shed-e commited on
Commit
9308d03
1 Parent(s): 3c6d6ee

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/rbt6",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "max_position_embeddings": 512,
35
+ "model_type": "bert",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 6,
38
+ "pad_token_id": 0,
39
+ "pooler_fc_size": 768,
40
+ "pooler_num_attention_heads": 12,
41
+ "pooler_num_fc_layers": 3,
42
+ "pooler_size_per_head": 128,
43
+ "pooler_type": "first_token_transform",
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.23.1",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 21128
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f702f634940948820cb04833308057cb08332f6353d81598e5c46b92823272c0
3
+ size 236658801
runs/Oct13_09-49-18_60669e6b686e/1665654574.0873575/events.out.tfevents.1665654574.60669e6b686e.1613.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f252959226f6638085015f7158c499ddfadef79502e1847344443af9b21c97a
3
+ size 5466
runs/Oct13_09-49-18_60669e6b686e/events.out.tfevents.1665654574.60669e6b686e.1613.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a71cc334480ca6bbe363d09d2fd781350d1480b481454397adf91993a0fee78c
3
+ size 4808
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "name_or_path": "hfl/rbt6",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--hfl--rbt6/snapshots/460e5cea82f393f75495db07da8055a957b53a2c/special_tokens_map.json",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9017c21fc2172360f5da303607ef2ed30a82235b645306f5d89fb5aefc1732
3
+ size 3375
vocab.txt ADDED
The diff for this file is too large to render. See raw diff