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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c9c369232afcf88c994171f38016074d01563b66b24e5c97ff565499dfcb572
|
| 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 1342555602
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f7195a86d976834a21a0ae42718d7a0210b77cd590463fa28ded8ea39f251bc
|
| 3 |
size 1342555602
|
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 sha256:720beb628244d3e7e52a4ee594799e93166f635e750e5ed19a3aa03970c87a85
|
| 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 sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
|
| 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": 12.302,
|
| 374 |
"eval_steps_per_second": 6.154,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -401,7 +759,7 @@
|
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.1823816299438477,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.08547008547008547,
|
| 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": 12.302,
|
| 374 |
"eval_steps_per_second": 6.154,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.04358974358974359,
|
| 379 |
+
"grad_norm": 3.2061870098114014,
|
| 380 |
+
"learning_rate": 9.285836503510562e-05,
|
| 381 |
+
"loss": 1.4302,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.044444444444444446,
|
| 386 |
+
"grad_norm": 1.6502684354782104,
|
| 387 |
+
"learning_rate": 9.24024048078213e-05,
|
| 388 |
+
"loss": 1.3225,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.0452991452991453,
|
| 393 |
+
"grad_norm": 1.1041203737258911,
|
| 394 |
+
"learning_rate": 9.193352839727121e-05,
|
| 395 |
+
"loss": 1.2989,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.046153846153846156,
|
| 400 |
+
"grad_norm": 1.7463825941085815,
|
| 401 |
+
"learning_rate": 9.145187862775209e-05,
|
| 402 |
+
"loss": 1.2729,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.04700854700854701,
|
| 407 |
+
"grad_norm": 1.2780969142913818,
|
| 408 |
+
"learning_rate": 9.09576022144496e-05,
|
| 409 |
+
"loss": 1.3126,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.04786324786324787,
|
| 414 |
+
"grad_norm": 1.2614237070083618,
|
| 415 |
+
"learning_rate": 9.045084971874738e-05,
|
| 416 |
+
"loss": 1.1834,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.04871794871794872,
|
| 421 |
+
"grad_norm": 1.0077286958694458,
|
| 422 |
+
"learning_rate": 8.993177550236464e-05,
|
| 423 |
+
"loss": 1.2083,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.04957264957264957,
|
| 428 |
+
"grad_norm": 0.9977828860282898,
|
| 429 |
+
"learning_rate": 8.940053768033609e-05,
|
| 430 |
+
"loss": 1.1614,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.05042735042735043,
|
| 435 |
+
"grad_norm": 0.989231526851654,
|
| 436 |
+
"learning_rate": 8.885729807284856e-05,
|
| 437 |
+
"loss": 1.1232,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.05128205128205128,
|
| 442 |
+
"grad_norm": 1.0418609380722046,
|
| 443 |
+
"learning_rate": 8.83022221559489e-05,
|
| 444 |
+
"loss": 1.2087,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.05213675213675214,
|
| 449 |
+
"grad_norm": 1.0184895992279053,
|
| 450 |
+
"learning_rate": 8.773547901113862e-05,
|
| 451 |
+
"loss": 1.2046,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.05299145299145299,
|
| 456 |
+
"grad_norm": 1.0147963762283325,
|
| 457 |
+
"learning_rate": 8.715724127386972e-05,
|
| 458 |
+
"loss": 1.1872,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.05384615384615385,
|
| 463 |
+
"grad_norm": 0.9887883067131042,
|
| 464 |
+
"learning_rate": 8.656768508095853e-05,
|
| 465 |
+
"loss": 1.1729,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.0547008547008547,
|
| 470 |
+
"grad_norm": 1.005417823791504,
|
| 471 |
+
"learning_rate": 8.596699001693255e-05,
|
| 472 |
+
"loss": 1.0677,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.05555555555555555,
|
| 477 |
+
"grad_norm": 0.9510125517845154,
|
| 478 |
+
"learning_rate": 8.535533905932738e-05,
|
| 479 |
+
"loss": 1.1557,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.05641025641025641,
|
| 484 |
+
"grad_norm": 0.9024305939674377,
|
| 485 |
+
"learning_rate": 8.473291852294987e-05,
|
| 486 |
+
"loss": 1.0331,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.05726495726495726,
|
| 491 |
+
"grad_norm": 1.053831934928894,
|
| 492 |
+
"learning_rate": 8.409991800312493e-05,
|
| 493 |
+
"loss": 1.161,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.05811965811965812,
|
| 498 |
+
"grad_norm": 0.9654093384742737,
|
| 499 |
+
"learning_rate": 8.345653031794292e-05,
|
| 500 |
+
"loss": 1.1771,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.05897435897435897,
|
| 505 |
+
"grad_norm": 1.001448631286621,
|
| 506 |
+
"learning_rate": 8.280295144952536e-05,
|
| 507 |
+
"loss": 1.1254,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.05982905982905983,
|
| 512 |
+
"grad_norm": 0.9279631972312927,
|
| 513 |
+
"learning_rate": 8.213938048432697e-05,
|
| 514 |
+
"loss": 1.0771,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.06068376068376068,
|
| 519 |
+
"grad_norm": 1.0175575017929077,
|
| 520 |
+
"learning_rate": 8.146601955249188e-05,
|
| 521 |
+
"loss": 1.0616,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.06153846153846154,
|
| 526 |
+
"grad_norm": 0.9312410354614258,
|
| 527 |
+
"learning_rate": 8.07830737662829e-05,
|
| 528 |
+
"loss": 1.0046,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.062393162393162394,
|
| 533 |
+
"grad_norm": 0.9600768089294434,
|
| 534 |
+
"learning_rate": 8.009075115760243e-05,
|
| 535 |
+
"loss": 1.0878,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.06324786324786325,
|
| 540 |
+
"grad_norm": 1.008412480354309,
|
| 541 |
+
"learning_rate": 7.938926261462366e-05,
|
| 542 |
+
"loss": 1.069,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.0641025641025641,
|
| 547 |
+
"grad_norm": 1.0578328371047974,
|
| 548 |
+
"learning_rate": 7.86788218175523e-05,
|
| 549 |
+
"loss": 1.0534,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.06495726495726496,
|
| 554 |
+
"grad_norm": 1.8800052404403687,
|
| 555 |
+
"learning_rate": 7.795964517353735e-05,
|
| 556 |
+
"loss": 1.3345,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.06581196581196581,
|
| 561 |
+
"grad_norm": 1.4857513904571533,
|
| 562 |
+
"learning_rate": 7.723195175075136e-05,
|
| 563 |
+
"loss": 1.2275,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.06666666666666667,
|
| 568 |
+
"grad_norm": 1.3094754219055176,
|
| 569 |
+
"learning_rate": 7.649596321166024e-05,
|
| 570 |
+
"loss": 1.2407,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.06752136752136752,
|
| 575 |
+
"grad_norm": 1.5381840467453003,
|
| 576 |
+
"learning_rate": 7.575190374550272e-05,
|
| 577 |
+
"loss": 1.3354,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.06837606837606838,
|
| 582 |
+
"grad_norm": 1.3986117839813232,
|
| 583 |
+
"learning_rate": 7.500000000000001e-05,
|
| 584 |
+
"loss": 1.1581,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.06923076923076923,
|
| 589 |
+
"grad_norm": 1.3145384788513184,
|
| 590 |
+
"learning_rate": 7.424048101231686e-05,
|
| 591 |
+
"loss": 1.121,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.07008547008547009,
|
| 596 |
+
"grad_norm": 1.4473127126693726,
|
| 597 |
+
"learning_rate": 7.347357813929454e-05,
|
| 598 |
+
"loss": 1.2764,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.07094017094017094,
|
| 603 |
+
"grad_norm": 1.4527322053909302,
|
| 604 |
+
"learning_rate": 7.269952498697734e-05,
|
| 605 |
+
"loss": 1.1666,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.07179487179487179,
|
| 610 |
+
"grad_norm": 1.3364454507827759,
|
| 611 |
+
"learning_rate": 7.191855733945387e-05,
|
| 612 |
+
"loss": 1.0724,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.07264957264957266,
|
| 617 |
+
"grad_norm": 1.418134093284607,
|
| 618 |
+
"learning_rate": 7.113091308703498e-05,
|
| 619 |
+
"loss": 1.1684,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.0735042735042735,
|
| 624 |
+
"grad_norm": 1.3991276025772095,
|
| 625 |
+
"learning_rate": 7.033683215379002e-05,
|
| 626 |
+
"loss": 1.1841,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.07435897435897436,
|
| 631 |
+
"grad_norm": 1.4230297803878784,
|
| 632 |
+
"learning_rate": 6.953655642446368e-05,
|
| 633 |
+
"loss": 1.1781,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.07521367521367521,
|
| 638 |
+
"grad_norm": 1.3617968559265137,
|
| 639 |
+
"learning_rate": 6.873032967079561e-05,
|
| 640 |
+
"loss": 1.1224,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.07606837606837606,
|
| 645 |
+
"grad_norm": 1.374157428741455,
|
| 646 |
+
"learning_rate": 6.7918397477265e-05,
|
| 647 |
+
"loss": 1.099,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.07692307692307693,
|
| 652 |
+
"grad_norm": 1.4025551080703735,
|
| 653 |
+
"learning_rate": 6.710100716628344e-05,
|
| 654 |
+
"loss": 1.2434,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.07777777777777778,
|
| 659 |
+
"grad_norm": 1.4835059642791748,
|
| 660 |
+
"learning_rate": 6.627840772285784e-05,
|
| 661 |
+
"loss": 1.2055,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.07863247863247863,
|
| 666 |
+
"grad_norm": 1.4067541360855103,
|
| 667 |
+
"learning_rate": 6.545084971874738e-05,
|
| 668 |
+
"loss": 1.202,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.07948717948717948,
|
| 673 |
+
"grad_norm": 1.3524061441421509,
|
| 674 |
+
"learning_rate": 6.461858523613684e-05,
|
| 675 |
+
"loss": 1.2138,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.08034188034188035,
|
| 680 |
+
"grad_norm": 1.4857449531555176,
|
| 681 |
+
"learning_rate": 6.378186779084995e-05,
|
| 682 |
+
"loss": 1.172,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.0811965811965812,
|
| 687 |
+
"grad_norm": 1.5069938898086548,
|
| 688 |
+
"learning_rate": 6.294095225512603e-05,
|
| 689 |
+
"loss": 1.1011,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.08205128205128205,
|
| 694 |
+
"grad_norm": 1.3394262790679932,
|
| 695 |
+
"learning_rate": 6.209609477998338e-05,
|
| 696 |
+
"loss": 1.0926,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.0829059829059829,
|
| 701 |
+
"grad_norm": 1.3197392225265503,
|
| 702 |
+
"learning_rate": 6.124755271719325e-05,
|
| 703 |
+
"loss": 1.1411,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.08376068376068375,
|
| 708 |
+
"grad_norm": 1.3767728805541992,
|
| 709 |
+
"learning_rate": 6.0395584540887963e-05,
|
| 710 |
+
"loss": 1.1834,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.08461538461538462,
|
| 715 |
+
"grad_norm": 1.352771520614624,
|
| 716 |
+
"learning_rate": 5.9540449768827246e-05,
|
| 717 |
+
"loss": 1.0231,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.08547008547008547,
|
| 722 |
+
"grad_norm": 1.4974371194839478,
|
| 723 |
+
"learning_rate": 5.868240888334653e-05,
|
| 724 |
+
"loss": 1.0963,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.08547008547008547,
|
| 729 |
+
"eval_loss": 1.1823816299438477,
|
| 730 |
+
"eval_runtime": 160.2027,
|
| 731 |
+
"eval_samples_per_second": 12.303,
|
| 732 |
+
"eval_steps_per_second": 6.155,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 1.508513578745856e+17,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|