shenbinqian commited on
Commit
84f5cf0
1 Parent(s): 6192527

Training in progress, step 35000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "surrey-nlp/roberta-large-finetuned-abbr",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-AC",
16
+ "2": "I-AC",
17
+ "3": "B-LF",
18
+ "4": "I-LF"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "label2id": {
23
+ "B-AC": 1,
24
+ "B-LF": 3,
25
+ "I-AC": 2,
26
+ "I-LF": 4,
27
+ "O": 0
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "max_position_embeddings": 514,
31
+ "model_type": "roberta",
32
+ "num_attention_heads": 16,
33
+ "num_hidden_layers": 24,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.16.2",
38
+ "type_vocab_size": 1,
39
+ "use_cache": true,
40
+ "vocab_size": 50265
41
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e083daf2f4cb0f2f06348847175c32fd861d031bf446bb8c0d0e0280306fc12
3
+ size 1417424497
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "surrey-nlp/roberta-large-finetuned-abbr", "tokenizer_class": "RobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39cc609b6f3ed2bb3dadc328c5600a63b1b367f126bd7af0de8e4ea06b05244a
3
+ size 3055
vocab.json ADDED
The diff for this file is too large to render. See raw diff