Junhoee commited on
Commit
5fb1c52
·
verified ·
1 Parent(s): 5137873

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,18 +1,16 @@
1
  {
2
- "_name_or_path": "monologg/kobigbird-bert-base",
3
  "architectures": [
4
- "BigBirdForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "attention_type": "block_sparse",
8
- "block_size": 64,
9
- "bos_token_id": 5,
10
  "classifier_dropout": null,
11
- "eos_token_id": 6,
12
  "gradient_checkpointing": false,
13
- "hidden_act": "gelu_new",
14
  "hidden_dropout_prob": 0.1,
15
- "hidden_size": 768,
16
  "id2label": {
17
  "0": "LABEL_0",
18
  "1": "LABEL_1",
@@ -32,7 +30,7 @@
32
  "15": "LABEL_15"
33
  },
34
  "initializer_range": 0.02,
35
- "intermediate_size": 3072,
36
  "label2id": {
37
  "LABEL_0": 0,
38
  "LABEL_1": 1,
@@ -51,22 +49,18 @@
51
  "LABEL_8": 8,
52
  "LABEL_9": 9
53
  },
54
- "layer_norm_eps": 1e-12,
55
- "max_position_embeddings": 4096,
56
- "model_type": "big_bird",
57
- "num_attention_heads": 12,
58
- "num_hidden_layers": 12,
59
- "num_random_blocks": 3,
60
- "pad_token_id": 0,
61
  "position_embedding_type": "absolute",
62
  "problem_type": "single_label_classification",
63
- "rescale_embeddings": false,
64
- "sep_token_id": 3,
65
  "tokenizer_class": "BertTokenizer",
66
  "torch_dtype": "float32",
67
  "transformers_version": "4.44.2",
68
- "type_vocab_size": 2,
69
- "use_bias": true,
70
  "use_cache": true,
71
- "vocab_size": 32500
72
  }
 
1
  {
2
+ "_name_or_path": "klue/roberta-large",
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
  "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
  "id2label": {
15
  "0": "LABEL_0",
16
  "1": "LABEL_1",
 
30
  "15": "LABEL_15"
31
  },
32
  "initializer_range": 0.02,
33
+ "intermediate_size": 4096,
34
  "label2id": {
35
  "LABEL_0": 0,
36
  "LABEL_1": 1,
 
49
  "LABEL_8": 8,
50
  "LABEL_9": 9
51
  },
52
+ "layer_norm_eps": 1e-05,
53
+ "max_position_embeddings": 514,
54
+ "model_type": "roberta",
55
+ "num_attention_heads": 16,
56
+ "num_hidden_layers": 24,
57
+ "pad_token_id": 1,
 
58
  "position_embedding_type": "absolute",
59
  "problem_type": "single_label_classification",
 
 
60
  "tokenizer_class": "BertTokenizer",
61
  "torch_dtype": "float32",
62
  "transformers_version": "4.44.2",
63
+ "type_vocab_size": 1,
 
64
  "use_cache": true,
65
+ "vocab_size": 32000
66
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7636615eb04a68a479e6af682e903731297d10780ad65e5e5014cfdbe5895c
3
- size 457450752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b00d7e20e0fa59cab7fa3df1326eef63e351dad6342e17072853bea7e31d0dd
3
+ size 1346739320
special_tokens_map.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "bos_token": {
3
- "content": "<s>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
@@ -14,7 +14,7 @@
14
  "single_word": false
15
  },
16
  "eos_token": {
17
- "content": "</s>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
 
1
  {
2
  "bos_token": {
3
+ "content": "[CLS]",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
 
14
  "single_word": false
15
  },
16
  "eos_token": {
17
+ "content": "[SEP]",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,7 +25,7 @@
25
  "special": true
26
  },
27
  "3": {
28
- "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
@@ -39,32 +39,16 @@
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
- },
43
- "5": {
44
- "content": "<s>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "6": {
52
- "content": "</s>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
  }
59
  },
60
- "bos_token": "<s>",
61
  "clean_up_tokenization_spaces": true,
62
  "cls_token": "[CLS]",
63
  "do_basic_tokenize": true,
64
  "do_lower_case": false,
65
- "eos_token": "</s>",
66
  "mask_token": "[MASK]",
67
- "model_max_length": 4096,
68
  "never_split": null,
69
  "pad_token": "[PAD]",
70
  "sep_token": "[SEP]",
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[CLS]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "[PAD]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "[SEP]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "3": {
28
+ "content": "[UNK]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
+ "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
  "do_basic_tokenize": true,
48
  "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
  "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
  "never_split": null,
53
  "pad_token": "[PAD]",
54
  "sep_token": "[SEP]",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe6dada52a7c01b019bdc28c2a8eb67611695982af2e49d756198b4176e501a8
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7cb1b9b57368fd720e08c31c2cd20700666c1352107b4f7e360b4554b202b0
3
  size 5176
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff