cuongpp commited on
Commit
5f2f4b2
1 Parent(s): a991340

Training in progress, epoch 0

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/bartpho-word-base",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "MBartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 768,
12
+ "decoder_attention_heads": 12,
13
+ "decoder_ffn_dim": 3072,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 6,
16
+ "decoder_start_token_id": 2,
17
+ "dropout": 0.1,
18
+ "encoder_attention_heads": 12,
19
+ "encoder_ffn_dim": 3072,
20
+ "encoder_layerdrop": 0.0,
21
+ "encoder_layers": 6,
22
+ "eos_token_id": 2,
23
+ "forced_eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "max_position_embeddings": 1024,
28
+ "model_type": "mbart",
29
+ "num_hidden_layers": 6,
30
+ "pad_token_id": 1,
31
+ "scale_embedding": false,
32
+ "tokenizer_class": "PhobertTokenizer",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.41.2",
35
+ "use_cache": true,
36
+ "vocab_size": 64001
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb4c12d419be7213b082b79ad32824db31fbc0084e6dae35bd13d0827d36f9d
3
+ size 600177236
runs/Jun19_10-48-53_52b5d57605c9/events.out.tfevents.1718794331.52b5d57605c9.337.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9bb226291fcf0a5f446234f88d16d5262d8954d1344c288402ddaddeef7c485
3
+ size 6259
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
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
+ "tokenizer_class": "PhobertTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb6cf4f490f907ad7e497134ce4148d846288c546f2da502b8d1e2bd6bd19c3
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff