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 sha256:43548233115b1926142897a151a3631f4b41acfc039eba671c18547dea043457
|
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 sha256:5ea7bc5a0a91d5c301ba6c460b885286f918d844ce5bae63bfed79ecfee6e0cd
|
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:a43a8e8f7a43259e117752927339073e85a6c1dbf46144320533f84404f82686
|
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 sha256:4dc8d98ee626b77f73911e2698b2c28a5b3957b432c4490fa0dd7b085c000ce8
|
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 sha256:60fa94abd044f5e7958be233ca015ec020ca9eebe87d1d6d93c07c87520fe077
|
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 sha256:441b78ea8c989351b599920fec3602f59a285e6ce627c641c6ab5a5fede13f4e
|
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 sha256:1cd079af7cf9e88b115010548d12e5344e06040fb0b30109605035bfba0fc3a9
|
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:c119560eda4b60d3c02bb728ac2516f57bfe083a6cf1582a6194c2e1c14a30de
|
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": 4.
|
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": 8.662742711628061e-05,
|
2827 |
"loss": 0.3303,
|
2828 |
"step": 235000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2829 |
}
|
2830 |
],
|
2831 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.085106382978723,
|
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": 8.662742711628061e-05,
|
2827 |
"loss": 0.3303,
|
2828 |
"step": 235000
|
2829 |
+
},
|
2830 |
+
{
|
2831 |
+
"epoch": 4.01,
|
2832 |
+
"learning_rate": 8.640847112943632e-05,
|
2833 |
+
"loss": 0.3301,
|
2834 |
+
"step": 235500
|
2835 |
+
},
|
2836 |
+
{
|
2837 |
+
"epoch": 4.02,
|
2838 |
+
"learning_rate": 8.618945189356917e-05,
|
2839 |
+
"loss": 0.3301,
|
2840 |
+
"step": 236000
|
2841 |
+
},
|
2842 |
+
{
|
2843 |
+
"epoch": 4.03,
|
2844 |
+
"learning_rate": 8.59703715703106e-05,
|
2845 |
+
"loss": 0.33,
|
2846 |
+
"step": 236500
|
2847 |
+
},
|
2848 |
+
{
|
2849 |
+
"epoch": 4.03,
|
2850 |
+
"learning_rate": 8.5751232321895e-05,
|
2851 |
+
"loss": 0.3298,
|
2852 |
+
"step": 237000
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 4.04,
|
2856 |
+
"learning_rate": 8.553203631113821e-05,
|
2857 |
+
"loss": 0.3301,
|
2858 |
+
"step": 237500
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 4.05,
|
2862 |
+
"learning_rate": 8.531278570141643e-05,
|
2863 |
+
"loss": 0.3297,
|
2864 |
+
"step": 238000
|
2865 |
+
},
|
2866 |
+
{
|
2867 |
+
"epoch": 4.06,
|
2868 |
+
"learning_rate": 8.509348265664461e-05,
|
2869 |
+
"loss": 0.3297,
|
2870 |
+
"step": 238500
|
2871 |
+
},
|
2872 |
+
{
|
2873 |
+
"epoch": 4.07,
|
2874 |
+
"learning_rate": 8.487412934125533e-05,
|
2875 |
+
"loss": 0.3296,
|
2876 |
+
"step": 239000
|
2877 |
+
},
|
2878 |
+
{
|
2879 |
+
"epoch": 4.08,
|
2880 |
+
"learning_rate": 8.465472792017723e-05,
|
2881 |
+
"loss": 0.3296,
|
2882 |
+
"step": 239500
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 4.09,
|
2886 |
+
"learning_rate": 8.44352805588137e-05,
|
2887 |
+
"loss": 0.3296,
|
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 sha256:5ea7bc5a0a91d5c301ba6c460b885286f918d844ce5bae63bfed79ecfee6e0cd
|
3 |
size 201355195
|