Training in progress, epoch 4, checkpoint
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 1980859973
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6139318cf513eafa3224f054690d83317b804a9c28a2577d7370471793ce1b21
|
3 |
size 1980859973
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990408885
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0fa9ab0647db949841272150c5f38714cb2e9d7c97e66166b9a8e4985840035
|
3 |
size 990408885
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58ddbd433b5599bf8b86b64743d5e39fd3dfe1434235c8a38c9b7bbdd7fa5b81
|
3 |
size 14575
|
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 sha256:9c334c84f22d7de01f067ab9bee69f31e2f916e7efdb35f8cf0f7917bfd43bda
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "dq158/morbius/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -154,13 +154,68 @@
|
|
154 |
"eval_steps_per_second": 1.46,
|
155 |
"eval_translation_length": 45550,
|
156 |
"step": 7890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
}
|
158 |
],
|
159 |
"logging_steps": 500,
|
160 |
"max_steps": 13150,
|
161 |
"num_train_epochs": 5,
|
162 |
"save_steps": 500,
|
163 |
-
"total_flos":
|
164 |
"trial_name": null,
|
165 |
"trial_params": null
|
166 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.3347413539886475,
|
3 |
+
"best_model_checkpoint": "dq158/morbius/checkpoint-10520",
|
4 |
+
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 10520,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
154 |
"eval_steps_per_second": 1.46,
|
155 |
"eval_translation_length": 45550,
|
156 |
"step": 7890
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 3.04,
|
160 |
+
"learning_rate": 1.958174904942966e-05,
|
161 |
+
"loss": 2.4461,
|
162 |
+
"step": 8000
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 3.23,
|
166 |
+
"learning_rate": 1.7680608365019013e-05,
|
167 |
+
"loss": 2.4042,
|
168 |
+
"step": 8500
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 3.42,
|
172 |
+
"learning_rate": 1.5779467680608364e-05,
|
173 |
+
"loss": 2.4027,
|
174 |
+
"step": 9000
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 3.61,
|
178 |
+
"learning_rate": 1.387832699619772e-05,
|
179 |
+
"loss": 2.3927,
|
180 |
+
"step": 9500
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 3.8,
|
184 |
+
"learning_rate": 1.1977186311787073e-05,
|
185 |
+
"loss": 2.3733,
|
186 |
+
"step": 10000
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 3.99,
|
190 |
+
"learning_rate": 1.0076045627376426e-05,
|
191 |
+
"loss": 2.3716,
|
192 |
+
"step": 10500
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 4.0,
|
196 |
+
"eval_bleu": 0.04869515928692814,
|
197 |
+
"eval_brevity_penalty": 0.9823324657661657,
|
198 |
+
"eval_length_ratio": 0.9824867144301728,
|
199 |
+
"eval_loss": 2.3347413539886475,
|
200 |
+
"eval_precisions": [
|
201 |
+
0.12663965838169275,
|
202 |
+
0.0574505431946487,
|
203 |
+
0.030477866031926728,
|
204 |
+
0.027230821761893922
|
205 |
+
],
|
206 |
+
"eval_reference_length": 46479,
|
207 |
+
"eval_runtime": 200.6451,
|
208 |
+
"eval_samples_per_second": 17.479,
|
209 |
+
"eval_steps_per_second": 1.46,
|
210 |
+
"eval_translation_length": 45665,
|
211 |
+
"step": 10520
|
212 |
}
|
213 |
],
|
214 |
"logging_steps": 500,
|
215 |
"max_steps": 13150,
|
216 |
"num_train_epochs": 5,
|
217 |
"save_steps": 500,
|
218 |
+
"total_flos": 8.644376817303552e+16,
|
219 |
"trial_name": null,
|
220 |
"trial_params": null
|
221 |
}
|