anhkiet269 commited on
Commit
1d8ec19
·
1 Parent(s): 38b706e

Training in progress, epoch 2

Browse files
config.json CHANGED
@@ -1,29 +1,26 @@
1
  {
2
- "_name_or_path": "vinai/phobert-large",
3
  "architectures": [
4
- "RobertaForMultipleChoice"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
  "classifier_dropout": null,
9
- "eos_token_id": 2,
10
  "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
13
- "hidden_size": 1024,
14
  "initializer_range": 0.02,
15
- "intermediate_size": 4096,
16
- "layer_norm_eps": 1e-05,
17
- "max_position_embeddings": 258,
18
- "model_type": "roberta",
19
- "num_attention_heads": 16,
20
- "num_hidden_layers": 24,
21
- "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
- "tokenizer_class": "PhobertTokenizer",
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.35.0",
26
- "type_vocab_size": 1,
27
  "use_cache": true,
28
- "vocab_size": 64001
29
  }
 
1
  {
2
+ "_name_or_path": "tbs17/MathBERT-custom",
3
  "architectures": [
4
+ "BertForMultipleChoice"
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
  "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
  "position_embedding_type": "absolute",
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.35.0",
23
+ "type_vocab_size": 2,
24
  "use_cache": true,
25
+ "vocab_size": 30522
26
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95182de06abaee60ec4be106f6f1811635c26cde2450aee6691017ca0f22b867
3
- size 1476705404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c9122746feb204290942c6922a03e430e73e4de4051ea59d68b5777b39b4ba8
3
+ size 437955572
runs/Dec01_12-08-02_79d7975407b3/events.out.tfevents.1701432489.79d7975407b3.47.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7481f0f55946946a3be27e1175d5c9a74df2582360dfd152a6fd88cbeeb70ec5
3
- size 4834
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8df343755d6982d23619d09f0e124f4953b5b76edf4d953c1092c3839d2965c
3
+ size 5628
special_tokens_map.json CHANGED
@@ -1,9 +1,7 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": "<mask>",
6
- "pad_token": "<pad>",
7
- "sep_token": "</s>",
8
- "unk_token": "<unk>"
9
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
7
  }
tokenizer_config.json CHANGED
@@ -1,39 +1,39 @@
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
- "64000": {
36
- "content": "<mask>",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
@@ -41,14 +41,15 @@
41
  "special": true
42
  }
43
  },
44
- "bos_token": "<s>",
45
  "clean_up_tokenization_spaces": true,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
- "mask_token": "<mask>",
49
- "model_max_length": 256,
50
- "pad_token": "<pad>",
51
- "sep_token": "</s>",
52
- "tokenizer_class": "PhobertTokenizer",
53
- "unk_token": "<unk>"
 
 
54
  }
 
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
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
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 sha256:71531f2ae872f4ab7275d7e524b16991a2db3e93cf051c767ce03237f28a8de4
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b28ff2f4a39813d7e0b54a5db3940079c1a8654ad98fd24ec75514b094b1ba
3
  size 4155
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff