Training in progress, step 90, 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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c660385d6439f2cd1581de9800d768a0a284dd447b152e5b6977566ce9e48ab7
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e241ec47be04250fdac190488e678f4df59217a13e8339ad6068a6100f3b16d
|
| 3 |
size 341314196
|
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 sha256:736357e081c134dab8a78c3d9516592c805f8c9e3877b443e8a1c64b81e67753
|
| 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 sha256:1969755bc21fc7060aa3a0aac2955c1e49faa350215ac29549a54ef247148d87
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.6604854464530945,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
-
"epoch":
|
| 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 +373,286 @@
|
|
| 373 |
"eval_samples_per_second": 8.725,
|
| 374 |
"eval_steps_per_second": 2.181,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -396,12 +676,12 @@
|
|
| 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": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.6604854464530945,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 1.0027855153203342,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 90,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 373 |
"eval_samples_per_second": 8.725,
|
| 374 |
"eval_steps_per_second": 2.181,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.5682451253481894,
|
| 379 |
+
"grad_norm": 0.8395673632621765,
|
| 380 |
+
"learning_rate": 4.8037009212046586e-05,
|
| 381 |
+
"loss": 0.5995,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.5793871866295265,
|
| 386 |
+
"grad_norm": 1.080180287361145,
|
| 387 |
+
"learning_rate": 4.607704521360776e-05,
|
| 388 |
+
"loss": 0.687,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.5905292479108635,
|
| 393 |
+
"grad_norm": 1.0408283472061157,
|
| 394 |
+
"learning_rate": 4.412313012710813e-05,
|
| 395 |
+
"loss": 0.6857,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.6016713091922006,
|
| 400 |
+
"grad_norm": 1.0837056636810303,
|
| 401 |
+
"learning_rate": 4.2178276747988446e-05,
|
| 402 |
+
"loss": 0.7375,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.6128133704735376,
|
| 407 |
+
"grad_norm": 1.1068450212478638,
|
| 408 |
+
"learning_rate": 4.0245483899193595e-05,
|
| 409 |
+
"loss": 0.6629,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.6239554317548747,
|
| 414 |
+
"grad_norm": 0.9491481184959412,
|
| 415 |
+
"learning_rate": 3.832773180720475e-05,
|
| 416 |
+
"loss": 0.6415,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.6350974930362117,
|
| 421 |
+
"grad_norm": 0.9771397709846497,
|
| 422 |
+
"learning_rate": 3.642797750674629e-05,
|
| 423 |
+
"loss": 0.6092,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.6462395543175488,
|
| 428 |
+
"grad_norm": 0.9483528733253479,
|
| 429 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 430 |
+
"loss": 0.6702,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.6573816155988857,
|
| 435 |
+
"grad_norm": 1.1656486988067627,
|
| 436 |
+
"learning_rate": 3.2694147146125345e-05,
|
| 437 |
+
"loss": 0.7169,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.6685236768802229,
|
| 442 |
+
"grad_norm": 1.362808346748352,
|
| 443 |
+
"learning_rate": 3.086582838174551e-05,
|
| 444 |
+
"loss": 0.7768,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.6796657381615598,
|
| 449 |
+
"grad_norm": 1.020258903503418,
|
| 450 |
+
"learning_rate": 2.9067013123128613e-05,
|
| 451 |
+
"loss": 0.6284,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.6908077994428969,
|
| 456 |
+
"grad_norm": 1.527144432067871,
|
| 457 |
+
"learning_rate": 2.7300475013022663e-05,
|
| 458 |
+
"loss": 0.5853,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.7019498607242339,
|
| 463 |
+
"grad_norm": 1.3415321111679077,
|
| 464 |
+
"learning_rate": 2.556893792515227e-05,
|
| 465 |
+
"loss": 0.5872,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.713091922005571,
|
| 470 |
+
"grad_norm": 1.19660484790802,
|
| 471 |
+
"learning_rate": 2.3875071764202563e-05,
|
| 472 |
+
"loss": 0.5428,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.724233983286908,
|
| 477 |
+
"grad_norm": 1.7170783281326294,
|
| 478 |
+
"learning_rate": 2.2221488349019903e-05,
|
| 479 |
+
"loss": 0.604,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.7353760445682451,
|
| 484 |
+
"grad_norm": 1.8448792695999146,
|
| 485 |
+
"learning_rate": 2.061073738537635e-05,
|
| 486 |
+
"loss": 0.6284,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.7465181058495822,
|
| 491 |
+
"grad_norm": 0.6753265261650085,
|
| 492 |
+
"learning_rate": 1.9045302534508297e-05,
|
| 493 |
+
"loss": 0.6319,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.7576601671309192,
|
| 498 |
+
"grad_norm": 0.8194894790649414,
|
| 499 |
+
"learning_rate": 1.7527597583490822e-05,
|
| 500 |
+
"loss": 0.5969,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.7688022284122563,
|
| 505 |
+
"grad_norm": 0.8043373227119446,
|
| 506 |
+
"learning_rate": 1.605996272335291e-05,
|
| 507 |
+
"loss": 0.6543,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.7799442896935933,
|
| 512 |
+
"grad_norm": 0.9129596948623657,
|
| 513 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 514 |
+
"loss": 0.7098,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.7910863509749304,
|
| 519 |
+
"grad_norm": 0.8895006775856018,
|
| 520 |
+
"learning_rate": 1.3283874528215733e-05,
|
| 521 |
+
"loss": 0.5837,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.8022284122562674,
|
| 526 |
+
"grad_norm": 0.7797386646270752,
|
| 527 |
+
"learning_rate": 1.1979701719998453e-05,
|
| 528 |
+
"loss": 0.6462,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.8133704735376045,
|
| 533 |
+
"grad_norm": 1.0365535020828247,
|
| 534 |
+
"learning_rate": 1.0734153455962765e-05,
|
| 535 |
+
"loss": 0.7263,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.8245125348189415,
|
| 540 |
+
"grad_norm": 0.8929746747016907,
|
| 541 |
+
"learning_rate": 9.549150281252633e-06,
|
| 542 |
+
"loss": 0.5768,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.8356545961002786,
|
| 547 |
+
"grad_norm": 0.9315441250801086,
|
| 548 |
+
"learning_rate": 8.426519384872733e-06,
|
| 549 |
+
"loss": 0.6044,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.8467966573816156,
|
| 554 |
+
"grad_norm": 0.9474170804023743,
|
| 555 |
+
"learning_rate": 7.367991782295391e-06,
|
| 556 |
+
"loss": 0.6207,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.8579387186629527,
|
| 561 |
+
"grad_norm": 1.0279390811920166,
|
| 562 |
+
"learning_rate": 6.375199646360142e-06,
|
| 563 |
+
"loss": 0.6206,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.8690807799442897,
|
| 568 |
+
"grad_norm": 1.0129948854446411,
|
| 569 |
+
"learning_rate": 5.449673790581611e-06,
|
| 570 |
+
"loss": 0.6151,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.8802228412256268,
|
| 575 |
+
"grad_norm": 0.9171512126922607,
|
| 576 |
+
"learning_rate": 4.592841308745932e-06,
|
| 577 |
+
"loss": 0.6025,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.8913649025069638,
|
| 582 |
+
"grad_norm": 1.0913035869598389,
|
| 583 |
+
"learning_rate": 3.8060233744356633e-06,
|
| 584 |
+
"loss": 0.7344,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.9025069637883009,
|
| 589 |
+
"grad_norm": 1.4194581508636475,
|
| 590 |
+
"learning_rate": 3.0904332038757977e-06,
|
| 591 |
+
"loss": 0.7239,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.9136490250696379,
|
| 596 |
+
"grad_norm": 1.1939295530319214,
|
| 597 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 598 |
+
"loss": 0.636,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.924791086350975,
|
| 603 |
+
"grad_norm": 1.0078566074371338,
|
| 604 |
+
"learning_rate": 1.8772381773176417e-06,
|
| 605 |
+
"loss": 0.5,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.935933147632312,
|
| 610 |
+
"grad_norm": 1.0714085102081299,
|
| 611 |
+
"learning_rate": 1.3815039801161721e-06,
|
| 612 |
+
"loss": 0.4576,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.947075208913649,
|
| 617 |
+
"grad_norm": 1.0616954565048218,
|
| 618 |
+
"learning_rate": 9.607359798384785e-07,
|
| 619 |
+
"loss": 0.4891,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.958217270194986,
|
| 624 |
+
"grad_norm": 1.1367872953414917,
|
| 625 |
+
"learning_rate": 6.15582970243117e-07,
|
| 626 |
+
"loss": 0.589,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.9693593314763231,
|
| 631 |
+
"grad_norm": 1.2933335304260254,
|
| 632 |
+
"learning_rate": 3.465771522536854e-07,
|
| 633 |
+
"loss": 0.5224,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.9805013927576601,
|
| 638 |
+
"grad_norm": 1.6042691469192505,
|
| 639 |
+
"learning_rate": 1.5413331334360182e-07,
|
| 640 |
+
"loss": 0.5322,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.9916434540389972,
|
| 645 |
+
"grad_norm": 0.7805180549621582,
|
| 646 |
+
"learning_rate": 3.8548187963854956e-08,
|
| 647 |
+
"loss": 0.6384,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.0027855153203342,
|
| 652 |
+
"grad_norm": 1.1597189903259277,
|
| 653 |
+
"learning_rate": 0.0,
|
| 654 |
+
"loss": 0.7541,
|
| 655 |
+
"step": 90
|
| 656 |
}
|
| 657 |
],
|
| 658 |
"logging_steps": 1,
|
|
|
|
| 676 |
"should_evaluate": false,
|
| 677 |
"should_log": false,
|
| 678 |
"should_save": true,
|
| 679 |
+
"should_training_stop": true
|
| 680 |
},
|
| 681 |
"attributes": {}
|
| 682 |
}
|
| 683 |
},
|
| 684 |
+
"total_flos": 1.3576622208712704e+17,
|
| 685 |
"train_batch_size": 8,
|
| 686 |
"trial_name": null,
|
| 687 |
"trial_params": null
|