update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: bert-finetuned-mutation-recognition-2
|
| 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 |
+
# bert-finetuned-mutation-recognition-2
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0804
|
| 23 |
+
- Dnamutation F1: 0.6706
|
| 24 |
+
- Proteinmutation F1: 0.8276
|
| 25 |
+
- Snp F1: 0.0455
|
| 26 |
+
- Precision: 0.7373
|
| 27 |
+
- Recall: 0.6948
|
| 28 |
+
- F1: 0.7154
|
| 29 |
+
- Accuracy: 0.9874
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 2e-05
|
| 49 |
+
- train_batch_size: 16
|
| 50 |
+
- eval_batch_size: 16
|
| 51 |
+
- seed: 42
|
| 52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
+
- lr_scheduler_type: linear
|
| 54 |
+
- num_epochs: 10
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Dnamutation F1 | Proteinmutation F1 | Snp F1 | Precision | Recall | F1 | Accuracy |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:------------------:|:------:|:---------:|:------:|:------:|:--------:|
|
| 60 |
+
| No log | 1.0 | 403 | 0.0433 | 0.4712 | 0.75 | 0.0 | 0.5581 | 0.6180 | 0.5865 | 0.9858 |
|
| 61 |
+
| 0.085 | 2.0 | 806 | 0.0461 | 0.5506 | 0.7673 | 0.0 | 0.6454 | 0.6219 | 0.6334 | 0.9856 |
|
| 62 |
+
| 0.0309 | 3.0 | 1209 | 0.0519 | 0.5022 | 0.7830 | 0.0 | 0.6781 | 0.5701 | 0.6194 | 0.9850 |
|
| 63 |
+
| 0.0188 | 4.0 | 1612 | 0.0452 | 0.6008 | 0.8180 | 0.1892 | 0.6757 | 0.6718 | 0.6737 | 0.9863 |
|
| 64 |
+
| 0.0128 | 5.0 | 2015 | 0.0494 | 0.6753 | 0.7974 | 0.0 | 0.6975 | 0.7083 | 0.7029 | 0.9870 |
|
| 65 |
+
| 0.0128 | 6.0 | 2418 | 0.0519 | 0.6654 | 0.8421 | 0.0645 | 0.7017 | 0.7179 | 0.7097 | 0.9881 |
|
| 66 |
+
| 0.007 | 7.0 | 2821 | 0.0745 | 0.5954 | 0.8055 | 0.2353 | 0.7072 | 0.6257 | 0.6640 | 0.9859 |
|
| 67 |
+
| 0.0037 | 8.0 | 3224 | 0.0717 | 0.6882 | 0.8486 | 0.0 | 0.7280 | 0.7294 | 0.7287 | 0.9874 |
|
| 68 |
+
| 0.0019 | 9.0 | 3627 | 0.0839 | 0.6373 | 0.8089 | 0.0 | 0.7209 | 0.6545 | 0.6861 | 0.9867 |
|
| 69 |
+
| 0.0012 | 10.0 | 4030 | 0.0804 | 0.6706 | 0.8276 | 0.0455 | 0.7373 | 0.6948 | 0.7154 | 0.9874 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.17.0
|
| 75 |
+
- Pytorch 1.10.2
|
| 76 |
+
- Datasets 2.0.0
|
| 77 |
+
- Tokenizers 0.12.1
|