beaconva commited on
Commit
1d732bb
1 Parent(s): 105e735

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 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "play_music",
17
+ "3": "last_news",
18
+ "4": "max_volume",
19
+ "5": "mute",
20
+ "6": "story",
21
+ "7": "min_volume",
22
+ "8": "un_mute",
23
+ "9": "gpt_ai",
24
+ "10": "pause_content",
25
+ "11": "restart_content",
26
+ "12": "most_read_news",
27
+ "13": "increase_volume",
28
+ "14": "weather",
29
+ "15": "change_voice",
30
+ "16": "save_news",
31
+ "17": "datetime",
32
+ "18": "shutdown",
33
+ "19": "user_manual",
34
+ "20": "decrease_volume",
35
+ "21": "resume_content",
36
+ "22": "save_music",
37
+ "23": "stop_content"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "label2id": {
42
+ "breaking_news": 1,
43
+ "change_voice": 15,
44
+ "datetime": 17,
45
+ "decrease_volume": 20,
46
+ "gpt_ai": 9,
47
+ "increase_volume": 13,
48
+ "last_news": 3,
49
+ "max_volume": 4,
50
+ "min_volume": 7,
51
+ "most_read_news": 12,
52
+ "mute": 5,
53
+ "pause_content": 10,
54
+ "play_music": 2,
55
+ "read_news": 0,
56
+ "restart_content": 11,
57
+ "resume_content": 21,
58
+ "save_music": 22,
59
+ "save_news": 16,
60
+ "shutdown": 18,
61
+ "stop_content": 23,
62
+ "story": 6,
63
+ "un_mute": 8,
64
+ "user_manual": 19,
65
+ "weather": 14
66
+ },
67
+ "layer_norm_eps": 1e-05,
68
+ "max_position_embeddings": 258,
69
+ "model_type": "roberta",
70
+ "num_attention_heads": 12,
71
+ "num_hidden_layers": 12,
72
+ "pad_token_id": 1,
73
+ "position_embedding_type": "absolute",
74
+ "problem_type": "single_label_classification",
75
+ "tokenizer_class": "PhobertTokenizer",
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.40.1",
78
+ "type_vocab_size": 1,
79
+ "use_cache": true,
80
+ "vocab_size": 64001
81
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f4286792bedd85867b0587e2f2cda086702552cdf15347e254d12a04009993
3
+ size 540091056
runs/Apr26_16-55-22_e1f3acd71db8/events.out.tfevents.1714150523.e1f3acd71db8.4429.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b9ba8d99f289d1938918a82f4654260e2d1fa9800c56610ddbffc180376d959
3
+ size 6171
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 sha256:7254aa3442fa2979dcdd31d96f4837dc422a9a5cd46ce6fb0281753bc3eba22f
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff