Training in progress, step 48000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8892045571a3d278c702547003643aa319e2898ce1daf1234d43784f70c642a0
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:361bbad0917e897be4b09c5130ad996566c0cdf177169848320c732f7678395a
|
| 3 |
size 1082379659
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f66e48699b199955664d97c152eda4d498658e8c242bfacea1b8e34bd9e4220b
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:989a59d2631ca368f80e57fef1957ec417fc83d6e6ffb3385f9e62ca59210c21
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3440,6 +3440,318 @@
|
|
| 3440 |
"eval_samples_per_second": 37.892,
|
| 3441 |
"eval_steps_per_second": 9.473,
|
| 3442 |
"step": 44000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3443 |
}
|
| 3444 |
],
|
| 3445 |
"logging_steps": 100,
|
|
@@ -3459,7 +3771,7 @@
|
|
| 3459 |
"attributes": {}
|
| 3460 |
}
|
| 3461 |
},
|
| 3462 |
-
"total_flos": 1.
|
| 3463 |
"train_batch_size": 22,
|
| 3464 |
"trial_name": null,
|
| 3465 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6233766233766234,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 48000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3440 |
"eval_samples_per_second": 37.892,
|
| 3441 |
"eval_steps_per_second": 9.473,
|
| 3442 |
"step": 44000
|
| 3443 |
+
},
|
| 3444 |
+
{
|
| 3445 |
+
"epoch": 0.5727272727272728,
|
| 3446 |
+
"grad_norm": 0.2565126419067383,
|
| 3447 |
+
"learning_rate": 0.0006617711426628536,
|
| 3448 |
+
"loss": 2.7398,
|
| 3449 |
+
"step": 44100
|
| 3450 |
+
},
|
| 3451 |
+
{
|
| 3452 |
+
"epoch": 0.574025974025974,
|
| 3453 |
+
"grad_norm": 0.22110450267791748,
|
| 3454 |
+
"learning_rate": 0.0006604062599708158,
|
| 3455 |
+
"loss": 2.7204,
|
| 3456 |
+
"step": 44200
|
| 3457 |
+
},
|
| 3458 |
+
{
|
| 3459 |
+
"epoch": 0.5753246753246753,
|
| 3460 |
+
"grad_norm": 0.2212057262659073,
|
| 3461 |
+
"learning_rate": 0.0006590400435537894,
|
| 3462 |
+
"loss": 2.7467,
|
| 3463 |
+
"step": 44300
|
| 3464 |
+
},
|
| 3465 |
+
{
|
| 3466 |
+
"epoch": 0.5766233766233766,
|
| 3467 |
+
"grad_norm": 0.24286267161369324,
|
| 3468 |
+
"learning_rate": 0.0006576725047714116,
|
| 3469 |
+
"loss": 2.7193,
|
| 3470 |
+
"step": 44400
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 0.577922077922078,
|
| 3474 |
+
"grad_norm": 0.23778927326202393,
|
| 3475 |
+
"learning_rate": 0.0006563036549943152,
|
| 3476 |
+
"loss": 2.7388,
|
| 3477 |
+
"step": 44500
|
| 3478 |
+
},
|
| 3479 |
+
{
|
| 3480 |
+
"epoch": 0.5792207792207792,
|
| 3481 |
+
"grad_norm": 0.22259333729743958,
|
| 3482 |
+
"learning_rate": 0.000654933505604033,
|
| 3483 |
+
"loss": 2.7296,
|
| 3484 |
+
"step": 44600
|
| 3485 |
+
},
|
| 3486 |
+
{
|
| 3487 |
+
"epoch": 0.5805194805194805,
|
| 3488 |
+
"grad_norm": 0.23351649940013885,
|
| 3489 |
+
"learning_rate": 0.0006535620679929045,
|
| 3490 |
+
"loss": 2.753,
|
| 3491 |
+
"step": 44700
|
| 3492 |
+
},
|
| 3493 |
+
{
|
| 3494 |
+
"epoch": 0.5818181818181818,
|
| 3495 |
+
"grad_norm": 0.22059041261672974,
|
| 3496 |
+
"learning_rate": 0.0006521893535639792,
|
| 3497 |
+
"loss": 2.7281,
|
| 3498 |
+
"step": 44800
|
| 3499 |
+
},
|
| 3500 |
+
{
|
| 3501 |
+
"epoch": 0.5831168831168831,
|
| 3502 |
+
"grad_norm": 0.23977316915988922,
|
| 3503 |
+
"learning_rate": 0.0006508153737309235,
|
| 3504 |
+
"loss": 2.7003,
|
| 3505 |
+
"step": 44900
|
| 3506 |
+
},
|
| 3507 |
+
{
|
| 3508 |
+
"epoch": 0.5844155844155844,
|
| 3509 |
+
"grad_norm": 0.25528889894485474,
|
| 3510 |
+
"learning_rate": 0.0006494401399179255,
|
| 3511 |
+
"loss": 2.7206,
|
| 3512 |
+
"step": 45000
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 0.5844155844155844,
|
| 3516 |
+
"eval_loss": 3.1150028705596924,
|
| 3517 |
+
"eval_runtime": 16.5286,
|
| 3518 |
+
"eval_samples_per_second": 34.849,
|
| 3519 |
+
"eval_steps_per_second": 8.712,
|
| 3520 |
+
"step": 45000
|
| 3521 |
+
},
|
| 3522 |
+
{
|
| 3523 |
+
"epoch": 0.5857142857142857,
|
| 3524 |
+
"grad_norm": 0.24675515294075012,
|
| 3525 |
+
"learning_rate": 0.0006480636635595993,
|
| 3526 |
+
"loss": 2.7617,
|
| 3527 |
+
"step": 45100
|
| 3528 |
+
},
|
| 3529 |
+
{
|
| 3530 |
+
"epoch": 0.587012987012987,
|
| 3531 |
+
"grad_norm": 0.23121733963489532,
|
| 3532 |
+
"learning_rate": 0.0006466859561008905,
|
| 3533 |
+
"loss": 2.721,
|
| 3534 |
+
"step": 45200
|
| 3535 |
+
},
|
| 3536 |
+
{
|
| 3537 |
+
"epoch": 0.5883116883116883,
|
| 3538 |
+
"grad_norm": 0.24000558257102966,
|
| 3539 |
+
"learning_rate": 0.0006453070289969807,
|
| 3540 |
+
"loss": 2.7091,
|
| 3541 |
+
"step": 45300
|
| 3542 |
+
},
|
| 3543 |
+
{
|
| 3544 |
+
"epoch": 0.5896103896103896,
|
| 3545 |
+
"grad_norm": 0.22867269814014435,
|
| 3546 |
+
"learning_rate": 0.0006439268937131929,
|
| 3547 |
+
"loss": 2.7395,
|
| 3548 |
+
"step": 45400
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 0.5909090909090909,
|
| 3552 |
+
"grad_norm": 0.23441274464130402,
|
| 3553 |
+
"learning_rate": 0.0006425455617248952,
|
| 3554 |
+
"loss": 2.7507,
|
| 3555 |
+
"step": 45500
|
| 3556 |
+
},
|
| 3557 |
+
{
|
| 3558 |
+
"epoch": 0.5922077922077922,
|
| 3559 |
+
"grad_norm": 0.22815178334712982,
|
| 3560 |
+
"learning_rate": 0.0006411630445174063,
|
| 3561 |
+
"loss": 2.7257,
|
| 3562 |
+
"step": 45600
|
| 3563 |
+
},
|
| 3564 |
+
{
|
| 3565 |
+
"epoch": 0.5935064935064935,
|
| 3566 |
+
"grad_norm": 0.22590583562850952,
|
| 3567 |
+
"learning_rate": 0.0006397793535858992,
|
| 3568 |
+
"loss": 2.7303,
|
| 3569 |
+
"step": 45700
|
| 3570 |
+
},
|
| 3571 |
+
{
|
| 3572 |
+
"epoch": 0.5948051948051948,
|
| 3573 |
+
"grad_norm": 0.2853323221206665,
|
| 3574 |
+
"learning_rate": 0.0006383945004353064,
|
| 3575 |
+
"loss": 2.7414,
|
| 3576 |
+
"step": 45800
|
| 3577 |
+
},
|
| 3578 |
+
{
|
| 3579 |
+
"epoch": 0.5961038961038961,
|
| 3580 |
+
"grad_norm": 0.2671266794204712,
|
| 3581 |
+
"learning_rate": 0.000637008496580224,
|
| 3582 |
+
"loss": 2.7558,
|
| 3583 |
+
"step": 45900
|
| 3584 |
+
},
|
| 3585 |
+
{
|
| 3586 |
+
"epoch": 0.5974025974025974,
|
| 3587 |
+
"grad_norm": 0.23534780740737915,
|
| 3588 |
+
"learning_rate": 0.0006356213535448151,
|
| 3589 |
+
"loss": 2.7498,
|
| 3590 |
+
"step": 46000
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 0.5974025974025974,
|
| 3594 |
+
"eval_loss": 3.1098833084106445,
|
| 3595 |
+
"eval_runtime": 14.8476,
|
| 3596 |
+
"eval_samples_per_second": 38.794,
|
| 3597 |
+
"eval_steps_per_second": 9.699,
|
| 3598 |
+
"step": 46000
|
| 3599 |
+
},
|
| 3600 |
+
{
|
| 3601 |
+
"epoch": 0.5987012987012987,
|
| 3602 |
+
"grad_norm": 0.25292590260505676,
|
| 3603 |
+
"learning_rate": 0.0006342330828627155,
|
| 3604 |
+
"loss": 2.7116,
|
| 3605 |
+
"step": 46100
|
| 3606 |
+
},
|
| 3607 |
+
{
|
| 3608 |
+
"epoch": 0.6,
|
| 3609 |
+
"grad_norm": 0.24926777184009552,
|
| 3610 |
+
"learning_rate": 0.0006328436960769364,
|
| 3611 |
+
"loss": 2.694,
|
| 3612 |
+
"step": 46200
|
| 3613 |
+
},
|
| 3614 |
+
{
|
| 3615 |
+
"epoch": 0.6012987012987013,
|
| 3616 |
+
"grad_norm": 0.22545288503170013,
|
| 3617 |
+
"learning_rate": 0.0006314532047397697,
|
| 3618 |
+
"loss": 2.7382,
|
| 3619 |
+
"step": 46300
|
| 3620 |
+
},
|
| 3621 |
+
{
|
| 3622 |
+
"epoch": 0.6025974025974026,
|
| 3623 |
+
"grad_norm": 0.24442555010318756,
|
| 3624 |
+
"learning_rate": 0.0006300616204126905,
|
| 3625 |
+
"loss": 2.7408,
|
| 3626 |
+
"step": 46400
|
| 3627 |
+
},
|
| 3628 |
+
{
|
| 3629 |
+
"epoch": 0.6038961038961039,
|
| 3630 |
+
"grad_norm": 0.2365717589855194,
|
| 3631 |
+
"learning_rate": 0.0006286689546662625,
|
| 3632 |
+
"loss": 2.7386,
|
| 3633 |
+
"step": 46500
|
| 3634 |
+
},
|
| 3635 |
+
{
|
| 3636 |
+
"epoch": 0.6051948051948052,
|
| 3637 |
+
"grad_norm": 0.26666414737701416,
|
| 3638 |
+
"learning_rate": 0.0006272752190800404,
|
| 3639 |
+
"loss": 2.7408,
|
| 3640 |
+
"step": 46600
|
| 3641 |
+
},
|
| 3642 |
+
{
|
| 3643 |
+
"epoch": 0.6064935064935065,
|
| 3644 |
+
"grad_norm": 0.2522192597389221,
|
| 3645 |
+
"learning_rate": 0.0006258804252424745,
|
| 3646 |
+
"loss": 2.7487,
|
| 3647 |
+
"step": 46700
|
| 3648 |
+
},
|
| 3649 |
+
{
|
| 3650 |
+
"epoch": 0.6077922077922078,
|
| 3651 |
+
"grad_norm": 0.32666802406311035,
|
| 3652 |
+
"learning_rate": 0.0006244845847508144,
|
| 3653 |
+
"loss": 2.7319,
|
| 3654 |
+
"step": 46800
|
| 3655 |
+
},
|
| 3656 |
+
{
|
| 3657 |
+
"epoch": 0.6090909090909091,
|
| 3658 |
+
"grad_norm": 0.2485225796699524,
|
| 3659 |
+
"learning_rate": 0.0006230877092110119,
|
| 3660 |
+
"loss": 2.7767,
|
| 3661 |
+
"step": 46900
|
| 3662 |
+
},
|
| 3663 |
+
{
|
| 3664 |
+
"epoch": 0.6103896103896104,
|
| 3665 |
+
"grad_norm": 0.28847283124923706,
|
| 3666 |
+
"learning_rate": 0.0006216898102376251,
|
| 3667 |
+
"loss": 2.7883,
|
| 3668 |
+
"step": 47000
|
| 3669 |
+
},
|
| 3670 |
+
{
|
| 3671 |
+
"epoch": 0.6103896103896104,
|
| 3672 |
+
"eval_loss": 3.108853340148926,
|
| 3673 |
+
"eval_runtime": 15.0323,
|
| 3674 |
+
"eval_samples_per_second": 38.317,
|
| 3675 |
+
"eval_steps_per_second": 9.579,
|
| 3676 |
+
"step": 47000
|
| 3677 |
+
},
|
| 3678 |
+
{
|
| 3679 |
+
"epoch": 0.6116883116883117,
|
| 3680 |
+
"grad_norm": 0.2481118142604828,
|
| 3681 |
+
"learning_rate": 0.0006202908994537215,
|
| 3682 |
+
"loss": 2.7383,
|
| 3683 |
+
"step": 47100
|
| 3684 |
+
},
|
| 3685 |
+
{
|
| 3686 |
+
"epoch": 0.612987012987013,
|
| 3687 |
+
"grad_norm": 0.2495453953742981,
|
| 3688 |
+
"learning_rate": 0.0006188909884907814,
|
| 3689 |
+
"loss": 2.7935,
|
| 3690 |
+
"step": 47200
|
| 3691 |
+
},
|
| 3692 |
+
{
|
| 3693 |
+
"epoch": 0.6142857142857143,
|
| 3694 |
+
"grad_norm": 0.257658451795578,
|
| 3695 |
+
"learning_rate": 0.0006174900889886015,
|
| 3696 |
+
"loss": 2.7703,
|
| 3697 |
+
"step": 47300
|
| 3698 |
+
},
|
| 3699 |
+
{
|
| 3700 |
+
"epoch": 0.6155844155844156,
|
| 3701 |
+
"grad_norm": 0.23015721142292023,
|
| 3702 |
+
"learning_rate": 0.0006160882125951977,
|
| 3703 |
+
"loss": 2.7421,
|
| 3704 |
+
"step": 47400
|
| 3705 |
+
},
|
| 3706 |
+
{
|
| 3707 |
+
"epoch": 0.6168831168831169,
|
| 3708 |
+
"grad_norm": 0.2232840657234192,
|
| 3709 |
+
"learning_rate": 0.0006146853709667086,
|
| 3710 |
+
"loss": 2.7372,
|
| 3711 |
+
"step": 47500
|
| 3712 |
+
},
|
| 3713 |
+
{
|
| 3714 |
+
"epoch": 0.6181818181818182,
|
| 3715 |
+
"grad_norm": 0.24996255338191986,
|
| 3716 |
+
"learning_rate": 0.0006132815757672979,
|
| 3717 |
+
"loss": 2.7654,
|
| 3718 |
+
"step": 47600
|
| 3719 |
+
},
|
| 3720 |
+
{
|
| 3721 |
+
"epoch": 0.6194805194805195,
|
| 3722 |
+
"grad_norm": 0.2613258361816406,
|
| 3723 |
+
"learning_rate": 0.0006118768386690587,
|
| 3724 |
+
"loss": 2.7143,
|
| 3725 |
+
"step": 47700
|
| 3726 |
+
},
|
| 3727 |
+
{
|
| 3728 |
+
"epoch": 0.6207792207792208,
|
| 3729 |
+
"grad_norm": 0.2545129656791687,
|
| 3730 |
+
"learning_rate": 0.0006104711713519152,
|
| 3731 |
+
"loss": 2.7443,
|
| 3732 |
+
"step": 47800
|
| 3733 |
+
},
|
| 3734 |
+
{
|
| 3735 |
+
"epoch": 0.6220779220779221,
|
| 3736 |
+
"grad_norm": 0.24030067026615143,
|
| 3737 |
+
"learning_rate": 0.000609064585503526,
|
| 3738 |
+
"loss": 2.7386,
|
| 3739 |
+
"step": 47900
|
| 3740 |
+
},
|
| 3741 |
+
{
|
| 3742 |
+
"epoch": 0.6233766233766234,
|
| 3743 |
+
"grad_norm": 0.23413017392158508,
|
| 3744 |
+
"learning_rate": 0.0006076570928191872,
|
| 3745 |
+
"loss": 2.7276,
|
| 3746 |
+
"step": 48000
|
| 3747 |
+
},
|
| 3748 |
+
{
|
| 3749 |
+
"epoch": 0.6233766233766234,
|
| 3750 |
+
"eval_loss": 3.097559690475464,
|
| 3751 |
+
"eval_runtime": 15.7054,
|
| 3752 |
+
"eval_samples_per_second": 36.675,
|
| 3753 |
+
"eval_steps_per_second": 9.169,
|
| 3754 |
+
"step": 48000
|
| 3755 |
}
|
| 3756 |
],
|
| 3757 |
"logging_steps": 100,
|
|
|
|
| 3771 |
"attributes": {}
|
| 3772 |
}
|
| 3773 |
},
|
| 3774 |
+
"total_flos": 1.42892706299904e+18,
|
| 3775 |
"train_batch_size": 22,
|
| 3776 |
"trial_name": null,
|
| 3777 |
"trial_params": null
|