Taewhoo commited on
Commit
07dbe3a
1 Parent(s): a6f3eed

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dmis-lab/biobert-v1.1",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
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": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.33.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 28996
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf455dc2bd35f79bdc7eed17dafe0152ecbb934da27b96823bbfe96c992cbf4
3
+ size 430952617
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85cf5a48c5c561057af50c5a67c7f856f196b5b1bdb67cc0b66eaa8d1010c9f5
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7cdbad5b7cea810fb6c95926e5eaa92b79706877979f018f690a6ec0e4b7eb7
3
+ size 627
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.683363148479428,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.89,
13
+ "learning_rate": 1.403697078115683e-05,
14
+ "loss": 2.5258,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 1.843708872795105,
20
+ "eval_runtime": 56.6033,
21
+ "eval_samples_per_second": 39.485,
22
+ "eval_steps_per_second": 2.473,
23
+ "step": 559
24
+ },
25
+ {
26
+ "epoch": 1.79,
27
+ "learning_rate": 8.073941562313657e-06,
28
+ "loss": 1.7826,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_loss": 1.7421672344207764,
34
+ "eval_runtime": 56.7224,
35
+ "eval_samples_per_second": 39.402,
36
+ "eval_steps_per_second": 2.468,
37
+ "step": 1118
38
+ },
39
+ {
40
+ "epoch": 2.68,
41
+ "learning_rate": 2.110912343470483e-06,
42
+ "loss": 1.6127,
43
+ "step": 1500
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 1677,
48
+ "num_train_epochs": 3,
49
+ "save_steps": 500,
50
+ "total_flos": 4700206060167168.0,
51
+ "trial_name": null,
52
+ "trial_params": null
53
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbafa3ffc00122d2a521dbf3bd6b93cc3f4bb88e7ebfbb3e5ff96ea5393a6b8
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff