Hugging Face's logo

preneond
/
newlinefix-encoder

Token Classification
Transformers
ONNX
Safetensors
roberta
newline-restoration
text-segmentation
Model card Files
xet
 Community
preneond commited on
Commit
dd6ef4f
·
verified ·
1 Parent(s): 6410323

Upload newline-fixer encoder

Browse files
Files changed (6) hide show
  1. config.json +40 -0
  2. model.safetensors +3 -0
  3. predictor_config.json +21 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +17 -0
  6. training_log.json +48 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "JOIN",
16
+ "1": "SPACE",
17
+ "2": "NEWLINE",
18
+ "3": "PARA"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "is_decoder": false,
23
+ "label2id": {
24
+ "JOIN": 0,
25
+ "NEWLINE": 2,
26
+ "PARA": 3,
27
+ "SPACE": 1
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "max_position_embeddings": 514,
31
+ "model_type": "roberta",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 6,
34
+ "pad_token_id": 1,
35
+ "tie_word_embeddings": true,
36
+ "transformers_version": "5.15.0",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 50265
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d743d89c3bf0de3f55efb3028b287577ada8c7aff7c19c47efd7a114209031
3
+ size 326135848
predictor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_words": 180,
3
+ "overlap": 64,
4
+ "model_name": "distilroberta-base",
5
+ "val_metrics": {
6
+ "accuracy": 0.9795400902058844,
7
+ "macro_f1_structural": 0.7832464081700393,
8
+ "precision_JOIN": 0.887536112257532,
9
+ "recall_JOIN": 0.9830857142857143,
10
+ "f1_JOIN": 0.9328706214076565,
11
+ "precision_SPACE": 0.9972153093227003,
12
+ "recall_SPACE": 0.9830608435529667,
13
+ "f1_SPACE": 0.9900874903362599,
14
+ "precision_NEWLINE": 0.6938279112192156,
15
+ "recall_NEWLINE": 0.8199784405318002,
16
+ "f1_NEWLINE": 0.7516469038208169,
17
+ "precision_PARA": 0.5414314516129032,
18
+ "recall_PARA": 0.8623956326268465,
19
+ "f1_PARA": 0.6652216992816448
20
+ }
21
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "mask_token": "<mask>",
11
+ "model_max_length": 512,
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "tokenizer_class": "RobertaTokenizer",
15
+ "trim_offsets": true,
16
+ "unk_token": "<unk>"
17
+ }
training_log.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "steps": [
3
+ {
4
+ "step": 50,
5
+ "loss": 0.50878637611866,
6
+ "lr": 8.510638297872341e-05
7
+ },
8
+ {
9
+ "step": 100,
10
+ "loss": 0.18682242080569267,
11
+ "lr": 6.382978723404256e-05
12
+ },
13
+ {
14
+ "step": 150,
15
+ "loss": 0.15591484516859055,
16
+ "lr": 4.2553191489361704e-05
17
+ },
18
+ {
19
+ "step": 200,
20
+ "loss": 0.1426215897500515,
21
+ "lr": 2.1276595744680852e-05
22
+ },
23
+ {
24
+ "step": 250,
25
+ "loss": 0.14926597610116005,
26
+ "lr": 0.0
27
+ }
28
+ ],
29
+ "epochs": [
30
+ {
31
+ "epoch": 1,
32
+ "accuracy": 0.9795400902058844,
33
+ "macro_f1_structural": 0.7832464081700393,
34
+ "precision_JOIN": 0.887536112257532,
35
+ "recall_JOIN": 0.9830857142857143,
36
+ "f1_JOIN": 0.9328706214076565,
37
+ "precision_SPACE": 0.9972153093227003,
38
+ "recall_SPACE": 0.9830608435529667,
39
+ "f1_SPACE": 0.9900874903362599,
40
+ "precision_NEWLINE": 0.6938279112192156,
41
+ "recall_NEWLINE": 0.8199784405318002,
42
+ "f1_NEWLINE": 0.7516469038208169,
43
+ "precision_PARA": 0.5414314516129032,
44
+ "recall_PARA": 0.8623956326268465,
45
+ "f1_PARA": 0.6652216992816448
46
+ }
47
+ ]
48
+ }