Training in progress, step 245000
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 sha256:35629f408cbad172b2e28da7148ab8a3d04950082d44cd48ed48732c437cb57f
|
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 sha256:11a5a80d34ec298b587f804efcd52e7bf2527b84bceed623b30c78421cbe718f
|
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 sha256:5c3a6c791623243b56012f79d83987e3b0dc5779920249d9ae4ea03b505501bc
|
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 sha256:7ac2dfe5db9998006b22784e76c8dd064b9c4e08de29a9b17b0c6f869a946672
|
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 sha256:7b495f15cbe98e92645a2e59b4b7d0bf151508e56bec48971aac5ce915087f86
|
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 sha256:9acd71132e2d8e066a52449af11b860af3b5a23b0cbfefab4464b5083aaaa337
|
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:e793c709171594bdb6d363d16e2d6ee4fd4c6345a635828dfbbbf96eefe8ced4
|
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 sha256:3db97da0b6a2242e49e6670afe664cc85b14a19e8472a9a2a8e2e5784aed9925
|
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,
|
@@ -2886,6 +2886,66 @@
|
|
2886 |
"learning_rate": 8.443791419097638e-05,
|
2887 |
"loss": 0.3312,
|
2888 |
"step": 240000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2889 |
}
|
2890 |
],
|
2891 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.170211317350491,
|
5 |
+
"global_step": 245000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2886 |
"learning_rate": 8.443791419097638e-05,
|
2887 |
"loss": 0.3312,
|
2888 |
"step": 240000
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 4.09,
|
2892 |
+
"learning_rate": 8.421842356763658e-05,
|
2893 |
+
"loss": 0.3314,
|
2894 |
+
"step": 240500
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 4.1,
|
2898 |
+
"learning_rate": 8.399889131015923e-05,
|
2899 |
+
"loss": 0.331,
|
2900 |
+
"step": 241000
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 4.11,
|
2904 |
+
"learning_rate": 8.377931958523902e-05,
|
2905 |
+
"loss": 0.3312,
|
2906 |
+
"step": 241500
|
2907 |
+
},
|
2908 |
+
{
|
2909 |
+
"epoch": 4.12,
|
2910 |
+
"learning_rate": 8.356014981379603e-05,
|
2911 |
+
"loss": 0.3313,
|
2912 |
+
"step": 242000
|
2913 |
+
},
|
2914 |
+
{
|
2915 |
+
"epoch": 4.13,
|
2916 |
+
"learning_rate": 8.334050572371366e-05,
|
2917 |
+
"loss": 0.3309,
|
2918 |
+
"step": 242500
|
2919 |
+
},
|
2920 |
+
{
|
2921 |
+
"epoch": 4.14,
|
2922 |
+
"learning_rate": 8.31208286641884e-05,
|
2923 |
+
"loss": 0.3309,
|
2924 |
+
"step": 243000
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 4.14,
|
2928 |
+
"learning_rate": 8.290112080334417e-05,
|
2929 |
+
"loss": 0.3309,
|
2930 |
+
"step": 243500
|
2931 |
+
},
|
2932 |
+
{
|
2933 |
+
"epoch": 4.15,
|
2934 |
+
"learning_rate": 8.268138430960883e-05,
|
2935 |
+
"loss": 0.3308,
|
2936 |
+
"step": 244000
|
2937 |
+
},
|
2938 |
+
{
|
2939 |
+
"epoch": 4.16,
|
2940 |
+
"learning_rate": 8.246206090257837e-05,
|
2941 |
+
"loss": 0.3308,
|
2942 |
+
"step": 244500
|
2943 |
+
},
|
2944 |
+
{
|
2945 |
+
"epoch": 4.17,
|
2946 |
+
"learning_rate": 8.224271329310167e-05,
|
2947 |
+
"loss": 0.3306,
|
2948 |
+
"step": 245000
|
2949 |
}
|
2950 |
],
|
2951 |
"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 sha256:11a5a80d34ec298b587f804efcd52e7bf2527b84bceed623b30c78421cbe718f
|
3 |
size 201355195
|