pruas commited on
Commit
06a79a9
1 Parent(s): 1cdaf07

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B",
14
+ "2": "I"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B": "1",
20
+ "I": "2",
21
+ "O": "0"
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.9.0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30522
35
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693a9cdf1f39d5be17b784c392dac0f5c731942b5053fb98c6011e128e0097ea
3
+ size 871267045
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689b3c4c7050ce920aea7b502de5e13f778bf760cf016ac3798133489732208a
3
+ size 435659249
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e244fb1edcd3f60e426f913f85f6cd71f7b52d1897f290f8d181b3596855e5a
3
+ size 17563
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ccb6f50dabab86c08404cacb3c0c74b424ea7b4370a1d5fca9f3bb1bdd23a7
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.034447334706783295,
3
+ "best_model_checkpoint": "data/models/disease/final/checkpoint-2370",
4
+ "epoch": 1.0,
5
+ "global_step": 2370,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.21,
12
+ "learning_rate": 7.528130801687764e-05,
13
+ "loss": 0.0918,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.42,
18
+ "learning_rate": 5.5152616033755274e-05,
19
+ "loss": 0.0641,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.63,
24
+ "learning_rate": 3.502392405063291e-05,
25
+ "loss": 0.0584,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.84,
30
+ "learning_rate": 1.4895232067510549e-05,
31
+ "loss": 0.0509,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "eval_accuracy": 1.0,
37
+ "eval_f1": 1.0,
38
+ "eval_loss": 0.034447334706783295,
39
+ "eval_precision": 1.0,
40
+ "eval_recall": 1.0,
41
+ "eval_runtime": 1.5068,
42
+ "eval_samples_per_second": 0.664,
43
+ "eval_steps_per_second": 0.664,
44
+ "step": 2370
45
+ }
46
+ ],
47
+ "max_steps": 2370,
48
+ "num_train_epochs": 1,
49
+ "total_flos": 9904804408756224.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:332e8d47ea509ebfa03bc0470020cec28333b6651682ea558ec1a275d944c3c7
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff