stefania-radu
commited on
Commit
•
2386eb8
1
Parent(s):
b34cce8
Training in progress, step 370000
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 sha256:2d5937fbf5a223bdee412711090b2afe19ccd59cb5aa00ff257849fe3abbc0df
|
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:cb18529144e5631f4110d550e5ae8dec1ab66ae10143ec11a390bb4bb1168003
|
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 sha256:57495da3e14701eaa78ba01626380cf06c08d77e93ad6e4f3e1fa2ad42d22c6c
|
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 sha256:83bbce26cd1d82261c68bda952c3a8a3f941ff6e36a11d4fea5bc7113b3bffa2
|
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,
|
@@ -2670,11 +2670,85 @@
|
|
2670 |
"eval_samples_per_second": 102.337,
|
2671 |
"eval_steps_per_second": 12.792,
|
2672 |
"step": 360000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2673 |
}
|
2674 |
],
|
2675 |
"max_steps": 1000000,
|
2676 |
"num_train_epochs": 9223372036854775807,
|
2677 |
-
"total_flos": 3.
|
2678 |
"trial_name": null,
|
2679 |
"trial_params": null
|
2680 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.37,
|
5 |
+
"global_step": 370000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2670 |
"eval_samples_per_second": 102.337,
|
2671 |
"eval_steps_per_second": 12.792,
|
2672 |
"step": 360000
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 0.36,
|
2676 |
+
"learning_rate": 1.6633112470897675e-05,
|
2677 |
+
"loss": 0.3442,
|
2678 |
+
"step": 361000
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 0.36,
|
2682 |
+
"learning_rate": 1.6620708362146338e-05,
|
2683 |
+
"loss": 0.3441,
|
2684 |
+
"step": 362000
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 0.36,
|
2688 |
+
"learning_rate": 1.6608279694688143e-05,
|
2689 |
+
"loss": 0.3441,
|
2690 |
+
"step": 363000
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 0.36,
|
2694 |
+
"learning_rate": 1.659582660444101e-05,
|
2695 |
+
"loss": 0.3419,
|
2696 |
+
"step": 364000
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 0.36,
|
2700 |
+
"learning_rate": 1.658334922758994e-05,
|
2701 |
+
"loss": 0.3405,
|
2702 |
+
"step": 365000
|
2703 |
+
},
|
2704 |
+
{
|
2705 |
+
"epoch": 0.36,
|
2706 |
+
"eval_runtime": 3198.5996,
|
2707 |
+
"eval_samples_per_second": 106.188,
|
2708 |
+
"eval_steps_per_second": 13.274,
|
2709 |
+
"step": 365000
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 0.37,
|
2713 |
+
"learning_rate": 1.6570847700585524e-05,
|
2714 |
+
"loss": 0.3406,
|
2715 |
+
"step": 366000
|
2716 |
+
},
|
2717 |
+
{
|
2718 |
+
"epoch": 0.37,
|
2719 |
+
"learning_rate": 1.6558322160142462e-05,
|
2720 |
+
"loss": 0.341,
|
2721 |
+
"step": 367000
|
2722 |
+
},
|
2723 |
+
{
|
2724 |
+
"epoch": 0.37,
|
2725 |
+
"learning_rate": 1.654577274323806e-05,
|
2726 |
+
"loss": 0.342,
|
2727 |
+
"step": 368000
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 0.37,
|
2731 |
+
"learning_rate": 1.653319958711072e-05,
|
2732 |
+
"loss": 0.3479,
|
2733 |
+
"step": 369000
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 0.37,
|
2737 |
+
"learning_rate": 1.6520602829258474e-05,
|
2738 |
+
"loss": 0.3487,
|
2739 |
+
"step": 370000
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 0.37,
|
2743 |
+
"eval_runtime": 3164.3305,
|
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": 3.2762057640955085e+21,
|
2752 |
"trial_name": null,
|
2753 |
"trial_params": null
|
2754 |
}
|
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:cb18529144e5631f4110d550e5ae8dec1ab66ae10143ec11a390bb4bb1168003
|
3 |
size 454197066
|