update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_ES12
|
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_ES12
|
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: 0.0173
|
23 |
+
- Precision: 0.8446
|
24 |
+
- Recall: 0.8811
|
25 |
+
- F1: 0.8624
|
26 |
+
- Accuracy: 0.9969
|
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: 1000
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
+
| 0.5018 | 1.47 | 25 | 0.1002 | 0.0 | 0.0 | 0.0 | 0.9843 |
|
58 |
+
| 0.0852 | 2.94 | 50 | 0.0509 | 0.9286 | 0.0703 | 0.1307 | 0.9852 |
|
59 |
+
| 0.0373 | 4.41 | 75 | 0.0283 | 0.5485 | 0.6108 | 0.5780 | 0.9918 |
|
60 |
+
| 0.0256 | 5.88 | 100 | 0.0204 | 0.6429 | 0.7297 | 0.6835 | 0.9938 |
|
61 |
+
| 0.0123 | 7.35 | 125 | 0.0188 | 0.8063 | 0.8324 | 0.8191 | 0.9956 |
|
62 |
+
| 0.008 | 8.82 | 150 | 0.0171 | 0.7979 | 0.8324 | 0.8148 | 0.9958 |
|
63 |
+
| 0.0047 | 10.29 | 175 | 0.0158 | 0.8010 | 0.8919 | 0.8440 | 0.9962 |
|
64 |
+
| 0.0037 | 11.76 | 200 | 0.0171 | 0.8511 | 0.8649 | 0.8579 | 0.9964 |
|
65 |
+
| 0.0025 | 13.24 | 225 | 0.0184 | 0.8368 | 0.8595 | 0.848 | 0.9962 |
|
66 |
+
| 0.002 | 14.71 | 250 | 0.0180 | 0.8223 | 0.8757 | 0.8482 | 0.9961 |
|
67 |
+
| 0.0018 | 16.18 | 275 | 0.0176 | 0.8571 | 0.8757 | 0.8663 | 0.9966 |
|
68 |
+
| 0.0014 | 17.65 | 300 | 0.0170 | 0.8402 | 0.8811 | 0.8602 | 0.9968 |
|
69 |
+
| 0.0011 | 19.12 | 325 | 0.0180 | 0.8438 | 0.8757 | 0.8594 | 0.9968 |
|
70 |
+
| 0.001 | 20.59 | 350 | 0.0197 | 0.8482 | 0.8757 | 0.8617 | 0.9968 |
|
71 |
+
| 0.001 | 22.06 | 375 | 0.0161 | 0.8402 | 0.8811 | 0.8602 | 0.9969 |
|
72 |
+
| 0.0009 | 23.53 | 400 | 0.0161 | 0.8316 | 0.8811 | 0.8556 | 0.9968 |
|
73 |
+
| 0.0008 | 25.0 | 425 | 0.0191 | 0.8663 | 0.8757 | 0.8710 | 0.9969 |
|
74 |
+
| 0.0009 | 26.47 | 450 | 0.0155 | 0.8639 | 0.8919 | 0.8777 | 0.9972 |
|
75 |
+
| 0.0008 | 27.94 | 475 | 0.0140 | 0.8737 | 0.9351 | 0.9034 | 0.9977 |
|
76 |
+
| 0.0008 | 29.41 | 500 | 0.0171 | 0.8534 | 0.8811 | 0.8670 | 0.9970 |
|
77 |
+
| 0.0007 | 30.88 | 525 | 0.0170 | 0.8632 | 0.8865 | 0.8747 | 0.9971 |
|
78 |
+
| 0.0007 | 32.35 | 550 | 0.0162 | 0.8601 | 0.8973 | 0.8783 | 0.9973 |
|
79 |
+
| 0.0006 | 33.82 | 575 | 0.0162 | 0.8601 | 0.8973 | 0.8783 | 0.9973 |
|
80 |
+
| 0.0006 | 35.29 | 600 | 0.0170 | 0.8534 | 0.8811 | 0.8670 | 0.9971 |
|
81 |
+
| 0.0006 | 36.76 | 625 | 0.0167 | 0.8557 | 0.8973 | 0.8760 | 0.9971 |
|
82 |
+
| 0.0005 | 38.24 | 650 | 0.0166 | 0.8549 | 0.8919 | 0.8730 | 0.9970 |
|
83 |
+
| 0.0005 | 39.71 | 675 | 0.0163 | 0.8513 | 0.8973 | 0.8737 | 0.9970 |
|
84 |
+
| 0.0005 | 41.18 | 700 | 0.0171 | 0.8497 | 0.8865 | 0.8677 | 0.9969 |
|
85 |
+
| 0.0005 | 42.65 | 725 | 0.0190 | 0.8526 | 0.8757 | 0.8640 | 0.9969 |
|
86 |
+
| 0.0005 | 44.12 | 750 | 0.0178 | 0.8490 | 0.8811 | 0.8647 | 0.9969 |
|
87 |
+
| 0.0005 | 45.59 | 775 | 0.0173 | 0.8446 | 0.8811 | 0.8624 | 0.9969 |
|
88 |
+
|
89 |
+
|
90 |
+
### Framework versions
|
91 |
+
|
92 |
+
- Transformers 4.27.4
|
93 |
+
- Pytorch 2.0.0+cu118
|
94 |
+
- Datasets 2.11.0
|
95 |
+
- Tokenizers 0.13.2
|