ChanBeDu commited on
Commit
9613281
1 Parent(s): ea6e191

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NlpHUST/electra-base-vn",
3
+ "architectures": [
4
+ "ElectraForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NOUN",
14
+ "1": "PUNCT",
15
+ "2": "ADP",
16
+ "3": "NUM",
17
+ "4": "SYM",
18
+ "5": "SCONJ",
19
+ "6": "ADJ",
20
+ "7": "PART",
21
+ "8": "DET",
22
+ "9": "CCONJ",
23
+ "10": "PROPN",
24
+ "11": "PRON",
25
+ "12": "X",
26
+ "13": "_",
27
+ "14": "ADV",
28
+ "15": "INTJ",
29
+ "16": "VERB",
30
+ "17": "AUX"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "ADJ": 6,
36
+ "ADP": 2,
37
+ "ADV": 14,
38
+ "AUX": 17,
39
+ "CCONJ": 9,
40
+ "DET": 8,
41
+ "INTJ": 15,
42
+ "NOUN": 0,
43
+ "NUM": 3,
44
+ "PART": 7,
45
+ "PRON": 11,
46
+ "PROPN": 10,
47
+ "PUNCT": 1,
48
+ "SCONJ": 5,
49
+ "SYM": 4,
50
+ "VERB": 16,
51
+ "X": 12,
52
+ "_": 13
53
+ },
54
+ "layer_norm_eps": 1e-12,
55
+ "max_position_embeddings": 512,
56
+ "model_type": "electra",
57
+ "num_attention_heads": 12,
58
+ "num_hidden_layers": 12,
59
+ "pad_token_id": 0,
60
+ "position_embedding_type": "absolute",
61
+ "summary_activation": "gelu",
62
+ "summary_last_dropout": 0.1,
63
+ "summary_type": "first",
64
+ "summary_use_proj": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.41.2",
67
+ "type_vocab_size": 2,
68
+ "use_cache": true,
69
+ "vocab_size": 62000
70
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bbbebab570a26f90db2669861b211eac28abff911a6d99d90e99ddab2984f5b
3
+ size 532346304
runs/Jun09_05-47-16_ce4f8fed8a06/events.out.tfevents.1717912037.ce4f8fed8a06.193.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38968e598b7be2c3357eda9fc0925c62e1e67e2b1dfdc981d60c84f5fdd455a7
3
+ size 4184
runs/Jun09_05-48-25_ce4f8fed8a06/events.out.tfevents.1717912105.ce4f8fed8a06.193.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95278a29a21752a7e9f28f4bfcf929359d148a90622c97dec32d5c567932d27d
3
+ size 6030
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "ElectraTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234a44e24914987c7e9c985642c7e39e47bb9ca692c4f5f1db8254eea2433f1f
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff