pruas commited on
Commit
a36400b
1 Parent(s): 02c1874

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:bbb485a6579f5db32427bc6fd7f142e558859132b6aa8fbbdd95ffddeca84dab
3
+ size 871267045
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b656312521d69b8a006dc0094343d54c401a35909edd7ca43a4a4a0ec1bd71c6
3
+ size 435659249
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdedc1d574e8fabf4db555ce5a0ba3b08f56163798433ea90bd35b3e49fc6e36
3
+ size 17563
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016e1255ae87f86ba423afc33cb7c20bb77df9d205269949849a26d18d1f1686
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 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.09137263894081116,
3
+ "best_model_checkpoint": "data/models/gene/final/checkpoint-11915",
4
+ "epoch": 1.0,
5
+ "global_step": 11915,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 9.082182123373897e-05,
13
+ "loss": 0.1639,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 8.684364246747798e-05,
19
+ "loss": 0.1393,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.13,
24
+ "learning_rate": 8.286546370121695e-05,
25
+ "loss": 0.1309,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.17,
30
+ "learning_rate": 7.888728493495594e-05,
31
+ "loss": 0.1286,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.21,
36
+ "learning_rate": 7.490910616869493e-05,
37
+ "loss": 0.1222,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.25,
42
+ "learning_rate": 7.093092740243391e-05,
43
+ "loss": 0.1202,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.29,
48
+ "learning_rate": 6.695274863617289e-05,
49
+ "loss": 0.1166,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.34,
54
+ "learning_rate": 6.297456986991188e-05,
55
+ "loss": 0.1164,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.38,
60
+ "learning_rate": 5.8996391103650865e-05,
61
+ "loss": 0.1099,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.42,
66
+ "learning_rate": 5.501821233738984e-05,
67
+ "loss": 0.1101,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.46,
72
+ "learning_rate": 5.1040033571128834e-05,
73
+ "loss": 0.1096,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.5,
78
+ "learning_rate": 4.7061854804867815e-05,
79
+ "loss": 0.1088,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.55,
84
+ "learning_rate": 4.3083676038606796e-05,
85
+ "loss": 0.1055,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.59,
90
+ "learning_rate": 3.9105497272345784e-05,
91
+ "loss": 0.1027,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.63,
96
+ "learning_rate": 3.512731850608477e-05,
97
+ "loss": 0.0961,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.67,
102
+ "learning_rate": 3.114913973982375e-05,
103
+ "loss": 0.1026,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.71,
108
+ "learning_rate": 2.7170960973562734e-05,
109
+ "loss": 0.1005,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.76,
114
+ "learning_rate": 2.3192782207301722e-05,
115
+ "loss": 0.1002,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.8,
120
+ "learning_rate": 1.9214603441040703e-05,
121
+ "loss": 0.1008,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.84,
126
+ "learning_rate": 1.523642467477969e-05,
127
+ "loss": 0.0947,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.88,
132
+ "learning_rate": 1.1258245908518674e-05,
133
+ "loss": 0.0935,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.92,
138
+ "learning_rate": 7.2800671422576585e-06,
139
+ "loss": 0.0961,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.97,
144
+ "learning_rate": 3.301888375996643e-06,
145
+ "loss": 0.0926,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.0,
150
+ "eval_accuracy": 0.9433962264150944,
151
+ "eval_f1": 0.6666666666666666,
152
+ "eval_loss": 0.09137263894081116,
153
+ "eval_precision": 0.5,
154
+ "eval_recall": 1.0,
155
+ "eval_runtime": 1.5459,
156
+ "eval_samples_per_second": 1.294,
157
+ "eval_steps_per_second": 0.647,
158
+ "step": 11915
159
+ }
160
+ ],
161
+ "max_steps": 11915,
162
+ "num_train_epochs": 1,
163
+ "total_flos": 4.981092847655731e+16,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e40086fb494d27319fad58db81cad2dbd1c40bc0f4dbabb543a1ce4e5aa4339
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff