blizrys commited on
Commit
6749469
1 Parent(s): 37d9a0e
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - null
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext-finetuned-pubmedqa
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ metrics:
16
+ - name: Accuracy
17
+ type: accuracy
18
+ value: 0.624
19
+ ---
20
+
21
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
22
+ should probably proofread and complete it, then remove this comment. -->
23
+
24
+ # BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext-finetuned-pubmedqa
25
+
26
+ This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset.
27
+ It achieves the following results on the evaluation set:
28
+ - Loss: 2.2547
29
+ - Accuracy: 0.624
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 5e-05
49
+ - train_batch_size: 8
50
+ - eval_batch_size: 8
51
+ - seed: 42
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - num_epochs: 10
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
60
+ | No log | 1.0 | 57 | 0.9716 | 0.52 |
61
+ | No log | 2.0 | 114 | 1.0295 | 0.54 |
62
+ | No log | 3.0 | 171 | 1.0311 | 0.54 |
63
+ | No log | 4.0 | 228 | 1.7516 | 0.44 |
64
+ | No log | 5.0 | 285 | 1.9604 | 0.54 |
65
+ | No log | 6.0 | 342 | 2.5517 | 0.48 |
66
+ | No log | 7.0 | 399 | 2.3635 | 0.62 |
67
+ | No log | 8.0 | 456 | 2.7461 | 0.52 |
68
+ | 0.4018 | 9.0 | 513 | 2.8469 | 0.5 |
69
+ | 0.4018 | 10.0 | 570 | 2.8675 | 0.52 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.10.2
75
+ - Pytorch 1.9.0+cu102
76
+ - Datasets 1.11.0
77
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.10.2",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 30522
37
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6b0add55e48f43cbe874ceb84765cfcc6eae8066da58239a4458c08a4bedce
3
+ size 438022317
runs/Sep12_04-41-50_b328a471c23e/1631421723.4454556/events.out.tfevents.1631421723.b328a471c23e.650.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f7267d1722df48af0fdc58aa38e17111f9447632e5a1817210c5783c5616d2
3
+ size 4247
runs/Sep12_04-41-50_b328a471c23e/events.out.tfevents.1631421723.b328a471c23e.650.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a10e6cff6df4e0a7e87640f93105747d4b7ec4e9e008d122bbf668d5ed2a3e73
3
+ size 6879
runs/Sep12_04-41-50_b328a471c23e/events.out.tfevents.1631422231.b328a471c23e.650.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6c4db8120f97422cc77bb385ef3242a9590ddfce2b799b75cc37de5bbc02d7
3
+ size 686
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-fulltext", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43284eae8d0b2e836d6d52b185c3dae9d72d21ff0f0807d934afb91201c2b97b
3
+ size 2735
vocab.txt ADDED
The diff for this file is too large to render. See raw diff