,
|
| 487 |
+
"loss": 0.2625,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.19781763686601414,
|
| 492 |
+
"grad_norm": 2.2087323665618896,
|
| 493 |
+
"learning_rate": 0.00029665675318158656,
|
| 494 |
+
"loss": 0.2945,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.2008148737882265,
|
| 499 |
+
"grad_norm": 3.766403913497925,
|
| 500 |
+
"learning_rate": 0.00029651045089103316,
|
| 501 |
+
"loss": 0.3807,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.2038121107104388,
|
| 506 |
+
"grad_norm": 2.598832368850708,
|
| 507 |
+
"learning_rate": 0.0002963610575282762,
|
| 508 |
+
"loss": 0.3149,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.20680934763265116,
|
| 513 |
+
"grad_norm": 0.677237331867218,
|
| 514 |
+
"learning_rate": 0.0002962085766047146,
|
| 515 |
+
"loss": 0.346,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.20980658455486348,
|
| 520 |
+
"grad_norm": 0.5142577886581421,
|
| 521 |
+
"learning_rate": 0.00029605301170431867,
|
| 522 |
+
"loss": 0.2855,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.21280382147707583,
|
| 527 |
+
"grad_norm": 0.5518949031829834,
|
| 528 |
+
"learning_rate": 0.00029589436648354566,
|
| 529 |
+
"loss": 0.3163,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.21580105839928815,
|
| 534 |
+
"grad_norm": 0.336823046207428,
|
| 535 |
+
"learning_rate": 0.00029573264467125377,
|
| 536 |
+
"loss": 0.16,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.2187982953215005,
|
| 541 |
+
"grad_norm": 0.2474360167980194,
|
| 542 |
+
"learning_rate": 0.0002955678500686147,
|
| 543 |
+
"loss": 0.0297,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.22179553224371282,
|
| 548 |
+
"grad_norm": 0.18458165228366852,
|
| 549 |
+
"learning_rate": 0.0002953999865490242,
|
| 550 |
+
"loss": 0.0609,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.22479276916592517,
|
| 555 |
+
"grad_norm": 0.36120983958244324,
|
| 556 |
+
"learning_rate": 0.0002952290580580109,
|
| 557 |
+
"loss": 0.0862,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.22479276916592517,
|
| 562 |
+
"eval_loss": 0.16452732682228088,
|
| 563 |
+
"eval_runtime": 0.2888,
|
| 564 |
+
"eval_samples_per_second": 173.11,
|
| 565 |
+
"eval_steps_per_second": 45.009,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.2277900060881375,
|
| 570 |
+
"grad_norm": 1.3333512544631958,
|
| 571 |
+
"learning_rate": 0.0002950550686131438,
|
| 572 |
+
"loss": 0.6146,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.23078724301034984,
|
| 577 |
+
"grad_norm": 1.2993559837341309,
|
| 578 |
+
"learning_rate": 0.00029487802230393777,
|
| 579 |
+
"loss": 0.2574,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.23378447993256216,
|
| 584 |
+
"grad_norm": 1.2781016826629639,
|
| 585 |
+
"learning_rate": 0.00029469792329175725,
|
| 586 |
+
"loss": 0.2978,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.2367817168547745,
|
| 591 |
+
"grad_norm": 5.145886421203613,
|
| 592 |
+
"learning_rate": 0.0002945147758097187,
|
| 593 |
+
"loss": 0.3251,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.23977895377698685,
|
| 598 |
+
"grad_norm": 5.573575019836426,
|
| 599 |
+
"learning_rate": 0.00029432858416259097,
|
| 600 |
+
"loss": 0.3483,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.24277619069919917,
|
| 605 |
+
"grad_norm": 2.6032469272613525,
|
| 606 |
+
"learning_rate": 0.0002941393527266941,
|
| 607 |
+
"loss": 0.306,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.24577342762141152,
|
| 612 |
+
"grad_norm": 0.6271111965179443,
|
| 613 |
+
"learning_rate": 0.00029394708594979657,
|
| 614 |
+
"loss": 0.318,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.24877066454362384,
|
| 619 |
+
"grad_norm": 0.5439050793647766,
|
| 620 |
+
"learning_rate": 0.0002937517883510106,
|
| 621 |
+
"loss": 0.2547,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.25176790146583616,
|
| 626 |
+
"grad_norm": 0.5188155770301819,
|
| 627 |
+
"learning_rate": 0.0002935534645206861,
|
| 628 |
+
"loss": 0.2402,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.25476513838804854,
|
| 633 |
+
"grad_norm": 1.3832889795303345,
|
| 634 |
+
"learning_rate": 0.00029335211912030247,
|
| 635 |
+
"loss": 0.147,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.25776237531026086,
|
| 640 |
+
"grad_norm": 0.20522421598434448,
|
| 641 |
+
"learning_rate": 0.0002931477568823596,
|
| 642 |
+
"loss": 0.0365,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.2607596122324732,
|
| 647 |
+
"grad_norm": 0.07317493855953217,
|
| 648 |
+
"learning_rate": 0.00029294038261026595,
|
| 649 |
+
"loss": 0.0178,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.2637568491546855,
|
| 654 |
+
"grad_norm": 5.754029273986816,
|
| 655 |
+
"learning_rate": 0.0002927300011782263,
|
| 656 |
+
"loss": 0.5049,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.2667540860768979,
|
| 661 |
+
"grad_norm": 1.9069617986679077,
|
| 662 |
+
"learning_rate": 0.0002925166175311266,
|
| 663 |
+
"loss": 0.297,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.2697513229991102,
|
| 668 |
+
"grad_norm": 1.4803589582443237,
|
| 669 |
+
"learning_rate": 0.0002923002366844182,
|
| 670 |
+
"loss": 0.2419,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.2727485599213225,
|
| 675 |
+
"grad_norm": 1.1726033687591553,
|
| 676 |
+
"learning_rate": 0.0002920808637239998,
|
| 677 |
+
"loss": 0.2449,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.27574579684353484,
|
| 682 |
+
"grad_norm": 1.1483900547027588,
|
| 683 |
+
"learning_rate": 0.00029185850380609757,
|
| 684 |
+
"loss": 0.2845,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.2787430337657472,
|
| 689 |
+
"grad_norm": 0.6498438715934753,
|
| 690 |
+
"learning_rate": 0.00029163316215714477,
|
| 691 |
+
"loss": 0.3168,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.28174027068795954,
|
| 696 |
+
"grad_norm": 3.8744821548461914,
|
| 697 |
+
"learning_rate": 0.00029140484407365807,
|
| 698 |
+
"loss": 0.3098,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.28473750761017186,
|
| 703 |
+
"grad_norm": 5.238924026489258,
|
| 704 |
+
"learning_rate": 0.00029117355492211345,
|
| 705 |
+
"loss": 0.3747,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.28773474453238423,
|
| 710 |
+
"grad_norm": 4.835148334503174,
|
| 711 |
+
"learning_rate": 0.0002909393001388201,
|
| 712 |
+
"loss": 0.311,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.29073198145459656,
|
| 717 |
+
"grad_norm": 3.1126749515533447,
|
| 718 |
+
"learning_rate": 0.00029070208522979246,
|
| 719 |
+
"loss": 0.1933,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.2937292183768089,
|
| 724 |
+
"grad_norm": 0.31741341948509216,
|
| 725 |
+
"learning_rate": 0.000290461915770621,
|
| 726 |
+
"loss": 0.0311,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.2967264552990212,
|
| 731 |
+
"grad_norm": 0.13816803693771362,
|
| 732 |
+
"learning_rate": 0.00029021879740634106,
|
| 733 |
+
"loss": 0.0489,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.2997236922212336,
|
| 738 |
+
"grad_norm": 0.16050726175308228,
|
| 739 |
+
"learning_rate": 0.0002899727358513002,
|
| 740 |
+
"loss": 0.0421,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.2997236922212336,
|
| 745 |
+
"eval_loss": 0.14205443859100342,
|
| 746 |
+
"eval_runtime": 0.2881,
|
| 747 |
+
"eval_samples_per_second": 173.58,
|
| 748 |
+
"eval_steps_per_second": 45.131,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 4.592226717086515e+16,
|
| 779 |
"train_batch_size": 1,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|