andrtest commited on
Commit
6e2788b
1 Parent(s): 09cbba7

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,42 +1,48 @@
1
  {
2
- "_name_or_path": "ukr-models/xlm-roberta-base-uk",
3
  "architectures": [
4
- "XLMRobertaForTokenClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
  "classifier_dropout": null,
9
- "eos_token_id": 2,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
  "0": "O",
15
- "1": "B-ACT",
16
- "2": "I-ACT",
17
  "3": "B-ORG",
18
- "4": "I-ORG"
 
 
 
 
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
- "B-ACT": 1,
 
24
  "B-ORG": 3,
25
- "I-ACT": 2,
 
 
26
  "I-ORG": 4,
 
27
  "O": 0
28
  },
29
- "layer_norm_eps": 1e-05,
30
- "max_position_embeddings": 514,
31
- "model_type": "xlm-roberta",
32
  "num_attention_heads": 12,
33
  "num_hidden_layers": 12,
34
- "output_past": true,
35
- "pad_token_id": 1,
36
  "position_embedding_type": "absolute",
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.41.2",
39
- "type_vocab_size": 1,
40
  "use_cache": true,
41
- "vocab_size": 31274
42
  }
 
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,
12
  "id2label": {
13
  "0": "O",
14
+ "1": "B-PER",
15
+ "2": "I-PER",
16
  "3": "B-ORG",
17
+ "4": "I-ORG",
18
+ "5": "B-LOC",
19
+ "6": "I-LOC",
20
+ "7": "B-MISC",
21
+ "8": "I-MISC"
22
  },
23
  "initializer_range": 0.02,
24
  "intermediate_size": 3072,
25
  "label2id": {
26
+ "B-LOC": 5,
27
+ "B-MISC": 7,
28
  "B-ORG": 3,
29
+ "B-PER": 1,
30
+ "I-LOC": 6,
31
+ "I-MISC": 8,
32
  "I-ORG": 4,
33
+ "I-PER": 2,
34
  "O": 0
35
  },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
  "num_attention_heads": 12,
40
  "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
 
42
  "position_embedding_type": "absolute",
43
  "torch_dtype": "float32",
44
  "transformers_version": "4.41.2",
45
+ "type_vocab_size": 2,
46
  "use_cache": true,
47
+ "vocab_size": 28996
48
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0027996fa74605cc2474327947736cde06148b95d5459648a621a78fc2afbeb0
3
- size 437919108
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:417c69d9303617f17e0950e03054af2a24a9647535ea1d0c28cb7f7a03dfd80a
3
+ size 430929740
runs/Jun10_11-50-03_a8141e4a0250/events.out.tfevents.1718020257.a8141e4a0250.305.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7d420ce9264b3cb935f3657c77633d314f80d6ab467899f25345986f06124a
3
+ size 5608
special_tokens_map.json CHANGED
@@ -1,15 +1,7 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
15
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,57 +1,55 @@
1
  {
2
- "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<s>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "1": {
13
- "content": "<pad>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
- "2": {
21
- "content": "</s>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
- "3": {
29
- "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "31273": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": true,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
45
- "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "extra_ids": 0,
50
- "mask_token": "<mask>",
51
- "model_max_length": 1000000000000000019884624838656,
52
- "pad_token": "<pad>",
53
- "sep_token": "</s>",
54
- "sp_model_kwargs": {},
55
- "tokenizer_class": "XLMRobertaTokenizer",
56
- "unk_token": "<unk>"
57
  }
 
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_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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:450de237fb3f0702eabddd6da2e1955911f12d72b85a847dad701b9d1c538941
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23d9288be53dc34e220f6a3638b099ef9f2f32ce53acbc2eb8752b3b9bd6c73e
3
  size 5112