Training in progress, step 270000
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 sha256:5db66f456c1a5ed0f600ddb4df527c6d6b0cdd5b149224e0ef8368d130a66703
|
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 sha256:0502bbc8816f236f5f256cefe1ca800a65c80ff6609a6ded9d6e1178f38426bc
|
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:d20c5ba8039f18e311c4813ba5449bbdf6a47d9bd5dd75da9f1918f05d6de38d
|
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:fd6933e9818b0b3f481941970dfbf0c8e8444d0c0e89caf850bd0b57474cf970
|
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:f9735cdd0588f78aac1e701708b599514da9ee2cfa3b101de7fd169969d82e79
|
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 sha256:35440be6a81f1e63637cc0a12732b0550f70ee7b16bf412f587355e45933af59
|
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 sha256:5a71e14dc08e057b5bcc992a7ae8edd73b0ff0c3c69844f7870daaf44a8fcc5d
|
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 sha256:543cb3a16eb55558b380edb7bf4748782727e104a595cf880769c499b3766ad0
|
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,
|
@@ -3186,6 +3186,66 @@
|
|
3186 |
"learning_rate": 7.345970965111851e-05,
|
3187 |
"loss": 0.3289,
|
3188 |
"step": 265000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3189 |
}
|
3190 |
],
|
3191 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.595739610726717,
|
5 |
+
"global_step": 270000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3186 |
"learning_rate": 7.345970965111851e-05,
|
3187 |
"loss": 0.3289,
|
3188 |
"step": 265000
|
3189 |
+
},
|
3190 |
+
{
|
3191 |
+
"epoch": 4.52,
|
3192 |
+
"learning_rate": 7.324079278226878e-05,
|
3193 |
+
"loss": 0.3287,
|
3194 |
+
"step": 265500
|
3195 |
+
},
|
3196 |
+
{
|
3197 |
+
"epoch": 4.53,
|
3198 |
+
"learning_rate": 7.302194262406548e-05,
|
3199 |
+
"loss": 0.3288,
|
3200 |
+
"step": 266000
|
3201 |
+
},
|
3202 |
+
{
|
3203 |
+
"epoch": 4.54,
|
3204 |
+
"learning_rate": 7.280316133647132e-05,
|
3205 |
+
"loss": 0.3288,
|
3206 |
+
"step": 266500
|
3207 |
+
},
|
3208 |
+
{
|
3209 |
+
"epoch": 4.54,
|
3210 |
+
"learning_rate": 7.258488842696201e-05,
|
3211 |
+
"loss": 0.3286,
|
3212 |
+
"step": 267000
|
3213 |
+
},
|
3214 |
+
{
|
3215 |
+
"epoch": 4.55,
|
3216 |
+
"learning_rate": 7.236625120920332e-05,
|
3217 |
+
"loss": 0.3288,
|
3218 |
+
"step": 267500
|
3219 |
+
},
|
3220 |
+
{
|
3221 |
+
"epoch": 4.56,
|
3222 |
+
"learning_rate": 7.214768933346332e-05,
|
3223 |
+
"loss": 0.3288,
|
3224 |
+
"step": 268000
|
3225 |
+
},
|
3226 |
+
{
|
3227 |
+
"epoch": 4.57,
|
3228 |
+
"learning_rate": 7.192920495685949e-05,
|
3229 |
+
"loss": 0.3285,
|
3230 |
+
"step": 268500
|
3231 |
+
},
|
3232 |
+
{
|
3233 |
+
"epoch": 4.58,
|
3234 |
+
"learning_rate": 7.17112369642576e-05,
|
3235 |
+
"loss": 0.3284,
|
3236 |
+
"step": 269000
|
3237 |
+
},
|
3238 |
+
{
|
3239 |
+
"epoch": 4.59,
|
3240 |
+
"learning_rate": 7.149335045150111e-05,
|
3241 |
+
"loss": 0.3286,
|
3242 |
+
"step": 269500
|
3243 |
+
},
|
3244 |
+
{
|
3245 |
+
"epoch": 4.6,
|
3246 |
+
"learning_rate": 7.127511116710097e-05,
|
3247 |
+
"loss": 0.3286,
|
3248 |
+
"step": 270000
|
3249 |
}
|
3250 |
],
|
3251 |
"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 sha256:0502bbc8816f236f5f256cefe1ca800a65c80ff6609a6ded9d6e1178f38426bc
|
3 |
size 201355195
|