Commit
•
aa9de5a
1
Parent(s):
695bbd3
Training in progress, step 390000
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:ea287e9b4ef69b399ab26f5a72f16419f78692f80f4478f9dc9fde54c01b3139
|
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 sha256:0754eb41ff5a1456b603e8b2753adb511ac0a9ee839b9d73f658f3c72064f5ce
|
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:ea76d909d3c482cb352315f678531422d38691040b817f22cbe42d6a4283267d
|
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:ceb7667759b15c886ebe5f226629aa0745d8db84769a12c7b2d7c8d4d08bd35a
|
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,
|
@@ -2818,11 +2818,85 @@
|
|
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.
|
2826 |
"trial_name": null,
|
2827 |
"trial_params": null
|
2828 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.39,
|
5 |
+
"global_step": 390000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2818 |
"eval_samples_per_second": 107.622,
|
2819 |
"eval_steps_per_second": 13.453,
|
2820 |
"step": 380000
|
2821 |
+
},
|
2822 |
+
{
|
2823 |
+
"epoch": 0.38,
|
2824 |
+
"learning_rate": 1.6380520358812106e-05,
|
2825 |
+
"loss": 0.3466,
|
2826 |
+
"step": 381000
|
2827 |
+
},
|
2828 |
+
{
|
2829 |
+
"epoch": 0.38,
|
2830 |
+
"learning_rate": 1.636765119754312e-05,
|
2831 |
+
"loss": 0.345,
|
2832 |
+
"step": 382000
|
2833 |
+
},
|
2834 |
+
{
|
2835 |
+
"epoch": 0.38,
|
2836 |
+
"learning_rate": 1.635476024495989e-05,
|
2837 |
+
"loss": 0.3439,
|
2838 |
+
"step": 383000
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 0.38,
|
2842 |
+
"learning_rate": 1.6341847642035807e-05,
|
2843 |
+
"loss": 0.3447,
|
2844 |
+
"step": 384000
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 0.39,
|
2848 |
+
"learning_rate": 1.632891352998103e-05,
|
2849 |
+
"loss": 0.3453,
|
2850 |
+
"step": 385000
|
2851 |
+
},
|
2852 |
+
{
|
2853 |
+
"epoch": 0.39,
|
2854 |
+
"eval_runtime": 3143.6271,
|
2855 |
+
"eval_samples_per_second": 108.045,
|
2856 |
+
"eval_steps_per_second": 13.506,
|
2857 |
+
"step": 385000
|
2858 |
+
},
|
2859 |
+
{
|
2860 |
+
"epoch": 0.39,
|
2861 |
+
"learning_rate": 1.631595805024093e-05,
|
2862 |
+
"loss": 0.3451,
|
2863 |
+
"step": 386000
|
2864 |
+
},
|
2865 |
+
{
|
2866 |
+
"epoch": 0.39,
|
2867 |
+
"learning_rate": 1.6302981344494562e-05,
|
2868 |
+
"loss": 0.3411,
|
2869 |
+
"step": 387000
|
2870 |
+
},
|
2871 |
+
{
|
2872 |
+
"epoch": 0.39,
|
2873 |
+
"learning_rate": 1.62899835546531e-05,
|
2874 |
+
"loss": 0.3435,
|
2875 |
+
"step": 388000
|
2876 |
+
},
|
2877 |
+
{
|
2878 |
+
"epoch": 0.39,
|
2879 |
+
"learning_rate": 1.6276964822858297e-05,
|
2880 |
+
"loss": 0.3437,
|
2881 |
+
"step": 389000
|
2882 |
+
},
|
2883 |
+
{
|
2884 |
+
"epoch": 0.39,
|
2885 |
+
"learning_rate": 1.6263925291480904e-05,
|
2886 |
+
"loss": 0.3446,
|
2887 |
+
"step": 390000
|
2888 |
+
},
|
2889 |
+
{
|
2890 |
+
"epoch": 0.39,
|
2891 |
+
"eval_runtime": 3211.4597,
|
2892 |
+
"eval_samples_per_second": 105.762,
|
2893 |
+
"eval_steps_per_second": 13.22,
|
2894 |
+
"step": 390000
|
2895 |
}
|
2896 |
],
|
2897 |
"max_steps": 1000000,
|
2898 |
"num_train_epochs": 9223372036854775807,
|
2899 |
+
"total_flos": 3.4532979675601306e+21,
|
2900 |
"trial_name": null,
|
2901 |
"trial_params": null
|
2902 |
}
|
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 sha256:0754eb41ff5a1456b603e8b2753adb511ac0a9ee839b9d73f658f3c72064f5ce
|
3 |
size 454197066
|