Commit
•
4daa96c
1
Parent(s):
9bda347
add ckpt-10500 / epoch-0
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- scheduler.pt +1 -1
- trainer_state.json +153 -3
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1057712183
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7700fcec392ea121226bbc3e9b325a706b1fee3fc0d121b37876c3782fd10133
|
| 3 |
size 1057712183
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 528910843
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12327197ea2594c4ffecc831bad5c1ede4a1b8cabecb84430e06b24108e2cd14
|
| 3 |
size 528910843
|
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 sha256:112b6ad0d91eba88b0a5c6b34586dddeefe7213a047a2f6f299e9b87aa672c89
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -6156,11 +6156,161 @@
|
|
| 6156 |
"learning_rate": 6.769676331116133e-05,
|
| 6157 |
"loss": 1.4452,
|
| 6158 |
"step": 10250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6159 |
}
|
| 6160 |
],
|
| 6161 |
"max_steps": 31521,
|
| 6162 |
"num_train_epochs": 3,
|
| 6163 |
-
"total_flos": 9.
|
| 6164 |
"trial_name": null,
|
| 6165 |
"trial_params": null
|
| 6166 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9993337774816788,
|
| 5 |
+
"global_step": 10500,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 6156 |
"learning_rate": 6.769676331116133e-05,
|
| 6157 |
"loss": 1.4452,
|
| 6158 |
"step": 10250
|
| 6159 |
+
},
|
| 6160 |
+
{
|
| 6161 |
+
"epoch": 0.98,
|
| 6162 |
+
"learning_rate": 6.766493746220682e-05,
|
| 6163 |
+
"loss": 1.4993,
|
| 6164 |
+
"step": 10260
|
| 6165 |
+
},
|
| 6166 |
+
{
|
| 6167 |
+
"epoch": 0.98,
|
| 6168 |
+
"learning_rate": 6.763311161325229e-05,
|
| 6169 |
+
"loss": 1.4982,
|
| 6170 |
+
"step": 10270
|
| 6171 |
+
},
|
| 6172 |
+
{
|
| 6173 |
+
"epoch": 0.98,
|
| 6174 |
+
"learning_rate": 6.760128576429776e-05,
|
| 6175 |
+
"loss": 1.651,
|
| 6176 |
+
"step": 10280
|
| 6177 |
+
},
|
| 6178 |
+
{
|
| 6179 |
+
"epoch": 0.98,
|
| 6180 |
+
"learning_rate": 6.756945991534325e-05,
|
| 6181 |
+
"loss": 1.6332,
|
| 6182 |
+
"step": 10290
|
| 6183 |
+
},
|
| 6184 |
+
{
|
| 6185 |
+
"epoch": 0.98,
|
| 6186 |
+
"learning_rate": 6.753763406638872e-05,
|
| 6187 |
+
"loss": 1.4433,
|
| 6188 |
+
"step": 10300
|
| 6189 |
+
},
|
| 6190 |
+
{
|
| 6191 |
+
"epoch": 0.98,
|
| 6192 |
+
"learning_rate": 6.75058082174342e-05,
|
| 6193 |
+
"loss": 1.485,
|
| 6194 |
+
"step": 10310
|
| 6195 |
+
},
|
| 6196 |
+
{
|
| 6197 |
+
"epoch": 0.98,
|
| 6198 |
+
"learning_rate": 6.747398236847968e-05,
|
| 6199 |
+
"loss": 1.6712,
|
| 6200 |
+
"step": 10320
|
| 6201 |
+
},
|
| 6202 |
+
{
|
| 6203 |
+
"epoch": 0.98,
|
| 6204 |
+
"learning_rate": 6.744215651952516e-05,
|
| 6205 |
+
"loss": 1.5196,
|
| 6206 |
+
"step": 10330
|
| 6207 |
+
},
|
| 6208 |
+
{
|
| 6209 |
+
"epoch": 0.98,
|
| 6210 |
+
"learning_rate": 6.741033067057064e-05,
|
| 6211 |
+
"loss": 1.586,
|
| 6212 |
+
"step": 10340
|
| 6213 |
+
},
|
| 6214 |
+
{
|
| 6215 |
+
"epoch": 0.99,
|
| 6216 |
+
"learning_rate": 6.737850482161611e-05,
|
| 6217 |
+
"loss": 1.4815,
|
| 6218 |
+
"step": 10350
|
| 6219 |
+
},
|
| 6220 |
+
{
|
| 6221 |
+
"epoch": 0.99,
|
| 6222 |
+
"learning_rate": 6.73466789726616e-05,
|
| 6223 |
+
"loss": 1.7372,
|
| 6224 |
+
"step": 10360
|
| 6225 |
+
},
|
| 6226 |
+
{
|
| 6227 |
+
"epoch": 0.99,
|
| 6228 |
+
"learning_rate": 6.731485312370708e-05,
|
| 6229 |
+
"loss": 1.2242,
|
| 6230 |
+
"step": 10370
|
| 6231 |
+
},
|
| 6232 |
+
{
|
| 6233 |
+
"epoch": 0.99,
|
| 6234 |
+
"learning_rate": 6.728302727475255e-05,
|
| 6235 |
+
"loss": 1.8329,
|
| 6236 |
+
"step": 10380
|
| 6237 |
+
},
|
| 6238 |
+
{
|
| 6239 |
+
"epoch": 0.99,
|
| 6240 |
+
"learning_rate": 6.725120142579803e-05,
|
| 6241 |
+
"loss": 1.6306,
|
| 6242 |
+
"step": 10390
|
| 6243 |
+
},
|
| 6244 |
+
{
|
| 6245 |
+
"epoch": 0.99,
|
| 6246 |
+
"learning_rate": 6.721937557684352e-05,
|
| 6247 |
+
"loss": 1.6169,
|
| 6248 |
+
"step": 10400
|
| 6249 |
+
},
|
| 6250 |
+
{
|
| 6251 |
+
"epoch": 0.99,
|
| 6252 |
+
"learning_rate": 6.7187549727889e-05,
|
| 6253 |
+
"loss": 1.8023,
|
| 6254 |
+
"step": 10410
|
| 6255 |
+
},
|
| 6256 |
+
{
|
| 6257 |
+
"epoch": 0.99,
|
| 6258 |
+
"learning_rate": 6.715572387893447e-05,
|
| 6259 |
+
"loss": 1.4764,
|
| 6260 |
+
"step": 10420
|
| 6261 |
+
},
|
| 6262 |
+
{
|
| 6263 |
+
"epoch": 0.99,
|
| 6264 |
+
"learning_rate": 6.712389802997994e-05,
|
| 6265 |
+
"loss": 1.718,
|
| 6266 |
+
"step": 10430
|
| 6267 |
+
},
|
| 6268 |
+
{
|
| 6269 |
+
"epoch": 0.99,
|
| 6270 |
+
"learning_rate": 6.709207218102544e-05,
|
| 6271 |
+
"loss": 1.6362,
|
| 6272 |
+
"step": 10440
|
| 6273 |
+
},
|
| 6274 |
+
{
|
| 6275 |
+
"epoch": 0.99,
|
| 6276 |
+
"learning_rate": 6.706024633207091e-05,
|
| 6277 |
+
"loss": 1.4818,
|
| 6278 |
+
"step": 10450
|
| 6279 |
+
},
|
| 6280 |
+
{
|
| 6281 |
+
"epoch": 1.0,
|
| 6282 |
+
"learning_rate": 6.70284204831164e-05,
|
| 6283 |
+
"loss": 1.8302,
|
| 6284 |
+
"step": 10460
|
| 6285 |
+
},
|
| 6286 |
+
{
|
| 6287 |
+
"epoch": 1.0,
|
| 6288 |
+
"learning_rate": 6.699659463416186e-05,
|
| 6289 |
+
"loss": 1.4897,
|
| 6290 |
+
"step": 10470
|
| 6291 |
+
},
|
| 6292 |
+
{
|
| 6293 |
+
"epoch": 1.0,
|
| 6294 |
+
"learning_rate": 6.696476878520735e-05,
|
| 6295 |
+
"loss": 1.3032,
|
| 6296 |
+
"step": 10480
|
| 6297 |
+
},
|
| 6298 |
+
{
|
| 6299 |
+
"epoch": 1.0,
|
| 6300 |
+
"learning_rate": 6.693294293625283e-05,
|
| 6301 |
+
"loss": 1.4236,
|
| 6302 |
+
"step": 10490
|
| 6303 |
+
},
|
| 6304 |
+
{
|
| 6305 |
+
"epoch": 1.0,
|
| 6306 |
+
"learning_rate": 6.69011170872983e-05,
|
| 6307 |
+
"loss": 1.5428,
|
| 6308 |
+
"step": 10500
|
| 6309 |
}
|
| 6310 |
],
|
| 6311 |
"max_steps": 31521,
|
| 6312 |
"num_train_epochs": 3,
|
| 6313 |
+
"total_flos": 9.955030912708116e+17,
|
| 6314 |
"trial_name": null,
|
| 6315 |
"trial_params": null
|
| 6316 |
}
|