update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: Variome_2e-05_0404_ES6_strict_tok
|
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 |
+
# Variome_2e-05_0404_ES6_strict_tok
|
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: 0.0707
|
23 |
+
- Precision: 0.5783
|
24 |
+
- Recall: 0.4750
|
25 |
+
- F1: 0.5216
|
26 |
+
- Accuracy: 0.9852
|
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 |
+
| 1.1357 | 0.13 | 25 | 0.1875 | 0.0 | 0.0 | 0.0 | 0.9759 |
|
58 |
+
| 0.1839 | 0.26 | 50 | 0.1827 | 0.0 | 0.0 | 0.0 | 0.9759 |
|
59 |
+
| 0.1925 | 0.39 | 75 | 0.1841 | 0.0 | 0.0 | 0.0 | 0.9759 |
|
60 |
+
| 0.1804 | 0.52 | 100 | 0.1797 | 0.0 | 0.0 | 0.0 | 0.9759 |
|
61 |
+
| 0.1677 | 0.65 | 125 | 0.1727 | 0.0 | 0.0 | 0.0 | 0.9759 |
|
62 |
+
| 0.1486 | 0.79 | 150 | 0.1293 | 0.0 | 0.0 | 0.0 | 0.9759 |
|
63 |
+
| 0.1231 | 0.92 | 175 | 0.1203 | 0.1706 | 0.0758 | 0.1050 | 0.9766 |
|
64 |
+
| 0.1011 | 1.05 | 200 | 0.1162 | 0.1591 | 0.0403 | 0.0643 | 0.9766 |
|
65 |
+
| 0.1206 | 1.18 | 225 | 0.1142 | 0.2467 | 0.1420 | 0.1803 | 0.9770 |
|
66 |
+
| 0.1189 | 1.31 | 250 | 0.1085 | 0.2264 | 0.0921 | 0.1310 | 0.9778 |
|
67 |
+
| 0.1086 | 1.44 | 275 | 0.1015 | 0.25 | 0.1958 | 0.2196 | 0.9790 |
|
68 |
+
| 0.0977 | 1.57 | 300 | 0.0948 | 0.2849 | 0.2505 | 0.2666 | 0.9800 |
|
69 |
+
| 0.0901 | 1.7 | 325 | 0.0944 | 0.2966 | 0.2534 | 0.2733 | 0.9796 |
|
70 |
+
| 0.0888 | 1.83 | 350 | 0.0891 | 0.3162 | 0.2543 | 0.2819 | 0.9811 |
|
71 |
+
| 0.0724 | 1.96 | 375 | 0.0920 | 0.4200 | 0.2495 | 0.3131 | 0.9812 |
|
72 |
+
| 0.0773 | 2.09 | 400 | 0.0850 | 0.4561 | 0.3090 | 0.3684 | 0.9826 |
|
73 |
+
| 0.0679 | 2.23 | 425 | 0.0803 | 0.4373 | 0.3378 | 0.3812 | 0.9825 |
|
74 |
+
| 0.0809 | 2.36 | 450 | 0.0871 | 0.4580 | 0.2562 | 0.3286 | 0.9814 |
|
75 |
+
| 0.0667 | 2.49 | 475 | 0.0769 | 0.4281 | 0.3656 | 0.3944 | 0.9835 |
|
76 |
+
| 0.0731 | 2.62 | 500 | 0.0742 | 0.5111 | 0.3752 | 0.4328 | 0.9841 |
|
77 |
+
| 0.0713 | 2.75 | 525 | 0.0724 | 0.5571 | 0.4165 | 0.4767 | 0.9848 |
|
78 |
+
| 0.063 | 2.88 | 550 | 0.0706 | 0.5687 | 0.4367 | 0.4940 | 0.9849 |
|
79 |
+
| 0.0714 | 3.01 | 575 | 0.0733 | 0.5448 | 0.4319 | 0.4818 | 0.9848 |
|
80 |
+
| 0.0572 | 3.14 | 600 | 0.0707 | 0.5783 | 0.4750 | 0.5216 | 0.9852 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.27.4
|
86 |
+
- Pytorch 2.0.0+cu118
|
87 |
+
- Datasets 2.11.0
|
88 |
+
- Tokenizers 0.13.3
|