HueyNemud commited on
Commit
3acf2ed
1 Parent(s): 22846c5

End of training

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</ENTRY>": 32014,
3
+ "<ENTRY>": 32035,
4
+ "<break>": 32036,
5
+ "<hspace-10>": 32030,
6
+ "<hspace-1>": 32038,
7
+ "<hspace-2>": 32020,
8
+ "<hspace-3>": 32009,
9
+ "<hspace-4>": 32021,
10
+ "<hspace-5>": 32015,
11
+ "<hspace-6>": 32026,
12
+ "<hspace-7>": 32012,
13
+ "<hspace-8>": 32010,
14
+ "<hspace-9>": 32023,
15
+ "<lhspace-10>": 32024,
16
+ "<lhspace-1>": 32032,
17
+ "<lhspace-2>": 32025,
18
+ "<lhspace-3>": 32027,
19
+ "<lhspace-4>": 32028,
20
+ "<lhspace-5>": 32016,
21
+ "<lhspace-6>": 32008,
22
+ "<lhspace-7>": 32033,
23
+ "<lhspace-8>": 32007,
24
+ "<lhspace-9>": 32018,
25
+ "<rhspace-10>": 32013,
26
+ "<rhspace-1>": 32019,
27
+ "<rhspace-2>": 32017,
28
+ "<rhspace-3>": 32011,
29
+ "<rhspace-4>": 32006,
30
+ "<rhspace-5>": 32031,
31
+ "<rhspace-6>": 32037,
32
+ "<rhspace-7>": 32022,
33
+ "<rhspace-8>": 32029,
34
+ "<rhspace-9>": 32034,
35
+ "<textline>": 32005
36
+ }
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HueyNemud/das22-10-camembert_pretrained",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "I-LOC",
17
+ "2": "I-PER",
18
+ "3": "I-MISC",
19
+ "4": "I-ORG",
20
+ "5": "I-CARDINAL",
21
+ "6": "I-ACT",
22
+ "7": "I-TITRE",
23
+ "8": "I-FT",
24
+ "9": "O+I-EBEGIN",
25
+ "10": "O+I-EEND",
26
+ "11": "I-LOC+I-EBEGIN",
27
+ "12": "I-LOC+I-EEND",
28
+ "13": "I-PER+I-EBEGIN",
29
+ "14": "I-PER+I-EEND",
30
+ "15": "I-CARDINAL+I-EBEGIN",
31
+ "16": "I-CARDINAL+I-EEND",
32
+ "17": "I-ACT+I-EBEGIN",
33
+ "18": "I-ACT+I-EEND",
34
+ "19": "I-TITRE+I-EBEGIN",
35
+ "20": "I-TITRE+I-EEND",
36
+ "21": "I-FT+I-EBEGIN",
37
+ "22": "I-FT+I-EEND"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "label2id": {
42
+ "I-ACT": 6,
43
+ "I-ACT+I-EBEGIN": 17,
44
+ "I-ACT+I-EEND": 18,
45
+ "I-CARDINAL": 5,
46
+ "I-CARDINAL+I-EBEGIN": 15,
47
+ "I-CARDINAL+I-EEND": 16,
48
+ "I-FT": 8,
49
+ "I-FT+I-EBEGIN": 21,
50
+ "I-FT+I-EEND": 22,
51
+ "I-LOC": 1,
52
+ "I-LOC+I-EBEGIN": 11,
53
+ "I-LOC+I-EEND": 12,
54
+ "I-MISC": 3,
55
+ "I-ORG": 4,
56
+ "I-PER": 2,
57
+ "I-PER+I-EBEGIN": 13,
58
+ "I-PER+I-EEND": 14,
59
+ "I-TITRE": 7,
60
+ "I-TITRE+I-EBEGIN": 19,
61
+ "I-TITRE+I-EEND": 20,
62
+ "O": 0,
63
+ "O+I-EBEGIN": 9,
64
+ "O+I-EEND": 10
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "max_position_embeddings": 514,
68
+ "model_type": "camembert",
69
+ "num_attention_heads": 12,
70
+ "num_hidden_layers": 12,
71
+ "output_past": true,
72
+ "pad_token_id": 1,
73
+ "position_embedding_type": "absolute",
74
+ "torch_dtype": "float32",
75
+ "transformers_version": "4.26.1",
76
+ "type_vocab_size": 1,
77
+ "use_cache": true,
78
+ "vocab_size": 32039
79
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d92ea622af8ef126305b04ea215b9d06712f428afafeed28a120d07a8defd2a
3
+ size 440373357
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<mask>",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "unk_token": "<unk>"
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "__type": "AddedToken",
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "model_max_length": 512,
18
+ "name_or_path": "HueyNemud/das22-10-camembert_pretrained",
19
+ "pad_token": "<pad>",
20
+ "sep_token": "</s>",
21
+ "sp_model_kwargs": {},
22
+ "special_tokens_map_file": "/lrde/home2/jchazalo/.cache/huggingface/transformers/fe0e213c44079a9ee091098f81fff2941484006e9ba3001a9bf1ee9f87537599.cb3ec3a6c1200d181228d8825ae9767572abca54efa1bbb37fd83d721b2ef323",
23
+ "tokenizer_class": "CamembertTokenizer",
24
+ "unk_token": "<unk>"
25
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a14576bea6a553fe82256417731c2de2e917c7fbfda4cbd4e482a033bef6a92
3
+ size 3579