Uploaded checkpoint-2000
Browse files- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +721 -5
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 119975656
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e83bbbf0870fbe09159719566d678fc0c4aeecbc451c1d4947915b25a14c64e
|
| 3 |
size 119975656
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 240145026
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdecaf2bf9e2cb3f8cde47cb9305ea2b8c70b9558e5279786a988f7c47d73b4d
|
| 3 |
size 240145026
|
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 sha256:00b2d8ce9c47af2735f9fc373d1aa74a8815666d3e7d1d7b5a7c6a3fa49ef6fe
|
| 3 |
size 14244
|
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 sha256:78180a777fabc8bdc6e37d70a05529fbfe5bbeb093c49dd0124cc2bdeb32db78
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "runs/deepseek_lora_20240423-133229/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -723,6 +723,722 @@
|
|
| 723 |
"eval_samples_per_second": 16.085,
|
| 724 |
"eval_steps_per_second": 16.085,
|
| 725 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 726 |
}
|
| 727 |
],
|
| 728 |
"logging_steps": 10,
|
|
@@ -730,7 +1446,7 @@
|
|
| 730 |
"num_input_tokens_seen": 0,
|
| 731 |
"num_train_epochs": 2,
|
| 732 |
"save_steps": 1000,
|
| 733 |
-
"total_flos":
|
| 734 |
"train_batch_size": 1,
|
| 735 |
"trial_name": null,
|
| 736 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.018313532695174217,
|
| 3 |
+
"best_model_checkpoint": "runs/deepseek_lora_20240423-133229/checkpoint-2000",
|
| 4 |
+
"epoch": 0.6266154930680661,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 723 |
"eval_samples_per_second": 16.085,
|
| 724 |
"eval_steps_per_second": 16.085,
|
| 725 |
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.32,
|
| 729 |
+
"grad_norm": 0.003431650809943676,
|
| 730 |
+
"learning_rate": 1.7733333333333335e-05,
|
| 731 |
+
"loss": 0.0425,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.32,
|
| 736 |
+
"grad_norm": 0.005604119040071964,
|
| 737 |
+
"learning_rate": 1.768888888888889e-05,
|
| 738 |
+
"loss": 0.0727,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.32,
|
| 743 |
+
"grad_norm": 0.058546032756567,
|
| 744 |
+
"learning_rate": 1.7644444444444446e-05,
|
| 745 |
+
"loss": 0.1304,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.33,
|
| 750 |
+
"grad_norm": 1.0267212390899658,
|
| 751 |
+
"learning_rate": 1.76e-05,
|
| 752 |
+
"loss": 0.0496,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.33,
|
| 757 |
+
"grad_norm": 3.5381667613983154,
|
| 758 |
+
"learning_rate": 1.7555555555555556e-05,
|
| 759 |
+
"loss": 0.0935,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.33,
|
| 764 |
+
"grad_norm": 0.006851164624094963,
|
| 765 |
+
"learning_rate": 1.751111111111111e-05,
|
| 766 |
+
"loss": 0.0344,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.34,
|
| 771 |
+
"grad_norm": 0.005180824548006058,
|
| 772 |
+
"learning_rate": 1.7466666666666667e-05,
|
| 773 |
+
"loss": 0.0195,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.34,
|
| 778 |
+
"grad_norm": 1.586403489112854,
|
| 779 |
+
"learning_rate": 1.7422222222222222e-05,
|
| 780 |
+
"loss": 0.0868,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.34,
|
| 785 |
+
"grad_norm": 0.14490236341953278,
|
| 786 |
+
"learning_rate": 1.737777777777778e-05,
|
| 787 |
+
"loss": 0.0489,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.34,
|
| 792 |
+
"grad_norm": 0.005752285942435265,
|
| 793 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 794 |
+
"loss": 0.0625,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.35,
|
| 799 |
+
"grad_norm": 0.8000261187553406,
|
| 800 |
+
"learning_rate": 1.728888888888889e-05,
|
| 801 |
+
"loss": 0.0923,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.35,
|
| 806 |
+
"grad_norm": 0.024827931076288223,
|
| 807 |
+
"learning_rate": 1.7244444444444446e-05,
|
| 808 |
+
"loss": 0.0355,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.35,
|
| 813 |
+
"grad_norm": 3.424243927001953,
|
| 814 |
+
"learning_rate": 1.72e-05,
|
| 815 |
+
"loss": 0.0659,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.36,
|
| 820 |
+
"grad_norm": 3.4055392742156982,
|
| 821 |
+
"learning_rate": 1.7155555555555557e-05,
|
| 822 |
+
"loss": 0.0681,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.36,
|
| 827 |
+
"grad_norm": 0.0077874124981462955,
|
| 828 |
+
"learning_rate": 1.7111111111111112e-05,
|
| 829 |
+
"loss": 0.106,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.36,
|
| 834 |
+
"grad_norm": 0.006299824919551611,
|
| 835 |
+
"learning_rate": 1.706666666666667e-05,
|
| 836 |
+
"loss": 0.0438,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.37,
|
| 841 |
+
"grad_norm": 0.004886701237410307,
|
| 842 |
+
"learning_rate": 1.7022222222222226e-05,
|
| 843 |
+
"loss": 0.0403,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.37,
|
| 848 |
+
"grad_norm": 0.0028305843006819487,
|
| 849 |
+
"learning_rate": 1.697777777777778e-05,
|
| 850 |
+
"loss": 0.0299,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.37,
|
| 855 |
+
"grad_norm": 0.36411717534065247,
|
| 856 |
+
"learning_rate": 1.6933333333333336e-05,
|
| 857 |
+
"loss": 0.0639,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.38,
|
| 862 |
+
"grad_norm": 0.004984024912118912,
|
| 863 |
+
"learning_rate": 1.688888888888889e-05,
|
| 864 |
+
"loss": 0.1363,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.38,
|
| 869 |
+
"grad_norm": 2.4117214679718018,
|
| 870 |
+
"learning_rate": 1.6844444444444447e-05,
|
| 871 |
+
"loss": 0.018,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.38,
|
| 876 |
+
"grad_norm": 1.2183905839920044,
|
| 877 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 878 |
+
"loss": 0.0062,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.39,
|
| 883 |
+
"grad_norm": 0.05338621512055397,
|
| 884 |
+
"learning_rate": 1.6755555555555557e-05,
|
| 885 |
+
"loss": 0.0343,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.39,
|
| 890 |
+
"grad_norm": 0.009272832423448563,
|
| 891 |
+
"learning_rate": 1.6711111111111112e-05,
|
| 892 |
+
"loss": 0.073,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.39,
|
| 897 |
+
"grad_norm": 0.0033628540113568306,
|
| 898 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 899 |
+
"loss": 0.0272,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.39,
|
| 904 |
+
"grad_norm": 0.055562809109687805,
|
| 905 |
+
"learning_rate": 1.6622222222222223e-05,
|
| 906 |
+
"loss": 0.0821,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.4,
|
| 911 |
+
"grad_norm": 1.6196753978729248,
|
| 912 |
+
"learning_rate": 1.6577777777777778e-05,
|
| 913 |
+
"loss": 0.0153,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.4,
|
| 918 |
+
"grad_norm": 0.004278264008462429,
|
| 919 |
+
"learning_rate": 1.6533333333333333e-05,
|
| 920 |
+
"loss": 0.022,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.4,
|
| 925 |
+
"grad_norm": 0.044023897498846054,
|
| 926 |
+
"learning_rate": 1.648888888888889e-05,
|
| 927 |
+
"loss": 0.0652,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.41,
|
| 932 |
+
"grad_norm": 0.08157920837402344,
|
| 933 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 934 |
+
"loss": 0.0745,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.41,
|
| 939 |
+
"grad_norm": 2.1145012378692627,
|
| 940 |
+
"learning_rate": 1.64e-05,
|
| 941 |
+
"loss": 0.0497,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.41,
|
| 946 |
+
"grad_norm": 0.00495466822758317,
|
| 947 |
+
"learning_rate": 1.6355555555555557e-05,
|
| 948 |
+
"loss": 0.0688,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.42,
|
| 953 |
+
"grad_norm": 2.055875778198242,
|
| 954 |
+
"learning_rate": 1.6311111111111113e-05,
|
| 955 |
+
"loss": 0.0456,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.42,
|
| 960 |
+
"grad_norm": 7.260204315185547,
|
| 961 |
+
"learning_rate": 1.6266666666666668e-05,
|
| 962 |
+
"loss": 0.0968,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.42,
|
| 967 |
+
"grad_norm": 0.00300275138579309,
|
| 968 |
+
"learning_rate": 1.6222222222222223e-05,
|
| 969 |
+
"loss": 0.0031,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.43,
|
| 974 |
+
"grad_norm": 0.6148861050605774,
|
| 975 |
+
"learning_rate": 1.617777777777778e-05,
|
| 976 |
+
"loss": 0.1008,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.43,
|
| 981 |
+
"grad_norm": 0.005163553170859814,
|
| 982 |
+
"learning_rate": 1.6133333333333334e-05,
|
| 983 |
+
"loss": 0.0454,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.43,
|
| 988 |
+
"grad_norm": 3.313544988632202,
|
| 989 |
+
"learning_rate": 1.608888888888889e-05,
|
| 990 |
+
"loss": 0.0843,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.44,
|
| 995 |
+
"grad_norm": 0.061028964817523956,
|
| 996 |
+
"learning_rate": 1.6044444444444444e-05,
|
| 997 |
+
"loss": 0.0467,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.44,
|
| 1002 |
+
"grad_norm": 0.011183706112205982,
|
| 1003 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 1004 |
+
"loss": 0.0539,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.44,
|
| 1009 |
+
"grad_norm": 0.00391357159242034,
|
| 1010 |
+
"learning_rate": 1.5955555555555558e-05,
|
| 1011 |
+
"loss": 0.007,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.44,
|
| 1016 |
+
"grad_norm": 0.21193568408489227,
|
| 1017 |
+
"learning_rate": 1.5911111111111113e-05,
|
| 1018 |
+
"loss": 0.0723,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.45,
|
| 1023 |
+
"grad_norm": 1.344232201576233,
|
| 1024 |
+
"learning_rate": 1.586666666666667e-05,
|
| 1025 |
+
"loss": 0.0093,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.45,
|
| 1030 |
+
"grad_norm": 2.125556707382202,
|
| 1031 |
+
"learning_rate": 1.5822222222222224e-05,
|
| 1032 |
+
"loss": 0.1089,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.45,
|
| 1037 |
+
"grad_norm": 1.9358251094818115,
|
| 1038 |
+
"learning_rate": 1.577777777777778e-05,
|
| 1039 |
+
"loss": 0.129,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.46,
|
| 1044 |
+
"grad_norm": 0.25835612416267395,
|
| 1045 |
+
"learning_rate": 1.5733333333333334e-05,
|
| 1046 |
+
"loss": 0.0225,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.46,
|
| 1051 |
+
"grad_norm": 0.004413430579006672,
|
| 1052 |
+
"learning_rate": 1.5688888888888893e-05,
|
| 1053 |
+
"loss": 0.0184,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.46,
|
| 1058 |
+
"grad_norm": 2.6624996662139893,
|
| 1059 |
+
"learning_rate": 1.5644444444444448e-05,
|
| 1060 |
+
"loss": 0.0924,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.47,
|
| 1065 |
+
"grad_norm": 0.023669052869081497,
|
| 1066 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 1067 |
+
"loss": 0.0468,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.47,
|
| 1072 |
+
"grad_norm": 0.9958231449127197,
|
| 1073 |
+
"learning_rate": 1.555555555555556e-05,
|
| 1074 |
+
"loss": 0.0602,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.47,
|
| 1079 |
+
"eval_loss": 0.023086324334144592,
|
| 1080 |
+
"eval_runtime": 62.044,
|
| 1081 |
+
"eval_samples_per_second": 16.118,
|
| 1082 |
+
"eval_steps_per_second": 16.118,
|
| 1083 |
+
"step": 1500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.47,
|
| 1087 |
+
"grad_norm": 0.0457289032638073,
|
| 1088 |
+
"learning_rate": 1.5511111111111114e-05,
|
| 1089 |
+
"loss": 0.0725,
|
| 1090 |
+
"step": 1510
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.48,
|
| 1094 |
+
"grad_norm": 2.0417847633361816,
|
| 1095 |
+
"learning_rate": 1.546666666666667e-05,
|
| 1096 |
+
"loss": 0.0446,
|
| 1097 |
+
"step": 1520
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.48,
|
| 1101 |
+
"grad_norm": 0.007491718512028456,
|
| 1102 |
+
"learning_rate": 1.5422222222222224e-05,
|
| 1103 |
+
"loss": 0.0693,
|
| 1104 |
+
"step": 1530
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.48,
|
| 1108 |
+
"grad_norm": 0.0023406276013702154,
|
| 1109 |
+
"learning_rate": 1.537777777777778e-05,
|
| 1110 |
+
"loss": 0.0398,
|
| 1111 |
+
"step": 1540
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.49,
|
| 1115 |
+
"grad_norm": 0.03808426856994629,
|
| 1116 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 1117 |
+
"loss": 0.0827,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.49,
|
| 1122 |
+
"grad_norm": 0.04878142476081848,
|
| 1123 |
+
"learning_rate": 1.528888888888889e-05,
|
| 1124 |
+
"loss": 0.0094,
|
| 1125 |
+
"step": 1560
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.49,
|
| 1129 |
+
"grad_norm": 0.002342456951737404,
|
| 1130 |
+
"learning_rate": 1.5244444444444447e-05,
|
| 1131 |
+
"loss": 0.0308,
|
| 1132 |
+
"step": 1570
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.5,
|
| 1136 |
+
"grad_norm": 0.002332750940695405,
|
| 1137 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 1138 |
+
"loss": 0.0703,
|
| 1139 |
+
"step": 1580
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.5,
|
| 1143 |
+
"grad_norm": 0.027806026861071587,
|
| 1144 |
+
"learning_rate": 1.5155555555555557e-05,
|
| 1145 |
+
"loss": 0.0577,
|
| 1146 |
+
"step": 1590
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.5,
|
| 1150 |
+
"grad_norm": 1.853770136833191,
|
| 1151 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 1152 |
+
"loss": 0.0872,
|
| 1153 |
+
"step": 1600
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.5,
|
| 1157 |
+
"grad_norm": 0.02809343859553337,
|
| 1158 |
+
"learning_rate": 1.5066666666666668e-05,
|
| 1159 |
+
"loss": 0.0651,
|
| 1160 |
+
"step": 1610
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.51,
|
| 1164 |
+
"grad_norm": 0.29635584354400635,
|
| 1165 |
+
"learning_rate": 1.5022222222222223e-05,
|
| 1166 |
+
"loss": 0.0784,
|
| 1167 |
+
"step": 1620
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.51,
|
| 1171 |
+
"grad_norm": 0.006036743987351656,
|
| 1172 |
+
"learning_rate": 1.497777777777778e-05,
|
| 1173 |
+
"loss": 0.0702,
|
| 1174 |
+
"step": 1630
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.51,
|
| 1178 |
+
"grad_norm": 0.0020562768913805485,
|
| 1179 |
+
"learning_rate": 1.4933333333333335e-05,
|
| 1180 |
+
"loss": 0.1133,
|
| 1181 |
+
"step": 1640
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.52,
|
| 1185 |
+
"grad_norm": 2.0853707790374756,
|
| 1186 |
+
"learning_rate": 1.488888888888889e-05,
|
| 1187 |
+
"loss": 0.0717,
|
| 1188 |
+
"step": 1650
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.52,
|
| 1192 |
+
"grad_norm": 2.024653434753418,
|
| 1193 |
+
"learning_rate": 1.4844444444444445e-05,
|
| 1194 |
+
"loss": 0.0978,
|
| 1195 |
+
"step": 1660
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.52,
|
| 1199 |
+
"grad_norm": 0.0029632914811372757,
|
| 1200 |
+
"learning_rate": 1.48e-05,
|
| 1201 |
+
"loss": 0.0269,
|
| 1202 |
+
"step": 1670
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.53,
|
| 1206 |
+
"grad_norm": 3.2619192600250244,
|
| 1207 |
+
"learning_rate": 1.4755555555555556e-05,
|
| 1208 |
+
"loss": 0.088,
|
| 1209 |
+
"step": 1680
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.53,
|
| 1213 |
+
"grad_norm": 0.9590596556663513,
|
| 1214 |
+
"learning_rate": 1.4711111111111111e-05,
|
| 1215 |
+
"loss": 0.0348,
|
| 1216 |
+
"step": 1690
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.53,
|
| 1220 |
+
"grad_norm": 0.01058279536664486,
|
| 1221 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 1222 |
+
"loss": 0.0473,
|
| 1223 |
+
"step": 1700
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.54,
|
| 1227 |
+
"grad_norm": 4.378236293792725,
|
| 1228 |
+
"learning_rate": 1.4622222222222225e-05,
|
| 1229 |
+
"loss": 0.0839,
|
| 1230 |
+
"step": 1710
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.54,
|
| 1234 |
+
"grad_norm": 0.04728490114212036,
|
| 1235 |
+
"learning_rate": 1.457777777777778e-05,
|
| 1236 |
+
"loss": 0.1131,
|
| 1237 |
+
"step": 1720
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.54,
|
| 1241 |
+
"grad_norm": 0.03082725591957569,
|
| 1242 |
+
"learning_rate": 1.4533333333333335e-05,
|
| 1243 |
+
"loss": 0.058,
|
| 1244 |
+
"step": 1730
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.55,
|
| 1248 |
+
"grad_norm": 1.4159008264541626,
|
| 1249 |
+
"learning_rate": 1.448888888888889e-05,
|
| 1250 |
+
"loss": 0.027,
|
| 1251 |
+
"step": 1740
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.55,
|
| 1255 |
+
"grad_norm": 0.09299231320619583,
|
| 1256 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 1257 |
+
"loss": 0.0152,
|
| 1258 |
+
"step": 1750
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.55,
|
| 1262 |
+
"grad_norm": 0.0018398365937173367,
|
| 1263 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 1264 |
+
"loss": 0.0005,
|
| 1265 |
+
"step": 1760
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.55,
|
| 1269 |
+
"grad_norm": 0.0032970942556858063,
|
| 1270 |
+
"learning_rate": 1.4355555555555556e-05,
|
| 1271 |
+
"loss": 0.068,
|
| 1272 |
+
"step": 1770
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.56,
|
| 1276 |
+
"grad_norm": 1.9869989156723022,
|
| 1277 |
+
"learning_rate": 1.4311111111111111e-05,
|
| 1278 |
+
"loss": 0.0802,
|
| 1279 |
+
"step": 1780
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.56,
|
| 1283 |
+
"grad_norm": 0.4349244236946106,
|
| 1284 |
+
"learning_rate": 1.4266666666666668e-05,
|
| 1285 |
+
"loss": 0.0022,
|
| 1286 |
+
"step": 1790
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.56,
|
| 1290 |
+
"grad_norm": 6.195014476776123,
|
| 1291 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 1292 |
+
"loss": 0.075,
|
| 1293 |
+
"step": 1800
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.57,
|
| 1297 |
+
"grad_norm": 4.658276557922363,
|
| 1298 |
+
"learning_rate": 1.4177777777777779e-05,
|
| 1299 |
+
"loss": 0.0341,
|
| 1300 |
+
"step": 1810
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.57,
|
| 1304 |
+
"grad_norm": 2.3556618690490723,
|
| 1305 |
+
"learning_rate": 1.4133333333333334e-05,
|
| 1306 |
+
"loss": 0.0735,
|
| 1307 |
+
"step": 1820
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.57,
|
| 1311 |
+
"grad_norm": 0.00235918490216136,
|
| 1312 |
+
"learning_rate": 1.408888888888889e-05,
|
| 1313 |
+
"loss": 0.0133,
|
| 1314 |
+
"step": 1830
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.58,
|
| 1318 |
+
"grad_norm": 0.0019710322376340628,
|
| 1319 |
+
"learning_rate": 1.4044444444444445e-05,
|
| 1320 |
+
"loss": 0.0714,
|
| 1321 |
+
"step": 1840
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.58,
|
| 1325 |
+
"grad_norm": 0.0038756057620048523,
|
| 1326 |
+
"learning_rate": 1.4e-05,
|
| 1327 |
+
"loss": 0.058,
|
| 1328 |
+
"step": 1850
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.58,
|
| 1332 |
+
"grad_norm": 0.13870251178741455,
|
| 1333 |
+
"learning_rate": 1.3955555555555558e-05,
|
| 1334 |
+
"loss": 0.0598,
|
| 1335 |
+
"step": 1860
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.59,
|
| 1339 |
+
"grad_norm": 0.0035449981223791838,
|
| 1340 |
+
"learning_rate": 1.3911111111111114e-05,
|
| 1341 |
+
"loss": 0.0825,
|
| 1342 |
+
"step": 1870
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.59,
|
| 1346 |
+
"grad_norm": 0.005458540748804808,
|
| 1347 |
+
"learning_rate": 1.3866666666666669e-05,
|
| 1348 |
+
"loss": 0.0485,
|
| 1349 |
+
"step": 1880
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.59,
|
| 1353 |
+
"grad_norm": 0.0037788543850183487,
|
| 1354 |
+
"learning_rate": 1.3822222222222224e-05,
|
| 1355 |
+
"loss": 0.0279,
|
| 1356 |
+
"step": 1890
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.6,
|
| 1360 |
+
"grad_norm": 2.4127650260925293,
|
| 1361 |
+
"learning_rate": 1.377777777777778e-05,
|
| 1362 |
+
"loss": 0.0414,
|
| 1363 |
+
"step": 1900
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.6,
|
| 1367 |
+
"grad_norm": 1.9315361976623535,
|
| 1368 |
+
"learning_rate": 1.3733333333333335e-05,
|
| 1369 |
+
"loss": 0.0541,
|
| 1370 |
+
"step": 1910
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.6,
|
| 1374 |
+
"grad_norm": 0.001827953034080565,
|
| 1375 |
+
"learning_rate": 1.368888888888889e-05,
|
| 1376 |
+
"loss": 0.0607,
|
| 1377 |
+
"step": 1920
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.6,
|
| 1381 |
+
"grad_norm": 3.0561037063598633,
|
| 1382 |
+
"learning_rate": 1.3644444444444445e-05,
|
| 1383 |
+
"loss": 0.0489,
|
| 1384 |
+
"step": 1930
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.61,
|
| 1388 |
+
"grad_norm": 1.7366918325424194,
|
| 1389 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 1390 |
+
"loss": 0.0107,
|
| 1391 |
+
"step": 1940
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.61,
|
| 1395 |
+
"grad_norm": 0.0025562909431755543,
|
| 1396 |
+
"learning_rate": 1.3555555555555557e-05,
|
| 1397 |
+
"loss": 0.0305,
|
| 1398 |
+
"step": 1950
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.61,
|
| 1402 |
+
"grad_norm": 0.006456757429987192,
|
| 1403 |
+
"learning_rate": 1.3511111111111112e-05,
|
| 1404 |
+
"loss": 0.0741,
|
| 1405 |
+
"step": 1960
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.62,
|
| 1409 |
+
"grad_norm": 0.003276415169239044,
|
| 1410 |
+
"learning_rate": 1.3466666666666668e-05,
|
| 1411 |
+
"loss": 0.0276,
|
| 1412 |
+
"step": 1970
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.62,
|
| 1416 |
+
"grad_norm": 0.0036139176227152348,
|
| 1417 |
+
"learning_rate": 1.3422222222222223e-05,
|
| 1418 |
+
"loss": 0.0886,
|
| 1419 |
+
"step": 1980
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.62,
|
| 1423 |
+
"grad_norm": 0.006649693939834833,
|
| 1424 |
+
"learning_rate": 1.3377777777777778e-05,
|
| 1425 |
+
"loss": 0.0179,
|
| 1426 |
+
"step": 1990
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.63,
|
| 1430 |
+
"grad_norm": 0.002991742454469204,
|
| 1431 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 1432 |
+
"loss": 0.0372,
|
| 1433 |
+
"step": 2000
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.63,
|
| 1437 |
+
"eval_loss": 0.018313532695174217,
|
| 1438 |
+
"eval_runtime": 62.0835,
|
| 1439 |
+
"eval_samples_per_second": 16.107,
|
| 1440 |
+
"eval_steps_per_second": 16.107,
|
| 1441 |
+
"step": 2000
|
| 1442 |
}
|
| 1443 |
],
|
| 1444 |
"logging_steps": 10,
|
|
|
|
| 1446 |
"num_input_tokens_seen": 0,
|
| 1447 |
"num_train_epochs": 2,
|
| 1448 |
"save_steps": 1000,
|
| 1449 |
+
"total_flos": 3.2204251987968e+16,
|
| 1450 |
"train_batch_size": 1,
|
| 1451 |
"trial_name": null,
|
| 1452 |
"trial_params": null
|