Ariffiq99 commited on
Commit
7d52cb5
·
verified ·
1 Parent(s): 65749c3

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,28 +1,31 @@
1
  {
2
- "_name_or_path": "FacebookAI/xlm-roberta-base",
3
  "architectures": [
4
- "XLMRobertaForMultipleChoice"
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
  "initializer_range": 0.02,
14
  "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 514,
17
- "model_type": "xlm-roberta",
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
20
- "output_past": true,
21
- "pad_token_id": 1,
 
 
 
 
22
  "position_embedding_type": "absolute",
23
  "torch_dtype": "float32",
24
  "transformers_version": "4.47.1",
25
- "type_vocab_size": 1,
26
  "use_cache": true,
27
- "vocab_size": 250002
28
  }
 
1
  {
2
+ "_name_or_path": "google-bert/bert-base-multilingual-cased",
3
  "architectures": [
4
+ "BertForMultipleChoice"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
8
+ "directionality": "bidi",
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
  "num_attention_heads": 12,
18
  "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
  "position_embedding_type": "absolute",
26
  "torch_dtype": "float32",
27
  "transformers_version": "4.47.1",
28
+ "type_vocab_size": 2,
29
  "use_cache": true,
30
+ "vocab_size": 119547
31
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db77df8bb5c7743605136647816d4f0b1120cf08f3156547c9a73d8ea10c0a37
3
- size 1112201908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136cafef75e31731fc55c516b16e8200632fdbdc4944a7fdea1accbc5fad0e11
3
+ size 711440380
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": false,
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
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
3
- size 17082832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d76a4d25ebe8f217654f1039bd991bfc96e7c2cd36e6d28aff941783ed1e9c8
3
+ size 2919460
tokenizer_config.json CHANGED
@@ -1,55 +1,56 @@
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": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "250001": {
36
- "content": "<mask>",
37
- "lstrip": true,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
44
- "bos_token": "<s>",
45
  "clean_up_tokenization_spaces": false,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
  "extra_special_tokens": {},
49
- "mask_token": "<mask>",
50
  "model_max_length": 512,
51
- "pad_token": "<pad>",
52
- "sep_token": "</s>",
53
- "tokenizer_class": "XLMRobertaTokenizer",
54
- "unk_token": "<unk>"
 
 
55
  }
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
  "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff9781b1044eee4b44c61809e2d59b9f80d00c464bf8242197f08aedd29a4cfd
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6fcae75d7dacf415f27c4d07d7bfe4df0427b89372f55674855abe105dedcc
3
  size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff