Hugging Face's logo

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

Token Classification
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
jaggernaut007 commited on
Commit
ff14611
·
verified ·
1 Parent(s): 2b8a899

End of training

Browse files
Files changed (6) hide show
  1. README.md +22 -31
  2. model.safetensors +2 -2
  3. special_tokens_map.json +49 -5
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +24 -22
  6. 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: 0.6069
24
- - Precision: 0.7971
25
- - Recall: 0.8633
26
- - F1: 0.8289
27
- - Accuracy: 0.7973
28
 
29
  ## Model description
30
 
@@ -44,42 +44,33 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-06
47
- - train_batch_size: 4
48
  - eval_batch_size: 4
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - num_epochs: 10
 
53
 
54
  ### Training results
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
 
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: 0.1440
24
+ - Precision: 0.9718
25
+ - Recall: 0.9695
26
+ - F1: 0.9706
27
+ - Accuracy: 0.9657
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-06
47
+ - train_batch_size: 16
48
  - eval_batch_size: 4
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - num_epochs: 10
53
+ - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | No log | 0.15 | 10 | 0.7087 | 0.8180 | 0.8564 | 0.8367 | 0.8231 |
60
+ | No log | 0.3 | 20 | 0.5231 | 0.8485 | 0.8766 | 0.8623 | 0.8516 |
61
+ | No log | 0.45 | 30 | 0.4027 | 0.8762 | 0.8963 | 0.8861 | 0.8776 |
62
+ | No log | 0.6 | 40 | 0.3328 | 0.9029 | 0.9150 | 0.9089 | 0.9031 |
63
+ | No log | 0.75 | 50 | 0.2861 | 0.9357 | 0.9403 | 0.9379 | 0.9314 |
64
+ | No log | 0.9 | 60 | 0.2518 | 0.9501 | 0.9540 | 0.9521 | 0.9463 |
65
+ | No log | 1.04 | 70 | 0.2245 | 0.9562 | 0.9606 | 0.9584 | 0.9529 |
66
+ | No log | 1.19 | 80 | 0.2020 | 0.9596 | 0.9638 | 0.9617 | 0.9566 |
67
+ | No log | 1.34 | 90 | 0.1834 | 0.9632 | 0.9671 | 0.9651 | 0.9600 |
68
+ | No log | 1.49 | 100 | 0.1672 | 0.9663 | 0.9672 | 0.9668 | 0.9607 |
69
+ | No log | 1.64 | 110 | 0.1532 | 0.9711 | 0.9695 | 0.9703 | 0.9655 |
70
+ | No log | 1.79 | 120 | 0.1440 | 0.9718 | 0.9695 | 0.9706 | 0.9657 |
71
+ | No log | 1.94 | 130 | 0.1375 | 0.9707 | 0.9678 | 0.9692 | 0.9640 |
72
+ | No log | 2.09 | 140 | 0.1329 | 0.9714 | 0.9679 | 0.9697 | 0.9641 |
73
+ | No log | 2.24 | 150 | 0.1292 | 0.9717 | 0.9681 | 0.9699 | 0.9647 |
 
 
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ad1b90e4f68842ea413f1618dbdfc42a2abd655a5c6ef7ba0e9e652b0c79394
3
- size 430914936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4265a2642b903ba19f74f27a66ef548d23212a474bd2da1af8c087a421b8f095
3
+ size 496256392
special_tokens_map.json CHANGED
@@ -1,7 +1,51 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -2,58 +2,60 @@
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
  }
 
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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf04021f522f7b43f71fefd316d8c0ca5b5751e7f8a24ac1e80c43c0137fe786
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7156be5afb84829dfd007bad6f79a530b762726c88701a28690b42eb6dbee581
3
  size 4984