Roverandom95 commited on
Commit
6364b16
1 Parent(s): 61e8e32

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "general",
15
+ "1": "crypto",
16
+ "2": "education",
17
+ "3": "finance",
18
+ "4": "fashion",
19
+ "5": "politics",
20
+ "6": "entertainment",
21
+ "7": "show_business",
22
+ "8": "technology",
23
+ "9": "travel"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 600,
27
+ "label2id": {
28
+ "crypto": 1,
29
+ "education": 2,
30
+ "entertainment": 6,
31
+ "fashion": 4,
32
+ "finance": 3,
33
+ "general": 0,
34
+ "politics": 5,
35
+ "show_business": 7,
36
+ "technology": 8,
37
+ "travel": 9
38
+ },
39
+ "layer_norm_eps": 1e-12,
40
+ "max_position_embeddings": 2048,
41
+ "model_type": "bert",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 3,
44
+ "pad_token_id": 0,
45
+ "position_embedding_type": "absolute",
46
+ "problem_type": "single_label_classification",
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.33.1",
49
+ "type_vocab_size": 2,
50
+ "use_cache": true,
51
+ "vocab_size": 83828
52
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cce2e7c2cd5d8007ae8816cdecb89eff39084f66ff351c9399e4eeffbbae1902
3
+ size 116805532
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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "max_length": 512,
8
+ "model_max_length": 2048,
9
+ "never_split": null,
10
+ "pad_to_multiple_of": null,
11
+ "pad_token": "[PAD]",
12
+ "pad_token_type_id": 0,
13
+ "padding_side": "right",
14
+ "sep_token": "[SEP]",
15
+ "stride": 0,
16
+ "strip_accents": null,
17
+ "tokenize_chinese_chars": true,
18
+ "tokenizer_class": "BertTokenizer",
19
+ "truncation_side": "right",
20
+ "truncation_strategy": "longest_first",
21
+ "unk_token": "[UNK]"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65868a487644d2f6a28ddba8704b1b92a5a9f6a61889c0ec03b1a1d4f5ccd7f0
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff