AntoineD commited on
Commit
e01fa4c
1 Parent(s): b9ed086

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 6,
3
+ "</s>NOTUSED": 2,
4
+ "<mask>": 32004,
5
+ "<pad>": 1,
6
+ "<s>": 5,
7
+ "<s>NOTUSED": 0,
8
+ "<unk>": 4
9
+ }
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "camembert-base",
3
+ "architectures": [
4
+ "CamembertForSequenceClassification"
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": "[TI][Cl]",
15
+ "1": "[TI][DO]",
16
+ "2": "[TI][Ca]",
17
+ "3": "[TI][RE]",
18
+ "4": "[RI][RW]",
19
+ "5": "[RI][RD]",
20
+ "6": "[AG][Cc]",
21
+ "7": "[autres]"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "[AG][Cc]": 6,
27
+ "[RI][RD]": 5,
28
+ "[RI][RW]": 4,
29
+ "[TI][Ca]": 2,
30
+ "[TI][Cl]": 0,
31
+ "[TI][DO]": 1,
32
+ "[TI][RE]": 3,
33
+ "[autres]": 7
34
+ },
35
+ "layer_norm_eps": 1e-05,
36
+ "max_position_embeddings": 514,
37
+ "model_type": "camembert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "output_past": true,
41
+ "pad_token_id": 1,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.34.0",
46
+ "type_vocab_size": 1,
47
+ "use_cache": true,
48
+ "vocab_size": 32005
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f113f9a51157d7b6706bbf1c6bcf3bf3e1a96ee5ac34966d704097d6e55f6929
3
+ size 442581361
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
+ size 810912
special_tokens_map.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "<pad>",
5
+ "</s>NOTUSED",
6
+ "<unk>",
7
+ "<s>",
8
+ "</s>",
9
+ "<mask>"
10
+ ],
11
+ "bos_token": "<s>",
12
+ "cls_token": "<s>",
13
+ "eos_token": "</s>",
14
+ "mask_token": "<mask>",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "unk_token": "<unk>"
18
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
60
+ "additional_special_tokens": [
61
+ "<s>NOTUSED",
62
+ "<pad>",
63
+ "</s>NOTUSED",
64
+ "<unk>",
65
+ "<s>",
66
+ "</s>",
67
+ "<mask>"
68
+ ],
69
+ "bos_token": "<s>",
70
+ "clean_up_tokenization_spaces": true,
71
+ "cls_token": "<s>",
72
+ "eos_token": "</s>",
73
+ "mask_token": "<mask>",
74
+ "max_length": 512,
75
+ "model_max_length": 512,
76
+ "pad_token": "<pad>",
77
+ "sep_token": "</s>",
78
+ "stride": 0,
79
+ "tokenizer_class": "CamembertTokenizer",
80
+ "truncation_side": "right",
81
+ "truncation_strategy": "longest_first",
82
+ "unk_token": "<unk>"
83
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58193ce3566d02076e936b114d5ac991b819ea709e030c4e43425ca30e0bff3
3
+ size 4091