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 34456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:569d5900555f4f6bc47455f45a803d41ea1a2478a16d1390511e03f8d7723c41
|
| 3 |
size 34456
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 73222
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5c60965fb996fe1caaef71edd225f2e532cf130fc0698b6edc0b687820c38aa
|
| 3 |
size 73222
|
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:fa542b36c9e64fd86f7d78aeff5bbdf2e518733aa9181247f6ed24c01e0ab095
|
| 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:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 11.5,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 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": 73.143,
|
| 374 |
"eval_steps_per_second": 18.288,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -387,7 +745,7 @@
|
|
| 387 |
"early_stopping_threshold": 0.0
|
| 388 |
},
|
| 389 |
"attributes": {
|
| 390 |
-
"early_stopping_patience_counter":
|
| 391 |
}
|
| 392 |
},
|
| 393 |
"TrainerControl": {
|
|
@@ -401,7 +759,7 @@
|
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 4,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 11.5,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.0020129432249363405,
|
| 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": 73.143,
|
| 374 |
"eval_steps_per_second": 18.288,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.0010266010447175337,
|
| 379 |
+
"grad_norm": 8.320242159243207e-06,
|
| 380 |
+
"learning_rate": 7.873473684210526e-05,
|
| 381 |
+
"loss": 23.0,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.0010467304769668972,
|
| 386 |
+
"grad_norm": 1.5145632460189518e-05,
|
| 387 |
+
"learning_rate": 7.820631578947369e-05,
|
| 388 |
+
"loss": 23.0,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.0010668599092162605,
|
| 393 |
+
"grad_norm": 1.1512304809002671e-05,
|
| 394 |
+
"learning_rate": 7.76778947368421e-05,
|
| 395 |
+
"loss": 23.0,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.001086989341465624,
|
| 400 |
+
"grad_norm": 1.528786015114747e-05,
|
| 401 |
+
"learning_rate": 7.714947368421052e-05,
|
| 402 |
+
"loss": 23.0,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.0011071187737149873,
|
| 407 |
+
"grad_norm": 2.5456898583797738e-05,
|
| 408 |
+
"learning_rate": 7.662105263157896e-05,
|
| 409 |
+
"loss": 23.0,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.0011272482059643508,
|
| 414 |
+
"grad_norm": 2.668505476322025e-05,
|
| 415 |
+
"learning_rate": 7.609263157894737e-05,
|
| 416 |
+
"loss": 23.0,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.0011473776382137143,
|
| 421 |
+
"grad_norm": 1.551048808323685e-05,
|
| 422 |
+
"learning_rate": 7.556421052631579e-05,
|
| 423 |
+
"loss": 23.0,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.0011675070704630776,
|
| 428 |
+
"grad_norm": 2.366452827118337e-05,
|
| 429 |
+
"learning_rate": 7.503578947368421e-05,
|
| 430 |
+
"loss": 23.0,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.001187636502712441,
|
| 435 |
+
"grad_norm": 2.2682577764499e-05,
|
| 436 |
+
"learning_rate": 7.450736842105263e-05,
|
| 437 |
+
"loss": 23.0,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.0012077659349618043,
|
| 442 |
+
"grad_norm": 5.866533319931477e-05,
|
| 443 |
+
"learning_rate": 7.397894736842105e-05,
|
| 444 |
+
"loss": 23.0,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.0012278953672111678,
|
| 449 |
+
"grad_norm": 1.637460991332773e-05,
|
| 450 |
+
"learning_rate": 7.345052631578948e-05,
|
| 451 |
+
"loss": 23.0,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.0012480247994605311,
|
| 456 |
+
"grad_norm": 1.6382557078031823e-05,
|
| 457 |
+
"learning_rate": 7.29221052631579e-05,
|
| 458 |
+
"loss": 23.0,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.0012681542317098946,
|
| 463 |
+
"grad_norm": 2.3177421098807827e-05,
|
| 464 |
+
"learning_rate": 7.239368421052631e-05,
|
| 465 |
+
"loss": 23.0,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.0012882836639592581,
|
| 470 |
+
"grad_norm": 6.291714089456946e-05,
|
| 471 |
+
"learning_rate": 7.186526315789474e-05,
|
| 472 |
+
"loss": 23.0,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.0013084130962086214,
|
| 477 |
+
"grad_norm": 7.432617712765932e-05,
|
| 478 |
+
"learning_rate": 7.133684210526316e-05,
|
| 479 |
+
"loss": 23.0,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.0013285425284579849,
|
| 484 |
+
"grad_norm": 3.0208946554921567e-05,
|
| 485 |
+
"learning_rate": 7.080842105263158e-05,
|
| 486 |
+
"loss": 23.0,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0013486719607073482,
|
| 491 |
+
"grad_norm": 3.2406318496214226e-05,
|
| 492 |
+
"learning_rate": 7.028e-05,
|
| 493 |
+
"loss": 23.0,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.0013688013929567117,
|
| 498 |
+
"grad_norm": 3.3409804018447176e-05,
|
| 499 |
+
"learning_rate": 6.975157894736843e-05,
|
| 500 |
+
"loss": 23.0,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.0013889308252060752,
|
| 505 |
+
"grad_norm": 4.153459667577408e-05,
|
| 506 |
+
"learning_rate": 6.922315789473685e-05,
|
| 507 |
+
"loss": 23.0,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.0014090602574554384,
|
| 512 |
+
"grad_norm": 3.1347994081443176e-05,
|
| 513 |
+
"learning_rate": 6.869473684210527e-05,
|
| 514 |
+
"loss": 23.0,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.001429189689704802,
|
| 519 |
+
"grad_norm": 3.106446092715487e-05,
|
| 520 |
+
"learning_rate": 6.816631578947368e-05,
|
| 521 |
+
"loss": 23.0,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.0014493191219541652,
|
| 526 |
+
"grad_norm": 2.5425708372495137e-05,
|
| 527 |
+
"learning_rate": 6.76378947368421e-05,
|
| 528 |
+
"loss": 23.0,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.0014694485542035287,
|
| 533 |
+
"grad_norm": 8.160302240867168e-05,
|
| 534 |
+
"learning_rate": 6.710947368421052e-05,
|
| 535 |
+
"loss": 23.0,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.0014895779864528922,
|
| 540 |
+
"grad_norm": 8.36909530335106e-05,
|
| 541 |
+
"learning_rate": 6.658105263157894e-05,
|
| 542 |
+
"loss": 23.0,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.0015097074187022555,
|
| 547 |
+
"grad_norm": 5.806803164887242e-05,
|
| 548 |
+
"learning_rate": 6.605263157894737e-05,
|
| 549 |
+
"loss": 23.0,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.001529836850951619,
|
| 554 |
+
"grad_norm": 2.5655506760813296e-05,
|
| 555 |
+
"learning_rate": 6.55242105263158e-05,
|
| 556 |
+
"loss": 23.0,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.0015499662832009823,
|
| 561 |
+
"grad_norm": 5.792943193227984e-05,
|
| 562 |
+
"learning_rate": 6.499578947368422e-05,
|
| 563 |
+
"loss": 23.0,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.0015700957154503458,
|
| 568 |
+
"grad_norm": 4.383608029456809e-05,
|
| 569 |
+
"learning_rate": 6.446736842105264e-05,
|
| 570 |
+
"loss": 23.0,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.001590225147699709,
|
| 575 |
+
"grad_norm": 4.217608875478618e-05,
|
| 576 |
+
"learning_rate": 6.393894736842105e-05,
|
| 577 |
+
"loss": 23.0,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.0016103545799490725,
|
| 582 |
+
"grad_norm": 0.0001017999675241299,
|
| 583 |
+
"learning_rate": 6.341052631578947e-05,
|
| 584 |
+
"loss": 23.0,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.001630484012198436,
|
| 589 |
+
"grad_norm": 7.253052172018215e-05,
|
| 590 |
+
"learning_rate": 6.288210526315789e-05,
|
| 591 |
+
"loss": 23.0,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.0016506134444477993,
|
| 596 |
+
"grad_norm": 4.4168151362100616e-05,
|
| 597 |
+
"learning_rate": 6.235368421052632e-05,
|
| 598 |
+
"loss": 23.0,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.0016707428766971628,
|
| 603 |
+
"grad_norm": 4.690126297646202e-05,
|
| 604 |
+
"learning_rate": 6.182526315789474e-05,
|
| 605 |
+
"loss": 23.0,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.001690872308946526,
|
| 610 |
+
"grad_norm": 5.543129373108968e-05,
|
| 611 |
+
"learning_rate": 6.129684210526316e-05,
|
| 612 |
+
"loss": 23.0,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.0017110017411958896,
|
| 617 |
+
"grad_norm": 3.422376903472468e-05,
|
| 618 |
+
"learning_rate": 6.076842105263158e-05,
|
| 619 |
+
"loss": 23.0,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.001731131173445253,
|
| 624 |
+
"grad_norm": 0.00011534958321135491,
|
| 625 |
+
"learning_rate": 6.024e-05,
|
| 626 |
+
"loss": 23.0,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.0017512606056946164,
|
| 631 |
+
"grad_norm": 5.733649231842719e-05,
|
| 632 |
+
"learning_rate": 5.971157894736842e-05,
|
| 633 |
+
"loss": 23.0,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.0017713900379439798,
|
| 638 |
+
"grad_norm": 9.903619502438232e-05,
|
| 639 |
+
"learning_rate": 5.9183157894736835e-05,
|
| 640 |
+
"loss": 23.0,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.0017915194701933431,
|
| 645 |
+
"grad_norm": 7.510482100769877e-05,
|
| 646 |
+
"learning_rate": 5.8654736842105267e-05,
|
| 647 |
+
"loss": 23.0,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.0018116489024427066,
|
| 652 |
+
"grad_norm": 4.391166294226423e-05,
|
| 653 |
+
"learning_rate": 5.8126315789473684e-05,
|
| 654 |
+
"loss": 23.0,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.0018317783346920701,
|
| 659 |
+
"grad_norm": 0.00010185052815359086,
|
| 660 |
+
"learning_rate": 5.759789473684211e-05,
|
| 661 |
+
"loss": 23.0,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.0018519077669414334,
|
| 666 |
+
"grad_norm": 9.979342576116323e-05,
|
| 667 |
+
"learning_rate": 5.706947368421053e-05,
|
| 668 |
+
"loss": 23.0,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.001872037199190797,
|
| 673 |
+
"grad_norm": 9.317202056990936e-05,
|
| 674 |
+
"learning_rate": 5.6541052631578945e-05,
|
| 675 |
+
"loss": 23.0,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.0018921666314401602,
|
| 680 |
+
"grad_norm": 7.172553159762174e-05,
|
| 681 |
+
"learning_rate": 5.601263157894736e-05,
|
| 682 |
+
"loss": 23.0,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.0019122960636895237,
|
| 687 |
+
"grad_norm": 5.0452064897399396e-05,
|
| 688 |
+
"learning_rate": 5.5484210526315794e-05,
|
| 689 |
+
"loss": 23.0,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.001932425495938887,
|
| 694 |
+
"grad_norm": 0.00011866455315612257,
|
| 695 |
+
"learning_rate": 5.495578947368421e-05,
|
| 696 |
+
"loss": 23.0,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.0019525549281882504,
|
| 701 |
+
"grad_norm": 6.334228237392381e-05,
|
| 702 |
+
"learning_rate": 5.442736842105264e-05,
|
| 703 |
+
"loss": 23.0,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.001972684360437614,
|
| 708 |
+
"grad_norm": 6.854250386822969e-05,
|
| 709 |
+
"learning_rate": 5.3898947368421055e-05,
|
| 710 |
+
"loss": 23.0,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.0019928137926869772,
|
| 715 |
+
"grad_norm": 0.00011966691090492532,
|
| 716 |
+
"learning_rate": 5.337052631578947e-05,
|
| 717 |
+
"loss": 23.0,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.0020129432249363405,
|
| 722 |
+
"grad_norm": 9.832581417867914e-05,
|
| 723 |
+
"learning_rate": 5.284210526315789e-05,
|
| 724 |
+
"loss": 23.0,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.0020129432249363405,
|
| 729 |
+
"eval_loss": 11.5,
|
| 730 |
+
"eval_runtime": 286.0829,
|
| 731 |
+
"eval_samples_per_second": 73.119,
|
| 732 |
+
"eval_steps_per_second": 18.281,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 745 |
"early_stopping_threshold": 0.0
|
| 746 |
},
|
| 747 |
"attributes": {
|
| 748 |
+
"early_stopping_patience_counter": 1
|
| 749 |
}
|
| 750 |
},
|
| 751 |
"TrainerControl": {
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 4120303042560.0,
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|