Sinanmz commited on
Commit
0eb1ce5
1 Parent(s): 5913f64

Training in progress, epoch 9

Browse files
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "dslim/bert-base-NER",
3
- "_num_labels": 9,
4
  "architectures": [
5
- "BertForTokenClassification"
6
  ],
7
  "attention_probs_dropout_prob": 0.1,
8
- "classifier_dropout": null,
 
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
@@ -27,17 +27,14 @@
27
  "profane/obscene": 4,
28
  "threat": 2
29
  },
30
- "layer_norm_eps": 1e-12,
31
- "max_position_embeddings": 512,
32
- "model_type": "bert",
33
  "num_attention_heads": 12,
34
  "num_hidden_layers": 12,
35
- "output_past": true,
36
- "pad_token_id": 0,
37
- "position_embedding_type": "absolute",
38
  "torch_dtype": "float32",
39
  "transformers_version": "4.35.2",
40
- "type_vocab_size": 2,
41
- "use_cache": true,
42
- "vocab_size": 28996
43
  }
 
1
  {
2
+ "_name_or_path": "microsoft/mpnet-base",
 
3
  "architectures": [
4
+ "MPNetForTokenClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
 
27
  "profane/obscene": 4,
28
  "threat": 2
29
  },
30
+ "layer_norm_eps": 1e-05,
31
+ "max_position_embeddings": 514,
32
+ "model_type": "mpnet",
33
  "num_attention_heads": 12,
34
  "num_hidden_layers": 12,
35
+ "pad_token_id": 1,
36
+ "relative_attention_num_buckets": 32,
 
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.35.2",
39
+ "vocab_size": 30527
 
 
40
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:410b85459f57e82f9baa4d05c888a550037f2f67932c645c0a7ec3cf95e6f9ef
3
- size 430920512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399c4714395674e7bab9da9b6854e82afb33a4b28e2cee7d965f453d1af9c781
3
+ size 435624920
runs/Feb06_14-04-10_935f66270e08/events.out.tfevents.1707228251.935f66270e08.190.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0acf8b9c7363aff1131df689ea0f574b9bf011261bde35b4510ffca83b3bd978
3
- size 8889
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864fe0e4a067e0a2c41183b3264825c24077584ea98a5750c2350caae421b807
3
+ size 9361
special_tokens_map.json CHANGED
@@ -1,7 +1,51 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,58 +1,65 @@
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,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
- "do_lower_case": false,
48
- "mask_token": "[MASK]",
49
- "max_len": 512,
50
  "model_max_length": 512,
51
- "never_split": null,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
  "strip_accents": null,
55
  "tokenize_chinese_chars": true,
56
- "tokenizer_class": "BertTokenizer",
57
  "unk_token": "[UNK]"
58
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>",
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>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
+ "content": "<unk>",
29
  "lstrip": false,
30
+ "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "104": {
36
+ "content": "[UNK]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
  }
51
  },
52
+ "bos_token": "<s>",
53
  "clean_up_tokenization_spaces": true,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "mask_token": "<mask>",
 
58
  "model_max_length": 512,
59
+ "pad_token": "<pad>",
60
+ "sep_token": "</s>",
 
61
  "strip_accents": null,
62
  "tokenize_chinese_chars": true,
63
+ "tokenizer_class": "MPNetTokenizer",
64
  "unk_token": "[UNK]"
65
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f315eae2dbf6f7f6a66817d4e22e0c1d8114730658228b10e07ce7fbcf482dd
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c07014679dcf0fa042e547a49225c8c154b79860b582e2b6c3d1ecabff3c83b2
3
  size 4600
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff