AptaArkana commited on
Commit
6896039
1 Parent(s): 88fc14c

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,37 +1,44 @@
1
  {
2
- "_name_or_path": "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "negative",
13
  "1": "netral",
14
  "2": "positive"
15
  },
16
  "initializer_range": 0.02,
 
17
  "label2id": {
18
  "negative": 0,
19
  "netral": 1,
20
  "positive": 2
21
  },
 
22
  "max_position_embeddings": 512,
23
- "max_split_size_mb": 100,
24
- "model_type": "distilbert",
25
- "n_heads": 12,
26
- "n_layers": 6,
27
  "output_past": true,
28
  "pad_token_id": 0,
 
 
 
 
 
 
29
  "problem_type": "single_label_classification",
30
- "qa_dropout": 0.1,
31
- "seq_classif_dropout": 0.2,
32
- "sinusoidal_pos_embds": false,
33
- "tie_weights_": true,
34
  "torch_dtype": "float32",
35
- "transformers_version": "4.37.2",
36
- "vocab_size": 119547
 
 
37
  }
 
1
  {
2
+ "_name_or_path": "naufalihsan/indonesian-sbert-large",
3
+ "_num_labels": 5,
4
  "architectures": [
5
+ "BertForSequenceClassification"
6
  ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
  "id2label": {
14
  "0": "negative",
15
  "1": "netral",
16
  "2": "positive"
17
  },
18
  "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
  "label2id": {
21
  "negative": 0,
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": 16,
29
+ "num_hidden_layers": 24,
 
30
  "output_past": true,
31
  "pad_token_id": 0,
32
+ "pooler_fc_size": 768,
33
+ "pooler_num_attention_heads": 12,
34
+ "pooler_num_fc_layers": 3,
35
+ "pooler_size_per_head": 128,
36
+ "pooler_type": "first_token_transform",
37
+ "position_embedding_type": "absolute",
38
  "problem_type": "single_label_classification",
 
 
 
 
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.35.2",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 30522
44
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d3cf7972da23d24bc6c61ff0a80d81ed459b03c3abf34c7116767bcc49a50e4
3
- size 541320452
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a413d2a8be19be7d7144f9d7b9e6c574691fb3f122beeec3ad9895fc73605a6e
3
+ size 2681258616
runs/Feb23_04-31-13_153b43858746/events.out.tfevents.1708662676.153b43858746.6732.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c794030a25a04b60553aa447ba27486f937a80da6cac1ae265924069ae085350
3
+ size 5046
runs/Feb23_06-12-03_153b43858746/events.out.tfevents.1708668724.153b43858746.6732.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2966d49e910934d283a9bb2c0173db92191a31377a400c65bcd6b5791df5f1
3
+ size 5203
special_tokens_map.json CHANGED
@@ -1,37 +1,7 @@
1
  {
2
- "cls_token": {
3
- "content": "[CLS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "mask_token": {
10
- "content": "[MASK]",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "sep_token": {
24
- "content": "[SEP]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "unk_token": {
31
- "content": "[UNK]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- }
37
  }
 
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
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -44,10 +44,10 @@
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
- "do_lower_case": false,
48
  "mask_token": "[MASK]",
49
  "max_length": 512,
50
- "model_max_length": 512,
51
  "never_split": null,
52
  "pad_to_multiple_of": null,
53
  "pad_token": "[PAD]",
@@ -57,7 +57,7 @@
57
  "stride": 0,
58
  "strip_accents": null,
59
  "tokenize_chinese_chars": true,
60
- "tokenizer_class": "DistilBertTokenizer",
61
  "truncation_side": "right",
62
  "truncation_strategy": "longest_first",
63
  "unk_token": "[UNK]"
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
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": 512,
50
+ "model_max_length": 1000000000000000019884624838656,
51
  "never_split": null,
52
  "pad_to_multiple_of": null,
53
  "pad_token": "[PAD]",
 
57
  "stride": 0,
58
  "strip_accents": null,
59
  "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
  "truncation_side": "right",
62
  "truncation_strategy": "longest_first",
63
  "unk_token": "[UNK]"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11bf066db97bce61d10cca02c8a5961d0917904ef5b22283d3f686b48d3816f6
3
- size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83046e28cccf1abc1c1cae120e6fe8bb463b8086565ed1d7bac02ff1cd2512ab
3
+ size 4536
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff