dafqi commited on
Commit
1680cce
1 Parent(s): 6ea7e9d

Training in progress, step 940

Browse files
config.json CHANGED
@@ -1,36 +1,39 @@
1
  {
2
- "_name_or_path": "cahya/distilbert-base-indonesian",
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": "LABEL_0",
13
  "1": "LABEL_1",
14
  "2": "LABEL_2"
15
  },
16
  "initializer_range": 0.02,
 
17
  "label2id": {
18
  "LABEL_0": 0,
19
  "LABEL_1": 1,
20
  "LABEL_2": 2
21
  },
 
22
  "max_position_embeddings": 512,
23
- "model_type": "distilbert",
24
- "n_heads": 12,
25
- "n_layers": 6,
26
- "output_hidden_states": true,
27
  "pad_token_id": 0,
 
28
  "problem_type": "single_label_classification",
29
- "qa_dropout": 0.1,
30
- "seq_classif_dropout": 0.2,
31
- "sinusoidal_pos_embds": true,
32
- "tie_weights_": true,
33
  "torch_dtype": "float32",
34
  "transformers_version": "4.41.2",
35
- "vocab_size": 32000
 
 
36
  }
 
1
  {
2
+ "_name_or_path": "ayameRushia/indobert-base-uncased-finetuned-indonlu-smsa",
 
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,
13
  "id2label": {
14
  "0": "LABEL_0",
15
  "1": "LABEL_1",
16
  "2": "LABEL_2"
17
  },
18
  "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
  "label2id": {
21
  "LABEL_0": 0,
22
  "LABEL_1": 1,
23
  "LABEL_2": 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": "4.41.2",
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 sha256:12c741f6548ff4d4f7cb08bca7cc1cbfe3a026e226b0055f9dc425d133bb89a7
3
- size 272376060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e80e6fbb317833d77826e5b45dca0fc2aa975ef7634e8d0ae02ac1a74176e67
3
+ size 442265596
runs/Jul03_16-05-05_7058a6f9e19a/events.out.tfevents.1720023038.7058a6f9e19a.34.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51b8a6abfc6c1f6bdd0949a98195fadfa87bebfe639a7989e26f45fa1f2e75d0
3
+ size 406
runs/Jul03_16-14-58_7058a6f9e19a/events.out.tfevents.1720023300.7058a6f9e19a.34.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31443d7f7caa599a7f1dddfd1308002264424c352163e4d45e11d2314248c831
3
+ size 17386
runs/Jul03_16-16-12_7058a6f9e19a/events.out.tfevents.1720023374.7058a6f9e19a.34.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7bac9838aedcc7ef72d68e44d877316102146d0d1f3b43b7059a77fcb0a430a
3
+ size 24755
runs/Jul03_16-16-48_7058a6f9e19a/events.out.tfevents.1720023411.7058a6f9e19a.34.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a1e0a24b3b957c007988bfc51e22d3cea743bcc07d999b22f1ea9459ae958c
3
+ size 106035
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
  }
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": "[UNK]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "[SEP]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "[PAD]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -33,7 +33,7 @@
33
  "special": true
34
  },
35
  "4": {
36
- "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
@@ -45,7 +45,6 @@
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
- "full_tokenizer_file": null,
49
  "mask_token": "[MASK]",
50
  "model_max_length": 1000000000000000019884624838656,
51
  "never_split": null,
@@ -53,6 +52,6 @@
53
  "sep_token": "[SEP]",
54
  "strip_accents": null,
55
  "tokenize_chinese_chars": true,
56
- "tokenizer_class": "DistilBertTokenizer",
57
  "unk_token": "[UNK]"
58
  }
 
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,
 
33
  "special": true
34
  },
35
  "4": {
36
+ "content": "[SEP]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
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,
 
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
  "unk_token": "[UNK]"
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:742a725cd9f1cd3413129a27de4ddc52c11113d3f829e61ec5bb7d01c34aba6b
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4d309e86e8e841c392bec9aabfe9d29a67ebf602cd751c52848c5d2ad6e28b
3
  size 5112
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff