Training in progress, step 12500, 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 891558696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84809acf96301d8b75572b9aa608e1f2afc0533f5ee30f46a0431492a1a275f4
|
3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783272762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:984c2e60f40d6b8ecdf43a9a9b2fa6e7fed8a14485e9250dde4344fd78072844
|
3 |
size 1783272762
|
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 sha256:96d212c2076c947a58295d88ed7a741f064eeda3b1a76832bac43470f08461ef
|
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:cb61de87e596461b3a2fd8b9e3ff4ac6a0ba9feb11b3f41b64bad2f67194d86a
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./fine-tuned/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -2647,6 +2647,116 @@
|
|
2647 |
"eval_samples_per_second": 25.43,
|
2648 |
"eval_steps_per_second": 3.182,
|
2649 |
"step": 12000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2650 |
}
|
2651 |
],
|
2652 |
"logging_steps": 50,
|
@@ -2666,7 +2776,7 @@
|
|
2666 |
"attributes": {}
|
2667 |
}
|
2668 |
},
|
2669 |
-
"total_flos":
|
2670 |
"train_batch_size": 8,
|
2671 |
"trial_name": null,
|
2672 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.10325244069099426,
|
3 |
+
"best_model_checkpoint": "./fine-tuned/checkpoint-12500",
|
4 |
+
"epoch": 2.195486080618249,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 12500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2647 |
"eval_samples_per_second": 25.43,
|
2648 |
"eval_steps_per_second": 3.182,
|
2649 |
"step": 12000
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 2.116448581715992,
|
2653 |
+
"grad_norm": 10527.5751953125,
|
2654 |
+
"learning_rate": 1.4125241524679432e-05,
|
2655 |
+
"loss": 0.0997,
|
2656 |
+
"step": 12050
|
2657 |
+
},
|
2658 |
+
{
|
2659 |
+
"epoch": 2.125230526038465,
|
2660 |
+
"grad_norm": 12505.5380859375,
|
2661 |
+
"learning_rate": 1.4059371157561918e-05,
|
2662 |
+
"loss": 0.0981,
|
2663 |
+
"step": 12100
|
2664 |
+
},
|
2665 |
+
{
|
2666 |
+
"epoch": 2.125230526038465,
|
2667 |
+
"eval_loss": 0.10333307832479477,
|
2668 |
+
"eval_runtime": 175.2906,
|
2669 |
+
"eval_samples_per_second": 25.443,
|
2670 |
+
"eval_steps_per_second": 3.183,
|
2671 |
+
"step": 12100
|
2672 |
+
},
|
2673 |
+
{
|
2674 |
+
"epoch": 2.134012470360938,
|
2675 |
+
"grad_norm": 9851.1923828125,
|
2676 |
+
"learning_rate": 1.3993500790444406e-05,
|
2677 |
+
"loss": 0.1006,
|
2678 |
+
"step": 12150
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 2.142794414683411,
|
2682 |
+
"grad_norm": 9354.9697265625,
|
2683 |
+
"learning_rate": 1.3927630423326893e-05,
|
2684 |
+
"loss": 0.1032,
|
2685 |
+
"step": 12200
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 2.142794414683411,
|
2689 |
+
"eval_loss": 0.10333764553070068,
|
2690 |
+
"eval_runtime": 175.147,
|
2691 |
+
"eval_samples_per_second": 25.464,
|
2692 |
+
"eval_steps_per_second": 3.186,
|
2693 |
+
"step": 12200
|
2694 |
+
},
|
2695 |
+
{
|
2696 |
+
"epoch": 2.151576359005884,
|
2697 |
+
"grad_norm": 7880.865234375,
|
2698 |
+
"learning_rate": 1.3861760056209381e-05,
|
2699 |
+
"loss": 0.0957,
|
2700 |
+
"step": 12250
|
2701 |
+
},
|
2702 |
+
{
|
2703 |
+
"epoch": 2.160358303328357,
|
2704 |
+
"grad_norm": 17636.8515625,
|
2705 |
+
"learning_rate": 1.3795889689091866e-05,
|
2706 |
+
"loss": 0.0952,
|
2707 |
+
"step": 12300
|
2708 |
+
},
|
2709 |
+
{
|
2710 |
+
"epoch": 2.160358303328357,
|
2711 |
+
"eval_loss": 0.10335990786552429,
|
2712 |
+
"eval_runtime": 175.3211,
|
2713 |
+
"eval_samples_per_second": 25.439,
|
2714 |
+
"eval_steps_per_second": 3.183,
|
2715 |
+
"step": 12300
|
2716 |
+
},
|
2717 |
+
{
|
2718 |
+
"epoch": 2.1691402476508297,
|
2719 |
+
"grad_norm": 15586.3701171875,
|
2720 |
+
"learning_rate": 1.3730019321974355e-05,
|
2721 |
+
"loss": 0.098,
|
2722 |
+
"step": 12350
|
2723 |
+
},
|
2724 |
+
{
|
2725 |
+
"epoch": 2.1779221919733027,
|
2726 |
+
"grad_norm": 11448.01953125,
|
2727 |
+
"learning_rate": 1.3664148954856841e-05,
|
2728 |
+
"loss": 0.0942,
|
2729 |
+
"step": 12400
|
2730 |
+
},
|
2731 |
+
{
|
2732 |
+
"epoch": 2.1779221919733027,
|
2733 |
+
"eval_loss": 0.10320650041103363,
|
2734 |
+
"eval_runtime": 175.2718,
|
2735 |
+
"eval_samples_per_second": 25.446,
|
2736 |
+
"eval_steps_per_second": 3.184,
|
2737 |
+
"step": 12400
|
2738 |
+
},
|
2739 |
+
{
|
2740 |
+
"epoch": 2.1867041362957758,
|
2741 |
+
"grad_norm": 13402.5732421875,
|
2742 |
+
"learning_rate": 1.359827858773933e-05,
|
2743 |
+
"loss": 0.1016,
|
2744 |
+
"step": 12450
|
2745 |
+
},
|
2746 |
+
{
|
2747 |
+
"epoch": 2.195486080618249,
|
2748 |
+
"grad_norm": 7308.1123046875,
|
2749 |
+
"learning_rate": 1.3532408220621816e-05,
|
2750 |
+
"loss": 0.0978,
|
2751 |
+
"step": 12500
|
2752 |
+
},
|
2753 |
+
{
|
2754 |
+
"epoch": 2.195486080618249,
|
2755 |
+
"eval_loss": 0.10325244069099426,
|
2756 |
+
"eval_runtime": 175.4131,
|
2757 |
+
"eval_samples_per_second": 25.426,
|
2758 |
+
"eval_steps_per_second": 3.181,
|
2759 |
+
"step": 12500
|
2760 |
}
|
2761 |
],
|
2762 |
"logging_steps": 50,
|
|
|
2776 |
"attributes": {}
|
2777 |
}
|
2778 |
},
|
2779 |
+
"total_flos": 6.089152635076608e+16,
|
2780 |
"train_batch_size": 8,
|
2781 |
"trial_name": null,
|
2782 |
"trial_params": null
|