vodailuong2510 commited on
Commit
bdddc2d
verified
1 Parent(s): 7e10662

Training in progress, step 32

Browse files
config.json CHANGED
@@ -1,27 +1,24 @@
1
  {
 
2
  "architectures": [
3
- "XLMRobertaForQuestionAnswering"
4
  ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 0,
7
- "classifier_dropout": null,
8
- "eos_token_id": 2,
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-05,
15
- "max_position_embeddings": 514,
16
- "model_type": "xlm-roberta",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
  "output_past": true,
20
- "pad_token_id": 1,
21
- "position_embedding_type": "absolute",
 
 
 
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.51.2",
24
- "type_vocab_size": 1,
25
- "use_cache": true,
26
- "vocab_size": 250002
27
  }
 
1
  {
2
+ "activation": "gelu",
3
  "architectures": [
4
+ "DistilBertForQuestionAnswering"
5
  ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
 
 
 
10
  "initializer_range": 0.02,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "distilbert",
13
+ "n_heads": 12,
14
+ "n_layers": 6,
 
 
15
  "output_past": true,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.51.2",
23
+ "vocab_size": 119547
 
 
24
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:086f979770ad2fd000c5e1cd19a2db620cc849a0f8f613ad2f1d00554f453118
3
- size 1109842416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f6b53ef6a00d7036b957e41caccb46ec31f2022695145730f674d78e3789c5d
3
+ size 538954840
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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
3
- size 17082734
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf1b59b7b11c95f194f51708d918eea378e09d05f84c0e1656dc5180e8117088
3
+ size 2919362
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": "DistilBertTokenizer",
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:eb663698b6d5d62fddd64dab39aad8278aa0265d9b10e6420695ad37ff2deb82
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc4800e0abcb6865dcdb6cef016efdf2c68508139f56208fb6e40a335557249
3
  size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff