BiggieW commited on
Commit
0087a8a
·
1 Parent(s): e3ea109

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/chinese-roberta-wwm-ext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "\u6559\u80b2",
16
+ "1": "\u91d1\u878d",
17
+ "2": "\u623f",
18
+ "3": "\u65c5\u6e38",
19
+ "4": "\u79d1\u6280",
20
+ "5": "\u4f53\u80b2",
21
+ "6": "\u6e38\u620f",
22
+ "7": "\u6587\u5316",
23
+ "8": "\u8f66",
24
+ "9": "\u6545\u4e8b",
25
+ "10": "\u5a31\u4e50",
26
+ "11": "\u519b\u4e8b",
27
+ "12": "\u519c\u4e1a",
28
+ "13": "\u4e16\u754c",
29
+ "14": "\u80a1\u5e02"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "label2id": {
34
+ "\u4e16\u754c": 13,
35
+ "\u4f53\u80b2": 5,
36
+ "\u519b\u4e8b": 11,
37
+ "\u519c\u4e1a": 12,
38
+ "\u5a31\u4e50": 10,
39
+ "\u623f": 2,
40
+ "\u6545\u4e8b": 9,
41
+ "\u6559\u80b2": 0,
42
+ "\u6587\u5316": 7,
43
+ "\u65c5\u6e38": 3,
44
+ "\u6e38\u620f": 6,
45
+ "\u79d1\u6280": 4,
46
+ "\u80a1\u5e02": 14,
47
+ "\u8f66": 8,
48
+ "\u91d1\u878d": 1
49
+ },
50
+ "layer_norm_eps": 1e-12,
51
+ "max_position_embeddings": 512,
52
+ "model_type": "bert",
53
+ "num_attention_heads": 12,
54
+ "num_hidden_layers": 12,
55
+ "output_past": true,
56
+ "pad_token_id": 0,
57
+ "pooler_fc_size": 768,
58
+ "pooler_num_attention_heads": 12,
59
+ "pooler_num_fc_layers": 3,
60
+ "pooler_size_per_head": 128,
61
+ "pooler_type": "first_token_transform",
62
+ "position_embedding_type": "absolute",
63
+ "problem_type": "single_label_classification",
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.25.1",
66
+ "type_vocab_size": 2,
67
+ "use_cache": true,
68
+ "vocab_size": 21128
69
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:179f254e3a2480a83482ba15798614c69d4e71a851865fa1e9b4486586f9fc32
3
+ size 409186741
runs/Dec25_13-05-01_e8bd451f7dd7/1671973512.6237926/events.out.tfevents.1671973512.e8bd451f7dd7.394.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4691fc35f95778038eed6d8f737a702e09c485404438b9144707afc47629cb
3
+ size 5527
runs/Dec25_13-05-01_e8bd451f7dd7/events.out.tfevents.1671973512.e8bd451f7dd7.394.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf93a3cef0f03c30136cb8d2fa3e6ca5f1fcd49fb73c67f8dd3ad7bdd4a00f4
3
+ size 5196
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "hfl/chinese-roberta-wwm-ext",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--hfl--chinese-roberta-wwm-ext/snapshots/5c58d0b8ec1d9014354d691c538661bf00bfdb44/special_tokens_map.json",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af39676c9de1c3f4470c61c6718ec322714cda2129decb39a532b2b7ed0d3c1
3
+ size 3451
vocab.txt ADDED
The diff for this file is too large to render. See raw diff