Hugging Face's logo

DevImpulse
/
lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1

Token Classification
Transformers
TensorBoard
Safetensors
lilt
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DevImpulse commited on
Commit
489dba0
•
1 Parent(s): bd6d9aa

Training in progress, step 500, checkpoint

Browse files
Files changed (10) hide show
  1. checkpoint-500/config.json +56 -0
  2. checkpoint-500/model.safetensors +3 -0
  3. checkpoint-500/optimizer.pt +3 -0
  4. checkpoint-500/rng_state.pth +3 -0
  5. checkpoint-500/scheduler.pt +3 -0
  6. checkpoint-500/special_tokens_map.json +51 -0
  7. checkpoint-500/tokenizer.json +3 -0
  8. checkpoint-500/tokenizer_config.json +54 -0
  9. checkpoint-500/trainer_state.json +100 -0
  10. checkpoint-500/training_args.bin +3 -0
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": "4.41.2",
53
+ "type_vocab_size": 1,
54
+ "use_cache": true,
55
+ "vocab_size": 250002
56
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e955a851c6f650b08f5f4167dbf6024dd2838ea368698a76355dbccca0e25cb
3
+ size 1134332228
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865e387bf95c995cf9e288f17303d7adeb80bf560d81ecbd42ec02b944555036
3
+ size 2265924830
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:befd64baba5bf8919c103ecc338ef923a2ca4754aa989a7ae7d377e5d7aead45
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b7c6a9086d3608e8caed027d389c2987b96091ff0b3c9127b24b0d8ba4aafb
3
+ size 1064
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
3
+ size 17082734
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8669088803936638,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-500",
4
+ "epoch": 0.26652452025586354,
5
+ "eval_steps": 100,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.053304904051172705,
13
+ "eval_accuracy": 0.6684599798377034,
14
+ "eval_f1": 0.6684599798377034,
15
+ "eval_loss": 0.9209221005439758,
16
+ "eval_precision": 0.6684599798377034,
17
+ "eval_recall": 0.6684599798377034,
18
+ "eval_runtime": 41.8743,
19
+ "eval_samples_per_second": 38.377,
20
+ "eval_steps_per_second": 2.412,
21
+ "step": 100
22
+ },
23
+ {
24
+ "epoch": 0.10660980810234541,
25
+ "eval_accuracy": 0.8154451176300318,
26
+ "eval_f1": 0.8154451176300318,
27
+ "eval_loss": 0.6488999724388123,
28
+ "eval_precision": 0.8154451176300318,
29
+ "eval_recall": 0.8154451176300318,
30
+ "eval_runtime": 44.2144,
31
+ "eval_samples_per_second": 36.346,
32
+ "eval_steps_per_second": 2.284,
33
+ "step": 200
34
+ },
35
+ {
36
+ "epoch": 0.15991471215351813,
37
+ "eval_accuracy": 0.7420323994130975,
38
+ "eval_f1": 0.7420323994130975,
39
+ "eval_loss": 0.7198283076286316,
40
+ "eval_precision": 0.7420323994130975,
41
+ "eval_recall": 0.7420323994130975,
42
+ "eval_runtime": 41.064,
43
+ "eval_samples_per_second": 39.134,
44
+ "eval_steps_per_second": 2.46,
45
+ "step": 300
46
+ },
47
+ {
48
+ "epoch": 0.21321961620469082,
49
+ "eval_accuracy": 0.7961212532564105,
50
+ "eval_f1": 0.7961212532564104,
51
+ "eval_loss": 0.5486767292022705,
52
+ "eval_precision": 0.7961212532564105,
53
+ "eval_recall": 0.7961212532564105,
54
+ "eval_runtime": 43.0362,
55
+ "eval_samples_per_second": 37.341,
56
+ "eval_steps_per_second": 2.347,
57
+ "step": 400
58
+ },
59
+ {
60
+ "epoch": 0.26652452025586354,
61
+ "grad_norm": 8.946574211120605,
62
+ "learning_rate": 1.4722814498933904e-05,
63
+ "loss": 0.736,
64
+ "step": 500
65
+ },
66
+ {
67
+ "epoch": 0.26652452025586354,
68
+ "eval_accuracy": 0.8669088803936639,
69
+ "eval_f1": 0.8669088803936638,
70
+ "eval_loss": 0.44298624992370605,
71
+ "eval_precision": 0.8669088803936639,
72
+ "eval_recall": 0.8669088803936639,
73
+ "eval_runtime": 42.8219,
74
+ "eval_samples_per_second": 37.527,
75
+ "eval_steps_per_second": 2.359,
76
+ "step": 500
77
+ }
78
+ ],
79
+ "logging_steps": 500,
80
+ "max_steps": 1876,
81
+ "num_input_tokens_seen": 0,
82
+ "num_train_epochs": 1,
83
+ "save_steps": 100,
84
+ "stateful_callbacks": {
85
+ "TrainerControl": {
86
+ "args": {
87
+ "should_epoch_stop": false,
88
+ "should_evaluate": false,
89
+ "should_log": false,
90
+ "should_save": true,
91
+ "should_training_stop": false
92
+ },
93
+ "attributes": {}
94
+ }
95
+ },
96
+ "total_flos": 1112688955392000.0,
97
+ "train_batch_size": 8,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:310ed091c3918a1d9ebfef484979290e5f98817614fea477d6988c3c827bc379
3
+ size 5304