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
a5ec683
•
1 Parent(s): 86104c8

Training in progress, step 9500

Browse files
Files changed (24) hide show
  1. {checkpoint-6000 → checkpoint-9000}/config.json +0 -0
  2. {checkpoint-6000 → checkpoint-9000}/optimizer.pt +1 -1
  3. {checkpoint-8000 → checkpoint-9000}/pytorch_model.bin +1 -1
  4. {checkpoint-8000 → checkpoint-9000}/rng_state.pth +1 -1
  5. {checkpoint-8000 → checkpoint-9000}/scaler.pt +1 -1
  6. {checkpoint-6000 → checkpoint-9000}/scheduler.pt +1 -1
  7. {checkpoint-6000 → checkpoint-9000}/special_tokens_map.json +0 -0
  8. {checkpoint-6000 → checkpoint-9000}/tokenizer.json +0 -0
  9. {checkpoint-6000 → checkpoint-9000}/tokenizer_config.json +0 -0
  10. {checkpoint-8000 → checkpoint-9000}/trainer_state.json +41 -5
  11. {checkpoint-6000 → checkpoint-9000}/training_args.bin +0 -0
  12. {checkpoint-8000 → checkpoint-9500}/config.json +0 -0
  13. {checkpoint-8000 → checkpoint-9500}/optimizer.pt +1 -1
  14. {checkpoint-6000 → checkpoint-9500}/pytorch_model.bin +1 -1
  15. {checkpoint-6000 → checkpoint-9500}/rng_state.pth +1 -1
  16. {checkpoint-6000 → checkpoint-9500}/scaler.pt +1 -1
  17. {checkpoint-8000 → checkpoint-9500}/scheduler.pt +1 -1
  18. {checkpoint-8000 → checkpoint-9500}/special_tokens_map.json +0 -0
  19. {checkpoint-8000 → checkpoint-9500}/tokenizer.json +0 -0
  20. {checkpoint-8000 → checkpoint-9500}/tokenizer_config.json +0 -0
  21. {checkpoint-6000 → checkpoint-9500}/trainer_state.json +131 -5
  22. {checkpoint-8000 → checkpoint-9500}/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-6000 → checkpoint-9000}/config.json RENAMED
File without changes
{checkpoint-6000 → checkpoint-9000}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6ccab808598cafaa3502eaf827acb795d751b863043a68024a8ebc252765dda
3
  size 2265828101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40339d30586ba971f477204d4f4c8debe5659e4bf8a6d0b40f0dbb3c2b86826a
3
  size 2265828101
{checkpoint-8000 → checkpoint-9000}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27b504e227955abd271e8dfb3a65060b57aab9124c9a51342289b2487370d857
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c1a967392a760a20a7df6b984ff6233fe3116a3a23a7d43741a55e255c2693b
3
  size 1134425553
{checkpoint-8000 → checkpoint-9000}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:960a0ff8566f0b77c05a97c9fc1c687f7ca7734da4222daf4902d9e243e0137d
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01363ad99044cbb1e1a9fcb3dd6afb6183c527494aaa4acdfea9b2eaf5f5bf59
3
  size 14575
{checkpoint-8000 → checkpoint-9000}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05c943ac5112ace01757b5472903bea87985b301a9f82c01afb7df322762c49c
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1806aaea912c20662a2d6b020295ab7bac23fe592dd3bbea0440ed7b24f4406
3
  size 557
{checkpoint-6000 → checkpoint-9000}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72f3b66da2277cfe6e060fe737d382a511cc283da3a6c66c08f0ac5f7793cfb9
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a80798daa30e7bf5f8f379f1b9078964abb834eb9f259b48dc7dee8a5246089f
3
  size 627
{checkpoint-6000 → checkpoint-9000}/special_tokens_map.json RENAMED
File without changes
{checkpoint-6000 → checkpoint-9000}/tokenizer.json RENAMED
File without changes
{checkpoint-6000 → checkpoint-9000}/tokenizer_config.json RENAMED
File without changes
{checkpoint-8000 → checkpoint-9000}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.8573209374145502,
3
- "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-6000",
4
- "epoch": 3.3236393851267136,
5
- "global_step": 8000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -294,11 +294,47 @@
294
  "eval_samples_per_second": 53.701,
295
  "eval_steps_per_second": 3.376,
296
  "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
297
  }
298
  ],
299
  "max_steps": 12035,
300
  "num_train_epochs": 5,
301
- "total_flos": 1.3347886251942144e+16,
302
  "trial_name": null,
303
  "trial_params": null
304
  }
 
1
  {
2
+ "best_metric": 0.8849383152916955,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-8500",
4
+ "epoch": 3.739094308267553,
5
+ "global_step": 9000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
294
  "eval_samples_per_second": 53.701,
295
  "eval_steps_per_second": 3.376,
296
  "step": 8000
297
+ },
298
+ {
299
+ "epoch": 3.53,
300
+ "learning_rate": 1.4715413377648527e-05,
301
+ "loss": 0.0802,
302
+ "step": 8500
303
+ },
304
+ {
305
+ "epoch": 3.53,
306
+ "eval_accuracy": 0.8849383152916955,
307
+ "eval_f1": 0.8849383152916955,
308
+ "eval_loss": 0.719699501991272,
309
+ "eval_precision": 0.8849383152916955,
310
+ "eval_recall": 0.8849383152916955,
311
+ "eval_runtime": 34.4056,
312
+ "eval_samples_per_second": 59.641,
313
+ "eval_steps_per_second": 3.749,
314
+ "step": 8500
315
+ },
316
+ {
317
+ "epoch": 3.74,
318
+ "learning_rate": 1.263813876194433e-05,
319
+ "loss": 0.0861,
320
+ "step": 9000
321
+ },
322
+ {
323
+ "epoch": 3.74,
324
+ "eval_accuracy": 0.8319634556304386,
325
+ "eval_f1": 0.8319634556304386,
326
+ "eval_loss": 1.1419589519500732,
327
+ "eval_precision": 0.8319634556304386,
328
+ "eval_recall": 0.8319634556304386,
329
+ "eval_runtime": 39.7118,
330
+ "eval_samples_per_second": 51.672,
331
+ "eval_steps_per_second": 3.248,
332
+ "step": 9000
333
  }
334
  ],
335
  "max_steps": 12035,
336
  "num_train_epochs": 5,
337
+ "total_flos": 1.5016919685030144e+16,
338
  "trial_name": null,
339
  "trial_params": null
340
  }
{checkpoint-6000 → checkpoint-9000}/training_args.bin RENAMED
File without changes
{checkpoint-8000 → checkpoint-9500}/config.json RENAMED
File without changes
{checkpoint-8000 → checkpoint-9500}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b39cb815a920edaf287fed25e2a19b016671ea73dd16f75036bf2bcfaf1b767a
3
  size 2265828101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df515ee9f576c12282bfb637ade8a8213293ddae59957acdc9ec3eda5ffc1ac5
3
  size 2265828101
{checkpoint-6000 → checkpoint-9500}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9effd102ed93d81722319ca88162190926ca77de0e9c79bcdf05fedc7571c41
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad997d71868e665d1c9e949c7c92bc5034dd4707d008ec6124c35f455b2bcef4
3
  size 1134425553
{checkpoint-6000 → checkpoint-9500}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33f25f963833bb60f4e565ecbfcbf34d003c383bcd545a16637c61002e2435ad
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b4759d5f134107f6410bb60b8fd4565f48e69d431a344d1a1528a493e1381e
3
  size 14575
{checkpoint-6000 → checkpoint-9500}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06535ee946097fce21c4464212b93d33310a3a654d4286c652849b57cf50a7f8
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b1fc83d0643172c218319c7eb8184122c8bb2e487f59ec1ecd32dd9f84926f
3
  size 557
{checkpoint-8000 → checkpoint-9500}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c82aba72db92b65d16e163361936c8fce2a4ed55ab1b817ceacaf38e10c5cade
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64aefeabc41f5c043cf4cf863f5c28e62b64e9dcac772198a29726d10c8d9e7
3
  size 627
{checkpoint-8000 → checkpoint-9500}/special_tokens_map.json RENAMED
File without changes
{checkpoint-8000 → checkpoint-9500}/tokenizer.json RENAMED
File without changes
{checkpoint-8000 → checkpoint-9500}/tokenizer_config.json RENAMED
File without changes
{checkpoint-6000 → checkpoint-9500}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.8573209374145502,
3
- "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-6000",
4
- "epoch": 2.4927295388450355,
5
- "global_step": 6000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -222,11 +222,137 @@
222
  "eval_samples_per_second": 51.849,
223
  "eval_steps_per_second": 3.259,
224
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
225
  }
226
  ],
227
  "max_steps": 12035,
228
  "num_train_epochs": 5,
229
- "total_flos": 1.0011279790020096e+16,
230
  "trial_name": null,
231
  "trial_params": null
232
  }
 
1
  {
2
+ "best_metric": 0.8849383152916955,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-8500",
4
+ "epoch": 3.946821769837973,
5
+ "global_step": 9500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
222
  "eval_samples_per_second": 51.849,
223
  "eval_steps_per_second": 3.259,
224
  "step": 6000
225
+ },
226
+ {
227
+ "epoch": 2.7,
228
+ "learning_rate": 2.302451184046531e-05,
229
+ "loss": 0.1354,
230
+ "step": 6500
231
+ },
232
+ {
233
+ "epoch": 2.7,
234
+ "eval_accuracy": 0.8255697994241689,
235
+ "eval_f1": 0.8255697994241689,
236
+ "eval_loss": 0.9870807528495789,
237
+ "eval_precision": 0.8255697994241689,
238
+ "eval_recall": 0.8255697994241689,
239
+ "eval_runtime": 34.6532,
240
+ "eval_samples_per_second": 59.215,
241
+ "eval_steps_per_second": 3.723,
242
+ "step": 6500
243
+ },
244
+ {
245
+ "epoch": 2.91,
246
+ "learning_rate": 2.0947237224761117e-05,
247
+ "loss": 0.1239,
248
+ "step": 7000
249
+ },
250
+ {
251
+ "epoch": 2.91,
252
+ "eval_accuracy": 0.8189268308375287,
253
+ "eval_f1": 0.8189268308375287,
254
+ "eval_loss": 1.1430405378341675,
255
+ "eval_precision": 0.8189268308375287,
256
+ "eval_recall": 0.8189268308375287,
257
+ "eval_runtime": 39.4751,
258
+ "eval_samples_per_second": 51.982,
259
+ "eval_steps_per_second": 3.268,
260
+ "step": 7000
261
+ },
262
+ {
263
+ "epoch": 3.12,
264
+ "learning_rate": 1.886996260905692e-05,
265
+ "loss": 0.1012,
266
+ "step": 7500
267
+ },
268
+ {
269
+ "epoch": 3.12,
270
+ "eval_accuracy": 0.8385581702079747,
271
+ "eval_f1": 0.8385581702079747,
272
+ "eval_loss": 0.8271787166595459,
273
+ "eval_precision": 0.8385581702079747,
274
+ "eval_recall": 0.8385581702079747,
275
+ "eval_runtime": 33.307,
276
+ "eval_samples_per_second": 61.609,
277
+ "eval_steps_per_second": 3.873,
278
+ "step": 7500
279
+ },
280
+ {
281
+ "epoch": 3.32,
282
+ "learning_rate": 1.6792687993352722e-05,
283
+ "loss": 0.0788,
284
+ "step": 8000
285
+ },
286
+ {
287
+ "epoch": 3.32,
288
+ "eval_accuracy": 0.8364993324862074,
289
+ "eval_f1": 0.8364993324862076,
290
+ "eval_loss": 1.028805136680603,
291
+ "eval_precision": 0.8364993324862074,
292
+ "eval_recall": 0.8364993324862074,
293
+ "eval_runtime": 38.2117,
294
+ "eval_samples_per_second": 53.701,
295
+ "eval_steps_per_second": 3.376,
296
+ "step": 8000
297
+ },
298
+ {
299
+ "epoch": 3.53,
300
+ "learning_rate": 1.4715413377648527e-05,
301
+ "loss": 0.0802,
302
+ "step": 8500
303
+ },
304
+ {
305
+ "epoch": 3.53,
306
+ "eval_accuracy": 0.8849383152916955,
307
+ "eval_f1": 0.8849383152916955,
308
+ "eval_loss": 0.719699501991272,
309
+ "eval_precision": 0.8849383152916955,
310
+ "eval_recall": 0.8849383152916955,
311
+ "eval_runtime": 34.4056,
312
+ "eval_samples_per_second": 59.641,
313
+ "eval_steps_per_second": 3.749,
314
+ "step": 8500
315
+ },
316
+ {
317
+ "epoch": 3.74,
318
+ "learning_rate": 1.263813876194433e-05,
319
+ "loss": 0.0861,
320
+ "step": 9000
321
+ },
322
+ {
323
+ "epoch": 3.74,
324
+ "eval_accuracy": 0.8319634556304386,
325
+ "eval_f1": 0.8319634556304386,
326
+ "eval_loss": 1.1419589519500732,
327
+ "eval_precision": 0.8319634556304386,
328
+ "eval_recall": 0.8319634556304386,
329
+ "eval_runtime": 39.7118,
330
+ "eval_samples_per_second": 51.672,
331
+ "eval_steps_per_second": 3.248,
332
+ "step": 9000
333
+ },
334
+ {
335
+ "epoch": 3.95,
336
+ "learning_rate": 1.0560864146240134e-05,
337
+ "loss": 0.0639,
338
+ "step": 9500
339
+ },
340
+ {
341
+ "epoch": 3.95,
342
+ "eval_accuracy": 0.8585272876421483,
343
+ "eval_f1": 0.8585272876421483,
344
+ "eval_loss": 0.9562506079673767,
345
+ "eval_precision": 0.8585272876421483,
346
+ "eval_recall": 0.8585272876421483,
347
+ "eval_runtime": 33.8854,
348
+ "eval_samples_per_second": 60.557,
349
+ "eval_steps_per_second": 3.807,
350
+ "step": 9500
351
  }
352
  ],
353
  "max_steps": 12035,
354
  "num_train_epochs": 5,
355
+ "total_flos": 1.5851436401574144e+16,
356
  "trial_name": null,
357
  "trial_params": null
358
  }
{checkpoint-8000 → checkpoint-9500}/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:e39c7d7515bc3fd9710bfa20bd4d1d7c408894096e55b518c4e64c07ac0ff33b
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad997d71868e665d1c9e949c7c92bc5034dd4707d008ec6124c35f455b2bcef4
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 sha256:4f7c4c7428bf319a3138119ab5d1663f67efa67393e048e30432a37e3bf8e016
3
- size 15322
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef9f72f97b923aecdda18d35791ba5a7ee11ec50095f3bf60d000a05b04019f
3
+ size 16580