Training in progress, step 22000, 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 517931840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b81985a8a1ebad5f960997d908e43f8d285835abd4645a1ad5e8d86d7a91e976
|
| 3 |
size 517931840
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1035661434
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e989ff28ea16b1edbb8530fe11c0f4057d65c6350ad0a17cbf0a4960b2cb6ea
|
| 3 |
size 1035661434
|
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 sha256:9ec14043d0cb9b7579fdf9075af0f9a31a2393b8ca68497f0e5375a4fe1a3cf9
|
| 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 sha256:0ce6ab6f335eafbbff78f85b703b750b35d8b96e0da89ad49a445d3e07ab4df8
|
| 3 |
size 1064
|
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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3568,11 +3568,367 @@
|
|
| 3568 |
"eval_steps_per_second": 18.841,
|
| 3569 |
"num_input_tokens_seen": 20971520000,
|
| 3570 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3571 |
}
|
| 3572 |
],
|
| 3573 |
"logging_steps": 50,
|
| 3574 |
"max_steps": 200000,
|
| 3575 |
-
"num_input_tokens_seen":
|
| 3576 |
"num_train_epochs": 5,
|
| 3577 |
"save_steps": 1000,
|
| 3578 |
"stateful_callbacks": {
|
|
@@ -3587,7 +3943,7 @@
|
|
| 3587 |
"attributes": {}
|
| 3588 |
}
|
| 3589 |
},
|
| 3590 |
-
"total_flos": 1.
|
| 3591 |
"train_batch_size": 64,
|
| 3592 |
"trial_name": null,
|
| 3593 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.48325295134384133,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 22000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3568 |
"eval_steps_per_second": 18.841,
|
| 3569 |
"num_input_tokens_seen": 20971520000,
|
| 3570 |
"step": 20000
|
| 3571 |
+
},
|
| 3572 |
+
{
|
| 3573 |
+
"epoch": 0.4404191670201827,
|
| 3574 |
+
"grad_norm": 0.14489957690238953,
|
| 3575 |
+
"learning_rate": 0.001,
|
| 3576 |
+
"loss": 2.7139,
|
| 3577 |
+
"num_input_tokens_seen": 21023948800,
|
| 3578 |
+
"step": 20050
|
| 3579 |
+
},
|
| 3580 |
+
{
|
| 3581 |
+
"epoch": 0.44151746918232776,
|
| 3582 |
+
"grad_norm": 0.13994646072387695,
|
| 3583 |
+
"learning_rate": 0.001,
|
| 3584 |
+
"loss": 2.7091,
|
| 3585 |
+
"num_input_tokens_seen": 21076377600,
|
| 3586 |
+
"step": 20100
|
| 3587 |
+
},
|
| 3588 |
+
{
|
| 3589 |
+
"epoch": 0.4426157713444729,
|
| 3590 |
+
"grad_norm": 0.17211903631687164,
|
| 3591 |
+
"learning_rate": 0.001,
|
| 3592 |
+
"loss": 2.7176,
|
| 3593 |
+
"num_input_tokens_seen": 21128806400,
|
| 3594 |
+
"step": 20150
|
| 3595 |
+
},
|
| 3596 |
+
{
|
| 3597 |
+
"epoch": 0.44371407350661796,
|
| 3598 |
+
"grad_norm": 0.16364862024784088,
|
| 3599 |
+
"learning_rate": 0.001,
|
| 3600 |
+
"loss": 2.7181,
|
| 3601 |
+
"num_input_tokens_seen": 21181235200,
|
| 3602 |
+
"step": 20200
|
| 3603 |
+
},
|
| 3604 |
+
{
|
| 3605 |
+
"epoch": 0.444812375668763,
|
| 3606 |
+
"grad_norm": 0.14166216552257538,
|
| 3607 |
+
"learning_rate": 0.001,
|
| 3608 |
+
"loss": 2.7127,
|
| 3609 |
+
"num_input_tokens_seen": 21233664000,
|
| 3610 |
+
"step": 20250
|
| 3611 |
+
},
|
| 3612 |
+
{
|
| 3613 |
+
"epoch": 0.44591067783090815,
|
| 3614 |
+
"grad_norm": 0.12995755672454834,
|
| 3615 |
+
"learning_rate": 0.001,
|
| 3616 |
+
"loss": 2.7085,
|
| 3617 |
+
"num_input_tokens_seen": 21286092800,
|
| 3618 |
+
"step": 20300
|
| 3619 |
+
},
|
| 3620 |
+
{
|
| 3621 |
+
"epoch": 0.4470089799930532,
|
| 3622 |
+
"grad_norm": 0.15717202425003052,
|
| 3623 |
+
"learning_rate": 0.001,
|
| 3624 |
+
"loss": 2.7071,
|
| 3625 |
+
"num_input_tokens_seen": 21338521600,
|
| 3626 |
+
"step": 20350
|
| 3627 |
+
},
|
| 3628 |
+
{
|
| 3629 |
+
"epoch": 0.44810728215519835,
|
| 3630 |
+
"grad_norm": 0.13354860246181488,
|
| 3631 |
+
"learning_rate": 0.001,
|
| 3632 |
+
"loss": 2.7094,
|
| 3633 |
+
"num_input_tokens_seen": 21390950400,
|
| 3634 |
+
"step": 20400
|
| 3635 |
+
},
|
| 3636 |
+
{
|
| 3637 |
+
"epoch": 0.4492055843173434,
|
| 3638 |
+
"grad_norm": 0.16004188358783722,
|
| 3639 |
+
"learning_rate": 0.001,
|
| 3640 |
+
"loss": 2.7109,
|
| 3641 |
+
"num_input_tokens_seen": 21443379200,
|
| 3642 |
+
"step": 20450
|
| 3643 |
+
},
|
| 3644 |
+
{
|
| 3645 |
+
"epoch": 0.45030388647948855,
|
| 3646 |
+
"grad_norm": 0.148077592253685,
|
| 3647 |
+
"learning_rate": 0.001,
|
| 3648 |
+
"loss": 2.7058,
|
| 3649 |
+
"num_input_tokens_seen": 21495808000,
|
| 3650 |
+
"step": 20500
|
| 3651 |
+
},
|
| 3652 |
+
{
|
| 3653 |
+
"epoch": 0.45030388647948855,
|
| 3654 |
+
"eval_loss": 2.6089115142822266,
|
| 3655 |
+
"eval_runtime": 65.5589,
|
| 3656 |
+
"eval_samples_per_second": 76.267,
|
| 3657 |
+
"eval_steps_per_second": 19.067,
|
| 3658 |
+
"num_input_tokens_seen": 21495808000,
|
| 3659 |
+
"step": 20500
|
| 3660 |
+
},
|
| 3661 |
+
{
|
| 3662 |
+
"epoch": 0.4514021886416336,
|
| 3663 |
+
"grad_norm": 0.16992634534835815,
|
| 3664 |
+
"learning_rate": 0.001,
|
| 3665 |
+
"loss": 2.7026,
|
| 3666 |
+
"num_input_tokens_seen": 21548236800,
|
| 3667 |
+
"step": 20550
|
| 3668 |
+
},
|
| 3669 |
+
{
|
| 3670 |
+
"epoch": 0.4525004908037787,
|
| 3671 |
+
"grad_norm": 0.14876551926136017,
|
| 3672 |
+
"learning_rate": 0.001,
|
| 3673 |
+
"loss": 2.7105,
|
| 3674 |
+
"num_input_tokens_seen": 21600665600,
|
| 3675 |
+
"step": 20600
|
| 3676 |
+
},
|
| 3677 |
+
{
|
| 3678 |
+
"epoch": 0.4535987929659238,
|
| 3679 |
+
"grad_norm": 0.16025613248348236,
|
| 3680 |
+
"learning_rate": 0.001,
|
| 3681 |
+
"loss": 2.707,
|
| 3682 |
+
"num_input_tokens_seen": 21653094400,
|
| 3683 |
+
"step": 20650
|
| 3684 |
+
},
|
| 3685 |
+
{
|
| 3686 |
+
"epoch": 0.4546970951280689,
|
| 3687 |
+
"grad_norm": 0.14609012007713318,
|
| 3688 |
+
"learning_rate": 0.001,
|
| 3689 |
+
"loss": 2.7086,
|
| 3690 |
+
"num_input_tokens_seen": 21705523200,
|
| 3691 |
+
"step": 20700
|
| 3692 |
+
},
|
| 3693 |
+
{
|
| 3694 |
+
"epoch": 0.455795397290214,
|
| 3695 |
+
"grad_norm": 0.14725832641124725,
|
| 3696 |
+
"learning_rate": 0.001,
|
| 3697 |
+
"loss": 2.7075,
|
| 3698 |
+
"num_input_tokens_seen": 21757952000,
|
| 3699 |
+
"step": 20750
|
| 3700 |
+
},
|
| 3701 |
+
{
|
| 3702 |
+
"epoch": 0.4568936994523591,
|
| 3703 |
+
"grad_norm": 0.1736454963684082,
|
| 3704 |
+
"learning_rate": 0.001,
|
| 3705 |
+
"loss": 2.7033,
|
| 3706 |
+
"num_input_tokens_seen": 21810380800,
|
| 3707 |
+
"step": 20800
|
| 3708 |
+
},
|
| 3709 |
+
{
|
| 3710 |
+
"epoch": 0.45799200161450415,
|
| 3711 |
+
"grad_norm": 0.14904257655143738,
|
| 3712 |
+
"learning_rate": 0.001,
|
| 3713 |
+
"loss": 2.7012,
|
| 3714 |
+
"num_input_tokens_seen": 21862809600,
|
| 3715 |
+
"step": 20850
|
| 3716 |
+
},
|
| 3717 |
+
{
|
| 3718 |
+
"epoch": 0.4590903037766493,
|
| 3719 |
+
"grad_norm": 0.14407765865325928,
|
| 3720 |
+
"learning_rate": 0.001,
|
| 3721 |
+
"loss": 2.7055,
|
| 3722 |
+
"num_input_tokens_seen": 21915238400,
|
| 3723 |
+
"step": 20900
|
| 3724 |
+
},
|
| 3725 |
+
{
|
| 3726 |
+
"epoch": 0.46018860593879435,
|
| 3727 |
+
"grad_norm": 0.13943473994731903,
|
| 3728 |
+
"learning_rate": 0.001,
|
| 3729 |
+
"loss": 2.6999,
|
| 3730 |
+
"num_input_tokens_seen": 21967667200,
|
| 3731 |
+
"step": 20950
|
| 3732 |
+
},
|
| 3733 |
+
{
|
| 3734 |
+
"epoch": 0.4612869081009395,
|
| 3735 |
+
"grad_norm": 0.1592896729707718,
|
| 3736 |
+
"learning_rate": 0.001,
|
| 3737 |
+
"loss": 2.7072,
|
| 3738 |
+
"num_input_tokens_seen": 22020096000,
|
| 3739 |
+
"step": 21000
|
| 3740 |
+
},
|
| 3741 |
+
{
|
| 3742 |
+
"epoch": 0.4612869081009395,
|
| 3743 |
+
"eval_loss": 2.605719566345215,
|
| 3744 |
+
"eval_runtime": 65.6879,
|
| 3745 |
+
"eval_samples_per_second": 76.117,
|
| 3746 |
+
"eval_steps_per_second": 19.029,
|
| 3747 |
+
"num_input_tokens_seen": 22020096000,
|
| 3748 |
+
"step": 21000
|
| 3749 |
+
},
|
| 3750 |
+
{
|
| 3751 |
+
"epoch": 0.46238521026308455,
|
| 3752 |
+
"grad_norm": 0.1428702473640442,
|
| 3753 |
+
"learning_rate": 0.001,
|
| 3754 |
+
"loss": 2.7042,
|
| 3755 |
+
"num_input_tokens_seen": 22072524800,
|
| 3756 |
+
"step": 21050
|
| 3757 |
+
},
|
| 3758 |
+
{
|
| 3759 |
+
"epoch": 0.46348351242522967,
|
| 3760 |
+
"grad_norm": 0.13529072701931,
|
| 3761 |
+
"learning_rate": 0.001,
|
| 3762 |
+
"loss": 2.7093,
|
| 3763 |
+
"num_input_tokens_seen": 22124953600,
|
| 3764 |
+
"step": 21100
|
| 3765 |
+
},
|
| 3766 |
+
{
|
| 3767 |
+
"epoch": 0.46458181458737474,
|
| 3768 |
+
"grad_norm": 0.17529748380184174,
|
| 3769 |
+
"learning_rate": 0.001,
|
| 3770 |
+
"loss": 2.713,
|
| 3771 |
+
"num_input_tokens_seen": 22177382400,
|
| 3772 |
+
"step": 21150
|
| 3773 |
+
},
|
| 3774 |
+
{
|
| 3775 |
+
"epoch": 0.4656801167495198,
|
| 3776 |
+
"grad_norm": 0.1479254513978958,
|
| 3777 |
+
"learning_rate": 0.001,
|
| 3778 |
+
"loss": 2.6984,
|
| 3779 |
+
"num_input_tokens_seen": 22229811200,
|
| 3780 |
+
"step": 21200
|
| 3781 |
+
},
|
| 3782 |
+
{
|
| 3783 |
+
"epoch": 0.46677841891166494,
|
| 3784 |
+
"grad_norm": 0.15110637247562408,
|
| 3785 |
+
"learning_rate": 0.001,
|
| 3786 |
+
"loss": 2.7128,
|
| 3787 |
+
"num_input_tokens_seen": 22282240000,
|
| 3788 |
+
"step": 21250
|
| 3789 |
+
},
|
| 3790 |
+
{
|
| 3791 |
+
"epoch": 0.46787672107381,
|
| 3792 |
+
"grad_norm": 0.13746944069862366,
|
| 3793 |
+
"learning_rate": 0.001,
|
| 3794 |
+
"loss": 2.7036,
|
| 3795 |
+
"num_input_tokens_seen": 22334668800,
|
| 3796 |
+
"step": 21300
|
| 3797 |
+
},
|
| 3798 |
+
{
|
| 3799 |
+
"epoch": 0.46897502323595514,
|
| 3800 |
+
"grad_norm": 0.17940136790275574,
|
| 3801 |
+
"learning_rate": 0.001,
|
| 3802 |
+
"loss": 2.7048,
|
| 3803 |
+
"num_input_tokens_seen": 22387097600,
|
| 3804 |
+
"step": 21350
|
| 3805 |
+
},
|
| 3806 |
+
{
|
| 3807 |
+
"epoch": 0.4700733253981002,
|
| 3808 |
+
"grad_norm": 0.14203256368637085,
|
| 3809 |
+
"learning_rate": 0.001,
|
| 3810 |
+
"loss": 2.6997,
|
| 3811 |
+
"num_input_tokens_seen": 22439526400,
|
| 3812 |
+
"step": 21400
|
| 3813 |
+
},
|
| 3814 |
+
{
|
| 3815 |
+
"epoch": 0.47117162756024533,
|
| 3816 |
+
"grad_norm": 0.14260704815387726,
|
| 3817 |
+
"learning_rate": 0.001,
|
| 3818 |
+
"loss": 2.7092,
|
| 3819 |
+
"num_input_tokens_seen": 22491955200,
|
| 3820 |
+
"step": 21450
|
| 3821 |
+
},
|
| 3822 |
+
{
|
| 3823 |
+
"epoch": 0.4722699297223904,
|
| 3824 |
+
"grad_norm": 0.16455897688865662,
|
| 3825 |
+
"learning_rate": 0.001,
|
| 3826 |
+
"loss": 2.6969,
|
| 3827 |
+
"num_input_tokens_seen": 22544384000,
|
| 3828 |
+
"step": 21500
|
| 3829 |
+
},
|
| 3830 |
+
{
|
| 3831 |
+
"epoch": 0.4722699297223904,
|
| 3832 |
+
"eval_loss": 2.60367751121521,
|
| 3833 |
+
"eval_runtime": 65.4304,
|
| 3834 |
+
"eval_samples_per_second": 76.417,
|
| 3835 |
+
"eval_steps_per_second": 19.104,
|
| 3836 |
+
"num_input_tokens_seen": 22544384000,
|
| 3837 |
+
"step": 21500
|
| 3838 |
+
},
|
| 3839 |
+
{
|
| 3840 |
+
"epoch": 0.4733682318845355,
|
| 3841 |
+
"grad_norm": 0.1529170274734497,
|
| 3842 |
+
"learning_rate": 0.001,
|
| 3843 |
+
"loss": 2.7003,
|
| 3844 |
+
"num_input_tokens_seen": 22596812800,
|
| 3845 |
+
"step": 21550
|
| 3846 |
+
},
|
| 3847 |
+
{
|
| 3848 |
+
"epoch": 0.4744665340466806,
|
| 3849 |
+
"grad_norm": 0.1921636164188385,
|
| 3850 |
+
"learning_rate": 0.001,
|
| 3851 |
+
"loss": 2.7014,
|
| 3852 |
+
"num_input_tokens_seen": 22649241600,
|
| 3853 |
+
"step": 21600
|
| 3854 |
+
},
|
| 3855 |
+
{
|
| 3856 |
+
"epoch": 0.47556483620882567,
|
| 3857 |
+
"grad_norm": 0.16029173135757446,
|
| 3858 |
+
"learning_rate": 0.001,
|
| 3859 |
+
"loss": 2.7028,
|
| 3860 |
+
"num_input_tokens_seen": 22701670400,
|
| 3861 |
+
"step": 21650
|
| 3862 |
+
},
|
| 3863 |
+
{
|
| 3864 |
+
"epoch": 0.4766631383709708,
|
| 3865 |
+
"grad_norm": 0.14740578830242157,
|
| 3866 |
+
"learning_rate": 0.001,
|
| 3867 |
+
"loss": 2.7019,
|
| 3868 |
+
"num_input_tokens_seen": 22754099200,
|
| 3869 |
+
"step": 21700
|
| 3870 |
+
},
|
| 3871 |
+
{
|
| 3872 |
+
"epoch": 0.47776144053311587,
|
| 3873 |
+
"grad_norm": 0.1734548658132553,
|
| 3874 |
+
"learning_rate": 0.001,
|
| 3875 |
+
"loss": 2.6985,
|
| 3876 |
+
"num_input_tokens_seen": 22806528000,
|
| 3877 |
+
"step": 21750
|
| 3878 |
+
},
|
| 3879 |
+
{
|
| 3880 |
+
"epoch": 0.47885974269526094,
|
| 3881 |
+
"grad_norm": 0.15502890944480896,
|
| 3882 |
+
"learning_rate": 0.001,
|
| 3883 |
+
"loss": 2.6973,
|
| 3884 |
+
"num_input_tokens_seen": 22858956800,
|
| 3885 |
+
"step": 21800
|
| 3886 |
+
},
|
| 3887 |
+
{
|
| 3888 |
+
"epoch": 0.47995804485740606,
|
| 3889 |
+
"grad_norm": 0.16783900558948517,
|
| 3890 |
+
"learning_rate": 0.001,
|
| 3891 |
+
"loss": 2.7003,
|
| 3892 |
+
"num_input_tokens_seen": 22911385600,
|
| 3893 |
+
"step": 21850
|
| 3894 |
+
},
|
| 3895 |
+
{
|
| 3896 |
+
"epoch": 0.48105634701955113,
|
| 3897 |
+
"grad_norm": 0.14911381900310516,
|
| 3898 |
+
"learning_rate": 0.001,
|
| 3899 |
+
"loss": 2.6992,
|
| 3900 |
+
"num_input_tokens_seen": 22963814400,
|
| 3901 |
+
"step": 21900
|
| 3902 |
+
},
|
| 3903 |
+
{
|
| 3904 |
+
"epoch": 0.48215464918169626,
|
| 3905 |
+
"grad_norm": 0.15027394890785217,
|
| 3906 |
+
"learning_rate": 0.001,
|
| 3907 |
+
"loss": 2.6957,
|
| 3908 |
+
"num_input_tokens_seen": 23016243200,
|
| 3909 |
+
"step": 21950
|
| 3910 |
+
},
|
| 3911 |
+
{
|
| 3912 |
+
"epoch": 0.48325295134384133,
|
| 3913 |
+
"grad_norm": 0.1261301189661026,
|
| 3914 |
+
"learning_rate": 0.001,
|
| 3915 |
+
"loss": 2.7064,
|
| 3916 |
+
"num_input_tokens_seen": 23068672000,
|
| 3917 |
+
"step": 22000
|
| 3918 |
+
},
|
| 3919 |
+
{
|
| 3920 |
+
"epoch": 0.48325295134384133,
|
| 3921 |
+
"eval_loss": 2.6012015342712402,
|
| 3922 |
+
"eval_runtime": 64.9701,
|
| 3923 |
+
"eval_samples_per_second": 76.958,
|
| 3924 |
+
"eval_steps_per_second": 19.24,
|
| 3925 |
+
"num_input_tokens_seen": 23068672000,
|
| 3926 |
+
"step": 22000
|
| 3927 |
}
|
| 3928 |
],
|
| 3929 |
"logging_steps": 50,
|
| 3930 |
"max_steps": 200000,
|
| 3931 |
+
"num_input_tokens_seen": 23068672000,
|
| 3932 |
"num_train_epochs": 5,
|
| 3933 |
"save_steps": 1000,
|
| 3934 |
"stateful_callbacks": {
|
|
|
|
| 3943 |
"attributes": {}
|
| 3944 |
}
|
| 3945 |
},
|
| 3946 |
+
"total_flos": 1.3137777751228416e+19,
|
| 3947 |
"train_batch_size": 64,
|
| 3948 |
"trial_name": null,
|
| 3949 |
"trial_params": null
|