Enyonam commited on
Commit
d7efb01
·
1 Parent(s): a64cea8

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,30 +1,28 @@
1
  {
2
- "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "cell": {},
8
  "classifier_dropout": null,
9
- "emb_size": 312,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
- "hidden_size": 312,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 1200,
15
- "layer_norm_eps": 1e-12,
16
- "max_position_embeddings": 512,
17
- "model_type": "bert",
18
  "num_attention_heads": 12,
19
- "num_hidden_layers": 4,
20
- "pad_token_id": 0,
21
  "position_embedding_type": "absolute",
22
- "pre_trained": "",
23
  "problem_type": "single_label_classification",
24
- "structure": [],
25
  "torch_dtype": "float32",
26
- "transformers_version": "4.34.1",
27
- "type_vocab_size": 2,
28
  "use_cache": true,
29
- "vocab_size": 30522
30
  }
 
1
  {
2
+ "_name_or_path": "roberta-base",
3
  "architectures": [
4
+ "RobertaForSequenceClassification"
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": "roberta",
18
  "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
 
22
  "problem_type": "single_label_classification",
 
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.35.0",
25
+ "type_vocab_size": 1,
26
  "use_cache": true,
27
+ "vocab_size": 50265
28
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18752dde6d10b26ec086389e9909621fafa5b325e7894fc21ff09b6d9d372dec
3
+ size 498612824
runs/Nov02_22-18-36_8737697ea2eb/events.out.tfevents.1698963580.8737697ea2eb.401.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86134f13be7fce1614e1198474246f22c317c4e0a41db634edf1ef9a3fb3e8b
3
+ size 5150
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
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": "<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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,57 +1,57 @@
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_basic_tokenize": true,
47
- "do_lower_case": true,
48
- "mask_token": "[MASK]",
49
- "model_max_length": 1000000000000000019884624838656,
50
- "never_split": null,
51
- "pad_token": "[PAD]",
52
- "sep_token": "[SEP]",
53
- "strip_accents": null,
54
- "tokenize_chinese_chars": true,
55
- "tokenizer_class": "BertTokenizer",
56
- "unk_token": "[UNK]"
57
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "1": {
13
+ "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "2": {
21
+ "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
+ "3": {
29
+ "content": "<unk>",
30
  "lstrip": false,
31
+ "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
  "normalized": false,
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
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
 
 
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7394a527677fd3bac4462986d77d463b8e0bf77b8351c0ab3b9fa35ed1abf2a1
3
- size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c6c68f40b6cace3e8a1917ee8b0349c6caaafb9e18412147901a63b04970699
3
+ size 4600