Hugging Face's logo

levshechter
/
tibetan-CS-detector

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
levshechter commited on
Commit
f77013f
·
verified ·
1 Parent(s): 8abba56

Model save

Browse files
Files changed (7) hide show
  1. README.md +34 -32
  2. final_model/config.json +2 -2
  3. final_model/model.safetensors +2 -2
  4. final_model/tokenizer.json +0 -0
  5. final_model/tokenizer_config.json +14 -11
  6. final_model/vocab.txt +0 -0
  7. model.safetensors +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: transformers
3
- base_model: OMRIDRORI/mbert-tibetan-continual-unicode-240k
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,25 +15,25 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # tibetan-CS-detector
17
 
18
- This model is a fine-tuned version of [OMRIDRORI/mbert-tibetan-continual-unicode-240k](https://huggingface.co/OMRIDRORI/mbert-tibetan-continual-unicode-240k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 6.3891
21
- - Accuracy: 0.7459
22
- - Switch Precision: 0.1522
23
- - Switch Recall: 0.7686
24
- - Switch F1: 0.2541
25
- - True Switches: 121
26
- - Pred Switches: 611
27
- - Exact Matches: 80
28
- - Proximity Matches: 13
29
- - To Auto Precision: 0.5909
30
- - To Auto Recall: 0.8966
31
- - To Allo Precision: 0.0784
32
- - To Allo Recall: 0.6508
33
- - True To Auto: 58
34
- - True To Allo: 63
35
- - Matched To Auto: 52
36
- - Matched To Allo: 41
37
 
38
  ## Model description
39
 
@@ -69,19 +69,21 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Switch Precision | Switch Recall | Switch F1 | True Switches | Pred Switches | Exact Matches | Proximity Matches | To Auto Precision | To Auto Recall | To Allo Precision | To Allo Recall | True To Auto | True To Allo | Matched To Auto | Matched To Allo |
71
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:----------------:|:-------------:|:---------:|:-------------:|:-------------:|:-------------:|:-----------------:|:-----------------:|:--------------:|:-----------------:|:--------------:|:------------:|:------------:|:---------------:|:---------------:|
72
- | 42.468 | 1.9355 | 30 | 3.7324 | 0.7603 | 0.0 | 0.0 | 0.0 | 121 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 58 | 63 | 0 | 0 |
73
- | 4.284 | 3.8710 | 60 | 3.5779 | 0.7669 | 0.0 | 0.0 | 0.0 | 121 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 58 | 63 | 0 | 0 |
74
- | 4.2817 | 5.8065 | 90 | 3.3614 | 0.7669 | 0.0 | 0.0 | 0.0 | 121 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 58 | 63 | 0 | 0 |
75
- | 8.0705 | 7.7419 | 120 | 3.1097 | 0.7669 | 0.0 | 0.0 | 0.0 | 121 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 58 | 63 | 0 | 0 |
76
- | 4.1077 | 9.6774 | 150 | 2.9941 | 0.7669 | 0.0 | 0.0 | 0.0 | 121 | 0 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 58 | 63 | 0 | 0 |
77
- | 3.7928 | 11.6129 | 180 | 2.8781 | 0.7670 | 1.0 | 0.0083 | 0.0164 | 121 | 1 | 1 | 0 | 1.0 | 0.0172 | 0.0 | 0.0 | 58 | 63 | 1 | 0 |
78
- | 6.5207 | 13.5484 | 210 | 32.2995 | 0.7648 | 0.2819 | 0.3471 | 0.3111 | 121 | 149 | 38 | 4 | 0.2819 | 0.7241 | 0.0 | 0.0 | 58 | 63 | 42 | 0 |
79
- | 3.8945 | 15.4839 | 240 | 9.5270 | 0.7660 | 0.36 | 0.3719 | 0.3659 | 121 | 125 | 43 | 2 | 0.4078 | 0.7241 | 0.1364 | 0.0476 | 58 | 63 | 42 | 3 |
80
- | 6.5655 | 17.4194 | 270 | 24.9038 | 0.7647 | 0.3077 | 0.3967 | 0.3466 | 121 | 156 | 46 | 2 | 0.4 | 0.7241 | 0.1176 | 0.0952 | 58 | 63 | 42 | 6 |
81
- | 6.7599 | 19.3548 | 300 | 25.3613 | 0.7547 | 0.1701 | 0.5537 | 0.2602 | 121 | 394 | 63 | 4 | 0.42 | 0.7241 | 0.0850 | 0.3968 | 58 | 63 | 42 | 25 |
82
- | 7.0001 | 21.2903 | 330 | 6.6858 | 0.7542 | 0.1903 | 0.6777 | 0.2971 | 121 | 431 | 77 | 5 | 0.5667 | 0.8793 | 0.0909 | 0.4921 | 58 | 63 | 51 | 31 |
83
- | 9.408 | 23.2258 | 360 | 5.7973 | 0.7546 | 0.2015 | 0.6860 | 0.3114 | 121 | 412 | 76 | 7 | 0.6047 | 0.8966 | 0.0951 | 0.4921 | 58 | 63 | 52 | 31 |
84
- | 6.6903 | 25.1613 | 390 | 6.3891 | 0.7459 | 0.1522 | 0.7686 | 0.2541 | 121 | 611 | 80 | 13 | 0.5909 | 0.8966 | 0.0784 | 0.6508 | 58 | 63 | 52 | 41 |
 
 
85
 
86
 
87
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ base_model: OMRIDRORI/mbert-tibetan-continual-wylie-final
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # tibetan-CS-detector
17
 
18
+ This model is a fine-tuned version of [OMRIDRORI/mbert-tibetan-continual-wylie-final](https://huggingface.co/OMRIDRORI/mbert-tibetan-continual-wylie-final) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.8365
21
+ - Accuracy: 0.9388
22
+ - Switch Precision: 0.4980
23
+ - Switch Recall: 0.9130
24
+ - Switch F1: 0.6445
25
+ - True Switches: 138
26
+ - Pred Switches: 253
27
+ - Exact Matches: 122
28
+ - Proximity Matches: 4
29
+ - To Auto Precision: 0.6966
30
+ - To Auto Recall: 0.9254
31
+ - To Allo Precision: 0.3902
32
+ - To Allo Recall: 0.9014
33
+ - True To Auto: 67
34
+ - True To Allo: 71
35
+ - Matched To Auto: 62
36
+ - Matched To Allo: 64
37
 
38
  ## Model description
39
 
 
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Switch Precision | Switch Recall | Switch F1 | True Switches | Pred Switches | Exact Matches | Proximity Matches | To Auto Precision | To Auto Recall | To Allo Precision | To Allo Recall | True To Auto | True To Allo | Matched To Auto | Matched To Allo |
71
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:----------------:|:-------------:|:---------:|:-------------:|:-------------:|:-------------:|:-----------------:|:-----------------:|:--------------:|:-----------------:|:--------------:|:------------:|:------------:|:---------------:|:---------------:|
72
+ | 6.9424 | 1.9355 | 30 | 3.9697 | 0.4816 | 0.0 | 0.0 | 0.0 | 138 | 8 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 67 | 71 | 0 | 0 |
73
+ | 4.7989 | 3.8710 | 60 | 3.2594 | 0.7331 | 0.0 | 0.0 | 0.0 | 138 | 1 | 0 | 0 | 0.0 | 0.0 | 0.0 | 0.0 | 67 | 71 | 0 | 0 |
74
+ | 9.9599 | 5.8065 | 90 | 3.9145 | 0.7658 | 0.5909 | 0.2826 | 0.3824 | 138 | 66 | 39 | 0 | 0.6786 | 0.5672 | 0.1 | 0.0141 | 67 | 71 | 38 | 1 |
75
+ | 7.1635 | 7.7419 | 120 | 4.4059 | 0.7665 | 0.3818 | 0.4565 | 0.4158 | 138 | 165 | 62 | 1 | 0.6438 | 0.7015 | 0.1739 | 0.2254 | 67 | 71 | 47 | 16 |
76
+ | 10.5361 | 9.6774 | 150 | 5.7618 | 0.7737 | 0.3556 | 0.6159 | 0.4509 | 138 | 239 | 82 | 3 | 0.6667 | 0.8358 | 0.1871 | 0.4085 | 67 | 71 | 56 | 29 |
77
+ | 9.5003 | 11.6129 | 180 | 4.0246 | 0.8587 | 0.5741 | 0.4493 | 0.5041 | 138 | 108 | 62 | 0 | 0.7237 | 0.8209 | 0.2188 | 0.0986 | 67 | 71 | 55 | 7 |
78
+ | 11.3652 | 13.5484 | 210 | 3.3524 | 0.9056 | 0.4911 | 0.6014 | 0.5407 | 138 | 169 | 82 | 1 | 0.6818 | 0.8955 | 0.2840 | 0.3239 | 67 | 71 | 60 | 23 |
79
+ | 4.7329 | 15.4839 | 240 | 2.6446 | 0.9111 | 0.5337 | 0.6304 | 0.5781 | 138 | 163 | 85 | 2 | 0.6667 | 0.8955 | 0.3699 | 0.3803 | 67 | 71 | 60 | 27 |
80
+ | 2.2142 | 17.4194 | 270 | 4.7999 | 0.9163 | 0.5 | 0.8406 | 0.6270 | 138 | 232 | 114 | 2 | 0.6778 | 0.9104 | 0.3873 | 0.7746 | 67 | 71 | 61 | 55 |
81
+ | 6.1957 | 19.3548 | 300 | 2.5471 | 0.9232 | 0.5928 | 0.8333 | 0.6928 | 138 | 194 | 113 | 2 | 0.6932 | 0.9104 | 0.5094 | 0.7606 | 67 | 71 | 61 | 54 |
82
+ | 6.6179 | 21.2903 | 330 | 2.7181 | 0.9266 | 0.5619 | 0.8551 | 0.6782 | 138 | 210 | 116 | 2 | 0.6977 | 0.8955 | 0.4677 | 0.8169 | 67 | 71 | 60 | 58 |
83
+ | 1.6293 | 23.2258 | 360 | 2.1611 | 0.9365 | 0.4939 | 0.8768 | 0.6319 | 138 | 245 | 118 | 3 | 0.6813 | 0.9254 | 0.3831 | 0.8310 | 67 | 71 | 62 | 59 |
84
+ | 1.7535 | 25.1613 | 390 | 2.1557 | 0.9381 | 0.5105 | 0.8841 | 0.6472 | 138 | 239 | 119 | 3 | 0.7093 | 0.9104 | 0.3987 | 0.8592 | 67 | 71 | 61 | 61 |
85
+ | 1.4616 | 27.0968 | 420 | 3.3062 | 0.9368 | 0.4808 | 0.9058 | 0.6281 | 138 | 260 | 121 | 4 | 0.6966 | 0.9254 | 0.3684 | 0.8873 | 67 | 71 | 62 | 63 |
86
+ | 10.5341 | 29.0323 | 450 | 2.8365 | 0.9388 | 0.4980 | 0.9130 | 0.6445 | 138 | 253 | 122 | 4 | 0.6966 | 0.9254 | 0.3902 | 0.9014 | 67 | 71 | 62 | 64 |
87
 
88
 
89
  ### Framework versions
final_model/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "OMRIDRORI/mbert-tibetan-continual-unicode-240k",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
@@ -39,5 +39,5 @@
39
  "transformers_version": "4.46.3",
40
  "type_vocab_size": 2,
41
  "use_cache": true,
42
- "vocab_size": 119547
43
  }
 
1
  {
2
+ "_name_or_path": "OMRIDRORI/mbert-tibetan-continual-wylie-final",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
 
39
  "transformers_version": "4.46.3",
40
  "type_vocab_size": 2,
41
  "use_cache": true,
42
+ "vocab_size": 30000
43
  }
final_model/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e3c8e1bcb0ebccf62361beee4bdb2f8b6e634ec5ceadc1abb046edab3eb4666
3
- size 709087056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8124c98a2ce284e4744042293de3ae0c6733a3f43b5765bb43bcad46b31499a9
3
+ size 433998648
final_model/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
final_model/tokenizer_config.json CHANGED
@@ -1,38 +1,38 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
- "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
- "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -41,12 +41,15 @@
41
  "special": true
42
  }
43
  },
44
- "clean_up_tokenization_spaces": false,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": false,
 
47
  "extra_special_tokens": {},
 
48
  "mask_token": "[MASK]",
49
- "model_max_length": 512,
 
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[UNK]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "[CLS]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "[SEP]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
+ "content": "[PAD]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
41
  "special": true
42
  }
43
  },
44
+ "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
  "extra_special_tokens": {},
49
+ "lowercase": false,
50
  "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
  "pad_token": "[PAD]",
54
  "sep_token": "[SEP]",
55
  "strip_accents": null,
final_model/vocab.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc42e0fcf383ddd5af112f5d7feb95de51d58efe3034d8cf14949b7393f58959
3
  size 433998648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8124c98a2ce284e4744042293de3ae0c6733a3f43b5765bb43bcad46b31499a9
3
  size 433998648