update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: tmvar_2e-05_0404_ES6_strict_tok1
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# tmvar_2e-05_0404_ES6_strict_tok1
|
19 |
+
|
20 |
+
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.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0330
|
23 |
+
- Precision: 0.8213
|
24 |
+
- Recall: 0.8629
|
25 |
+
- F1: 0.8416
|
26 |
+
- Accuracy: 0.9916
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 2e-05
|
46 |
+
- train_batch_size: 16
|
47 |
+
- eval_batch_size: 16
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- training_steps: 2000
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
+
| 0.7315 | 0.49 | 25 | 0.2102 | 0.0 | 0.0 | 0.0 | 0.9555 |
|
58 |
+
| 0.1371 | 0.98 | 50 | 0.1021 | 0.0 | 0.0 | 0.0 | 0.9698 |
|
59 |
+
| 0.0836 | 1.47 | 75 | 0.0960 | 0.0 | 0.0 | 0.0 | 0.9725 |
|
60 |
+
| 0.0666 | 1.96 | 100 | 0.0526 | 0.0 | 0.0 | 0.0 | 0.9804 |
|
61 |
+
| 0.0391 | 2.45 | 125 | 0.0521 | 0.7294 | 0.3147 | 0.4397 | 0.9843 |
|
62 |
+
| 0.0252 | 2.94 | 150 | 0.0382 | 0.8630 | 0.6396 | 0.7347 | 0.9899 |
|
63 |
+
| 0.016 | 3.43 | 175 | 0.0452 | 0.6496 | 0.7716 | 0.7053 | 0.9872 |
|
64 |
+
| 0.0145 | 3.92 | 200 | 0.0272 | 0.8730 | 0.8376 | 0.8549 | 0.9923 |
|
65 |
+
| 0.0082 | 4.41 | 225 | 0.0301 | 0.8804 | 0.8223 | 0.8504 | 0.9920 |
|
66 |
+
| 0.0058 | 4.9 | 250 | 0.0330 | 0.8213 | 0.8629 | 0.8416 | 0.9916 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.27.4
|
72 |
+
- Pytorch 2.0.0+cu118
|
73 |
+
- Datasets 2.11.0
|
74 |
+
- Tokenizers 0.13.3
|