Commit
•
695bbd3
1
Parent(s):
2386eb8
Training in progress, step 380000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893441530
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7d80b5fe4b73581493fbf7e8d5375ba0cc27fca0abae2f649940dc93608ed91
|
3 |
size 893441530
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaf5cca6f5ad9c15d0fba6e119e98e99e1b26c717ce470e245593e0001049d48
|
3 |
size 454197066
|
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:fda2635cf5eb97c959b3473ee8ed882086ce2dab72fcbeb241e25a40c966b7bf
|
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:b42df27cb36c10cd745fac26ea88f136bc616f898f1fd1486819c4852d2c54f3
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2744,11 +2744,85 @@
|
|
2744 |
"eval_samples_per_second": 107.338,
|
2745 |
"eval_steps_per_second": 13.417,
|
2746 |
"step": 370000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2747 |
}
|
2748 |
],
|
2749 |
"max_steps": 1000000,
|
2750 |
"num_train_epochs": 9223372036854775807,
|
2751 |
-
"total_flos": 3.
|
2752 |
"trial_name": null,
|
2753 |
"trial_params": null
|
2754 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.38,
|
5 |
+
"global_step": 380000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2744 |
"eval_samples_per_second": 107.338,
|
2745 |
"eval_steps_per_second": 13.417,
|
2746 |
"step": 370000
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 0.37,
|
2750 |
+
"learning_rate": 1.650798260743744e-05,
|
2751 |
+
"loss": 0.3488,
|
2752 |
+
"step": 371000
|
2753 |
+
},
|
2754 |
+
{
|
2755 |
+
"epoch": 0.37,
|
2756 |
+
"learning_rate": 1.6495339059660347e-05,
|
2757 |
+
"loss": 0.3483,
|
2758 |
+
"step": 372000
|
2759 |
+
},
|
2760 |
+
{
|
2761 |
+
"epoch": 0.37,
|
2762 |
+
"learning_rate": 1.6482672324195004e-05,
|
2763 |
+
"loss": 0.3477,
|
2764 |
+
"step": 373000
|
2765 |
+
},
|
2766 |
+
{
|
2767 |
+
"epoch": 0.37,
|
2768 |
+
"learning_rate": 1.6469982539562804e-05,
|
2769 |
+
"loss": 0.3446,
|
2770 |
+
"step": 374000
|
2771 |
+
},
|
2772 |
+
{
|
2773 |
+
"epoch": 0.38,
|
2774 |
+
"learning_rate": 1.6457269844537196e-05,
|
2775 |
+
"loss": 0.3442,
|
2776 |
+
"step": 375000
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 0.38,
|
2780 |
+
"eval_runtime": 3159.753,
|
2781 |
+
"eval_samples_per_second": 107.493,
|
2782 |
+
"eval_steps_per_second": 13.437,
|
2783 |
+
"step": 375000
|
2784 |
+
},
|
2785 |
+
{
|
2786 |
+
"epoch": 0.38,
|
2787 |
+
"learning_rate": 1.644453437814218e-05,
|
2788 |
+
"loss": 0.3423,
|
2789 |
+
"step": 376000
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 0.38,
|
2793 |
+
"learning_rate": 1.643177627965077e-05,
|
2794 |
+
"loss": 0.3422,
|
2795 |
+
"step": 377000
|
2796 |
+
},
|
2797 |
+
{
|
2798 |
+
"epoch": 0.38,
|
2799 |
+
"learning_rate": 1.641899568858349e-05,
|
2800 |
+
"loss": 0.3442,
|
2801 |
+
"step": 378000
|
2802 |
+
},
|
2803 |
+
{
|
2804 |
+
"epoch": 0.38,
|
2805 |
+
"learning_rate": 1.640619274470684e-05,
|
2806 |
+
"loss": 0.3418,
|
2807 |
+
"step": 379000
|
2808 |
+
},
|
2809 |
+
{
|
2810 |
+
"epoch": 0.38,
|
2811 |
+
"learning_rate": 1.639336758803176e-05,
|
2812 |
+
"loss": 0.3446,
|
2813 |
+
"step": 380000
|
2814 |
+
},
|
2815 |
+
{
|
2816 |
+
"epoch": 0.38,
|
2817 |
+
"eval_runtime": 3155.9637,
|
2818 |
+
"eval_samples_per_second": 107.622,
|
2819 |
+
"eval_steps_per_second": 13.453,
|
2820 |
+
"step": 380000
|
2821 |
}
|
2822 |
],
|
2823 |
"max_steps": 1000000,
|
2824 |
"num_train_epochs": 9223372036854775807,
|
2825 |
+
"total_flos": 3.3647518658278195e+21,
|
2826 |
"trial_name": null,
|
2827 |
"trial_params": null
|
2828 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaf5cca6f5ad9c15d0fba6e119e98e99e1b26c717ce470e245593e0001049d48
|
3 |
size 454197066
|