pierreguillou
commited on
Commit
•
7419b6c
1
Parent(s):
0a6fb58
Training in progress, step 1800
Browse files- {checkpoint-1200 → checkpoint-1700}/config.json +0 -0
- {checkpoint-1200 → checkpoint-1700}/optimizer.pt +1 -1
- {checkpoint-1300 → checkpoint-1700}/pytorch_model.bin +1 -1
- {checkpoint-1300 → checkpoint-1700}/rng_state.pth +1 -1
- {checkpoint-1300 → checkpoint-1700}/scaler.pt +1 -1
- {checkpoint-1200 → checkpoint-1700}/scheduler.pt +1 -1
- {checkpoint-1200 → checkpoint-1700}/special_tokens_map.json +0 -0
- {checkpoint-1200 → checkpoint-1700}/tokenizer.json +0 -0
- {checkpoint-1200 → checkpoint-1700}/tokenizer_config.json +0 -0
- {checkpoint-1300 → checkpoint-1700}/trainer_state.json +57 -3
- {checkpoint-1200 → checkpoint-1700}/training_args.bin +0 -0
- {checkpoint-1300 → checkpoint-1800}/config.json +0 -0
- {checkpoint-1300 → checkpoint-1800}/optimizer.pt +1 -1
- {checkpoint-1200 → checkpoint-1800}/pytorch_model.bin +1 -1
- {checkpoint-1200 → checkpoint-1800}/rng_state.pth +1 -1
- {checkpoint-1200 → checkpoint-1800}/scaler.pt +1 -1
- {checkpoint-1300 → checkpoint-1800}/scheduler.pt +1 -1
- {checkpoint-1300 → checkpoint-1800}/special_tokens_map.json +0 -0
- {checkpoint-1300 → checkpoint-1800}/tokenizer.json +0 -0
- {checkpoint-1300 → checkpoint-1800}/tokenizer_config.json +0 -0
- {checkpoint-1200 → checkpoint-1800}/trainer_state.json +81 -3
- {checkpoint-1300 → checkpoint-1800}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
- runs/Feb15_07-53-26_e220f522c880/events.out.tfevents.1676447621.e220f522c880.495.0 +2 -2
{checkpoint-1200 → checkpoint-1700}/config.json
RENAMED
File without changes
|
{checkpoint-1200 → checkpoint-1700}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2265828101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:729004fcf99456996b5021ebe5a947784fe395af38a311463a6c8394258a65e1
|
3 |
size 2265828101
|
{checkpoint-1300 → checkpoint-1700}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1134425553
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:071823a09cad0d0ee1a84e696398cf09288e9b6d735bcc30cdd2d342f3f51d7b
|
3 |
size 1134425553
|
{checkpoint-1300 → checkpoint-1700}/rng_state.pth
RENAMED
@@ -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 sha256:601d09199bbd913a7215c8cba0939124457c2a49e668a60ddf927eb5c0634883
|
3 |
size 14575
|
{checkpoint-1300 → checkpoint-1700}/scaler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bd9cd8c155d5657070f8ed265a80ce72d9d2060869298c24c5bdd0b74109812
|
3 |
size 557
|
{checkpoint-1200 → checkpoint-1700}/scheduler.pt
RENAMED
@@ -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 sha256:52c3445de958aa8136571bb30deff20a540a52b3340cc380d53bac08e004773d
|
3 |
size 627
|
{checkpoint-1200 → checkpoint-1700}/special_tokens_map.json
RENAMED
File without changes
|
{checkpoint-1200 → checkpoint-1700}/tokenizer.json
RENAMED
File without changes
|
{checkpoint-1200 → checkpoint-1700}/tokenizer_config.json
RENAMED
File without changes
|
{checkpoint-1300 → checkpoint-1700}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.885723696687195,
|
3 |
"best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600",
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -174,11 +174,65 @@
|
|
174 |
"eval_samples_per_second": 40.44,
|
175 |
"eval_steps_per_second": 2.542,
|
176 |
"step": 1300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
177 |
}
|
178 |
],
|
179 |
"max_steps": 1876,
|
180 |
"num_train_epochs": 1,
|
181 |
-
"total_flos":
|
182 |
"trial_name": null,
|
183 |
"trial_params": null
|
184 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.885723696687195,
|
3 |
"best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600",
|
4 |
+
"epoch": 0.906183368869936,
|
5 |
+
"global_step": 1700,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
174 |
"eval_samples_per_second": 40.44,
|
175 |
"eval_steps_per_second": 2.542,
|
176 |
"step": 1300
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.75,
|
180 |
+
"eval_accuracy": 0.874334993562039,
|
181 |
+
"eval_f1": 0.874334993562039,
|
182 |
+
"eval_loss": 0.4129931926727295,
|
183 |
+
"eval_precision": 0.874334993562039,
|
184 |
+
"eval_recall": 0.874334993562039,
|
185 |
+
"eval_runtime": 44.8477,
|
186 |
+
"eval_samples_per_second": 35.832,
|
187 |
+
"eval_steps_per_second": 2.252,
|
188 |
+
"step": 1400
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.8,
|
192 |
+
"learning_rate": 4.051172707889126e-06,
|
193 |
+
"loss": 0.3672,
|
194 |
+
"step": 1500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.8,
|
198 |
+
"eval_accuracy": 0.8288799944104525,
|
199 |
+
"eval_f1": 0.8288799944104525,
|
200 |
+
"eval_loss": 0.45351940393447876,
|
201 |
+
"eval_precision": 0.8288799944104525,
|
202 |
+
"eval_recall": 0.8288799944104525,
|
203 |
+
"eval_runtime": 45.3573,
|
204 |
+
"eval_samples_per_second": 35.43,
|
205 |
+
"eval_steps_per_second": 2.227,
|
206 |
+
"step": 1500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.85,
|
210 |
+
"eval_accuracy": 0.8712607424116902,
|
211 |
+
"eval_f1": 0.8712607424116902,
|
212 |
+
"eval_loss": 0.36811864376068115,
|
213 |
+
"eval_precision": 0.8712607424116902,
|
214 |
+
"eval_recall": 0.8712607424116902,
|
215 |
+
"eval_runtime": 44.3035,
|
216 |
+
"eval_samples_per_second": 36.273,
|
217 |
+
"eval_steps_per_second": 2.28,
|
218 |
+
"step": 1600
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.91,
|
222 |
+
"eval_accuracy": 0.885723696687195,
|
223 |
+
"eval_f1": 0.885723696687195,
|
224 |
+
"eval_loss": 0.34459415078163147,
|
225 |
+
"eval_precision": 0.885723696687195,
|
226 |
+
"eval_recall": 0.885723696687195,
|
227 |
+
"eval_runtime": 44.6077,
|
228 |
+
"eval_samples_per_second": 36.025,
|
229 |
+
"eval_steps_per_second": 2.264,
|
230 |
+
"step": 1700
|
231 |
}
|
232 |
],
|
233 |
"max_steps": 1876,
|
234 |
"num_train_epochs": 1,
|
235 |
+
"total_flos": 3783142448332800.0,
|
236 |
"trial_name": null,
|
237 |
"trial_params": null
|
238 |
}
|
{checkpoint-1200 → checkpoint-1700}/training_args.bin
RENAMED
File without changes
|
{checkpoint-1300 → checkpoint-1800}/config.json
RENAMED
File without changes
|
{checkpoint-1300 → checkpoint-1800}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2265828101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:420937e4631c6307bb20626a94737518c49ba06b50213dcba5ba3656760807c6
|
3 |
size 2265828101
|
{checkpoint-1200 → checkpoint-1800}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1134425553
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ce50e2c3bc965514eb957251870b9e018aa89a1eb3c0b2d421e00f4020f51b
|
3 |
size 1134425553
|
{checkpoint-1200 → checkpoint-1800}/rng_state.pth
RENAMED
@@ -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 sha256:1adfb71bc946adddba7d7a4adf2692f3ecca6f938e6cec06e55e91f7eded59d3
|
3 |
size 14575
|
{checkpoint-1200 → checkpoint-1800}/scaler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cc6b9e5879ad27aed996bd80d0156e04156a49f5d5c05c63381b2d7ef1e56ee
|
3 |
size 557
|
{checkpoint-1300 → checkpoint-1800}/scheduler.pt
RENAMED
@@ -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:bdd460548c31edca36710a211911ae5cae45a7d2e78b27979617c353a46d75e9
|
3 |
size 627
|
{checkpoint-1300 → checkpoint-1800}/special_tokens_map.json
RENAMED
File without changes
|
{checkpoint-1300 → checkpoint-1800}/tokenizer.json
RENAMED
File without changes
|
{checkpoint-1300 → checkpoint-1800}/tokenizer_config.json
RENAMED
File without changes
|
{checkpoint-1200 → checkpoint-1800}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.885723696687195,
|
3 |
"best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600",
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -162,11 +162,89 @@
|
|
162 |
"eval_samples_per_second": 35.614,
|
163 |
"eval_steps_per_second": 2.238,
|
164 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
165 |
}
|
166 |
],
|
167 |
"max_steps": 1876,
|
168 |
"num_train_epochs": 1,
|
169 |
-
"total_flos":
|
170 |
"trial_name": null,
|
171 |
"trial_params": null
|
172 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.885723696687195,
|
3 |
"best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600",
|
4 |
+
"epoch": 0.9594882729211087,
|
5 |
+
"global_step": 1800,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
162 |
"eval_samples_per_second": 35.614,
|
163 |
"eval_steps_per_second": 2.238,
|
164 |
"step": 1200
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.69,
|
168 |
+
"eval_accuracy": 0.8612794075079601,
|
169 |
+
"eval_f1": 0.8612794075079601,
|
170 |
+
"eval_loss": 0.41840043663978577,
|
171 |
+
"eval_precision": 0.8612794075079601,
|
172 |
+
"eval_recall": 0.8612794075079601,
|
173 |
+
"eval_runtime": 39.7377,
|
174 |
+
"eval_samples_per_second": 40.44,
|
175 |
+
"eval_steps_per_second": 2.542,
|
176 |
+
"step": 1300
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.75,
|
180 |
+
"eval_accuracy": 0.874334993562039,
|
181 |
+
"eval_f1": 0.874334993562039,
|
182 |
+
"eval_loss": 0.4129931926727295,
|
183 |
+
"eval_precision": 0.874334993562039,
|
184 |
+
"eval_recall": 0.874334993562039,
|
185 |
+
"eval_runtime": 44.8477,
|
186 |
+
"eval_samples_per_second": 35.832,
|
187 |
+
"eval_steps_per_second": 2.252,
|
188 |
+
"step": 1400
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.8,
|
192 |
+
"learning_rate": 4.051172707889126e-06,
|
193 |
+
"loss": 0.3672,
|
194 |
+
"step": 1500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.8,
|
198 |
+
"eval_accuracy": 0.8288799944104525,
|
199 |
+
"eval_f1": 0.8288799944104525,
|
200 |
+
"eval_loss": 0.45351940393447876,
|
201 |
+
"eval_precision": 0.8288799944104525,
|
202 |
+
"eval_recall": 0.8288799944104525,
|
203 |
+
"eval_runtime": 45.3573,
|
204 |
+
"eval_samples_per_second": 35.43,
|
205 |
+
"eval_steps_per_second": 2.227,
|
206 |
+
"step": 1500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.85,
|
210 |
+
"eval_accuracy": 0.8712607424116902,
|
211 |
+
"eval_f1": 0.8712607424116902,
|
212 |
+
"eval_loss": 0.36811864376068115,
|
213 |
+
"eval_precision": 0.8712607424116902,
|
214 |
+
"eval_recall": 0.8712607424116902,
|
215 |
+
"eval_runtime": 44.3035,
|
216 |
+
"eval_samples_per_second": 36.273,
|
217 |
+
"eval_steps_per_second": 2.28,
|
218 |
+
"step": 1600
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.91,
|
222 |
+
"eval_accuracy": 0.885723696687195,
|
223 |
+
"eval_f1": 0.885723696687195,
|
224 |
+
"eval_loss": 0.34459415078163147,
|
225 |
+
"eval_precision": 0.885723696687195,
|
226 |
+
"eval_recall": 0.885723696687195,
|
227 |
+
"eval_runtime": 44.6077,
|
228 |
+
"eval_samples_per_second": 36.025,
|
229 |
+
"eval_steps_per_second": 2.264,
|
230 |
+
"step": 1700
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.96,
|
234 |
+
"eval_accuracy": 0.8634353758471658,
|
235 |
+
"eval_f1": 0.8634353758471657,
|
236 |
+
"eval_loss": 0.41038718819618225,
|
237 |
+
"eval_precision": 0.8634353758471658,
|
238 |
+
"eval_recall": 0.8634353758471658,
|
239 |
+
"eval_runtime": 40.0758,
|
240 |
+
"eval_samples_per_second": 40.099,
|
241 |
+
"eval_steps_per_second": 2.52,
|
242 |
+
"step": 1800
|
243 |
}
|
244 |
],
|
245 |
"max_steps": 1876,
|
246 |
"num_train_epochs": 1,
|
247 |
+
"total_flos": 4005680239411200.0,
|
248 |
"trial_name": null,
|
249 |
"trial_params": null
|
250 |
}
|
{checkpoint-1300 → checkpoint-1800}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1134425553
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ce50e2c3bc965514eb957251870b9e018aa89a1eb3c0b2d421e00f4020f51b
|
3 |
size 1134425553
|
runs/Feb15_07-53-26_e220f522c880/events.out.tfevents.1676447621.e220f522c880.495.0
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:e10b4927301c942673e8c171300cc1481b2f2efdb1f5cf8e239edc99ad8f3db1
|
3 |
+
size 13631
|