daijin219 commited on
Commit
291f0f1
1 Parent(s): 4238856

Training for 10 epoches

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/biogpt",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2ForTokenClassification"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "attn_pdrop": 0.1,
10
+ "bos_token_id": 0,
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-Disease",
18
+ "2": "I-Disease"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "label2id": {
23
+ "B-Disease": 1,
24
+ "I-Disease": 2,
25
+ "O": 0
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "layer_norm_epsilon": 1e-05,
29
+ "layerdrop": 0.0,
30
+ "model_type": "gpt2",
31
+ "n_embd": 1024,
32
+ "n_head": 16,
33
+ "n_inner": null,
34
+ "n_layer": 24,
35
+ "n_positions": 1024,
36
+ "pad_token_id": 1,
37
+ "reorder_and_upcast_attn": false,
38
+ "resid_pdrop": 0.1,
39
+ "scale_attn_by_inverse_layer_idx": false,
40
+ "scale_attn_weights": true,
41
+ "scale_embedding": true,
42
+ "summary_activation": null,
43
+ "summary_first_dropout": 0.1,
44
+ "summary_proj_to_labels": true,
45
+ "summary_type": "cls_index",
46
+ "summary_use_proj": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.28.1",
49
+ "use_cache": true,
50
+ "vocab_size": 42384
51
+ }
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:e73cdb9678191e80ad02d86447f2e305c0e68cb6f6b5f437c7c899a712c237b3
3
+ size 1412334373
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "sep_token": "</s>",
6
+ "unk_token": "<unk>"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1024,
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "tokenizer_class": "BioGptTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ea65bc8433e5b959ce9efd8a8426c5a334ce78ddd7d040fb002c885f90fb0c
3
+ size 3579
vocab.json ADDED
The diff for this file is too large to render. See raw diff