Training in progress, step 240000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e68b4a0a6b94eb632e742bc345c16192cd89f209b7b0ac29f628146840be4449
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9366ce17f6091afd924db97ceef8386221ffc910f4dd47184a5d10c2b3e3faee
|
3 |
size 201355195
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:737a82a6d5b6942164fc12e8fa155db845012b151e3b5584843823716397ae9b
|
3 |
size 14503
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8198603ed51ffe435cd9043f9c18e4d58e7063c081adbb17d80023dc24f958c1
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d948fece76679c907d39a4e4079899eafaedf0343121e7b9351f217fbc1b73d
|
3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b88b6a39c725a5780e307b5c113a0136f71b07fc7b1ee9c05302ac9608780860
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d2f9b1be4f6270a10823e97008556f76ee3d60fb8c03eb426ae573481e83ca6
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c9bf7a79e8018cc90ca641ad1e1612dcd5dbd5bc900083188de90e0d76e12ef
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2826,6 +2826,66 @@
|
|
2826 |
"learning_rate": 8.66296163494292e-05,
|
2827 |
"loss": 0.3321,
|
2828 |
"step": 235000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2829 |
}
|
2830 |
],
|
2831 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.085105658675245,
|
5 |
+
"global_step": 240000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2826 |
"learning_rate": 8.66296163494292e-05,
|
2827 |
"loss": 0.3321,
|
2828 |
"step": 235000
|
2829 |
+
},
|
2830 |
+
{
|
2831 |
+
"epoch": 4.01,
|
2832 |
+
"learning_rate": 8.641066100598926e-05,
|
2833 |
+
"loss": 0.332,
|
2834 |
+
"step": 235500
|
2835 |
+
},
|
2836 |
+
{
|
2837 |
+
"epoch": 4.02,
|
2838 |
+
"learning_rate": 8.619164239191329e-05,
|
2839 |
+
"loss": 0.3319,
|
2840 |
+
"step": 236000
|
2841 |
+
},
|
2842 |
+
{
|
2843 |
+
"epoch": 4.03,
|
2844 |
+
"learning_rate": 8.59725626688266e-05,
|
2845 |
+
"loss": 0.3319,
|
2846 |
+
"step": 236500
|
2847 |
+
},
|
2848 |
+
{
|
2849 |
+
"epoch": 4.03,
|
2850 |
+
"learning_rate": 8.575342399895754e-05,
|
2851 |
+
"loss": 0.3315,
|
2852 |
+
"step": 237000
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 4.04,
|
2856 |
+
"learning_rate": 8.55342285451164e-05,
|
2857 |
+
"loss": 0.3316,
|
2858 |
+
"step": 237500
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 4.05,
|
2862 |
+
"learning_rate": 8.531497847067375e-05,
|
2863 |
+
"loss": 0.3317,
|
2864 |
+
"step": 238000
|
2865 |
+
},
|
2866 |
+
{
|
2867 |
+
"epoch": 4.06,
|
2868 |
+
"learning_rate": 8.509567593953936e-05,
|
2869 |
+
"loss": 0.3314,
|
2870 |
+
"step": 238500
|
2871 |
+
},
|
2872 |
+
{
|
2873 |
+
"epoch": 4.07,
|
2874 |
+
"learning_rate": 8.487632311614066e-05,
|
2875 |
+
"loss": 0.3315,
|
2876 |
+
"step": 239000
|
2877 |
+
},
|
2878 |
+
{
|
2879 |
+
"epoch": 4.08,
|
2880 |
+
"learning_rate": 8.465692216540142e-05,
|
2881 |
+
"loss": 0.3315,
|
2882 |
+
"step": 239500
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 4.09,
|
2886 |
+
"learning_rate": 8.443791419097638e-05,
|
2887 |
+
"loss": 0.3312,
|
2888 |
+
"step": 240000
|
2889 |
}
|
2890 |
],
|
2891 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9366ce17f6091afd924db97ceef8386221ffc910f4dd47184a5d10c2b3e3faee
|
3 |
size 201355195
|