nguyenvanvi0812 commited on
Commit
f2d8c88
1 Parent(s): 4ff12fb

Training in progress, epoch 1

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 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-base-v2",
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
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "read_news",
15
+ "1": "breaking_news",
16
+ "2": "user_manual",
17
+ "3": "last_news",
18
+ "4": "play_music",
19
+ "5": "resume_content",
20
+ "6": "max_volume",
21
+ "7": "restart_content",
22
+ "8": "increase_volume",
23
+ "9": "un_mute",
24
+ "10": "default_volume",
25
+ "11": "most_read_news",
26
+ "12": "min_volume",
27
+ "13": "gpt_ai",
28
+ "14": "decrease_volume",
29
+ "15": "next_content",
30
+ "16": "stop_content",
31
+ "17": "pause_content",
32
+ "18": "mute",
33
+ "19": "unknow",
34
+ "20": "pre_content",
35
+ "21": "start_content"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "label2id": {
40
+ "breaking_news": 1,
41
+ "decrease_volume": 14,
42
+ "default_volume": 10,
43
+ "gpt_ai": 13,
44
+ "increase_volume": 8,
45
+ "last_news": 3,
46
+ "max_volume": 6,
47
+ "min_volume": 12,
48
+ "most_read_news": 11,
49
+ "mute": 18,
50
+ "next_content": 15,
51
+ "pause_content": 17,
52
+ "play_music": 4,
53
+ "pre_content": 20,
54
+ "read_news": 0,
55
+ "restart_content": 7,
56
+ "resume_content": 5,
57
+ "start_content": 21,
58
+ "stop_content": 16,
59
+ "un_mute": 9,
60
+ "unknow": 19,
61
+ "user_manual": 2
62
+ },
63
+ "layer_norm_eps": 1e-05,
64
+ "max_position_embeddings": 258,
65
+ "model_type": "roberta",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 12,
68
+ "pad_token_id": 1,
69
+ "position_embedding_type": "absolute",
70
+ "problem_type": "single_label_classification",
71
+ "tokenizer_class": "PhobertTokenizer",
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.36.0",
74
+ "type_vocab_size": 1,
75
+ "use_cache": true,
76
+ "vocab_size": 64001
77
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f424d43259b0428576e91cce98b7411aea9780888ac6f9f1cf144ce0b02fa4c6
3
+ size 540084904
runs/Dec13_15-09-27_5eb01ada6583/events.out.tfevents.1702480169.5eb01ada6583.14733.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc11bb7080d779c50e4a133311a1ac053d436155d602d5f130a33be3c6a988a7
3
+ size 5794
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 sha256:27bccac5d7de2d6cd21f482734042e166f29efb5f9042bd91296a5b74e014e46
3
+ size 4664
vocab.txt ADDED
The diff for this file is too large to render. See raw diff