Hugging Face's logo

pierreguillou
/
lilt-xlm-roberta-base-finetuned-with-DocLayNet-base-at-linelevel-ml384

Token Classification
Transformers
PyTorch
TensorBoard
lilt
object-detection
vision
Generated from Trainer
DocLayNet
COCO
PDF
IBM
Financial-Reports
Finance
Manuals
Scientific-Articles
Science
Laws
Law
Regulations
Patents
Government-Tenders
image-segmentation
Eval Results
Model card Files Metrics Community
1
pierreguillou commited on
Commit
a00a34d
•
1 Parent(s): f735930

Training in progress, step 5500

Browse files
Files changed (24) hide show
  1. {checkpoint-2000 → checkpoint-5000}/config.json +0 -0
  2. {checkpoint-2000 → checkpoint-5000}/optimizer.pt +1 -1
  3. {checkpoint-4000 → checkpoint-5000}/pytorch_model.bin +1 -1
  4. {checkpoint-4000 → checkpoint-5000}/rng_state.pth +1 -1
  5. {checkpoint-4000 → checkpoint-5000}/scaler.pt +1 -1
  6. {checkpoint-2000 → checkpoint-5000}/scheduler.pt +1 -1
  7. {checkpoint-2000 → checkpoint-5000}/special_tokens_map.json +0 -0
  8. {checkpoint-2000 → checkpoint-5000}/tokenizer.json +0 -0
  9. {checkpoint-2000 → checkpoint-5000}/tokenizer_config.json +0 -0
  10. {checkpoint-4000 → checkpoint-5000}/trainer_state.json +41 -5
  11. {checkpoint-2000 → checkpoint-5000}/training_args.bin +0 -0
  12. {checkpoint-4000 → checkpoint-5500}/config.json +0 -0
  13. {checkpoint-4000 → checkpoint-5500}/optimizer.pt +1 -1
  14. {checkpoint-2000 → checkpoint-5500}/pytorch_model.bin +1 -1
  15. {checkpoint-2000 → checkpoint-5500}/rng_state.pth +1 -1
  16. {checkpoint-2000 → checkpoint-5500}/scaler.pt +1 -1
  17. {checkpoint-4000 → checkpoint-5500}/scheduler.pt +1 -1
  18. {checkpoint-4000 → checkpoint-5500}/special_tokens_map.json +0 -0
  19. {checkpoint-4000 → checkpoint-5500}/tokenizer.json +0 -0
  20. {checkpoint-4000 → checkpoint-5500}/tokenizer_config.json +0 -0
  21. {checkpoint-2000 → checkpoint-5500}/trainer_state.json +131 -5
  22. {checkpoint-4000 → checkpoint-5500}/training_args.bin +0 -0
  23. pytorch_model.bin +1 -1
  24. runs/Feb09_15-43-15_f1c8d3a96fe7/events.out.tfevents.1675957409.f1c8d3a96fe7.143.0 +2 -2
{checkpoint-2000 → checkpoint-5000}/config.json RENAMED
File without changes
{checkpoint-2000 → checkpoint-5000}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:613d8fa70e254c004e083c947d84f82b9a9af60135de2c32941968d039eef6b3
3
  size 2265828101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b84d52785a38380247450ccf7219098ead85f3af921462c7f9cea34fc457af
3
  size 2265828101
{checkpoint-4000 → checkpoint-5000}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1b773b79696ebeb8879d5f1947d14bc904b03897e2b091eb01a3cbac2e0c1e1
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:826a115bd1f49a5fd6ad8834ab59356109e291dab9ee2ebf7e7079622823f521
3
  size 1134425553
{checkpoint-4000 → checkpoint-5000}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a1a169e5890b20e56e1dadd1f1db5e7fe9d48999bb9423445e7bd7870fc67db
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:322213ce84acef97a1d009f4a95470d562524fe104f583c777a9886789ed90a6
3
  size 14575
{checkpoint-4000 → checkpoint-5000}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16689ae0e2d7f94e61eaa80e88732b3e2ba18a5214f441cdec4a6948dba4bd23
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d521e0e6865aafff22fef97e6b783e4fcbd42a34dedc30bf0c2f849637dfbde6
3
  size 557
{checkpoint-2000 → checkpoint-5000}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5ddf4069c5d951aba1b5e1ba075edf7cf23ab79e49bb15ca733c224e0645616
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edd7471042c806219d2a11bac18a23846c94c3ba80ac0f47d46e260c2e00b6a4
3
  size 627
{checkpoint-2000 → checkpoint-5000}/special_tokens_map.json RENAMED
File without changes
{checkpoint-2000 → checkpoint-5000}/tokenizer.json RENAMED
File without changes
{checkpoint-2000 → checkpoint-5000}/tokenizer_config.json RENAMED
File without changes
{checkpoint-4000 → checkpoint-5000}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.8337166846278812,
3
- "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-2000",
4
- "epoch": 1.6618196925633568,
5
- "global_step": 4000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -150,11 +150,47 @@
150
  "eval_samples_per_second": 51.932,
151
  "eval_steps_per_second": 3.265,
152
  "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
153
  }
154
  ],
155
  "max_steps": 12035,
156
  "num_train_epochs": 5,
157
- "total_flos": 6674673328098048.0,
158
  "trial_name": null,
159
  "trial_params": null
160
  }
 
1
  {
2
+ "best_metric": 0.842474787280243,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-4500",
4
+ "epoch": 2.077274615704196,
5
+ "global_step": 5000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
150
  "eval_samples_per_second": 51.932,
151
  "eval_steps_per_second": 3.265,
152
  "step": 4000
153
+ },
154
+ {
155
+ "epoch": 1.87,
156
+ "learning_rate": 3.133361030328209e-05,
157
+ "loss": 0.1909,
158
+ "step": 4500
159
+ },
160
+ {
161
+ "epoch": 1.87,
162
+ "eval_accuracy": 0.8424747872802432,
163
+ "eval_f1": 0.842474787280243,
164
+ "eval_loss": 0.7545156478881836,
165
+ "eval_precision": 0.8424747872802432,
166
+ "eval_recall": 0.8424747872802432,
167
+ "eval_runtime": 35.061,
168
+ "eval_samples_per_second": 58.527,
169
+ "eval_steps_per_second": 3.679,
170
+ "step": 4500
171
+ },
172
+ {
173
+ "epoch": 2.08,
174
+ "learning_rate": 2.9256335687577903e-05,
175
+ "loss": 0.1704,
176
+ "step": 5000
177
+ },
178
+ {
179
+ "epoch": 2.08,
180
+ "eval_accuracy": 0.8317543549243216,
181
+ "eval_f1": 0.8317543549243216,
182
+ "eval_loss": 0.856721818447113,
183
+ "eval_precision": 0.8317543549243216,
184
+ "eval_recall": 0.8317543549243216,
185
+ "eval_runtime": 38.2513,
186
+ "eval_samples_per_second": 53.645,
187
+ "eval_steps_per_second": 3.372,
188
+ "step": 5000
189
  }
190
  ],
191
  "max_steps": 12035,
192
  "num_train_epochs": 5,
193
+ "total_flos": 8342246356932096.0,
194
  "trial_name": null,
195
  "trial_params": null
196
  }
{checkpoint-2000 → checkpoint-5000}/training_args.bin RENAMED
File without changes
{checkpoint-4000 → checkpoint-5500}/config.json RENAMED
File without changes
{checkpoint-4000 → checkpoint-5500}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11162014b289cd3940a224d38390df4c8ec1476d10bd55eef5f65d0e04fc0381
3
  size 2265828101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3a74874f53beb0dd61e7742a119b65b3a7c6efdfcf021d79679adb8f4e296d
3
  size 2265828101
{checkpoint-2000 → checkpoint-5500}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5720cd89747751c7c694b6d0850b33d8d7cb5b110874811ddebb3863d2d1efff
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad5877b0b97895626b7a47603fd8c76c7a1dcb7f8da77da732de52ebd6fe498
3
  size 1134425553
{checkpoint-2000 → checkpoint-5500}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c47ea06035da0f03affb7446f943fc4b8c01009a413e5b1c44c006b293b9f6f6
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b2654002f35c8d69a538e102e8376633570a6ea9bfd4a14b35a0f1a0043945
3
  size 14575
{checkpoint-2000 → checkpoint-5500}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e447d7d1f92db78968e506c9d447a6cd713bb7af4075f3660bdec681ecbc7740
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609eb953721cf5cce74da27a7bae781c2bfe011d3b35b8e9f9b5692c47839041
3
  size 557
{checkpoint-4000 → checkpoint-5500}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:300e3554b41711f11a6d6ca18c629d7822b75f388588821b025f96e99c2bedc9
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96574ab09e5e2e54af42547122334b19c9d0414475ddd65dd2890b9b6e6b7def
3
  size 627
{checkpoint-4000 → checkpoint-5500}/special_tokens_map.json RENAMED
File without changes
{checkpoint-4000 → checkpoint-5500}/tokenizer.json RENAMED
File without changes
{checkpoint-4000 → checkpoint-5500}/tokenizer_config.json RENAMED
File without changes
{checkpoint-2000 → checkpoint-5500}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.8337166846278812,
3
- "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-2000",
4
- "epoch": 0.8309098462816784,
5
- "global_step": 2000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -78,11 +78,137 @@
78
  "eval_samples_per_second": 53.084,
79
  "eval_steps_per_second": 3.337,
80
  "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
  }
82
  ],
83
  "max_steps": 12035,
84
  "num_train_epochs": 5,
85
- "total_flos": 3338066866176000.0,
86
  "trial_name": null,
87
  "trial_params": null
88
  }
 
1
  {
2
+ "best_metric": 0.8489327821653182,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-5500",
4
+ "epoch": 2.2850020772746156,
5
+ "global_step": 5500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
78
  "eval_samples_per_second": 53.084,
79
  "eval_steps_per_second": 3.337,
80
  "step": 2000
81
+ },
82
+ {
83
+ "epoch": 1.04,
84
+ "learning_rate": 3.964270876609888e-05,
85
+ "loss": 0.2784,
86
+ "step": 2500
87
+ },
88
+ {
89
+ "epoch": 1.04,
90
+ "eval_accuracy": 0.8119380418523106,
91
+ "eval_f1": 0.8119380418523107,
92
+ "eval_loss": 0.7512525320053101,
93
+ "eval_precision": 0.8119380418523106,
94
+ "eval_recall": 0.8119380418523106,
95
+ "eval_runtime": 33.6314,
96
+ "eval_samples_per_second": 61.014,
97
+ "eval_steps_per_second": 3.836,
98
+ "step": 2500
99
+ },
100
+ {
101
+ "epoch": 1.25,
102
+ "learning_rate": 3.756543415039468e-05,
103
+ "loss": 0.2377,
104
+ "step": 3000
105
+ },
106
+ {
107
+ "epoch": 1.25,
108
+ "eval_accuracy": 0.8165945537308391,
109
+ "eval_f1": 0.8165945537308391,
110
+ "eval_loss": 0.9047627449035645,
111
+ "eval_precision": 0.8165945537308391,
112
+ "eval_recall": 0.8165945537308391,
113
+ "eval_runtime": 39.8436,
114
+ "eval_samples_per_second": 51.501,
115
+ "eval_steps_per_second": 3.238,
116
+ "step": 3000
117
+ },
118
+ {
119
+ "epoch": 1.45,
120
+ "learning_rate": 3.548815953469049e-05,
121
+ "loss": 0.2401,
122
+ "step": 3500
123
+ },
124
+ {
125
+ "epoch": 1.45,
126
+ "eval_accuracy": 0.7939071271171446,
127
+ "eval_f1": 0.7939071271171445,
128
+ "eval_loss": 1.241086721420288,
129
+ "eval_precision": 0.7939071271171446,
130
+ "eval_recall": 0.7939071271171446,
131
+ "eval_runtime": 34.8048,
132
+ "eval_samples_per_second": 58.957,
133
+ "eval_steps_per_second": 3.706,
134
+ "step": 3500
135
+ },
136
+ {
137
+ "epoch": 1.66,
138
+ "learning_rate": 3.341088491898629e-05,
139
+ "loss": 0.2054,
140
+ "step": 4000
141
+ },
142
+ {
143
+ "epoch": 1.66,
144
+ "eval_accuracy": 0.8079812131057889,
145
+ "eval_f1": 0.8079812131057889,
146
+ "eval_loss": 1.1594407558441162,
147
+ "eval_precision": 0.8079812131057889,
148
+ "eval_recall": 0.8079812131057889,
149
+ "eval_runtime": 39.5136,
150
+ "eval_samples_per_second": 51.932,
151
+ "eval_steps_per_second": 3.265,
152
+ "step": 4000
153
+ },
154
+ {
155
+ "epoch": 1.87,
156
+ "learning_rate": 3.133361030328209e-05,
157
+ "loss": 0.1909,
158
+ "step": 4500
159
+ },
160
+ {
161
+ "epoch": 1.87,
162
+ "eval_accuracy": 0.8424747872802432,
163
+ "eval_f1": 0.842474787280243,
164
+ "eval_loss": 0.7545156478881836,
165
+ "eval_precision": 0.8424747872802432,
166
+ "eval_recall": 0.8424747872802432,
167
+ "eval_runtime": 35.061,
168
+ "eval_samples_per_second": 58.527,
169
+ "eval_steps_per_second": 3.679,
170
+ "step": 4500
171
+ },
172
+ {
173
+ "epoch": 2.08,
174
+ "learning_rate": 2.9256335687577903e-05,
175
+ "loss": 0.1704,
176
+ "step": 5000
177
+ },
178
+ {
179
+ "epoch": 2.08,
180
+ "eval_accuracy": 0.8317543549243216,
181
+ "eval_f1": 0.8317543549243216,
182
+ "eval_loss": 0.856721818447113,
183
+ "eval_precision": 0.8317543549243216,
184
+ "eval_recall": 0.8317543549243216,
185
+ "eval_runtime": 38.2513,
186
+ "eval_samples_per_second": 53.645,
187
+ "eval_steps_per_second": 3.372,
188
+ "step": 5000
189
+ },
190
+ {
191
+ "epoch": 2.29,
192
+ "learning_rate": 2.7179061071873702e-05,
193
+ "loss": 0.1294,
194
+ "step": 5500
195
+ },
196
+ {
197
+ "epoch": 2.29,
198
+ "eval_accuracy": 0.8489327821653182,
199
+ "eval_f1": 0.8489327821653182,
200
+ "eval_loss": 0.8485749959945679,
201
+ "eval_precision": 0.8489327821653182,
202
+ "eval_recall": 0.8489327821653182,
203
+ "eval_runtime": 33.5765,
204
+ "eval_samples_per_second": 61.114,
205
+ "eval_steps_per_second": 3.842,
206
+ "step": 5500
207
  }
208
  ],
209
  "max_steps": 12035,
210
  "num_train_epochs": 5,
211
+ "total_flos": 9176763073476096.0,
212
  "trial_name": null,
213
  "trial_params": null
214
  }
{checkpoint-4000 → checkpoint-5500}/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 sha256:1ab31af496b83252a0734273c407717be54e25e7236af6050a2c0755b5a8410e
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad5877b0b97895626b7a47603fd8c76c7a1dcb7f8da77da732de52ebd6fe498
3
  size 1134425553
runs/Feb09_15-43-15_f1c8d3a96fe7/events.out.tfevents.1675957409.f1c8d3a96fe7.143.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ad47993644304babb1777876766a415242e49ea131939995d1617cc033dd7ff
3
- size 10290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4350d0a4bb2974f01fdf48b3f8f7990549e813e56d160d998d704b15030fe2ef
3
+ size 11548