Hugging Face's logo

pierreguillou
/
lilt-xlm-roberta-base-finetuned-with-DocLayNet-base-at-paragraphlevel-ml512

Token Classification
Transformers
PyTorch
TensorBoard
5 languages
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
c3d2988
•
1 Parent(s): 3e965b9

Training in progress, step 100

Browse files
Files changed (20) hide show
  1. .gitattributes +2 -0
  2. checkpoint-100/config.json +56 -0
  3. checkpoint-100/optimizer.pt +3 -0
  4. checkpoint-100/pytorch_model.bin +3 -0
  5. checkpoint-100/rng_state.pth +3 -0
  6. checkpoint-100/scaler.pt +3 -0
  7. checkpoint-100/scheduler.pt +3 -0
  8. checkpoint-100/special_tokens_map.json +15 -0
  9. checkpoint-100/tokenizer.json +3 -0
  10. checkpoint-100/tokenizer_config.json +20 -0
  11. checkpoint-100/trainer_state.json +28 -0
  12. checkpoint-100/training_args.bin +3 -0
  13. config.json +56 -0
  14. pytorch_model.bin +3 -0
  15. runs/Feb15_07-53-26_e220f522c880/1676447621.8825216/events.out.tfevents.1676447621.e220f522c880.495.1 +3 -0
  16. runs/Feb15_07-53-26_e220f522c880/events.out.tfevents.1676447621.e220f522c880.495.0 +3 -0
  17. special_tokens_map.json +15 -0
  18. tokenizer.json +3 -0
  19. tokenizer_config.json +20 -0
  20. training_args.bin +3 -0
.gitattributes CHANGED
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-100/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nielsr/lilt-xlm-roberta-base",
3
+ "architectures": [
4
+ "LiltForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "channel_shrink_ratio": 4,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "Caption",
16
+ "1": "Footnote",
17
+ "2": "Formula",
18
+ "3": "List-item",
19
+ "4": "Page-footer",
20
+ "5": "Page-header",
21
+ "6": "Picture",
22
+ "7": "Section-header",
23
+ "8": "Table",
24
+ "9": "Text",
25
+ "10": "Title"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "Caption": 0,
31
+ "Footnote": 1,
32
+ "Formula": 2,
33
+ "List-item": 3,
34
+ "Page-footer": 4,
35
+ "Page-header": 5,
36
+ "Picture": 6,
37
+ "Section-header": 7,
38
+ "Table": 8,
39
+ "Text": 9,
40
+ "Title": 10
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "max_2d_position_embeddings": 1024,
44
+ "max_position_embeddings": 514,
45
+ "model_type": "lilt",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 12,
48
+ "output_past": true,
49
+ "pad_token_id": 1,
50
+ "position_embedding_type": "absolute",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.26.1",
53
+ "type_vocab_size": 1,
54
+ "use_cache": true,
55
+ "vocab_size": 250002
56
+ }
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3bb7f798b7faa9ffe19d5e1bb8395f1909a3e12768cc1876e800e16f389c7a
3
+ size 2265827717
checkpoint-100/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ddccc8aa50bfb082d45e1d9486a1480ff83d9b46e9e73c0609138717d6e917e
3
+ size 1134425553
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f5812fac2dd8ce54f144d17e5819925f261f779dbbc7a7fe69a7fcaf2e80f8
3
+ size 14575
checkpoint-100/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49275945ecfd0346ebdc51411033b3b40ac9d7fd86faa2315017693f738a1151
3
+ size 557
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26589aff2b7c88281509e1e9d0ce9b63736104f150596456f9ee599b4187ae0d
3
+ size 627
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "nielsr/lilt-xlm-roberta-base",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6585185702735884,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-100",
4
+ "epoch": 0.053304904051172705,
5
+ "global_step": 100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "eval_accuracy": 0.6585185702735884,
13
+ "eval_f1": 0.6585185702735884,
14
+ "eval_loss": 0.9875321388244629,
15
+ "eval_precision": 0.6585185702735884,
16
+ "eval_recall": 0.6585185702735884,
17
+ "eval_runtime": 47.6616,
18
+ "eval_samples_per_second": 33.717,
19
+ "eval_steps_per_second": 2.119,
20
+ "step": 100
21
+ }
22
+ ],
23
+ "max_steps": 1876,
24
+ "num_train_epochs": 1,
25
+ "total_flos": 222537791078400.0,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:575d482dfbe4b5795db81627b295d36a31851f66bb801524d15bc53043f733c4
3
+ size 3707
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nielsr/lilt-xlm-roberta-base",
3
+ "architectures": [
4
+ "LiltForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "channel_shrink_ratio": 4,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "Caption",
16
+ "1": "Footnote",
17
+ "2": "Formula",
18
+ "3": "List-item",
19
+ "4": "Page-footer",
20
+ "5": "Page-header",
21
+ "6": "Picture",
22
+ "7": "Section-header",
23
+ "8": "Table",
24
+ "9": "Text",
25
+ "10": "Title"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "Caption": 0,
31
+ "Footnote": 1,
32
+ "Formula": 2,
33
+ "List-item": 3,
34
+ "Page-footer": 4,
35
+ "Page-header": 5,
36
+ "Picture": 6,
37
+ "Section-header": 7,
38
+ "Table": 8,
39
+ "Text": 9,
40
+ "Title": 10
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "max_2d_position_embeddings": 1024,
44
+ "max_position_embeddings": 514,
45
+ "model_type": "lilt",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 12,
48
+ "output_past": true,
49
+ "pad_token_id": 1,
50
+ "position_embedding_type": "absolute",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.26.1",
53
+ "type_vocab_size": 1,
54
+ "use_cache": true,
55
+ "vocab_size": 250002
56
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ddccc8aa50bfb082d45e1d9486a1480ff83d9b46e9e73c0609138717d6e917e
3
+ size 1134425553
runs/Feb15_07-53-26_e220f522c880/1676447621.8825216/events.out.tfevents.1676447621.e220f522c880.495.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ab99c2e3312f93ffe136339bff7c2d7a17733683c195183d8bceafb2a905f2
3
+ size 5933
runs/Feb15_07-53-26_e220f522c880/events.out.tfevents.1676447621.e220f522c880.495.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5505a2df10be119c29733e09f107dae909925262ce13ec35de03e8b1cf862391
3
+ size 5136
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "nielsr/lilt-xlm-roberta-base",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:575d482dfbe4b5795db81627b295d36a31851f66bb801524d15bc53043f733c4
3
+ size 3707