Hugging Face's logo

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

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
a6276de
•
1 Parent(s): fe66323

Training in progress, step 500

Browse files
Files changed (20) hide show
  1. .gitattributes +2 -0
  2. checkpoint-500/config.json +56 -0
  3. checkpoint-500/optimizer.pt +3 -0
  4. checkpoint-500/pytorch_model.bin +3 -0
  5. checkpoint-500/rng_state.pth +3 -0
  6. checkpoint-500/scaler.pt +3 -0
  7. checkpoint-500/scheduler.pt +3 -0
  8. checkpoint-500/special_tokens_map.json +15 -0
  9. checkpoint-500/tokenizer.json +3 -0
  10. checkpoint-500/tokenizer_config.json +20 -0
  11. checkpoint-500/trainer_state.json +34 -0
  12. checkpoint-500/training_args.bin +3 -0
  13. config.json +56 -0
  14. pytorch_model.bin +3 -0
  15. runs/Feb09_15-43-15_f1c8d3a96fe7/1675957409.791511/events.out.tfevents.1675957409.f1c8d3a96fe7.143.1 +3 -0
  16. runs/Feb09_15-43-15_f1c8d3a96fe7/events.out.tfevents.1675957409.f1c8d3a96fe7.143.0 +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-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-500/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": "4.26.0",
53
+ "type_vocab_size": 1,
54
+ "use_cache": true,
55
+ "vocab_size": 250002
56
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e752df9708b3ee64f9cfb6d6199f3b86de73e8b6d9cae131372a7ef9fae1bee2
3
+ size 2265828101
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5de718e31c9f491c0dfba691cef2fadf6de01ce7e4513429474a72b167fc8394
3
+ size 1134425553
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e197e1d8eee50ea05047e5b4ef2d4ecafd2134a21154c71e42b26344bf3a700
3
+ size 14575
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57891f859dc5fbae9d30bcda05aba26f7dc6d900c47dc4de4abfa58a72b670d1
3
+ size 557
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aceb2a9a45ec8c783f35e02c2288f9a94bec6c4f26a9fd6c2cbd758327dadb4
3
+ size 627
checkpoint-500/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-500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
checkpoint-500/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-500/trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7741471103890881,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-500",
4
+ "epoch": 0.2077274615704196,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.21,
12
+ "learning_rate": 4.793934358122144e-05,
13
+ "loss": 0.7223,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.21,
18
+ "eval_accuracy": 0.7741471103890881,
19
+ "eval_f1": 0.7741471103890881,
20
+ "eval_loss": 0.7764509916305542,
21
+ "eval_precision": 0.7741471103890881,
22
+ "eval_recall": 0.7741471103890881,
23
+ "eval_runtime": 33.2902,
24
+ "eval_samples_per_second": 61.64,
25
+ "eval_steps_per_second": 3.875,
26
+ "step": 500
27
+ }
28
+ ],
29
+ "max_steps": 12035,
30
+ "num_train_epochs": 5,
31
+ "total_flos": 834516716544000.0,
32
+ "trial_name": null,
33
+ "trial_params": null
34
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b3cb303483efa6f2dc51db1cfb9b16000da398e2d72673041025bfff104b3b8
3
+ size 3643
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": "4.26.0",
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 sha256:5de718e31c9f491c0dfba691cef2fadf6de01ce7e4513429474a72b167fc8394
3
+ size 1134425553
runs/Feb09_15-43-15_f1c8d3a96fe7/1675957409.791511/events.out.tfevents.1675957409.f1c8d3a96fe7.143.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03dd619771f23c85de18df041f1ebf354517f3e9d7bda49dcf1aefc2682928c6
3
+ size 5889
runs/Feb09_15-43-15_f1c8d3a96fe7/events.out.tfevents.1675957409.f1c8d3a96fe7.143.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01422eac22c1e831a9f9acda84370c4c1858be607d7cd440776b6e970bb0b54f
3
+ size 5258
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 sha256:2b3cb303483efa6f2dc51db1cfb9b16000da398e2d72673041025bfff104b3b8
3
+ size 3643