thangvip commited on
Commit
a19e9ff
1 Parent(s): 065898a

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,18 +1,15 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
  "BertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
  "attention_probs_dropout_prob": 0.1,
 
9
  "classifier_dropout": null,
10
- "dim": 768,
11
- "dropout": 0.1,
12
  "hidden_act": "gelu",
13
- "hidden_dim": 3072,
14
  "hidden_dropout_prob": 0.1,
15
- "hidden_size": 768,
16
  "id2label": {
17
  "0": 0,
18
  "1": 1,
@@ -193,7 +190,7 @@
193
  "176": 176
194
  },
195
  "initializer_range": 0.02,
196
- "intermediate_size": 3072,
197
  "label2id": {
198
  "0": 0,
199
  "1": 1,
@@ -373,23 +370,18 @@
373
  "175": 175,
374
  "176": 176
375
  },
376
- "layer_norm_eps": 1e-12,
377
- "max_position_embeddings": 512,
378
  "model_type": "bert",
379
- "n_heads": 12,
380
- "n_layers": 6,
381
- "num_attention_heads": 12,
382
- "num_hidden_layers": 12,
383
- "pad_token_id": 0,
384
  "position_embedding_type": "absolute",
385
  "problem_type": "single_label_classification",
386
- "qa_dropout": 0.1,
387
- "seq_classif_dropout": 0.2,
388
- "sinusoidal_pos_embds": false,
389
- "tie_weights_": true,
390
  "torch_dtype": "float32",
391
  "transformers_version": "4.37.1",
392
- "type_vocab_size": 2,
393
  "use_cache": true,
394
- "vocab_size": 30522
395
  }
 
1
  {
2
+ "_name_or_path": "vietgpt/bert-30M-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_id": 2,
 
10
  "hidden_act": "gelu",
 
11
  "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 512,
13
  "id2label": {
14
  "0": 0,
15
  "1": 1,
 
190
  "176": 176
191
  },
192
  "initializer_range": 0.02,
193
+ "intermediate_size": 1024,
194
  "label2id": {
195
  "0": 0,
196
  "1": 1,
 
370
  "175": 175,
371
  "176": 176
372
  },
373
+ "layer_norm_eps": 1e-05,
374
+ "max_position_embeddings": 514,
375
  "model_type": "bert",
376
+ "num_attention_heads": 4,
377
+ "num_hidden_layers": 4,
378
+ "pad_token_id": 1,
 
 
379
  "position_embedding_type": "absolute",
380
  "problem_type": "single_label_classification",
381
+ "tokenizer_class": "BartphoTokenizer",
 
 
 
382
  "torch_dtype": "float32",
383
  "transformers_version": "4.37.1",
384
+ "type_vocab_size": 1,
385
  "use_cache": true,
386
+ "vocab_size": 50001
387
  }
dict.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c130907e71d640b7522ec8f93123c7c12a43029cc31249c10e930d83c64c157
3
- size 438496948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5f97cdf749d94ea1d5590b1c780f34c602d9ca463a371b1304f4554a09bb35
3
+ size 138527692
runs/Jan26_07-36-30_9533dac6c070/events.out.tfevents.1706254592.9533dac6c070.2896.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54caf2d281bd8cc135aeb1b620380fec697690c67671934d03ff2dd1f0244ddf
3
+ size 10068
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63e0e8f2d912f8ebf14402e66c2afef07b078099b953efb690d18c6c00af23a
3
+ size 1027111
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": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
  }
tokenizer_config.json CHANGED
@@ -1,55 +1,55 @@
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_lower_case": true,
47
- "mask_token": "[MASK]",
48
- "model_max_length": 512,
49
- "pad_token": "[PAD]",
50
- "sep_token": "[SEP]",
51
- "strip_accents": null,
52
- "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
- "unk_token": "[UNK]"
55
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "</s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
+ "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "50000": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
44
+ "bos_token": "<s>",
45
  "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "BartphoTokenizer",
54
+ "unk_token": "<unk>"
 
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa7047f50dbd21ea1978181102ffd71486ba18eb5e48f9bcb474210f31905dda
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f9eccc3448f3efb92df68c6f7f0bdb64758addb2976e0f7dffe8d74f247b4f
3
  size 4728