Training in progress, step 160
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3544920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dc7b5a5ba3656e7e3ba33577f9d5c221551eb9ac38a8241da63b379cad73607
|
3 |
size 3544920
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1140034381
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:694ade40292a0236fc581f36db7f75221ac5f2bf62938e0d5acefb6040f8d4ce
|
3 |
size 1140034381
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5134742d8a3e0eb4235ccb75ae0c32f1d18107769b8c95d8a28999819cb8fa18
|
3 |
+
size 14511
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e25f2c0298e32eb32bc4fd13a32a452c19048d5a88e784c5908ed1a05a2bbb1
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -183,11 +183,70 @@
|
|
183 |
"eval_samples_per_second": 0.062,
|
184 |
"eval_steps_per_second": 0.032,
|
185 |
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
186 |
}
|
187 |
],
|
188 |
"max_steps": 369,
|
189 |
"num_train_epochs": 3,
|
190 |
-
"total_flos":
|
191 |
"trial_name": null,
|
192 |
"trial_params": null
|
193 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2929292929292928,
|
5 |
+
"global_step": 160,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
183 |
"eval_samples_per_second": 0.062,
|
184 |
"eval_steps_per_second": 0.032,
|
185 |
"step": 120
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 1.01,
|
189 |
+
"learning_rate": 3.3333333333333335e-05,
|
190 |
+
"loss": 3.6139,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.05,
|
195 |
+
"learning_rate": 3.265582655826558e-05,
|
196 |
+
"loss": 3.5873,
|
197 |
+
"step": 130
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.09,
|
201 |
+
"learning_rate": 3.197831978319784e-05,
|
202 |
+
"loss": 3.3622,
|
203 |
+
"step": 135
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 1.13,
|
207 |
+
"learning_rate": 3.130081300813008e-05,
|
208 |
+
"loss": 3.4854,
|
209 |
+
"step": 140
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.17,
|
213 |
+
"learning_rate": 3.0623306233062334e-05,
|
214 |
+
"loss": 3.4429,
|
215 |
+
"step": 145
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 1.21,
|
219 |
+
"learning_rate": 2.9945799457994585e-05,
|
220 |
+
"loss": 3.1618,
|
221 |
+
"step": 150
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.25,
|
225 |
+
"learning_rate": 2.926829268292683e-05,
|
226 |
+
"loss": 3.428,
|
227 |
+
"step": 155
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.29,
|
231 |
+
"learning_rate": 2.859078590785908e-05,
|
232 |
+
"loss": 3.2305,
|
233 |
+
"step": 160
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.29,
|
237 |
+
"eval_loss": 3.152249336242676,
|
238 |
+
"eval_rouge2_fmeasure": 0.0037,
|
239 |
+
"eval_rouge2_precision": 0.0062,
|
240 |
+
"eval_rouge2_recall": 0.0026,
|
241 |
+
"eval_runtime": 372.2318,
|
242 |
+
"eval_samples_per_second": 0.073,
|
243 |
+
"eval_steps_per_second": 0.038,
|
244 |
+
"step": 160
|
245 |
}
|
246 |
],
|
247 |
"max_steps": 369,
|
248 |
"num_train_epochs": 3,
|
249 |
+
"total_flos": 6243604695613440.0,
|
250 |
"trial_name": null,
|
251 |
"trial_params": null
|
252 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1140034381
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:694ade40292a0236fc581f36db7f75221ac5f2bf62938e0d5acefb6040f8d4ce
|
3 |
size 1140034381
|