Training in progress, step 250000
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 sha256:3b3dce95b40f57c2d7bedbfc5420425ddf243bad64d4a7dad23d37d44573c0da
|
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 sha256:7ec1f5a292bdfa9e19c29267731b24c0773f5a756483c66eedc84561d2537885
|
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 sha256:875fb5f7abc78db3c0f951c832de94e220e94d35b3a770e977237a117347a3e1
|
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 sha256:4d6df91df03a3a354f3df7778d828788730790670017161af3e0b62698a02760
|
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 sha256:5b1ba37016484bd99da644bdcd74650919d5bcd40003139326ad1f0c19d76103
|
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:b307f9f106943263fa7aba376bd0db04cd0bccb12f72c55e1d1a2a69e0ed8e49
|
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 sha256:63f255a6473157a0b12def91394c1dddb1f0826cb4a20c9a74522de194833645
|
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 sha256:9c15e98f3847883266d7f064f67c6b07ddec40c6ad4bd9ad6cdb8b647893cfe4
|
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,
|
@@ -2946,6 +2946,66 @@
|
|
2946 |
"learning_rate": 8.224271329310167e-05,
|
2947 |
"loss": 0.3306,
|
2948 |
"step": 245000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2949 |
}
|
2950 |
],
|
2951 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.255316976025736,
|
5 |
+
"global_step": 250000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2946 |
"learning_rate": 8.224271329310167e-05,
|
2947 |
"loss": 0.3306,
|
2948 |
"step": 245000
|
2949 |
+
},
|
2950 |
+
{
|
2951 |
+
"epoch": 4.18,
|
2952 |
+
"learning_rate": 8.20229039981619e-05,
|
2953 |
+
"loss": 0.3306,
|
2954 |
+
"step": 245500
|
2955 |
+
},
|
2956 |
+
{
|
2957 |
+
"epoch": 4.19,
|
2958 |
+
"learning_rate": 8.180307473797635e-05,
|
2959 |
+
"loss": 0.3308,
|
2960 |
+
"step": 246000
|
2961 |
+
},
|
2962 |
+
{
|
2963 |
+
"epoch": 4.2,
|
2964 |
+
"learning_rate": 8.158322768217107e-05,
|
2965 |
+
"loss": 0.3303,
|
2966 |
+
"step": 246500
|
2967 |
+
},
|
2968 |
+
{
|
2969 |
+
"epoch": 4.2,
|
2970 |
+
"learning_rate": 8.136336500054776e-05,
|
2971 |
+
"loss": 0.3302,
|
2972 |
+
"step": 247000
|
2973 |
+
},
|
2974 |
+
{
|
2975 |
+
"epoch": 4.21,
|
2976 |
+
"learning_rate": 8.114348886306229e-05,
|
2977 |
+
"loss": 0.3305,
|
2978 |
+
"step": 247500
|
2979 |
+
},
|
2980 |
+
{
|
2981 |
+
"epoch": 4.22,
|
2982 |
+
"learning_rate": 8.092360143980338e-05,
|
2983 |
+
"loss": 0.3302,
|
2984 |
+
"step": 248000
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 4.23,
|
2988 |
+
"learning_rate": 8.070414470170364e-05,
|
2989 |
+
"loss": 0.3305,
|
2990 |
+
"step": 248500
|
2991 |
+
},
|
2992 |
+
{
|
2993 |
+
"epoch": 4.24,
|
2994 |
+
"learning_rate": 8.048424122931269e-05,
|
2995 |
+
"loss": 0.3303,
|
2996 |
+
"step": 249000
|
2997 |
+
},
|
2998 |
+
{
|
2999 |
+
"epoch": 4.25,
|
3000 |
+
"learning_rate": 8.02643329776563e-05,
|
3001 |
+
"loss": 0.3301,
|
3002 |
+
"step": 249500
|
3003 |
+
},
|
3004 |
+
{
|
3005 |
+
"epoch": 4.26,
|
3006 |
+
"learning_rate": 8.004442211714013e-05,
|
3007 |
+
"loss": 0.3298,
|
3008 |
+
"step": 250000
|
3009 |
}
|
3010 |
],
|
3011 |
"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 sha256:7ec1f5a292bdfa9e19c29267731b24c0773f5a756483c66eedc84561d2537885
|
3 |
size 201355195
|