Hugging Face's logo

ali972
/
my_awesome_wnut_model

Token Classification
Transformers
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
ali972 commited on
Commit
1f38af6
·
verified ·
1 Parent(s): a83e7cc

text_mapping

Browse files
Files changed (8) hide show
  1. README.md +22 -22
  2. config.json +28 -21
  3. model.safetensors +2 -2
  4. special_tokens_map.json +5 -18
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +19 -47
  7. training_args.bin +2 -2
  8. vocab.txt +0 -0
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
- license: mit
4
- base_model: camembert-base
5
  tags:
6
  - generated_from_trainer
7
  metrics:
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # my_awesome_wnut_model
21
 
22
- This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.0033
25
  - Precision: 0.0
26
  - Recall: 0.0
27
  - F1: 0.0
28
- - Accuracy: 0.9990
29
 
30
  ## Model description
31
 
@@ -44,33 +44,33 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 2e-05
48
  - train_batch_size: 16
49
  - eval_batch_size: 16
50
  - seed: 42
51
- - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
  - num_epochs: 10
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:---:|:--------:|
59
- | 0.0136 | 1.0 | 1559 | 0.0085 | 0.0 | 0.0 | 0.0 | 0.9983 |
60
- | 0.0087 | 2.0 | 3118 | 0.0056 | 0.0 | 0.0 | 0.0 | 0.9986 |
61
- | 0.0061 | 3.0 | 4677 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.9987 |
62
- | 0.0061 | 4.0 | 6236 | 0.0040 | 0.0 | 0.0 | 0.0 | 0.9988 |
63
- | 0.005 | 5.0 | 7795 | 0.0038 | 0.0 | 0.0 | 0.0 | 0.9988 |
64
- | 0.0049 | 6.0 | 9354 | 0.0035 | 0.0 | 0.0 | 0.0 | 0.9989 |
65
- | 0.0044 | 7.0 | 10913 | 0.0034 | 0.0 | 0.0 | 0.0 | 0.9989 |
66
- | 0.004 | 8.0 | 12472 | 0.0036 | 0.0 | 0.0 | 0.0 | 0.9988 |
67
- | 0.004 | 9.0 | 14031 | 0.0034 | 0.0 | 0.0 | 0.0 | 0.9990 |
68
- | 0.0044 | 10.0 | 15590 | 0.0033 | 0.0 | 0.0 | 0.0 | 0.9990 |
69
 
70
 
71
  ### Framework versions
72
 
73
- - Transformers 4.46.2
74
  - Pytorch 2.5.1
75
- - Datasets 3.1.0
76
- - Tokenizers 0.20.3
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert/distilbert-base-cased
5
  tags:
6
  - generated_from_trainer
7
  metrics:
 
19
 
20
  # my_awesome_wnut_model
21
 
22
+ This model is a fine-tuned version of [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.0832
25
  - Precision: 0.0
26
  - Recall: 0.0
27
  - F1: 0.0
28
+ - Accuracy: 0.9821
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 0.0002
48
  - train_batch_size: 16
49
  - eval_batch_size: 16
50
  - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - num_epochs: 10
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
59
+ | No log | 1.0 | 118 | 0.0767 | 0.0 | 0.0 | 0.0 | 0.9725 |
60
+ | No log | 2.0 | 236 | 0.0554 | 0.0 | 0.0 | 0.0 | 0.9799 |
61
+ | No log | 3.0 | 354 | 0.0695 | 0.0 | 0.0 | 0.0 | 0.9799 |
62
+ | No log | 4.0 | 472 | 0.0762 | 0.0 | 0.0 | 0.0 | 0.9795 |
63
+ | 0.0497 | 5.0 | 590 | 0.0888 | 0.0 | 0.0 | 0.0 | 0.9804 |
64
+ | 0.0497 | 6.0 | 708 | 0.0820 | 0.0 | 0.0 | 0.0 | 0.9812 |
65
+ | 0.0497 | 7.0 | 826 | 0.0877 | 0.0 | 0.0 | 0.0 | 0.9814 |
66
+ | 0.0497 | 8.0 | 944 | 0.0864 | 0.0 | 0.0 | 0.0 | 0.9815 |
67
+ | 0.003 | 9.0 | 1062 | 0.0876 | 0.0 | 0.0 | 0.0 | 0.9823 |
68
+ | 0.003 | 10.0 | 1180 | 0.0832 | 0.0 | 0.0 | 0.0 | 0.9821 |
69
 
70
 
71
  ### Framework versions
72
 
73
+ - Transformers 4.44.2
74
  - Pytorch 2.5.1
75
+ - Datasets 2.19.0
76
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -1,28 +1,35 @@
1
  {
2
- "_name_or_path": "camembert-base",
 
3
  "architectures": [
4
- "CamembertForTokenClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 5,
8
- "classifier_dropout": null,
9
- "eos_token_id": 6,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
 
 
13
  "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 514,
17
- "model_type": "camembert",
18
- "num_attention_heads": 12,
19
- "num_hidden_layers": 12,
 
 
 
20
  "output_past": true,
21
- "pad_token_id": 1,
22
- "position_embedding_type": "absolute",
 
 
 
23
  "torch_dtype": "float32",
24
- "transformers_version": "4.46.2",
25
- "type_vocab_size": 1,
26
- "use_cache": true,
27
- "vocab_size": 32005
28
  }
 
1
  {
2
+ "_name_or_path": "distilbert/distilbert-base-cased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForTokenClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
  "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
  "output_past": true,
27
+ "pad_token_id": 0,
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
  "torch_dtype": "float32",
33
+ "transformers_version": "4.44.2",
34
+ "vocab_size": 28996
 
 
35
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bec9a9d5a6c8205f96eb8fbdc58958cf267523e17c2dc6b383919549f17236da
3
- size 440155504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47facfb339c6465ee025b15245c249ea6e96b6de40abddd120f09695af1dc24
3
+ size 260785212
special_tokens_map.json CHANGED
@@ -1,20 +1,7 @@
1
  {
2
- "additional_special_tokens": [
3
- "<s>NOTUSED",
4
- "</s>NOTUSED",
5
- "<unk>NOTUSED"
6
- ],
7
- "bos_token": "<s>",
8
- "cls_token": "<s>",
9
- "eos_token": "</s>",
10
- "mask_token": {
11
- "content": "<mask>",
12
- "lstrip": true,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- "pad_token": "<pad>",
18
- "sep_token": "</s>",
19
- "unk_token": "<unk>"
20
  }
 
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
@@ -2,63 +2,39 @@
2
  "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<s>NOTUSED",
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>NOTUSED",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
- "4": {
29
- "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "5": {
37
- "content": "<s>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "6": {
45
- "content": "</s>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "32004": {
53
- "content": "<mask>",
54
- "lstrip": true,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "32005": {
61
- "content": "<unk>NOTUSED",
62
  "lstrip": false,
63
  "normalized": false,
64
  "rstrip": false,
@@ -66,19 +42,15 @@
66
  "special": true
67
  }
68
  },
69
- "additional_special_tokens": [
70
- "<s>NOTUSED",
71
- "</s>NOTUSED",
72
- "<unk>NOTUSED"
73
- ],
74
- "bos_token": "<s>",
75
- "clean_up_tokenization_spaces": false,
76
- "cls_token": "<s>",
77
- "eos_token": "</s>",
78
- "mask_token": "<mask>",
79
  "model_max_length": 512,
80
- "pad_token": "<pad>",
81
- "sep_token": "</s>",
82
- "tokenizer_class": "CamembertTokenizer",
83
- "unk_token": "<unk>"
 
 
84
  }
 
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,
 
42
  "special": true
43
  }
44
  },
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
 
 
 
 
 
 
49
  "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28226c1b70e899c61ac969dfed2363de9a7e92518ee348172294ed0b822cbccc
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43497cc82970d13d7ba5492c2e1f1013a8ed4b26030c75dd08816764f5f51b7
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff