huggingfleece commited on
Commit
9bd3d9f
1 Parent(s): 55e37eb

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>NOTUSED": 32005
3
+ }
config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
2
- "_name_or_path": "bert-base-cased",
3
  "architectures": [
4
- "BertForTokenClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
@@ -57,16 +58,17 @@
57
  "I-PROC": 4,
58
  "O": 0
59
  },
60
- "layer_norm_eps": 1e-12,
61
- "max_position_embeddings": 512,
62
- "model_type": "bert",
63
  "num_attention_heads": 12,
64
  "num_hidden_layers": 12,
65
- "pad_token_id": 0,
 
66
  "position_embedding_type": "absolute",
67
  "torch_dtype": "float32",
68
  "transformers_version": "4.42.3",
69
- "type_vocab_size": 2,
70
  "use_cache": true,
71
- "vocab_size": 28996
72
  }
 
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,
 
58
  "I-PROC": 4,
59
  "O": 0
60
  },
61
+ "layer_norm_eps": 1e-05,
62
+ "max_position_embeddings": 514,
63
+ "model_type": "camembert",
64
  "num_attention_heads": 12,
65
  "num_hidden_layers": 12,
66
+ "output_past": true,
67
+ "pad_token_id": 1,
68
  "position_embedding_type": "absolute",
69
  "torch_dtype": "float32",
70
  "transformers_version": "4.42.3",
71
+ "type_vocab_size": 1,
72
  "use_cache": true,
73
+ "vocab_size": 32005
74
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25a1b2fd6e335bfd7cf6045ebf930c97feb5bb257b9ddb9aa43ed2d323b7d1cd
3
- size 430966652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e16f577e4106057ed5af1395b51c777f7ee74043e613e98cad6c439b87a5f5f
3
+ size 440213956
runs/Jul04_08-28-42_a6439592a7b2/events.out.tfevents.1720081723.a6439592a7b2.453.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a102fd691bf7f49ad6034041968974e3e6220c92aace3e1c16d90ed735d4f5cb
3
+ size 6139
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 CHANGED
@@ -1,7 +1,20 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,39 +1,63 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
- "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
- "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
- "content": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
@@ -41,15 +65,19 @@
41
  "special": true
42
  }
43
  },
 
 
 
 
 
 
44
  "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": false,
47
- "mask_token": "[MASK]",
48
  "model_max_length": 512,
49
- "pad_token": "[PAD]",
50
- "sep_token": "[SEP]",
51
- "strip_accents": null,
52
- "tokenize_chinese_chars": true,
53
- "tokenizer_class": "BertTokenizer",
54
- "unk_token": "[UNK]"
55
  }
 
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,
 
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
+ "mask_token": "<mask>",
78
  "model_max_length": 512,
79
+ "pad_token": "<pad>",
80
+ "sep_token": "</s>",
81
+ "tokenizer_class": "CamembertTokenizer",
82
+ "unk_token": "<unk>"
 
 
83
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:844d180a2044032df9afa014e0535f38882b0afeac563f37d73f04e1d5d2d3b4
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c5c5b45a5fde37427e19cc375234ddb51ef80678768201fd4690f8a333fbc99
3
  size 5112