sofia-todeschini
commited on
Commit
•
e62038a
1
Parent(s):
9996c9c
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: BioELECTRA-LitCovid-v1.3.1
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# BioELECTRA-LitCovid-v1.3.1
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [kamalkraj/bioelectra-base-discriminator-pubmed](https://huggingface.co/kamalkraj/bioelectra-base-discriminator-pubmed) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.6749
|
19 |
+
- Hamming loss: 0.0257
|
20 |
+
- F1 micro: 0.7955
|
21 |
+
- F1 macro: 0.3005
|
22 |
+
- F1 weighted: 0.8714
|
23 |
+
- F1 samples: 0.8642
|
24 |
+
- Precision micro: 0.6936
|
25 |
+
- Precision macro: 0.2470
|
26 |
+
- Precision weighted: 0.8294
|
27 |
+
- Precision samples: 0.8463
|
28 |
+
- Recall micro: 0.9326
|
29 |
+
- Recall macro: 0.7358
|
30 |
+
- Recall weighted: 0.9326
|
31 |
+
- Recall samples: 0.9427
|
32 |
+
- Roc Auc: 0.9546
|
33 |
+
- Accuracy: 0.6664
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 2e-05
|
53 |
+
- train_batch_size: 16
|
54 |
+
- eval_batch_size: 16
|
55 |
+
- seed: 42
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 5
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Hamming loss | F1 micro | F1 macro | F1 weighted | F1 samples | Precision micro | Precision macro | Precision weighted | Precision samples | Recall micro | Recall macro | Recall weighted | Recall samples | Roc Auc | Accuracy |
|
63 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------------:|:--------:|:--------:|:-----------:|:----------:|:---------------:|:---------------:|:------------------:|:-----------------:|:------------:|:------------:|:---------------:|:--------------:|:-------:|:--------:|
|
64 |
+
| 1.385 | 1.0 | 2272 | 0.6961 | 0.0592 | 0.6188 | 0.2176 | 0.7539 | 0.7422 | 0.4725 | 0.1706 | 0.6672 | 0.6890 | 0.8965 | 0.6896 | 0.8965 | 0.9065 | 0.9199 | 0.3887 |
|
65 |
+
| 1.2034 | 2.0 | 4544 | 0.6242 | 0.0342 | 0.7421 | 0.2668 | 0.8404 | 0.8354 | 0.6231 | 0.2180 | 0.7922 | 0.8120 | 0.9172 | 0.6872 | 0.9172 | 0.9319 | 0.9429 | 0.5906 |
|
66 |
+
| 1.0857 | 3.0 | 6816 | 0.6185 | 0.0270 | 0.7869 | 0.2949 | 0.8615 | 0.8587 | 0.6815 | 0.2402 | 0.8153 | 0.8382 | 0.9308 | 0.7164 | 0.9308 | 0.9437 | 0.9531 | 0.6444 |
|
67 |
+
| 0.8846 | 4.0 | 9088 | 0.6143 | 0.0260 | 0.7936 | 0.2994 | 0.8677 | 0.8626 | 0.6916 | 0.2460 | 0.8237 | 0.8444 | 0.9309 | 0.7254 | 0.9309 | 0.9421 | 0.9537 | 0.6594 |
|
68 |
+
| 0.6753 | 5.0 | 11360 | 0.6749 | 0.0257 | 0.7955 | 0.3005 | 0.8714 | 0.8642 | 0.6936 | 0.2470 | 0.8294 | 0.8463 | 0.9326 | 0.7358 | 0.9326 | 0.9427 | 0.9546 | 0.6664 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.28.0
|
74 |
+
- Pytorch 2.1.0+cu118
|
75 |
+
- Datasets 2.14.6
|
76 |
+
- Tokenizers 0.13.3
|