Training in progress, step 265000
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:b76e3c7386418d063bbe78d0933400876ab54a7fc04f45f533b7c072f00d7339
|
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 sha256:9bf8fc69e95780ea6866eec0c10eb47e3a1ecb0839c210593306d9b1aea6eff9
|
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 sha256:159e788a512a85a95c925378965f303a1957ae09096cc42b57c7df579637727c
|
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 sha256:48294b249ca8fc3f491543d2d226227b34a4cab78327a3b48c3dd645531c3792
|
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:e6fd75c8a25ccdc0c7925898fdc2013ad2238ac8821a0dcc94dc8f83727e54ef
|
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:f11cfacad74035ecf31e856b164f6f33914b2b784bd97c65644b4828af151e39
|
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:a55b34a104abc0da331b8a7701661fcfd2da8fae2d644c96a6a1ff55cfc2fbc1
|
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:f51790c1a5e15be889b7ba3e645f5e490e4ac235bab9dab5f3eb23ac2727ed53
|
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,
|
@@ -3126,6 +3126,66 @@
|
|
3126 |
"learning_rate": 7.565119384297032e-05,
|
3127 |
"loss": 0.3292,
|
3128 |
"step": 260000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3129 |
}
|
3130 |
],
|
3131 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.510633952051472,
|
5 |
+
"global_step": 265000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3126 |
"learning_rate": 7.565119384297032e-05,
|
3127 |
"loss": 0.3292,
|
3128 |
"step": 260000
|
3129 |
+
},
|
3130 |
+
{
|
3131 |
+
"epoch": 4.43,
|
3132 |
+
"learning_rate": 7.54317289758932e-05,
|
3133 |
+
"loss": 0.3294,
|
3134 |
+
"step": 260500
|
3135 |
+
},
|
3136 |
+
{
|
3137 |
+
"epoch": 4.44,
|
3138 |
+
"learning_rate": 7.521230919580681e-05,
|
3139 |
+
"loss": 0.329,
|
3140 |
+
"step": 261000
|
3141 |
+
},
|
3142 |
+
{
|
3143 |
+
"epoch": 4.45,
|
3144 |
+
"learning_rate": 7.499293666829577e-05,
|
3145 |
+
"loss": 0.3291,
|
3146 |
+
"step": 261500
|
3147 |
+
},
|
3148 |
+
{
|
3149 |
+
"epoch": 4.46,
|
3150 |
+
"learning_rate": 7.47736135584784e-05,
|
3151 |
+
"loss": 0.3289,
|
3152 |
+
"step": 262000
|
3153 |
+
},
|
3154 |
+
{
|
3155 |
+
"epoch": 4.47,
|
3156 |
+
"learning_rate": 7.455478052112257e-05,
|
3157 |
+
"loss": 0.3292,
|
3158 |
+
"step": 262500
|
3159 |
+
},
|
3160 |
+
{
|
3161 |
+
"epoch": 4.48,
|
3162 |
+
"learning_rate": 7.43355626304227e-05,
|
3163 |
+
"loss": 0.329,
|
3164 |
+
"step": 263000
|
3165 |
+
},
|
3166 |
+
{
|
3167 |
+
"epoch": 4.49,
|
3168 |
+
"learning_rate": 7.411640064543287e-05,
|
3169 |
+
"loss": 0.3294,
|
3170 |
+
"step": 263500
|
3171 |
+
},
|
3172 |
+
{
|
3173 |
+
"epoch": 4.49,
|
3174 |
+
"learning_rate": 7.389773487763577e-05,
|
3175 |
+
"loss": 0.329,
|
3176 |
+
"step": 264000
|
3177 |
+
},
|
3178 |
+
{
|
3179 |
+
"epoch": 4.5,
|
3180 |
+
"learning_rate": 7.367869106999357e-05,
|
3181 |
+
"loss": 0.3288,
|
3182 |
+
"step": 264500
|
3183 |
+
},
|
3184 |
+
{
|
3185 |
+
"epoch": 4.51,
|
3186 |
+
"learning_rate": 7.345970965111851e-05,
|
3187 |
+
"loss": 0.3289,
|
3188 |
+
"step": 265000
|
3189 |
}
|
3190 |
],
|
3191 |
"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 sha256:9bf8fc69e95780ea6866eec0c10eb47e3a1ecb0839c210593306d9b1aea6eff9
|
3 |
size 201355195
|