BATCH_SIZE=8
Browse filesLEARNING_RATE=5e-05
MAX_LENGTH=512
FOLD=0
- .gitignore +1 -0
- README.md +76 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- runs/Sep12_13-57-14_f78a04431978/1631455039.6600327/events.out.tfevents.1631455039.f78a04431978.87.1 +3 -0
- runs/Sep12_13-57-14_f78a04431978/events.out.tfevents.1631455039.f78a04431978.87.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- null
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: biobert-base-cased-v1.1-finetuned-pubmedqa
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Text Classification
|
13 |
+
type: text-classification
|
14 |
+
metrics:
|
15 |
+
- name: Accuracy
|
16 |
+
type: accuracy
|
17 |
+
value: 0.46
|
18 |
+
---
|
19 |
+
|
20 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
21 |
+
should probably proofread and complete it, then remove this comment. -->
|
22 |
+
|
23 |
+
# biobert-base-cased-v1.1-finetuned-pubmedqa
|
24 |
+
|
25 |
+
This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.1](https://huggingface.co/dmis-lab/biobert-base-cased-v1.1) on the None dataset.
|
26 |
+
It achieves the following results on the evaluation set:
|
27 |
+
- Loss: 2.8824
|
28 |
+
- Accuracy: 0.46
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 5e-05
|
48 |
+
- train_batch_size: 8
|
49 |
+
- eval_batch_size: 8
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 10
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
59 |
+
| No log | 1.0 | 57 | 0.9643 | 0.54 |
|
60 |
+
| No log | 2.0 | 114 | 0.9745 | 0.54 |
|
61 |
+
| No log | 3.0 | 171 | 0.9266 | 0.54 |
|
62 |
+
| No log | 4.0 | 228 | 1.2575 | 0.58 |
|
63 |
+
| No log | 5.0 | 285 | 1.7315 | 0.54 |
|
64 |
+
| No log | 6.0 | 342 | 2.3958 | 0.54 |
|
65 |
+
| No log | 7.0 | 399 | 2.2061 | 0.6 |
|
66 |
+
| No log | 8.0 | 456 | 2.5503 | 0.52 |
|
67 |
+
| 0.462 | 9.0 | 513 | 2.8652 | 0.46 |
|
68 |
+
| 0.462 | 10.0 | 570 | 2.8824 | 0.46 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.10.2
|
74 |
+
- Pytorch 1.9.0+cu102
|
75 |
+
- Datasets 1.11.0
|
76 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dmis-lab/biobert-base-cased-v1.1",
|
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": 28996
|
37 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:864c2be915dc73fbacb98cc7183d2c85d7e3e38d4599fdde362f01e08c9cf257
|
3 |
+
size 433334445
|
runs/Sep12_13-57-14_f78a04431978/1631455039.6600327/events.out.tfevents.1631455039.f78a04431978.87.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6f553cc62ff7d9c6360c78b11f7bb2be8547d86a3b9604fc1918751db50d8c9
|
3 |
+
size 4219
|
runs/Sep12_13-57-14_f78a04431978/events.out.tfevents.1631455039.f78a04431978.87.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eff1975662f89204713cfab7ec3767ea5f08da2189df3831da4e7db635df274
|
3 |
+
size 6821
|
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": "dmis-lab/biobert-base-cased-v1.1", "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 sha256:2dd3802ee2bc8de1c4a3c6fbf9df710e5cb087837aeae85cbd35bed809cd1fff
|
3 |
+
size 2671
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|