loss 2.7
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +213 -3
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 352532601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cde460e97bad04f84a56ae7ff816ff1cdeff3b03a09474465cd292b7b6c31a4
|
3 |
size 352532601
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 688496379
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bb094630c57c0076f7966d01611056cb86c230bb1ce7b15571b9741513a969a
|
3 |
size 688496379
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8da5ab5e4c8996c9e9ca7255e01ed8f4458a8c14e30fe5aa54d259faeef742fb
|
3 |
size 14503
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffecd9835fe8fdd7e333d29c70739f7ca849a8c7b68d33c0cc301eaacafda24e
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 6.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -3516,11 +3516,221 @@
|
|
3516 |
"learning_rate": 3.6461388074291305e-05,
|
3517 |
"loss": 2.7954,
|
3518 |
"step": 58500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3519 |
}
|
3520 |
],
|
3521 |
"max_steps": 92070,
|
3522 |
"num_train_epochs": 10,
|
3523 |
-
"total_flos": 1.
|
3524 |
"trial_name": null,
|
3525 |
"trial_params": null
|
3526 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.73398680387738,
|
5 |
+
"global_step": 62000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3516 |
"learning_rate": 3.6461388074291305e-05,
|
3517 |
"loss": 2.7954,
|
3518 |
"step": 58500
|
3519 |
+
},
|
3520 |
+
{
|
3521 |
+
"epoch": 6.36,
|
3522 |
+
"learning_rate": 3.6352775062452485e-05,
|
3523 |
+
"loss": 2.7937,
|
3524 |
+
"step": 58600
|
3525 |
+
},
|
3526 |
+
{
|
3527 |
+
"epoch": 6.38,
|
3528 |
+
"learning_rate": 3.6244162050613665e-05,
|
3529 |
+
"loss": 2.7426,
|
3530 |
+
"step": 58700
|
3531 |
+
},
|
3532 |
+
{
|
3533 |
+
"epoch": 6.39,
|
3534 |
+
"learning_rate": 3.6135549038774845e-05,
|
3535 |
+
"loss": 2.8019,
|
3536 |
+
"step": 58800
|
3537 |
+
},
|
3538 |
+
{
|
3539 |
+
"epoch": 6.4,
|
3540 |
+
"learning_rate": 3.602693602693603e-05,
|
3541 |
+
"loss": 2.7112,
|
3542 |
+
"step": 58900
|
3543 |
+
},
|
3544 |
+
{
|
3545 |
+
"epoch": 6.41,
|
3546 |
+
"learning_rate": 3.591832301509721e-05,
|
3547 |
+
"loss": 2.809,
|
3548 |
+
"step": 59000
|
3549 |
+
},
|
3550 |
+
{
|
3551 |
+
"epoch": 6.42,
|
3552 |
+
"learning_rate": 3.580971000325839e-05,
|
3553 |
+
"loss": 2.7244,
|
3554 |
+
"step": 59100
|
3555 |
+
},
|
3556 |
+
{
|
3557 |
+
"epoch": 6.43,
|
3558 |
+
"learning_rate": 3.570109699141958e-05,
|
3559 |
+
"loss": 2.7719,
|
3560 |
+
"step": 59200
|
3561 |
+
},
|
3562 |
+
{
|
3563 |
+
"epoch": 6.44,
|
3564 |
+
"learning_rate": 3.559248397958075e-05,
|
3565 |
+
"loss": 2.9352,
|
3566 |
+
"step": 59300
|
3567 |
+
},
|
3568 |
+
{
|
3569 |
+
"epoch": 6.45,
|
3570 |
+
"learning_rate": 3.548387096774194e-05,
|
3571 |
+
"loss": 2.711,
|
3572 |
+
"step": 59400
|
3573 |
+
},
|
3574 |
+
{
|
3575 |
+
"epoch": 6.46,
|
3576 |
+
"learning_rate": 3.537525795590312e-05,
|
3577 |
+
"loss": 2.7434,
|
3578 |
+
"step": 59500
|
3579 |
+
},
|
3580 |
+
{
|
3581 |
+
"epoch": 6.47,
|
3582 |
+
"learning_rate": 3.5266644944064304e-05,
|
3583 |
+
"loss": 2.7573,
|
3584 |
+
"step": 59600
|
3585 |
+
},
|
3586 |
+
{
|
3587 |
+
"epoch": 6.48,
|
3588 |
+
"learning_rate": 3.5158031932225484e-05,
|
3589 |
+
"loss": 2.6963,
|
3590 |
+
"step": 59700
|
3591 |
+
},
|
3592 |
+
{
|
3593 |
+
"epoch": 6.5,
|
3594 |
+
"learning_rate": 3.5049418920386664e-05,
|
3595 |
+
"loss": 2.8267,
|
3596 |
+
"step": 59800
|
3597 |
+
},
|
3598 |
+
{
|
3599 |
+
"epoch": 6.51,
|
3600 |
+
"learning_rate": 3.4940805908547844e-05,
|
3601 |
+
"loss": 2.7864,
|
3602 |
+
"step": 59900
|
3603 |
+
},
|
3604 |
+
{
|
3605 |
+
"epoch": 6.52,
|
3606 |
+
"learning_rate": 3.4832192896709024e-05,
|
3607 |
+
"loss": 2.7585,
|
3608 |
+
"step": 60000
|
3609 |
+
},
|
3610 |
+
{
|
3611 |
+
"epoch": 6.53,
|
3612 |
+
"learning_rate": 3.472357988487021e-05,
|
3613 |
+
"loss": 2.714,
|
3614 |
+
"step": 60100
|
3615 |
+
},
|
3616 |
+
{
|
3617 |
+
"epoch": 6.54,
|
3618 |
+
"learning_rate": 3.461496687303139e-05,
|
3619 |
+
"loss": 2.7202,
|
3620 |
+
"step": 60200
|
3621 |
+
},
|
3622 |
+
{
|
3623 |
+
"epoch": 6.55,
|
3624 |
+
"learning_rate": 3.450635386119258e-05,
|
3625 |
+
"loss": 2.8636,
|
3626 |
+
"step": 60300
|
3627 |
+
},
|
3628 |
+
{
|
3629 |
+
"epoch": 6.56,
|
3630 |
+
"learning_rate": 3.439774084935376e-05,
|
3631 |
+
"loss": 2.8138,
|
3632 |
+
"step": 60400
|
3633 |
+
},
|
3634 |
+
{
|
3635 |
+
"epoch": 6.57,
|
3636 |
+
"learning_rate": 3.428912783751494e-05,
|
3637 |
+
"loss": 2.74,
|
3638 |
+
"step": 60500
|
3639 |
+
},
|
3640 |
+
{
|
3641 |
+
"epoch": 6.58,
|
3642 |
+
"learning_rate": 3.418051482567612e-05,
|
3643 |
+
"loss": 2.7704,
|
3644 |
+
"step": 60600
|
3645 |
+
},
|
3646 |
+
{
|
3647 |
+
"epoch": 6.59,
|
3648 |
+
"learning_rate": 3.40719018138373e-05,
|
3649 |
+
"loss": 2.7326,
|
3650 |
+
"step": 60700
|
3651 |
+
},
|
3652 |
+
{
|
3653 |
+
"epoch": 6.6,
|
3654 |
+
"learning_rate": 3.396328880199848e-05,
|
3655 |
+
"loss": 2.7531,
|
3656 |
+
"step": 60800
|
3657 |
+
},
|
3658 |
+
{
|
3659 |
+
"epoch": 6.61,
|
3660 |
+
"learning_rate": 3.385467579015966e-05,
|
3661 |
+
"loss": 2.67,
|
3662 |
+
"step": 60900
|
3663 |
+
},
|
3664 |
+
{
|
3665 |
+
"epoch": 6.63,
|
3666 |
+
"learning_rate": 3.374606277832085e-05,
|
3667 |
+
"loss": 2.7537,
|
3668 |
+
"step": 61000
|
3669 |
+
},
|
3670 |
+
{
|
3671 |
+
"epoch": 6.64,
|
3672 |
+
"learning_rate": 3.363744976648203e-05,
|
3673 |
+
"loss": 2.7866,
|
3674 |
+
"step": 61100
|
3675 |
+
},
|
3676 |
+
{
|
3677 |
+
"epoch": 6.65,
|
3678 |
+
"learning_rate": 3.35288367546432e-05,
|
3679 |
+
"loss": 2.7174,
|
3680 |
+
"step": 61200
|
3681 |
+
},
|
3682 |
+
{
|
3683 |
+
"epoch": 6.66,
|
3684 |
+
"learning_rate": 3.342022374280439e-05,
|
3685 |
+
"loss": 2.7214,
|
3686 |
+
"step": 61300
|
3687 |
+
},
|
3688 |
+
{
|
3689 |
+
"epoch": 6.67,
|
3690 |
+
"learning_rate": 3.331161073096557e-05,
|
3691 |
+
"loss": 2.7205,
|
3692 |
+
"step": 61400
|
3693 |
+
},
|
3694 |
+
{
|
3695 |
+
"epoch": 6.68,
|
3696 |
+
"learning_rate": 3.3202997719126756e-05,
|
3697 |
+
"loss": 2.8244,
|
3698 |
+
"step": 61500
|
3699 |
+
},
|
3700 |
+
{
|
3701 |
+
"epoch": 6.69,
|
3702 |
+
"learning_rate": 3.3094384707287936e-05,
|
3703 |
+
"loss": 2.7776,
|
3704 |
+
"step": 61600
|
3705 |
+
},
|
3706 |
+
{
|
3707 |
+
"epoch": 6.7,
|
3708 |
+
"learning_rate": 3.2985771695449116e-05,
|
3709 |
+
"loss": 2.7184,
|
3710 |
+
"step": 61700
|
3711 |
+
},
|
3712 |
+
{
|
3713 |
+
"epoch": 6.71,
|
3714 |
+
"learning_rate": 3.2877158683610296e-05,
|
3715 |
+
"loss": 2.7534,
|
3716 |
+
"step": 61800
|
3717 |
+
},
|
3718 |
+
{
|
3719 |
+
"epoch": 6.72,
|
3720 |
+
"learning_rate": 3.2768545671771476e-05,
|
3721 |
+
"loss": 2.7492,
|
3722 |
+
"step": 61900
|
3723 |
+
},
|
3724 |
+
{
|
3725 |
+
"epoch": 6.73,
|
3726 |
+
"learning_rate": 3.265993265993266e-05,
|
3727 |
+
"loss": 2.7351,
|
3728 |
+
"step": 62000
|
3729 |
}
|
3730 |
],
|
3731 |
"max_steps": 92070,
|
3732 |
"num_train_epochs": 10,
|
3733 |
+
"total_flos": 1.2714223024540877e+17,
|
3734 |
"trial_name": null,
|
3735 |
"trial_params": null
|
3736 |
}
|