DioulaD commited on
Commit
974a6b0
1 Parent(s): 73ca330

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "camembert/camembert-base",
3
+ "architectures": [
4
+ "CamembertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "eos_token_ids": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "B-PER",
17
+ "2": "I-PER",
18
+ "3": "B-ORG",
19
+ "4": "I-ORG",
20
+ "5": "B-LOC",
21
+ "6": "I-LOC",
22
+ "7": "B-MISC",
23
+ "8": "I-MISC",
24
+ "9": "B-ADRESS",
25
+ "10": "I-ADRESS",
26
+ "11": "B-DATE",
27
+ "12": "I-DATE"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "label2id": {
32
+ "B-ADRESS": 9,
33
+ "B-DATE": 11,
34
+ "B-LOC": 5,
35
+ "B-MISC": 7,
36
+ "B-ORG": 3,
37
+ "B-PER": 1,
38
+ "I-ADRESS": 10,
39
+ "I-DATE": 12,
40
+ "I-LOC": 6,
41
+ "I-MISC": 8,
42
+ "I-ORG": 4,
43
+ "I-PER": 2,
44
+ "O": 0
45
+ },
46
+ "layer_norm_eps": 1e-05,
47
+ "max_position_embeddings": 514,
48
+ "model_type": "camembert",
49
+ "num_attention_heads": 12,
50
+ "num_hidden_layers": 12,
51
+ "output_past": true,
52
+ "pad_token_id": 0,
53
+ "position_embedding_type": "absolute",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.33.0.dev0",
56
+ "type_vocab_size": 1,
57
+ "use_cache": true,
58
+ "vocab_size": 32005
59
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdea5801879fcff2313f6441d630a6d02d3d96d074ef95c5c7b8f2761ed4ab83
3
+ size 440233705
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 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "unk_token": "<unk>"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "clean_up_tokenization_spaces": true,
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "__type": "AddedToken",
12
+ "content": "<mask>",
13
+ "lstrip": true,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "model_max_length": 1000000000000000019884624838656,
19
+ "pad_token": "<pad>",
20
+ "sep_token": "</s>",
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "CamembertTokenizer",
23
+ "unk_token": "<unk>"
24
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d335ce313b0277ea3d878ec037a94bb216856166403c8589fbaa1e4ab2b69d2b
3
+ size 4091