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 50358592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a499d923fc8b0362c81987e3172fbcd093b0effe5bdc768e70faf0811be15f5e
|
| 3 |
size 50358592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100824826
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc86c2c3b62f1125d16831eb4312c9bd1507cc6ded424140a435b9659edc365e
|
| 3 |
size 100824826
|
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 sha256:3603ae0f461c0309918a469bb88361702e8fe7031d469296ef29915e59cd15f4
|
| 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 sha256:95019e029f304009516750a4bbe05ba42bcbfeab090e08f3a47061c7683127e4
|
| 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:c93ea150dedd152785349606801d73a50b174319e11bd7bc4c752090cefb4196
|
| 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:f5e3858bb07bc0e1a65c01d5084480d194b61020c06fc22f6fa0708b202f0e34
|
| 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:ba08b4a1855b48cf82b864725b4104527747dc0aacfb5a9d0a509cb25e565a06
|
| 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":
|
| 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": 79.667,
|
| 382 |
"eval_steps_per_second": 3.187,
|
| 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": 0.6968957781791687,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 2.5901374292643493,
|
| 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": 79.667,
|
| 382 |
"eval_steps_per_second": 3.187,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.3209377526273243,
|
| 387 |
+
"grad_norm": 15.50403118133545,
|
| 388 |
+
"learning_rate": 0.0002022302453151598,
|
| 389 |
+
"loss": 22.3089,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.3468067906224737,
|
| 394 |
+
"grad_norm": 24.226417541503906,
|
| 395 |
+
"learning_rate": 0.0001980404780794256,
|
| 396 |
+
"loss": 23.1566,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.3726758286176233,
|
| 401 |
+
"grad_norm": 20.176647186279297,
|
| 402 |
+
"learning_rate": 0.00019380851559554636,
|
| 403 |
+
"loss": 22.929,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.3985448666127729,
|
| 408 |
+
"grad_norm": 15.459396362304688,
|
| 409 |
+
"learning_rate": 0.00018953807491036011,
|
| 410 |
+
"loss": 22.6978,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.4244139046079223,
|
| 415 |
+
"grad_norm": 14.14704418182373,
|
| 416 |
+
"learning_rate": 0.00018523290686714756,
|
| 417 |
+
"loss": 22.7141,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.450282942603072,
|
| 422 |
+
"grad_norm": 7.990035533905029,
|
| 423 |
+
"learning_rate": 0.00018089679281116472,
|
| 424 |
+
"loss": 23.1633,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.4761519805982215,
|
| 429 |
+
"grad_norm": 3.211017608642578,
|
| 430 |
+
"learning_rate": 0.00017653354126838592,
|
| 431 |
+
"loss": 22.3353,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.502021018593371,
|
| 436 |
+
"grad_norm": 18.740083694458008,
|
| 437 |
+
"learning_rate": 0.00017214698460037218,
|
| 438 |
+
"loss": 23.5309,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.5278900565885207,
|
| 443 |
+
"grad_norm": 16.11014175415039,
|
| 444 |
+
"learning_rate": 0.00016774097563820485,
|
| 445 |
+
"loss": 22.8019,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.5537590945836701,
|
| 450 |
+
"grad_norm": 26.232606887817383,
|
| 451 |
+
"learning_rate": 0.00016331938429844022,
|
| 452 |
+
"loss": 23.5109,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.5796281325788197,
|
| 457 |
+
"grad_norm": 16.256412506103516,
|
| 458 |
+
"learning_rate": 0.00015888609418405713,
|
| 459 |
+
"loss": 22.8009,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.6054971705739693,
|
| 464 |
+
"grad_norm": 11.629958152770996,
|
| 465 |
+
"learning_rate": 0.00015444499917338395,
|
| 466 |
+
"loss": 22.3203,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.6313662085691187,
|
| 471 |
+
"grad_norm": 11.147138595581055,
|
| 472 |
+
"learning_rate": 0.00015,
|
| 473 |
+
"loss": 22.4757,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.6572352465642683,
|
| 478 |
+
"grad_norm": 5.99025297164917,
|
| 479 |
+
"learning_rate": 0.00014555500082661602,
|
| 480 |
+
"loss": 22.2444,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.683104284559418,
|
| 485 |
+
"grad_norm": 11.468669891357422,
|
| 486 |
+
"learning_rate": 0.00014111390581594284,
|
| 487 |
+
"loss": 22.2462,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.7089733225545674,
|
| 492 |
+
"grad_norm": 14.979022979736328,
|
| 493 |
+
"learning_rate": 0.00013668061570155978,
|
| 494 |
+
"loss": 21.7589,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.7348423605497172,
|
| 499 |
+
"grad_norm": 12.94080924987793,
|
| 500 |
+
"learning_rate": 0.00013225902436179513,
|
| 501 |
+
"loss": 22.4269,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.7607113985448666,
|
| 506 |
+
"grad_norm": 11.411182403564453,
|
| 507 |
+
"learning_rate": 0.00012785301539962782,
|
| 508 |
+
"loss": 21.7354,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.7865804365400162,
|
| 513 |
+
"grad_norm": 27.090801239013672,
|
| 514 |
+
"learning_rate": 0.00012346645873161408,
|
| 515 |
+
"loss": 23.5318,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.8124494745351658,
|
| 520 |
+
"grad_norm": 17.46219825744629,
|
| 521 |
+
"learning_rate": 0.00011910320718883525,
|
| 522 |
+
"loss": 22.8003,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.8383185125303152,
|
| 527 |
+
"grad_norm": 17.276792526245117,
|
| 528 |
+
"learning_rate": 0.00011476709313285244,
|
| 529 |
+
"loss": 22.7198,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.8641875505254648,
|
| 534 |
+
"grad_norm": 13.101729393005371,
|
| 535 |
+
"learning_rate": 0.00011046192508963989,
|
| 536 |
+
"loss": 22.2413,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.8900565885206144,
|
| 541 |
+
"grad_norm": 10.330924987792969,
|
| 542 |
+
"learning_rate": 0.00010619148440445364,
|
| 543 |
+
"loss": 21.9412,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.9159256265157638,
|
| 548 |
+
"grad_norm": 16.028894424438477,
|
| 549 |
+
"learning_rate": 0.00010195952192057438,
|
| 550 |
+
"loss": 22.5098,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.9417946645109136,
|
| 555 |
+
"grad_norm": 8.1192626953125,
|
| 556 |
+
"learning_rate": 9.776975468484019e-05,
|
| 557 |
+
"loss": 22.1182,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.9417946645109136,
|
| 562 |
+
"eval_loss": 0.7175214886665344,
|
| 563 |
+
"eval_runtime": 0.6276,
|
| 564 |
+
"eval_samples_per_second": 79.669,
|
| 565 |
+
"eval_steps_per_second": 3.187,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.967663702506063,
|
| 570 |
+
"grad_norm": 11.423409461975098,
|
| 571 |
+
"learning_rate": 9.36258626828643e-05,
|
| 572 |
+
"loss": 22.3389,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.9935327405012127,
|
| 577 |
+
"grad_norm": 12.934334754943848,
|
| 578 |
+
"learning_rate": 8.953148560680418e-05,
|
| 579 |
+
"loss": 22.7501,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 2.021018593371059,
|
| 584 |
+
"grad_norm": 22.10219383239746,
|
| 585 |
+
"learning_rate": 8.549021965852197e-05,
|
| 586 |
+
"loss": 23.1807,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.0468876313662085,
|
| 591 |
+
"grad_norm": 15.90378475189209,
|
| 592 |
+
"learning_rate": 8.150561439094303e-05,
|
| 593 |
+
"loss": 22.5372,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.072756669361358,
|
| 598 |
+
"grad_norm": 10.656487464904785,
|
| 599 |
+
"learning_rate": 7.758116959038828e-05,
|
| 600 |
+
"loss": 22.1827,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.0986257073565078,
|
| 605 |
+
"grad_norm": 22.766876220703125,
|
| 606 |
+
"learning_rate": 7.372033220261696e-05,
|
| 607 |
+
"loss": 22.6163,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.124494745351657,
|
| 612 |
+
"grad_norm": 11.259724617004395,
|
| 613 |
+
"learning_rate": 6.992649330528145e-05,
|
| 614 |
+
"loss": 22.0147,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.1503637833468066,
|
| 619 |
+
"grad_norm": 12.66515827178955,
|
| 620 |
+
"learning_rate": 6.620298512945214e-05,
|
| 621 |
+
"loss": 21.9512,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.1762328213419564,
|
| 626 |
+
"grad_norm": 5.229973793029785,
|
| 627 |
+
"learning_rate": 6.255307813282921e-05,
|
| 628 |
+
"loss": 22.17,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.202101859337106,
|
| 633 |
+
"grad_norm": 6.952908992767334,
|
| 634 |
+
"learning_rate": 5.897997812721103e-05,
|
| 635 |
+
"loss": 22.418,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 2.2279708973322556,
|
| 640 |
+
"grad_norm": 9.438949584960938,
|
| 641 |
+
"learning_rate": 5.5486823462743344e-05,
|
| 642 |
+
"loss": 22.334,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 2.253839935327405,
|
| 647 |
+
"grad_norm": 13.546004295349121,
|
| 648 |
+
"learning_rate": 5.2076682271421774e-05,
|
| 649 |
+
"loss": 22.3634,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.2797089733225544,
|
| 654 |
+
"grad_norm": 14.096308708190918,
|
| 655 |
+
"learning_rate": 4.8752549772268444e-05,
|
| 656 |
+
"loss": 22.6631,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.3055780113177042,
|
| 661 |
+
"grad_norm": 18.847871780395508,
|
| 662 |
+
"learning_rate": 4.551734564055049e-05,
|
| 663 |
+
"loss": 22.0801,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.3314470493128536,
|
| 668 |
+
"grad_norm": 7.903066635131836,
|
| 669 |
+
"learning_rate": 4.2373911443350286e-05,
|
| 670 |
+
"loss": 22.043,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.3573160873080035,
|
| 675 |
+
"grad_norm": 16.976978302001953,
|
| 676 |
+
"learning_rate": 3.932500814374089e-05,
|
| 677 |
+
"loss": 22.2002,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.383185125303153,
|
| 682 |
+
"grad_norm": 11.1248140335083,
|
| 683 |
+
"learning_rate": 3.637331367575698e-05,
|
| 684 |
+
"loss": 22.1329,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.4090541632983022,
|
| 689 |
+
"grad_norm": 5.761756896972656,
|
| 690 |
+
"learning_rate": 3.352142059229365e-05,
|
| 691 |
+
"loss": 22.0856,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.434923201293452,
|
| 696 |
+
"grad_norm": 12.847921371459961,
|
| 697 |
+
"learning_rate": 3.077183378799699e-05,
|
| 698 |
+
"loss": 22.0646,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.4607922392886015,
|
| 703 |
+
"grad_norm": 9.289769172668457,
|
| 704 |
+
"learning_rate": 2.81269682991478e-05,
|
| 705 |
+
"loss": 21.8848,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.486661277283751,
|
| 710 |
+
"grad_norm": 13.644316673278809,
|
| 711 |
+
"learning_rate": 2.5589147182469732e-05,
|
| 712 |
+
"loss": 23.1436,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.5125303152789007,
|
| 717 |
+
"grad_norm": 16.434682846069336,
|
| 718 |
+
"learning_rate": 2.316059947472607e-05,
|
| 719 |
+
"loss": 22.212,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.53839935327405,
|
| 724 |
+
"grad_norm": 6.969300270080566,
|
| 725 |
+
"learning_rate": 2.0843458234896666e-05,
|
| 726 |
+
"loss": 22.2793,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 2.5642683912691995,
|
| 731 |
+
"grad_norm": 21.42749786376953,
|
| 732 |
+
"learning_rate": 1.8639758670654486e-05,
|
| 733 |
+
"loss": 22.3692,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.5901374292643493,
|
| 738 |
+
"grad_norm": 13.674956321716309,
|
| 739 |
+
"learning_rate": 1.6551436350787918e-05,
|
| 740 |
+
"loss": 22.2481,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.5901374292643493,
|
| 745 |
+
"eval_loss": 0.6968957781791687,
|
| 746 |
+
"eval_runtime": 0.6272,
|
| 747 |
+
"eval_samples_per_second": 79.714,
|
| 748 |
+
"eval_steps_per_second": 3.189,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 1.020403094913024e+17,
|
| 779 |
"train_batch_size": 1,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|