update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: DNABert_K6_G_quad
|
| 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 |
+
# DNABert_K6_G_quad
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [armheb/DNA_bert_6](https://huggingface.co/armheb/DNA_bert_6) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.2424
|
| 19 |
+
- Accuracy: 0.9737
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 1e-05
|
| 39 |
+
- train_batch_size: 32
|
| 40 |
+
- eval_batch_size: 32
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 25
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
| 51 |
+
| 0.0927 | 1.0 | 9375 | 0.0818 | 0.9719 |
|
| 52 |
+
| 0.0681 | 2.0 | 18750 | 0.0714 | 0.9756 |
|
| 53 |
+
| 0.0607 | 3.0 | 28125 | 0.0863 | 0.9734 |
|
| 54 |
+
| 0.055 | 4.0 | 37500 | 0.0787 | 0.9757 |
|
| 55 |
+
| 0.0496 | 5.0 | 46875 | 0.0882 | 0.9758 |
|
| 56 |
+
| 0.0445 | 6.0 | 56250 | 0.0968 | 0.9752 |
|
| 57 |
+
| 0.0391 | 7.0 | 65625 | 0.1024 | 0.9755 |
|
| 58 |
+
| 0.0345 | 8.0 | 75000 | 0.1108 | 0.9739 |
|
| 59 |
+
| 0.0304 | 9.0 | 84375 | 0.1235 | 0.9745 |
|
| 60 |
+
| 0.0261 | 10.0 | 93750 | 0.1348 | 0.9730 |
|
| 61 |
+
| 0.023 | 11.0 | 103125 | 0.1427 | 0.9733 |
|
| 62 |
+
| 0.0197 | 12.0 | 112500 | 0.1462 | 0.9738 |
|
| 63 |
+
| 0.0182 | 13.0 | 121875 | 0.1570 | 0.9730 |
|
| 64 |
+
| 0.0145 | 14.0 | 131250 | 0.1757 | 0.9729 |
|
| 65 |
+
| 0.0122 | 15.0 | 140625 | 0.1911 | 0.9735 |
|
| 66 |
+
| 0.0108 | 16.0 | 150000 | 0.1977 | 0.9736 |
|
| 67 |
+
| 0.01 | 17.0 | 159375 | 0.1993 | 0.9732 |
|
| 68 |
+
| 0.0083 | 18.0 | 168750 | 0.2172 | 0.9736 |
|
| 69 |
+
| 0.0074 | 19.0 | 178125 | 0.2242 | 0.9740 |
|
| 70 |
+
| 0.0059 | 20.0 | 187500 | 0.2245 | 0.9732 |
|
| 71 |
+
| 0.0058 | 21.0 | 196875 | 0.2306 | 0.9733 |
|
| 72 |
+
| 0.0043 | 22.0 | 206250 | 0.2414 | 0.9737 |
|
| 73 |
+
| 0.0044 | 23.0 | 215625 | 0.2394 | 0.9735 |
|
| 74 |
+
| 0.0039 | 24.0 | 225000 | 0.2420 | 0.9736 |
|
| 75 |
+
| 0.0032 | 25.0 | 234375 | 0.2424 | 0.9737 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.22.1
|
| 81 |
+
- Pytorch 1.12.1
|
| 82 |
+
- Datasets 2.4.0
|
| 83 |
+
- Tokenizers 0.12.1
|