Hugging Face's logo

jaggernaut007
/
roberta-base-finetuned-abbr-finetuned-ner

Token Classification
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
 Community
jaggernaut007 commited on
Commit
2b8a899
·
verified ·
1 Parent(s): 2604026

End of training

Browse files
Files changed (7) hide show
  1. README.md +30 -31
  2. config.json +8 -10
  3. model.safetensors +2 -2
  4. special_tokens_map.json +5 -49
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +22 -24
  7. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [surrey-nlp/roberta-base-finetuned-abbr](https://huggingface.co/surrey-nlp/roberta-base-finetuned-abbr) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.6133
24
- - Precision: 0.8024
25
- - Recall: 0.8627
26
- - F1: 0.8314
27
- - Accuracy: 0.8039
28
 
29
  ## Model description
30
 
@@ -55,32 +55,31 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | No log | 0.37 | 100 | 0.7097 | 0.7957 | 0.8581 | 0.8257 | 0.7957 |
59
- | No log | 0.75 | 200 | 0.6784 | 0.7957 | 0.8581 | 0.8257 | 0.7957 |
60
- | No log | 1.12 | 300 | 0.6705 | 0.7957 | 0.8581 | 0.8257 | 0.7957 |
61
- | No log | 1.49 | 400 | 0.6435 | 0.7959 | 0.8583 | 0.8259 | 0.7965 |
62
- | 0.7623 | 1.87 | 500 | 0.6364 | 0.7973 | 0.8598 | 0.8274 | 0.7979 |
63
- | 0.7623 | 2.24 | 600 | 0.6384 | 0.7948 | 0.8552 | 0.8239 | 0.7973 |
64
- | 0.7623 | 2.61 | 700 | 0.6359 | 0.7975 | 0.8600 | 0.8275 | 0.7982 |
65
- | 0.7623 | 2.99 | 800 | 0.6209 | 0.7977 | 0.8600 | 0.8277 | 0.7987 |
66
- | 0.7623 | 3.36 | 900 | 0.6178 | 0.7992 | 0.8598 | 0.8284 | 0.8011 |
67
- | 0.6887 | 3.73 | 1000 | 0.6140 | 0.7992 | 0.8591 | 0.8281 | 0.8003 |
68
- | 0.6887 | 4.1 | 1100 | 0.6122 | 0.7996 | 0.8595 | 0.8285 | 0.8009 |
69
- | 0.6887 | 4.48 | 1200 | 0.6119 | 0.7997 | 0.8601 | 0.8288 | 0.8014 |
70
- | 0.6887 | 4.85 | 1300 | 0.6083 | 0.7992 | 0.8578 | 0.8274 | 0.8030 |
71
- | 0.6887 | 5.22 | 1400 | 0.6222 | 0.8007 | 0.8613 | 0.8299 | 0.8014 |
72
- | 0.6564 | 5.6 | 1500 | 0.6055 | 0.8013 | 0.8617 | 0.8304 | 0.8031 |
73
- | 0.6564 | 5.97 | 1600 | 0.6063 | 0.8004 | 0.8596 | 0.8290 | 0.8025 |
74
- | 0.6564 | 6.34 | 1700 | 0.6143 | 0.8011 | 0.8613 | 0.8301 | 0.8028 |
75
- | 0.6564 | 6.72 | 1800 | 0.5942 | 0.8034 | 0.8622 | 0.8318 | 0.8064 |
76
- | 0.6564 | 7.09 | 1900 | 0.6061 | 0.8012 | 0.8610 | 0.8300 | 0.8028 |
77
- | 0.6318 | 7.46 | 2000 | 0.6133 | 0.8024 | 0.8627 | 0.8314 | 0.8039 |
78
- | 0.6318 | 7.84 | 2100 | 0.6001 | 0.8027 | 0.8627 | 0.8316 | 0.8050 |
79
- | 0.6318 | 8.21 | 2200 | 0.6088 | 0.8014 | 0.8615 | 0.8304 | 0.8031 |
80
- | 0.6318 | 8.58 | 2300 | 0.5915 | 0.8042 | 0.8630 | 0.8326 | 0.8072 |
81
- | 0.6318 | 8.96 | 2400 | 0.6025 | 0.8017 | 0.8617 | 0.8306 | 0.8037 |
82
- | 0.6216 | 9.33 | 2500 | 0.6003 | 0.8022 | 0.8620 | 0.8311 | 0.8045 |
83
- | 0.6216 | 9.7 | 2600 | 0.5954 | 0.8035 | 0.8632 | 0.8323 | 0.8059 |
84
 
85
 
86
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [surrey-nlp/roberta-base-finetuned-abbr](https://huggingface.co/surrey-nlp/roberta-base-finetuned-abbr) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.6069
24
+ - Precision: 0.7971
25
+ - Recall: 0.8633
26
+ - F1: 0.8289
27
+ - Accuracy: 0.7973
28
 
29
  ## Model description
30
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 0.37 | 100 | 0.7456 | 0.7807 | 0.8460 | 0.8120 | 0.7807 |
59
+ | No log | 0.75 | 200 | 0.7377 | 0.7807 | 0.8460 | 0.8120 | 0.7807 |
60
+ | No log | 1.12 | 300 | 0.7192 | 0.7807 | 0.8460 | 0.8120 | 0.7807 |
61
+ | No log | 1.49 | 400 | 0.7027 | 0.7808 | 0.8461 | 0.8122 | 0.7808 |
62
+ | 0.8312 | 1.87 | 500 | 0.6920 | 0.7817 | 0.8471 | 0.8131 | 0.7817 |
63
+ | 0.8312 | 2.24 | 600 | 0.6785 | 0.7813 | 0.8466 | 0.8126 | 0.7813 |
64
+ | 0.8312 | 2.61 | 700 | 0.6826 | 0.7826 | 0.8480 | 0.8140 | 0.7826 |
65
+ | 0.8312 | 2.99 | 800 | 0.6590 | 0.7855 | 0.8511 | 0.8170 | 0.7855 |
66
+ | 0.8312 | 3.36 | 900 | 0.6499 | 0.7904 | 0.8564 | 0.8221 | 0.7904 |
67
+ | 0.755 | 3.73 | 1000 | 0.6440 | 0.7933 | 0.8596 | 0.8251 | 0.7933 |
68
+ | 0.755 | 4.1 | 1100 | 0.6378 | 0.7941 | 0.8605 | 0.8260 | 0.7943 |
69
+ | 0.755 | 4.48 | 1200 | 0.6291 | 0.7950 | 0.8615 | 0.8269 | 0.7951 |
70
+ | 0.755 | 4.85 | 1300 | 0.6269 | 0.7927 | 0.8588 | 0.8244 | 0.7927 |
71
+ | 0.755 | 5.22 | 1400 | 0.6202 | 0.7949 | 0.8613 | 0.8267 | 0.7950 |
72
+ | 0.7217 | 5.6 | 1500 | 0.6154 | 0.7962 | 0.8627 | 0.8281 | 0.7963 |
73
+ | 0.7217 | 5.97 | 1600 | 0.6126 | 0.7964 | 0.8627 | 0.8282 | 0.7966 |
74
+ | 0.7217 | 6.34 | 1700 | 0.6099 | 0.7960 | 0.8624 | 0.8279 | 0.7960 |
75
+ | 0.7217 | 6.72 | 1800 | 0.6094 | 0.7926 | 0.8580 | 0.8240 | 0.7933 |
76
+ | 0.7217 | 7.09 | 1900 | 0.6087 | 0.7964 | 0.8629 | 0.8283 | 0.7966 |
77
+ | 0.6873 | 7.46 | 2000 | 0.6069 | 0.7971 | 0.8633 | 0.8289 | 0.7973 |
78
+ | 0.6873 | 7.84 | 2100 | 0.6048 | 0.7968 | 0.8629 | 0.8285 | 0.7970 |
79
+ | 0.6873 | 8.21 | 2200 | 0.6017 | 0.7974 | 0.8630 | 0.8289 | 0.7973 |
80
+ | 0.6873 | 8.58 | 2300 | 0.6025 | 0.7941 | 0.8591 | 0.8253 | 0.7951 |
81
+ | 0.6873 | 8.96 | 2400 | 0.5981 | 0.7964 | 0.8616 | 0.8277 | 0.7964 |
82
+ | 0.6731 | 9.33 | 2500 | 0.5993 | 0.7968 | 0.8622 | 0.8282 | 0.7969 |
 
83
 
84
 
85
  ### Framework versions
config.json CHANGED
@@ -11,20 +11,18 @@
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
- "0": "O",
15
- "1": "B-AC",
16
- "2": "I-AC",
17
- "3": "B-LF",
18
- "4": "I-LF"
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
- "B-AC": 1,
24
- "B-LF": 3,
25
- "I-AC": 2,
26
- "I-LF": 4,
27
- "O": 0
28
  },
29
  "layer_norm_eps": 1e-05,
30
  "max_position_embeddings": 514,
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3"
 
18
  },
19
  "initializer_range": 0.02,
20
  "intermediate_size": 3072,
21
  "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3
 
26
  },
27
  "layer_norm_eps": 1e-05,
28
  "max_position_embeddings": 514,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac457083130ac8326d0e9684d6d8c3fe64c815ad110bf895707357c8af2c407d
3
- size 496259468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ad1b90e4f68842ea413f1618dbdfc42a2abd655a5c6ef7ba0e9e652b0c79394
3
+ size 430914936
special_tokens_map.json CHANGED
@@ -1,51 +1,7 @@
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
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -2,60 +2,58 @@
2
  "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<s>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "1": {
13
- "content": "<pad>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
- "2": {
21
- "content": "</s>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
- "3": {
29
- "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": false,
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
- "max_length": 512,
52
  "model_max_length": 512,
53
- "pad_token": "<pad>",
54
- "sep_token": "</s>",
55
- "stride": 0,
56
- "tokenizer_class": "RobertaTokenizer",
57
- "trim_offsets": true,
58
- "truncation_side": "right",
59
- "truncation_strategy": "longest_first",
60
- "unk_token": "<unk>"
61
  }
 
2
  "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "[PAD]",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "100": {
13
+ "content": "[UNK]",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "101": {
21
+ "content": "[CLS]",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
+ "102": {
29
+ "content": "[SEP]",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "103": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
 
45
  "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "mask_token": "[MASK]",
50
+ "max_len": 512,
51
  "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
 
59
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f77bd9fc6a934fd533f798e9305546a22e88b48b3556c8a97fa21e49ad2b46f
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf04021f522f7b43f71fefd316d8c0ca5b5751e7f8a24ac1e80c43c0137fe786
3
  size 4984