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 216151256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4facc156c8138f6cd4dbdf726826d05dd8bef73535dff7d50a8dbfa60ff338f7
|
| 3 |
size 216151256
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 432640054
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c210e24b16e9395f87905f2217650293255c901265fdf6cbc461a24c9403092
|
| 3 |
size 432640054
|
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 sha256:70d83e548d524173a0adaf547d65ac04c6800e46601615d1fd59220cf7bcde12
|
| 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 sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 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": 7.408,
|
| 374 |
"eval_steps_per_second": 1.852,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -396,12 +754,12 @@
|
|
| 396 |
"should_evaluate": false,
|
| 397 |
"should_log": false,
|
| 398 |
"should_save": true,
|
| 399 |
-
"should_training_stop":
|
| 400 |
},
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 4,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.325927972793579,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.006487503446486206,
|
| 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": 7.408,
|
| 374 |
"eval_steps_per_second": 1.852,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.0033086267577079652,
|
| 379 |
+
"grad_norm": 0.4849475920200348,
|
| 380 |
+
"learning_rate": 5.695865504800327e-05,
|
| 381 |
+
"loss": 0.8282,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.003373501792172827,
|
| 386 |
+
"grad_norm": 0.37002480030059814,
|
| 387 |
+
"learning_rate": 5.522642316338268e-05,
|
| 388 |
+
"loss": 0.7841,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.0034383768266376892,
|
| 393 |
+
"grad_norm": 0.4096565544605255,
|
| 394 |
+
"learning_rate": 5.348782368720626e-05,
|
| 395 |
+
"loss": 0.7244,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.003503251861102551,
|
| 400 |
+
"grad_norm": 0.4696180820465088,
|
| 401 |
+
"learning_rate": 5.174497483512506e-05,
|
| 402 |
+
"loss": 1.1759,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.0035681268955674132,
|
| 407 |
+
"grad_norm": 0.43438711762428284,
|
| 408 |
+
"learning_rate": 5e-05,
|
| 409 |
+
"loss": 0.9274,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.0036330019300322754,
|
| 414 |
+
"grad_norm": 0.41294389963150024,
|
| 415 |
+
"learning_rate": 4.825502516487497e-05,
|
| 416 |
+
"loss": 0.8646,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.0036978769644971372,
|
| 421 |
+
"grad_norm": 0.36452946066856384,
|
| 422 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 423 |
+
"loss": 0.9131,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.0037627519989619994,
|
| 428 |
+
"grad_norm": 0.3747154772281647,
|
| 429 |
+
"learning_rate": 4.477357683661734e-05,
|
| 430 |
+
"loss": 0.9117,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.0038276270334268617,
|
| 435 |
+
"grad_norm": 0.40438297390937805,
|
| 436 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 437 |
+
"loss": 1.2761,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.0038925020678917234,
|
| 442 |
+
"grad_norm": 0.352256715297699,
|
| 443 |
+
"learning_rate": 4.131759111665349e-05,
|
| 444 |
+
"loss": 1.0757,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.003957377102356586,
|
| 449 |
+
"grad_norm": 0.34723353385925293,
|
| 450 |
+
"learning_rate": 3.960441545911204e-05,
|
| 451 |
+
"loss": 0.8732,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.004022252136821448,
|
| 456 |
+
"grad_norm": 0.37071236968040466,
|
| 457 |
+
"learning_rate": 3.790390522001662e-05,
|
| 458 |
+
"loss": 0.9158,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.00408712717128631,
|
| 463 |
+
"grad_norm": 0.38852158188819885,
|
| 464 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 465 |
+
"loss": 0.8826,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.004152002205751171,
|
| 470 |
+
"grad_norm": 0.360282838344574,
|
| 471 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 472 |
+
"loss": 0.8892,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.004216877240216034,
|
| 477 |
+
"grad_norm": 0.38755518198013306,
|
| 478 |
+
"learning_rate": 3.289899283371657e-05,
|
| 479 |
+
"loss": 1.1074,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.004281752274680896,
|
| 484 |
+
"grad_norm": 0.39956825971603394,
|
| 485 |
+
"learning_rate": 3.12696703292044e-05,
|
| 486 |
+
"loss": 1.0231,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.004346627309145758,
|
| 491 |
+
"grad_norm": 0.401048868894577,
|
| 492 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 493 |
+
"loss": 1.1309,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.00441150234361062,
|
| 498 |
+
"grad_norm": 0.39506635069847107,
|
| 499 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 500 |
+
"loss": 1.1455,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.0044763773780754825,
|
| 505 |
+
"grad_norm": 0.3784264028072357,
|
| 506 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 507 |
+
"loss": 0.8688,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.004541252412540344,
|
| 512 |
+
"grad_norm": 0.4321235120296478,
|
| 513 |
+
"learning_rate": 2.500000000000001e-05,
|
| 514 |
+
"loss": 0.8886,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.004606127447005206,
|
| 519 |
+
"grad_norm": 0.4353868067264557,
|
| 520 |
+
"learning_rate": 2.350403678833976e-05,
|
| 521 |
+
"loss": 1.2471,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.004671002481470068,
|
| 526 |
+
"grad_norm": 0.44864824414253235,
|
| 527 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 528 |
+
"loss": 1.0473,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.0047358775159349305,
|
| 533 |
+
"grad_norm": 0.46487781405448914,
|
| 534 |
+
"learning_rate": 2.061073738537635e-05,
|
| 535 |
+
"loss": 0.9981,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.004800752550399793,
|
| 540 |
+
"grad_norm": 0.4789814352989197,
|
| 541 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 542 |
+
"loss": 0.9889,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.004865627584864654,
|
| 547 |
+
"grad_norm": 0.46205461025238037,
|
| 548 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 549 |
+
"loss": 1.0581,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.004930502619329516,
|
| 554 |
+
"grad_norm": 0.4730319380760193,
|
| 555 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 556 |
+
"loss": 0.9925,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.0049953776537943785,
|
| 561 |
+
"grad_norm": 0.47287988662719727,
|
| 562 |
+
"learning_rate": 1.526708147705013e-05,
|
| 563 |
+
"loss": 1.2184,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.005060252688259241,
|
| 568 |
+
"grad_norm": 0.5465039610862732,
|
| 569 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 570 |
+
"loss": 1.4309,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.005125127722724103,
|
| 575 |
+
"grad_norm": 0.5158198475837708,
|
| 576 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 577 |
+
"loss": 1.446,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.005190002757188965,
|
| 582 |
+
"grad_norm": 0.5407456755638123,
|
| 583 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 584 |
+
"loss": 1.1469,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.0052548777916538265,
|
| 589 |
+
"grad_norm": 0.606384813785553,
|
| 590 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 591 |
+
"loss": 1.6318,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.005319752826118689,
|
| 596 |
+
"grad_norm": 0.5945765972137451,
|
| 597 |
+
"learning_rate": 9.549150281252633e-06,
|
| 598 |
+
"loss": 1.4171,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.005384627860583551,
|
| 603 |
+
"grad_norm": 0.5641322135925293,
|
| 604 |
+
"learning_rate": 8.548121372247918e-06,
|
| 605 |
+
"loss": 1.6514,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.005449502895048413,
|
| 610 |
+
"grad_norm": 0.7056270241737366,
|
| 611 |
+
"learning_rate": 7.597595192178702e-06,
|
| 612 |
+
"loss": 1.4912,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.005514377929513275,
|
| 617 |
+
"grad_norm": 0.6317409873008728,
|
| 618 |
+
"learning_rate": 6.698729810778065e-06,
|
| 619 |
+
"loss": 2.0169,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.005579252963978137,
|
| 624 |
+
"grad_norm": 0.7745837569236755,
|
| 625 |
+
"learning_rate": 5.852620357053651e-06,
|
| 626 |
+
"loss": 1.9579,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.005644127998442999,
|
| 631 |
+
"grad_norm": 0.7412452101707458,
|
| 632 |
+
"learning_rate": 5.060297685041659e-06,
|
| 633 |
+
"loss": 1.8417,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.005709003032907861,
|
| 638 |
+
"grad_norm": 0.6834709644317627,
|
| 639 |
+
"learning_rate": 4.322727117869951e-06,
|
| 640 |
+
"loss": 1.5746,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.005773878067372723,
|
| 645 |
+
"grad_norm": 0.7952920198440552,
|
| 646 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 647 |
+
"loss": 1.6825,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.005838753101837586,
|
| 652 |
+
"grad_norm": 0.6980010271072388,
|
| 653 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 654 |
+
"loss": 1.8503,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.005903628136302448,
|
| 659 |
+
"grad_norm": 0.842880129814148,
|
| 660 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 661 |
+
"loss": 1.8676,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.005968503170767309,
|
| 666 |
+
"grad_norm": 0.8270924091339111,
|
| 667 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 668 |
+
"loss": 1.8416,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.006033378205232171,
|
| 673 |
+
"grad_norm": 0.877210795879364,
|
| 674 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 675 |
+
"loss": 1.8189,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.006098253239697034,
|
| 680 |
+
"grad_norm": 0.9402266144752502,
|
| 681 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 682 |
+
"loss": 1.5157,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.006163128274161896,
|
| 687 |
+
"grad_norm": 1.0260732173919678,
|
| 688 |
+
"learning_rate": 7.596123493895991e-07,
|
| 689 |
+
"loss": 1.6211,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.006228003308626758,
|
| 694 |
+
"grad_norm": 1.1405702829360962,
|
| 695 |
+
"learning_rate": 4.865965629214819e-07,
|
| 696 |
+
"loss": 1.8139,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.006292878343091619,
|
| 701 |
+
"grad_norm": 1.3093563318252563,
|
| 702 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 703 |
+
"loss": 1.876,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.006357753377556482,
|
| 708 |
+
"grad_norm": 1.6507575511932373,
|
| 709 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 710 |
+
"loss": 1.8827,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.006422628412021344,
|
| 715 |
+
"grad_norm": 2.4827072620391846,
|
| 716 |
+
"learning_rate": 3.04586490452119e-08,
|
| 717 |
+
"loss": 2.0387,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.006487503446486206,
|
| 722 |
+
"grad_norm": 2.8122284412384033,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 1.9601,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.006487503446486206,
|
| 729 |
+
"eval_loss": 1.325927972793579,
|
| 730 |
+
"eval_runtime": 1752.2492,
|
| 731 |
+
"eval_samples_per_second": 7.408,
|
| 732 |
+
"eval_steps_per_second": 1.852,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 754 |
"should_evaluate": false,
|
| 755 |
"should_log": false,
|
| 756 |
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
},
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 8.503799496415642e+16,
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|