Training in progress, step 75, 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 767856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08e8f236ddc10d222b452de6add8c677dadee23ccf4fc5bcb9ea3cf2ce3d9a63
|
| 3 |
size 767856
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1601338
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:547db67dff947af01503691e9c9cb4bb33f39e71f280016ee6de23e93b44192e
|
| 3 |
size 1601338
|
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 sha256:918745a6ed2ec5b68116d4c4abbbcd68f28310827cc74e2c6f42fa8fb9df5afa
|
| 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:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 9,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -405,6 +405,205 @@
|
|
| 405 |
"learning_rate": 5.868240888334653e-05,
|
| 406 |
"loss": 6.5004,
|
| 407 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 408 |
}
|
| 409 |
],
|
| 410 |
"logging_steps": 1,
|
|
@@ -424,7 +623,7 @@
|
|
| 424 |
"attributes": {}
|
| 425 |
}
|
| 426 |
},
|
| 427 |
-
"total_flos":
|
| 428 |
"train_batch_size": 8,
|
| 429 |
"trial_name": null,
|
| 430 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.19710906701708278,
|
| 5 |
"eval_steps": 9,
|
| 6 |
+
"global_step": 75,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 405 |
"learning_rate": 5.868240888334653e-05,
|
| 406 |
"loss": 6.5004,
|
| 407 |
"step": 50
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.1340341655716163,
|
| 411 |
+
"grad_norm": 2.622481107711792,
|
| 412 |
+
"learning_rate": 5.695865504800327e-05,
|
| 413 |
+
"loss": 6.5451,
|
| 414 |
+
"step": 51
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.1366622864651774,
|
| 418 |
+
"grad_norm": 3.3432939052581787,
|
| 419 |
+
"learning_rate": 5.522642316338268e-05,
|
| 420 |
+
"loss": 7.1003,
|
| 421 |
+
"step": 52
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.1392904073587385,
|
| 425 |
+
"grad_norm": 3.460822820663452,
|
| 426 |
+
"learning_rate": 5.348782368720626e-05,
|
| 427 |
+
"loss": 7.5412,
|
| 428 |
+
"step": 53
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.14191852825229961,
|
| 432 |
+
"grad_norm": 4.498050689697266,
|
| 433 |
+
"learning_rate": 5.174497483512506e-05,
|
| 434 |
+
"loss": 7.1544,
|
| 435 |
+
"step": 54
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.14191852825229961,
|
| 439 |
+
"eval_loss": 6.912955284118652,
|
| 440 |
+
"eval_runtime": 7.8343,
|
| 441 |
+
"eval_samples_per_second": 40.974,
|
| 442 |
+
"eval_steps_per_second": 5.233,
|
| 443 |
+
"step": 54
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.1445466491458607,
|
| 447 |
+
"grad_norm": 3.7371087074279785,
|
| 448 |
+
"learning_rate": 5e-05,
|
| 449 |
+
"loss": 6.9554,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.1471747700394218,
|
| 454 |
+
"grad_norm": 3.3637523651123047,
|
| 455 |
+
"learning_rate": 4.825502516487497e-05,
|
| 456 |
+
"loss": 6.8556,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.1498028909329829,
|
| 461 |
+
"grad_norm": 3.845339298248291,
|
| 462 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 463 |
+
"loss": 7.8125,
|
| 464 |
+
"step": 57
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.15243101182654403,
|
| 468 |
+
"grad_norm": 2.977215051651001,
|
| 469 |
+
"learning_rate": 4.477357683661734e-05,
|
| 470 |
+
"loss": 6.8587,
|
| 471 |
+
"step": 58
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.15505913272010513,
|
| 475 |
+
"grad_norm": 2.899541139602661,
|
| 476 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 477 |
+
"loss": 7.1409,
|
| 478 |
+
"step": 59
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.15768725361366623,
|
| 482 |
+
"grad_norm": 3.146878719329834,
|
| 483 |
+
"learning_rate": 4.131759111665349e-05,
|
| 484 |
+
"loss": 7.0631,
|
| 485 |
+
"step": 60
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.16031537450722733,
|
| 489 |
+
"grad_norm": 2.8929479122161865,
|
| 490 |
+
"learning_rate": 3.960441545911204e-05,
|
| 491 |
+
"loss": 6.9279,
|
| 492 |
+
"step": 61
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.16294349540078842,
|
| 496 |
+
"grad_norm": 3.5399699211120605,
|
| 497 |
+
"learning_rate": 3.790390522001662e-05,
|
| 498 |
+
"loss": 6.9131,
|
| 499 |
+
"step": 62
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.16557161629434955,
|
| 503 |
+
"grad_norm": 2.8847124576568604,
|
| 504 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 505 |
+
"loss": 6.5008,
|
| 506 |
+
"step": 63
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.16557161629434955,
|
| 510 |
+
"eval_loss": 6.859212398529053,
|
| 511 |
+
"eval_runtime": 7.823,
|
| 512 |
+
"eval_samples_per_second": 41.033,
|
| 513 |
+
"eval_steps_per_second": 5.241,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.16819973718791065,
|
| 518 |
+
"grad_norm": 3.6189582347869873,
|
| 519 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 520 |
+
"loss": 6.6061,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.17082785808147175,
|
| 525 |
+
"grad_norm": 4.201334476470947,
|
| 526 |
+
"learning_rate": 3.289899283371657e-05,
|
| 527 |
+
"loss": 7.1914,
|
| 528 |
+
"step": 65
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.17345597897503284,
|
| 532 |
+
"grad_norm": 4.052191257476807,
|
| 533 |
+
"learning_rate": 3.12696703292044e-05,
|
| 534 |
+
"loss": 6.8996,
|
| 535 |
+
"step": 66
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.17608409986859397,
|
| 539 |
+
"grad_norm": 2.797459125518799,
|
| 540 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 541 |
+
"loss": 7.1348,
|
| 542 |
+
"step": 67
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.17871222076215507,
|
| 546 |
+
"grad_norm": 3.1193556785583496,
|
| 547 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 548 |
+
"loss": 7.3041,
|
| 549 |
+
"step": 68
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.18134034165571616,
|
| 553 |
+
"grad_norm": 3.285179376602173,
|
| 554 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 555 |
+
"loss": 6.87,
|
| 556 |
+
"step": 69
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.18396846254927726,
|
| 560 |
+
"grad_norm": 3.520158052444458,
|
| 561 |
+
"learning_rate": 2.500000000000001e-05,
|
| 562 |
+
"loss": 6.8825,
|
| 563 |
+
"step": 70
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.18659658344283836,
|
| 567 |
+
"grad_norm": 3.528801918029785,
|
| 568 |
+
"learning_rate": 2.350403678833976e-05,
|
| 569 |
+
"loss": 6.9256,
|
| 570 |
+
"step": 71
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.18922470433639949,
|
| 574 |
+
"grad_norm": 3.827869415283203,
|
| 575 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 576 |
+
"loss": 6.7786,
|
| 577 |
+
"step": 72
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.18922470433639949,
|
| 581 |
+
"eval_loss": 6.8246331214904785,
|
| 582 |
+
"eval_runtime": 7.8447,
|
| 583 |
+
"eval_samples_per_second": 40.919,
|
| 584 |
+
"eval_steps_per_second": 5.226,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.19185282522996058,
|
| 589 |
+
"grad_norm": 4.021266937255859,
|
| 590 |
+
"learning_rate": 2.061073738537635e-05,
|
| 591 |
+
"loss": 6.4212,
|
| 592 |
+
"step": 73
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.19448094612352168,
|
| 596 |
+
"grad_norm": 3.4979543685913086,
|
| 597 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 598 |
+
"loss": 6.6614,
|
| 599 |
+
"step": 74
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.19710906701708278,
|
| 603 |
+
"grad_norm": 2.2178640365600586,
|
| 604 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 605 |
+
"loss": 7.0153,
|
| 606 |
+
"step": 75
|
| 607 |
}
|
| 608 |
],
|
| 609 |
"logging_steps": 1,
|
|
|
|
| 623 |
"attributes": {}
|
| 624 |
}
|
| 625 |
},
|
| 626 |
+
"total_flos": 35701618900992.0,
|
| 627 |
"train_batch_size": 8,
|
| 628 |
"trial_name": null,
|
| 629 |
"trial_params": null
|