ThuanPhong commited on
Commit
a1481b6
1 Parent(s): adbf139

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "VinAI/Phobert-base",
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,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6
33
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_position_embeddings": 258,
36
+ "model_type": "roberta",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
+ "problem_type": "single_label_classification",
42
+ "tokenizer_class": "PhobertTokenizer",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.28.0",
45
+ "type_vocab_size": 1,
46
+ "use_cache": true,
47
+ "vocab_size": 64001
48
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69998dc05c4cddb965feaebac069ffc56dcfb858cf8d5bf09efcbb6a85a1a515
3
+ size 540085941
runs/May23_15-36-50_3f3d5f8b3df2/1684856229.3178058/events.out.tfevents.1684856229.3f3d5f8b3df2.4474.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcebd1a9dd3ba814fc2a657c9efc651445280ebc8573670e99f4159564ed27a6
3
+ size 5907
runs/May23_15-36-50_3f3d5f8b3df2/events.out.tfevents.1684856229.3f3d5f8b3df2.4474.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ae39f83c81b1e63fd09604c52f0f92a6b8ada967918ebfb821f410c6eb0718
3
+ size 4740
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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": "<mask>",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "<pad>",
9
+ "sep_token": "</s>",
10
+ "tokenizer_class": "PhobertTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ba18282d7ff05f4ac58bee9f750b95a7fe0ebd76204bb7fcf27f24f3caf529c
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff