polejowska
commited on
Commit
•
a2ca8aa
1
Parent(s):
8ff5379
End of training
Browse files- trainer_state.json +84 -14
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "detr-r50-cd45rb-2ah-6l-corrected\\checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -148,18 +148,88 @@
|
|
148 |
"step": 46060
|
149 |
},
|
150 |
{
|
151 |
-
"epoch":
|
152 |
-
"
|
153 |
-
"
|
154 |
-
"
|
155 |
-
|
156 |
-
|
157 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
158 |
}
|
159 |
],
|
160 |
-
"max_steps":
|
161 |
-
"num_train_epochs":
|
162 |
-
"total_flos":
|
163 |
"trial_name": null,
|
164 |
"trial_params": null
|
165 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.8243227005004883,
|
3 |
+
"best_model_checkpoint": "detr-r50-cd45rb-2ah-6l-corrected\\checkpoint-69090",
|
4 |
+
"epoch": 15.0,
|
5 |
+
"global_step": 69090,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
148 |
"step": 46060
|
149 |
},
|
150 |
{
|
151 |
+
"epoch": 11.0,
|
152 |
+
"learning_rate": 2.6707193515704154e-06,
|
153 |
+
"loss": 2.3423,
|
154 |
+
"step": 50666
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 11.0,
|
158 |
+
"eval_loss": 1.8636469841003418,
|
159 |
+
"eval_runtime": 238.0394,
|
160 |
+
"eval_samples_per_second": 7.482,
|
161 |
+
"eval_steps_per_second": 0.937,
|
162 |
+
"step": 50666
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 12.0,
|
166 |
+
"learning_rate": 2.004052684903749e-06,
|
167 |
+
"loss": 2.3292,
|
168 |
+
"step": 55272
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 12.0,
|
172 |
+
"eval_loss": 1.8500159978866577,
|
173 |
+
"eval_runtime": 233.3265,
|
174 |
+
"eval_samples_per_second": 7.633,
|
175 |
+
"eval_steps_per_second": 0.956,
|
176 |
+
"step": 55272
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 13.0,
|
180 |
+
"learning_rate": 1.3378202344767697e-06,
|
181 |
+
"loss": 2.3078,
|
182 |
+
"step": 59878
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 13.0,
|
186 |
+
"eval_loss": 1.835439682006836,
|
187 |
+
"eval_runtime": 237.6682,
|
188 |
+
"eval_samples_per_second": 7.494,
|
189 |
+
"eval_steps_per_second": 0.938,
|
190 |
+
"step": 59878
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 14.0,
|
194 |
+
"learning_rate": 6.712983065566653e-07,
|
195 |
+
"loss": 2.2958,
|
196 |
+
"step": 64484
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 14.0,
|
200 |
+
"eval_loss": 1.8350275754928589,
|
201 |
+
"eval_runtime": 235.9233,
|
202 |
+
"eval_samples_per_second": 7.549,
|
203 |
+
"eval_steps_per_second": 0.945,
|
204 |
+
"step": 64484
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 15.0,
|
208 |
+
"learning_rate": 4.7763786365610075e-09,
|
209 |
+
"loss": 2.2779,
|
210 |
+
"step": 69090
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 15.0,
|
214 |
+
"eval_loss": 1.8243227005004883,
|
215 |
+
"eval_runtime": 233.2527,
|
216 |
+
"eval_samples_per_second": 7.635,
|
217 |
+
"eval_steps_per_second": 0.956,
|
218 |
+
"step": 69090
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 15.0,
|
222 |
+
"step": 69090,
|
223 |
+
"total_flos": 1.3204884717123845e+20,
|
224 |
+
"train_loss": 0.7701958609241569,
|
225 |
+
"train_runtime": 16614.0798,
|
226 |
+
"train_samples_per_second": 16.631,
|
227 |
+
"train_steps_per_second": 4.159
|
228 |
}
|
229 |
],
|
230 |
+
"max_steps": 69090,
|
231 |
+
"num_train_epochs": 15,
|
232 |
+
"total_flos": 1.3204884717123845e+20,
|
233 |
"trial_name": null,
|
234 |
"trial_params": null
|
235 |
}
|