thusken commited on
Commit
007ce17
1 Parent(s): 78cefb9

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NbAiLab/nb-bert-large",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "need_divert",
14
+ "1": "need_educate",
15
+ "2": "need_inspire",
16
+ "3": "need_perspective",
17
+ "4": "need_trend",
18
+ "5": "need_update"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "label2id": {
23
+ "need_divert": "0",
24
+ "need_educate": "1",
25
+ "need_inspire": "2",
26
+ "need_perspective": "3",
27
+ "need_trend": "4",
28
+ "need_update": "5"
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 16,
34
+ "num_hidden_layers": 24,
35
+ "pad_token_id": 0,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.17.0",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 50000
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6e4f0ccb47d73198754ff3059c5fc192f979cf49e7804684dcd25b8fc0effe7
3
+ size 1420537581
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "special_tokens_map_file": null, "name_or_path": "NbAiLab/nb-bert-large", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f2ad9cbd8f5fc0f32a24652165bb4c99137ec14dc75e10fabe7470da95b7f4
3
+ size 3055
vocab.txt ADDED
The diff for this file is too large to render. See raw diff