AptaArkana commited on
Commit
7e78e78
1 Parent(s): 0714d57

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,13 +1,12 @@
1
  {
2
- "_name_or_path": "ayameRushia/roberta-base-indonesian-1.5G-sentiment-analysis-smsa",
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": 768,
@@ -23,18 +22,18 @@
23
  "netral": 1,
24
  "positive": 2
25
  },
26
- "layer_norm_eps": 1e-05,
27
- "max_position_embeddings": 514,
28
- "model_type": "roberta",
29
  "num_attention_heads": 12,
30
  "num_hidden_layers": 12,
31
- "pad_token_id": 1,
 
32
  "position_embedding_type": "absolute",
33
  "problem_type": "single_label_classification",
34
  "torch_dtype": "float32",
35
- "total_flos": 1.1223329811709559e+19,
36
  "transformers_version": "4.35.2",
37
- "type_vocab_size": 1,
38
  "use_cache": true,
39
- "vocab_size": 52000
40
  }
 
1
  {
2
+ "_name_or_path": "indolem/indobert-base-uncased",
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
+ "eos_token_ids": 0,
 
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
 
22
  "netral": 1,
23
  "positive": 2
24
  },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
  "num_attention_heads": 12,
29
  "num_hidden_layers": 12,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
  "position_embedding_type": "absolute",
33
  "problem_type": "single_label_classification",
34
  "torch_dtype": "float32",
 
35
  "transformers_version": "4.35.2",
36
+ "type_vocab_size": 2,
37
  "use_cache": true,
38
+ "vocab_size": 31923
39
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6147c5fc2f6bff6ee302ec19b74bb6460237feb649f875cc4aa3865c7e6e2254
3
- size 503945820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:150cb775089f62752be04de517d506b6acb6e58a9c8aabc52fa14fe30499f5d3
3
+ size 442265596
runs/Feb16_07-30-59_0e31e9a0c9e2/events.out.tfevents.1708068660.0e31e9a0c9e2.846.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1a0dba3a642382479ec046c78c9480d4a7d65dc56e41f1aeb0d02497f15071
3
+ size 4536
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<s>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
@@ -10,7 +9,7 @@
10
  "special": true
11
  },
12
  "1": {
13
- "content": "<pad>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
@@ -18,7 +17,7 @@
18
  "special": true
19
  },
20
  "2": {
21
- "content": "</s>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
@@ -26,7 +25,7 @@
26
  "special": true
27
  },
28
  "3": {
29
- "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
@@ -34,26 +33,26 @@
34
  "special": true
35
  },
36
  "4": {
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
- "full_tokenizer_file": null,
51
- "mask_token": "<mask>",
52
  "max_length": 128,
53
  "model_max_length": 1000000000000000019884624838656,
54
- "pad_token": "<pad>",
55
- "sep_token": "</s>",
56
- "tokenizer_class": "RobertaTokenizer",
57
- "trim_offsets": true,
58
- "unk_token": "<unk>"
 
 
59
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "[MASK]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "3": {
28
+ "content": "[CLS]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
33
  "special": true
34
  },
35
  "4": {
36
+ "content": "[SEP]",
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
  "max_length": 128,
50
  "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e4ef060c3c92337cbd19dae6e1eea44fd114e8705845faa38648f1f6f78ac88
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1000ba8c5bb38cf03e0fc64179d8933180dfba0a6abcadc46d06b15177f19dd9
3
  size 4536
vocab.txt ADDED
The diff for this file is too large to render. See raw diff