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:a48bad1f819ddc3013572bf99c151a921e55a4af20b731852ee0e46d88eaee51
|
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:cad14b1cb902903a51d46e48755d8fe0174fb56fc95f8b31e1b37f75eb04c41b
|
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:f480c12df85d7d62b9288dff26e7fb3564d488a2596bee0aa01faa8f62db9748
|
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 sha256:2827935cd36ee7cb5602be773fd4208bb60227558e00d8c81ba15b2265ced517
|
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 sha256:0266ea3154fd0d408fdafbc26b32f680ca64fc45683262c94c54f1d6532df9dd
|
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:dbf5ced51778fecbfe5d8600c85859cc64777898a2a19bf7df73c9953bef58c4
|
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 sha256:5043aeb7eb33dbce8efa7aed911efa4dfa38c674e048a936318cfd8150771baf
|
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 sha256:96e9a880a82d984853bbc66cb947669014e6532679459441593342c6ef897aa3
|
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": 8.22400757084387e-05,
|
2947 |
"loss": 0.3293,
|
2948 |
"step": 245000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2949 |
}
|
2950 |
],
|
2951 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.25531914893617,
|
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": 8.22400757084387e-05,
|
2947 |
"loss": 0.3293,
|
2948 |
"step": 245000
|
2949 |
+
},
|
2950 |
+
{
|
2951 |
+
"epoch": 4.18,
|
2952 |
+
"learning_rate": 8.202026616105521e-05,
|
2953 |
+
"loss": 0.329,
|
2954 |
+
"step": 245500
|
2955 |
+
},
|
2956 |
+
{
|
2957 |
+
"epoch": 4.19,
|
2958 |
+
"learning_rate": 8.18004366744603e-05,
|
2959 |
+
"loss": 0.3289,
|
2960 |
+
"step": 246000
|
2961 |
+
},
|
2962 |
+
{
|
2963 |
+
"epoch": 4.2,
|
2964 |
+
"learning_rate": 8.158102912908653e-05,
|
2965 |
+
"loss": 0.3288,
|
2966 |
+
"step": 246500
|
2967 |
+
},
|
2968 |
+
{
|
2969 |
+
"epoch": 4.2,
|
2970 |
+
"learning_rate": 8.136116630216305e-05,
|
2971 |
+
"loss": 0.3289,
|
2972 |
+
"step": 247000
|
2973 |
+
},
|
2974 |
+
{
|
2975 |
+
"epoch": 4.21,
|
2976 |
+
"learning_rate": 8.114129004107772e-05,
|
2977 |
+
"loss": 0.3289,
|
2978 |
+
"step": 247500
|
2979 |
+
},
|
2980 |
+
{
|
2981 |
+
"epoch": 4.22,
|
2982 |
+
"learning_rate": 8.092184230076983e-05,
|
2983 |
+
"loss": 0.329,
|
2984 |
+
"step": 248000
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 4.23,
|
2988 |
+
"learning_rate": 8.070194569776352e-05,
|
2989 |
+
"loss": 0.3286,
|
2990 |
+
"step": 248500
|
2991 |
+
},
|
2992 |
+
{
|
2993 |
+
"epoch": 4.24,
|
2994 |
+
"learning_rate": 8.048204216683654e-05,
|
2995 |
+
"loss": 0.3288,
|
2996 |
+
"step": 249000
|
2997 |
+
},
|
2998 |
+
{
|
2999 |
+
"epoch": 4.25,
|
3000 |
+
"learning_rate": 8.0262133878348e-05,
|
3001 |
+
"loss": 0.3287,
|
3002 |
+
"step": 249500
|
3003 |
+
},
|
3004 |
+
{
|
3005 |
+
"epoch": 4.26,
|
3006 |
+
"learning_rate": 8.004266282559454e-05,
|
3007 |
+
"loss": 0.3291,
|
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:cad14b1cb902903a51d46e48755d8fe0174fb56fc95f8b31e1b37f75eb04c41b
|
3 |
size 201355195
|