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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6bc9d91d9a60b7700203af96a974794d27be7eea3f420ff1ae5b370210ee2ea
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84e7123b1ce19594fbb22be55c4498bf5de4fe017896adc3ad66d3524c9c9c54
|
| 3 |
size 938825803
|
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 sha256:9623f80738737f22c717a4262aa756fc5e2cd7d18d0d2842f53148de45dc81ec
|
| 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 sha256:2acdb6c434c9b8d7057c6d627425c7ddfd0a206d98e9d43b0c3e164d01587a81
|
| 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": 77.396,
|
| 3441 |
"eval_steps_per_second": 19.349,
|
| 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": 0.10909090909090909,
|
| 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": 77.396,
|
| 3441 |
"eval_steps_per_second": 19.349,
|
| 3442 |
"step": 44000
|
| 3443 |
+
},
|
| 3444 |
+
{
|
| 3445 |
+
"epoch": 0.07363636363636364,
|
| 3446 |
+
"grad_norm": 0.14658956229686737,
|
| 3447 |
+
"learning_rate": 0.0006543860956689131,
|
| 3448 |
+
"loss": 2.7102786254882814,
|
| 3449 |
+
"step": 44100
|
| 3450 |
+
},
|
| 3451 |
+
{
|
| 3452 |
+
"epoch": 0.07454545454545454,
|
| 3453 |
+
"grad_norm": 0.1424274891614914,
|
| 3454 |
+
"learning_rate": 0.0006530253924518484,
|
| 3455 |
+
"loss": 2.682833557128906,
|
| 3456 |
+
"step": 44200
|
| 3457 |
+
},
|
| 3458 |
+
{
|
| 3459 |
+
"epoch": 0.07545454545454545,
|
| 3460 |
+
"grad_norm": 0.1558665931224823,
|
| 3461 |
+
"learning_rate": 0.0006516634376426387,
|
| 3462 |
+
"loss": 2.7235848999023435,
|
| 3463 |
+
"step": 44300
|
| 3464 |
+
},
|
| 3465 |
+
{
|
| 3466 |
+
"epoch": 0.07636363636363637,
|
| 3467 |
+
"grad_norm": 0.1660631000995636,
|
| 3468 |
+
"learning_rate": 0.0006503002423806897,
|
| 3469 |
+
"loss": 2.6941436767578124,
|
| 3470 |
+
"step": 44400
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 0.07727272727272727,
|
| 3474 |
+
"grad_norm": 0.15640541911125183,
|
| 3475 |
+
"learning_rate": 0.0006489358178155531,
|
| 3476 |
+
"loss": 2.7176858520507814,
|
| 3477 |
+
"step": 44500
|
| 3478 |
+
},
|
| 3479 |
+
{
|
| 3480 |
+
"epoch": 0.07818181818181819,
|
| 3481 |
+
"grad_norm": 0.1507701575756073,
|
| 3482 |
+
"learning_rate": 0.0006475701751068345,
|
| 3483 |
+
"loss": 2.72189697265625,
|
| 3484 |
+
"step": 44600
|
| 3485 |
+
},
|
| 3486 |
+
{
|
| 3487 |
+
"epoch": 0.07909090909090909,
|
| 3488 |
+
"grad_norm": 0.1533944010734558,
|
| 3489 |
+
"learning_rate": 0.000646203325424103,
|
| 3490 |
+
"loss": 2.6939328002929686,
|
| 3491 |
+
"step": 44700
|
| 3492 |
+
},
|
| 3493 |
+
{
|
| 3494 |
+
"epoch": 0.08,
|
| 3495 |
+
"grad_norm": 0.13101057708263397,
|
| 3496 |
+
"learning_rate": 0.0006448352799467994,
|
| 3497 |
+
"loss": 2.743724365234375,
|
| 3498 |
+
"step": 44800
|
| 3499 |
+
},
|
| 3500 |
+
{
|
| 3501 |
+
"epoch": 0.0809090909090909,
|
| 3502 |
+
"grad_norm": 0.15205194056034088,
|
| 3503 |
+
"learning_rate": 0.0006434660498641453,
|
| 3504 |
+
"loss": 2.6808477783203126,
|
| 3505 |
+
"step": 44900
|
| 3506 |
+
},
|
| 3507 |
+
{
|
| 3508 |
+
"epoch": 0.08181818181818182,
|
| 3509 |
+
"grad_norm": 0.16786165535449982,
|
| 3510 |
+
"learning_rate": 0.0006420956463750505,
|
| 3511 |
+
"loss": 2.7101092529296875,
|
| 3512 |
+
"step": 45000
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 0.08181818181818182,
|
| 3516 |
+
"eval_loss": 3.100367307662964,
|
| 3517 |
+
"eval_runtime": 7.4121,
|
| 3518 |
+
"eval_samples_per_second": 77.711,
|
| 3519 |
+
"eval_steps_per_second": 19.428,
|
| 3520 |
+
"step": 45000
|
| 3521 |
+
},
|
| 3522 |
+
{
|
| 3523 |
+
"epoch": 0.08272727272727273,
|
| 3524 |
+
"grad_norm": 0.1478699892759323,
|
| 3525 |
+
"learning_rate": 0.0006407240806880225,
|
| 3526 |
+
"loss": 2.717208251953125,
|
| 3527 |
+
"step": 45100
|
| 3528 |
+
},
|
| 3529 |
+
{
|
| 3530 |
+
"epoch": 0.08363636363636363,
|
| 3531 |
+
"grad_norm": 0.1527082324028015,
|
| 3532 |
+
"learning_rate": 0.0006393513640210743,
|
| 3533 |
+
"loss": 2.7066421508789062,
|
| 3534 |
+
"step": 45200
|
| 3535 |
+
},
|
| 3536 |
+
{
|
| 3537 |
+
"epoch": 0.08454545454545455,
|
| 3538 |
+
"grad_norm": 0.16474194824695587,
|
| 3539 |
+
"learning_rate": 0.0006379775076016327,
|
| 3540 |
+
"loss": 2.6989260864257814,
|
| 3541 |
+
"step": 45300
|
| 3542 |
+
},
|
| 3543 |
+
{
|
| 3544 |
+
"epoch": 0.08545454545454545,
|
| 3545 |
+
"grad_norm": 0.17212653160095215,
|
| 3546 |
+
"learning_rate": 0.0006366025226664465,
|
| 3547 |
+
"loss": 2.72157958984375,
|
| 3548 |
+
"step": 45400
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 0.08636363636363636,
|
| 3552 |
+
"grad_norm": 0.1925841122865677,
|
| 3553 |
+
"learning_rate": 0.0006352264204614946,
|
| 3554 |
+
"loss": 2.7147427368164063,
|
| 3555 |
+
"step": 45500
|
| 3556 |
+
},
|
| 3557 |
+
{
|
| 3558 |
+
"epoch": 0.08727272727272728,
|
| 3559 |
+
"grad_norm": 0.19100086390972137,
|
| 3560 |
+
"learning_rate": 0.0006338492122418944,
|
| 3561 |
+
"loss": 2.6837368774414063,
|
| 3562 |
+
"step": 45600
|
| 3563 |
+
},
|
| 3564 |
+
{
|
| 3565 |
+
"epoch": 0.08818181818181818,
|
| 3566 |
+
"grad_norm": 0.15223105251789093,
|
| 3567 |
+
"learning_rate": 0.0006324709092718088,
|
| 3568 |
+
"loss": 2.6951806640625,
|
| 3569 |
+
"step": 45700
|
| 3570 |
+
},
|
| 3571 |
+
{
|
| 3572 |
+
"epoch": 0.0890909090909091,
|
| 3573 |
+
"grad_norm": 0.16720791161060333,
|
| 3574 |
+
"learning_rate": 0.000631091522824355,
|
| 3575 |
+
"loss": 2.6881533813476564,
|
| 3576 |
+
"step": 45800
|
| 3577 |
+
},
|
| 3578 |
+
{
|
| 3579 |
+
"epoch": 0.09,
|
| 3580 |
+
"grad_norm": 0.28359341621398926,
|
| 3581 |
+
"learning_rate": 0.0006297110641815118,
|
| 3582 |
+
"loss": 2.695024108886719,
|
| 3583 |
+
"step": 45900
|
| 3584 |
+
},
|
| 3585 |
+
{
|
| 3586 |
+
"epoch": 0.09090909090909091,
|
| 3587 |
+
"grad_norm": 0.16058634221553802,
|
| 3588 |
+
"learning_rate": 0.0006283295446340276,
|
| 3589 |
+
"loss": 2.694168701171875,
|
| 3590 |
+
"step": 46000
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 0.09090909090909091,
|
| 3594 |
+
"eval_loss": 3.092599630355835,
|
| 3595 |
+
"eval_runtime": 7.4402,
|
| 3596 |
+
"eval_samples_per_second": 77.417,
|
| 3597 |
+
"eval_steps_per_second": 19.354,
|
| 3598 |
+
"step": 46000
|
| 3599 |
+
},
|
| 3600 |
+
{
|
| 3601 |
+
"epoch": 0.09181818181818181,
|
| 3602 |
+
"grad_norm": 0.14820711314678192,
|
| 3603 |
+
"learning_rate": 0.0006269469754813277,
|
| 3604 |
+
"loss": 2.678899841308594,
|
| 3605 |
+
"step": 46100
|
| 3606 |
+
},
|
| 3607 |
+
{
|
| 3608 |
+
"epoch": 0.09272727272727273,
|
| 3609 |
+
"grad_norm": 0.14676456153392792,
|
| 3610 |
+
"learning_rate": 0.0006255633680314226,
|
| 3611 |
+
"loss": 2.6948358154296876,
|
| 3612 |
+
"step": 46200
|
| 3613 |
+
},
|
| 3614 |
+
{
|
| 3615 |
+
"epoch": 0.09363636363636364,
|
| 3616 |
+
"grad_norm": 0.14033126831054688,
|
| 3617 |
+
"learning_rate": 0.0006241787336008143,
|
| 3618 |
+
"loss": 2.6942843627929687,
|
| 3619 |
+
"step": 46300
|
| 3620 |
+
},
|
| 3621 |
+
{
|
| 3622 |
+
"epoch": 0.09454545454545454,
|
| 3623 |
+
"grad_norm": 0.15463101863861084,
|
| 3624 |
+
"learning_rate": 0.000622793083514405,
|
| 3625 |
+
"loss": 2.6831298828125,
|
| 3626 |
+
"step": 46400
|
| 3627 |
+
},
|
| 3628 |
+
{
|
| 3629 |
+
"epoch": 0.09545454545454546,
|
| 3630 |
+
"grad_norm": 0.1568794697523117,
|
| 3631 |
+
"learning_rate": 0.0006214064291054039,
|
| 3632 |
+
"loss": 2.6844097900390627,
|
| 3633 |
+
"step": 46500
|
| 3634 |
+
},
|
| 3635 |
+
{
|
| 3636 |
+
"epoch": 0.09636363636363636,
|
| 3637 |
+
"grad_norm": 0.15985362231731415,
|
| 3638 |
+
"learning_rate": 0.0006200187817152341,
|
| 3639 |
+
"loss": 2.6705093383789062,
|
| 3640 |
+
"step": 46600
|
| 3641 |
+
},
|
| 3642 |
+
{
|
| 3643 |
+
"epoch": 0.09727272727272727,
|
| 3644 |
+
"grad_norm": 0.18481206893920898,
|
| 3645 |
+
"learning_rate": 0.0006186301526934407,
|
| 3646 |
+
"loss": 2.7399118041992185,
|
| 3647 |
+
"step": 46700
|
| 3648 |
+
},
|
| 3649 |
+
{
|
| 3650 |
+
"epoch": 0.09818181818181818,
|
| 3651 |
+
"grad_norm": 0.17036649584770203,
|
| 3652 |
+
"learning_rate": 0.0006172405533975973,
|
| 3653 |
+
"loss": 2.7174920654296875,
|
| 3654 |
+
"step": 46800
|
| 3655 |
+
},
|
| 3656 |
+
{
|
| 3657 |
+
"epoch": 0.09909090909090909,
|
| 3658 |
+
"grad_norm": 0.21465139091014862,
|
| 3659 |
+
"learning_rate": 0.0006158499951932138,
|
| 3660 |
+
"loss": 2.7115213012695314,
|
| 3661 |
+
"step": 46900
|
| 3662 |
+
},
|
| 3663 |
+
{
|
| 3664 |
+
"epoch": 0.1,
|
| 3665 |
+
"grad_norm": 0.16568434238433838,
|
| 3666 |
+
"learning_rate": 0.0006144584894536423,
|
| 3667 |
+
"loss": 2.7298922729492188,
|
| 3668 |
+
"step": 47000
|
| 3669 |
+
},
|
| 3670 |
+
{
|
| 3671 |
+
"epoch": 0.1,
|
| 3672 |
+
"eval_loss": 3.0938024520874023,
|
| 3673 |
+
"eval_runtime": 7.4616,
|
| 3674 |
+
"eval_samples_per_second": 77.195,
|
| 3675 |
+
"eval_steps_per_second": 19.299,
|
| 3676 |
+
"step": 47000
|
| 3677 |
+
},
|
| 3678 |
+
{
|
| 3679 |
+
"epoch": 0.1009090909090909,
|
| 3680 |
+
"grad_norm": 0.14605851471424103,
|
| 3681 |
+
"learning_rate": 0.0006130660475599854,
|
| 3682 |
+
"loss": 2.7149703979492186,
|
| 3683 |
+
"step": 47100
|
| 3684 |
+
},
|
| 3685 |
+
{
|
| 3686 |
+
"epoch": 0.10181818181818182,
|
| 3687 |
+
"grad_norm": 0.21608054637908936,
|
| 3688 |
+
"learning_rate": 0.0006116726809010022,
|
| 3689 |
+
"loss": 2.7035641479492187,
|
| 3690 |
+
"step": 47200
|
| 3691 |
+
},
|
| 3692 |
+
{
|
| 3693 |
+
"epoch": 0.10272727272727272,
|
| 3694 |
+
"grad_norm": 0.1545097827911377,
|
| 3695 |
+
"learning_rate": 0.0006102784008730155,
|
| 3696 |
+
"loss": 2.6880255126953125,
|
| 3697 |
+
"step": 47300
|
| 3698 |
+
},
|
| 3699 |
+
{
|
| 3700 |
+
"epoch": 0.10363636363636364,
|
| 3701 |
+
"grad_norm": 0.14439067244529724,
|
| 3702 |
+
"learning_rate": 0.0006088832188798183,
|
| 3703 |
+
"loss": 2.6835076904296873,
|
| 3704 |
+
"step": 47400
|
| 3705 |
+
},
|
| 3706 |
+
{
|
| 3707 |
+
"epoch": 0.10454545454545454,
|
| 3708 |
+
"grad_norm": 0.17214855551719666,
|
| 3709 |
+
"learning_rate": 0.0006074871463325809,
|
| 3710 |
+
"loss": 2.6864669799804686,
|
| 3711 |
+
"step": 47500
|
| 3712 |
+
},
|
| 3713 |
+
{
|
| 3714 |
+
"epoch": 0.10545454545454545,
|
| 3715 |
+
"grad_norm": 0.15308986604213715,
|
| 3716 |
+
"learning_rate": 0.0006060901946497581,
|
| 3717 |
+
"loss": 2.6995504760742186,
|
| 3718 |
+
"step": 47600
|
| 3719 |
+
},
|
| 3720 |
+
{
|
| 3721 |
+
"epoch": 0.10636363636363637,
|
| 3722 |
+
"grad_norm": 0.21875260770320892,
|
| 3723 |
+
"learning_rate": 0.000604692375256994,
|
| 3724 |
+
"loss": 2.6868545532226564,
|
| 3725 |
+
"step": 47700
|
| 3726 |
+
},
|
| 3727 |
+
{
|
| 3728 |
+
"epoch": 0.10727272727272727,
|
| 3729 |
+
"grad_norm": 0.1660732924938202,
|
| 3730 |
+
"learning_rate": 0.0006032936995870303,
|
| 3731 |
+
"loss": 2.718809814453125,
|
| 3732 |
+
"step": 47800
|
| 3733 |
+
},
|
| 3734 |
+
{
|
| 3735 |
+
"epoch": 0.10818181818181818,
|
| 3736 |
+
"grad_norm": 0.1624031513929367,
|
| 3737 |
+
"learning_rate": 0.000601894179079612,
|
| 3738 |
+
"loss": 2.718572692871094,
|
| 3739 |
+
"step": 47900
|
| 3740 |
+
},
|
| 3741 |
+
{
|
| 3742 |
+
"epoch": 0.10909090909090909,
|
| 3743 |
+
"grad_norm": 0.17190197110176086,
|
| 3744 |
+
"learning_rate": 0.0006004938251813943,
|
| 3745 |
+
"loss": 2.7020748901367186,
|
| 3746 |
+
"step": 48000
|
| 3747 |
+
},
|
| 3748 |
+
{
|
| 3749 |
+
"epoch": 0.10909090909090909,
|
| 3750 |
+
"eval_loss": 3.089716911315918,
|
| 3751 |
+
"eval_runtime": 7.4415,
|
| 3752 |
+
"eval_samples_per_second": 77.404,
|
| 3753 |
+
"eval_steps_per_second": 19.351,
|
| 3754 |
+
"step": 48000
|
| 3755 |
}
|
| 3756 |
],
|
| 3757 |
"logging_steps": 100,
|
|
|
|
| 3771 |
"attributes": {}
|
| 3772 |
}
|
| 3773 |
},
|
| 3774 |
+
"total_flos": 1.195899887812608e+18,
|
| 3775 |
"train_batch_size": 22,
|
| 3776 |
"trial_name": null,
|
| 3777 |
"trial_params": null
|