Hugging Face's logo

evangeliazve
/
camembert-base-articles-ner-v4

Token Classification
Transformers
Safetensors
camembert
Generated from Trainer
Inference Endpoints
Model card Files Community
evangeliazve commited on
Commit
d76df5c
·
verified ·
1 Parent(s): ee5651a

evangeliazve/articles-ner-camembert-legi

Browse files
Files changed (7) hide show
  1. README.md +109 -0
  2. config.json +50 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +20 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +84 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: camembert-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ model-index:
9
+ - name: camembert-base-articles-ner-v4
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # camembert-base-articles-ner-v4
17
+
18
+ This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6720
21
+ - F1: 0.6484
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 50
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
51
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 2.0241 | 1.0 | 5 | 1.7392 | 0.0 |
53
+ | 1.706 | 2.0 | 10 | 1.5603 | 0.0 |
54
+ | 1.5411 | 3.0 | 15 | 1.5006 | 0.0 |
55
+ | 1.4327 | 4.0 | 20 | 1.4519 | 0.0 |
56
+ | 1.4006 | 5.0 | 25 | 1.3972 | 0.0 |
57
+ | 1.3422 | 6.0 | 30 | 1.3435 | 0.0 |
58
+ | 1.329 | 7.0 | 35 | 1.2744 | 0.0979 |
59
+ | 1.1985 | 8.0 | 40 | 1.2313 | 0.0982 |
60
+ | 1.1433 | 9.0 | 45 | 1.1661 | 0.1798 |
61
+ | 1.14 | 10.0 | 50 | 1.1327 | 0.1379 |
62
+ | 1.0554 | 11.0 | 55 | 1.1010 | 0.1310 |
63
+ | 0.9679 | 12.0 | 60 | 1.0609 | 0.0769 |
64
+ | 0.9281 | 13.0 | 65 | 1.0207 | 0.1520 |
65
+ | 0.8697 | 14.0 | 70 | 0.9726 | 0.1743 |
66
+ | 0.8641 | 15.0 | 75 | 0.9455 | 0.4355 |
67
+ | 0.7648 | 16.0 | 80 | 0.8995 | 0.5138 |
68
+ | 0.7321 | 17.0 | 85 | 0.8895 | 0.5929 |
69
+ | 0.7009 | 18.0 | 90 | 0.8631 | 0.5594 |
70
+ | 0.6914 | 19.0 | 95 | 0.8692 | 0.5926 |
71
+ | 0.6339 | 20.0 | 100 | 0.8335 | 0.5637 |
72
+ | 0.6184 | 21.0 | 105 | 0.8327 | 0.6136 |
73
+ | 0.6095 | 22.0 | 110 | 0.8194 | 0.5735 |
74
+ | 0.5999 | 23.0 | 115 | 0.7862 | 0.5789 |
75
+ | 0.5695 | 24.0 | 120 | 0.7849 | 0.5962 |
76
+ | 0.5535 | 25.0 | 125 | 0.7711 | 0.6084 |
77
+ | 0.5525 | 26.0 | 130 | 0.7802 | 0.5977 |
78
+ | 0.5295 | 27.0 | 135 | 0.7753 | 0.6038 |
79
+ | 0.5148 | 28.0 | 140 | 0.7450 | 0.6332 |
80
+ | 0.5177 | 29.0 | 145 | 0.7274 | 0.6561 |
81
+ | 0.4961 | 30.0 | 150 | 0.7235 | 0.6561 |
82
+ | 0.4948 | 31.0 | 155 | 0.7263 | 0.6510 |
83
+ | 0.4774 | 32.0 | 160 | 0.7259 | 0.6484 |
84
+ | 0.4766 | 33.0 | 165 | 0.7168 | 0.6434 |
85
+ | 0.4623 | 34.0 | 170 | 0.7145 | 0.6459 |
86
+ | 0.4821 | 35.0 | 175 | 0.7094 | 0.6535 |
87
+ | 0.4522 | 36.0 | 180 | 0.7030 | 0.664 |
88
+ | 0.4555 | 37.0 | 185 | 0.6975 | 0.6640 |
89
+ | 0.4409 | 38.0 | 190 | 0.6963 | 0.6667 |
90
+ | 0.4386 | 39.0 | 195 | 0.6947 | 0.6745 |
91
+ | 0.4387 | 40.0 | 200 | 0.6810 | 0.6825 |
92
+ | 0.4321 | 41.0 | 205 | 0.6722 | 0.664 |
93
+ | 0.4358 | 42.0 | 210 | 0.6722 | 0.6693 |
94
+ | 0.4201 | 43.0 | 215 | 0.6802 | 0.6719 |
95
+ | 0.4223 | 44.0 | 220 | 0.6856 | 0.6667 |
96
+ | 0.4227 | 45.0 | 225 | 0.6821 | 0.6693 |
97
+ | 0.4226 | 46.0 | 230 | 0.6757 | 0.6563 |
98
+ | 0.4142 | 47.0 | 235 | 0.6740 | 0.6484 |
99
+ | 0.417 | 48.0 | 240 | 0.6725 | 0.6459 |
100
+ | 0.4144 | 49.0 | 245 | 0.6723 | 0.6459 |
101
+ | 0.4144 | 50.0 | 250 | 0.6720 | 0.6484 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.37.2
107
+ - Pytorch 2.2.0+cu121
108
+ - Datasets 2.16.1
109
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
14
+ "0": "B-JOB",
15
+ "1": "I-JOB",
16
+ "2": "B-MINISTERE",
17
+ "3": "I-MINISTERE",
18
+ "4": "B-ORG",
19
+ "5": "I-ORG",
20
+ "6": "B-PER",
21
+ "7": "I-PER",
22
+ "8": "O"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "B-JOB": 0,
28
+ "B-MINISTERE": 2,
29
+ "B-ORG": 4,
30
+ "B-PER": 6,
31
+ "I-JOB": 1,
32
+ "I-MINISTERE": 3,
33
+ "I-ORG": 5,
34
+ "I-PER": 7,
35
+ "O": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "camembert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.37.2",
47
+ "type_vocab_size": 1,
48
+ "use_cache": true,
49
+ "vocab_size": 32005
50
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1274c4402acfd03a44aadfe8d3588620f778c33efabc301c8eeede55c0b2ae
3
+ size 440177044
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>NOTUSED",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>NOTUSED",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "<s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "</s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32004": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32005": {
60
+ "content": "<unk>NOTUSED",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<s>NOTUSED",
70
+ "</s>NOTUSED",
71
+ "<unk>NOTUSED"
72
+ ],
73
+ "bos_token": "<s>",
74
+ "clean_up_tokenization_spaces": true,
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "ignore_mismatched_sizes": true,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a212cc504c222cf1fa9bb36e289dc38e97dec0197beadac516d7c14a69ab17
3
+ size 4728