Hugging Face's logo

iamfadi
/
us-roberta-edgar-ner

JAX
roberta
Model card Files Community
iamfadi commited on
Commit
15fd40e
•
1 Parent(s): 2cd175b

Saving weights and logs of epoch 20

Browse files
Files changed (7) hide show
  1. epoch_20/config.json +63 -0
  2. epoch_20/flax_model.msgpack +3 -0
  3. epoch_20/merges.txt +0 -0
  4. epoch_20/special_tokens_map.json +51 -0
  5. epoch_20/tokenizer.json +0 -0
  6. epoch_20/tokenizer_config.json +57 -0
  7. epoch_20/vocab.json +0 -0
epoch_20/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "iamfadi/us-roberta",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "ner",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "B-BUSINESS",
16
+ "1": "B-GOVERNMENT",
17
+ "2": "B-LEGISLATION/ACT",
18
+ "3": "B-LOCATION",
19
+ "4": "B-MISCELLANEOUS",
20
+ "5": "B-PERSON",
21
+ "6": "I-BUSINESS",
22
+ "7": "I-COURT",
23
+ "8": "I-GOVERNMENT",
24
+ "9": "I-LEGISLATION/ACT",
25
+ "10": "I-LOC",
26
+ "11": "I-LOCATION",
27
+ "12": "I-MISCELLANEOUS",
28
+ "13": "I-PERSON",
29
+ "14": "O",
30
+ "15": "P"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "B-BUSINESS": 0,
36
+ "B-GOVERNMENT": 1,
37
+ "B-LEGISLATION/ACT": 2,
38
+ "B-LOCATION": 3,
39
+ "B-MISCELLANEOUS": 4,
40
+ "B-PERSON": 5,
41
+ "I-BUSINESS": 6,
42
+ "I-COURT": 7,
43
+ "I-GOVERNMENT": 8,
44
+ "I-LEGISLATION/ACT": 9,
45
+ "I-LOC": 10,
46
+ "I-LOCATION": 11,
47
+ "I-MISCELLANEOUS": 12,
48
+ "I-PERSON": 13,
49
+ "O": 14,
50
+ "P": 15
51
+ },
52
+ "layer_norm_eps": 1e-05,
53
+ "max_position_embeddings": 514,
54
+ "model_type": "roberta",
55
+ "num_attention_heads": 12,
56
+ "num_hidden_layers": 12,
57
+ "pad_token_id": 1,
58
+ "position_embedding_type": "absolute",
59
+ "transformers_version": "4.45.0.dev0",
60
+ "type_vocab_size": 1,
61
+ "use_cache": true,
62
+ "vocab_size": 50265
63
+ }
epoch_20/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7099bec69274f619f782671d838aa6194d1dddc339ef110aaed67a3887f7c833
3
+ size 496276521
epoch_20/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
epoch_20/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
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": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
epoch_20/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
epoch_20/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
epoch_20/vocab.json ADDED
The diff for this file is too large to render. See raw diff