update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: DNADebertaK6_Arabidopsis
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# DNADebertaK6_Arabidopsis
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 1.7194
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 64
|
| 37 |
+
- eval_batch_size: 64
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- training_steps: 600001
|
| 42 |
+
- mixed_precision_training: Native AMP
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:------:|:------:|:---------------:|
|
| 48 |
+
| 4.6174 | 6.12 | 20000 | 1.9257 |
|
| 49 |
+
| 1.8873 | 12.24 | 40000 | 1.8098 |
|
| 50 |
+
| 1.8213 | 18.36 | 60000 | 1.7952 |
|
| 51 |
+
| 1.8042 | 24.48 | 80000 | 1.7888 |
|
| 52 |
+
| 1.7945 | 30.6 | 100000 | 1.7861 |
|
| 53 |
+
| 1.7873 | 36.72 | 120000 | 1.7772 |
|
| 54 |
+
| 1.782 | 42.84 | 140000 | 1.7757 |
|
| 55 |
+
| 1.7761 | 48.96 | 160000 | 1.7632 |
|
| 56 |
+
| 1.7714 | 55.08 | 180000 | 1.7685 |
|
| 57 |
+
| 1.7677 | 61.2 | 200000 | 1.7568 |
|
| 58 |
+
| 1.7637 | 67.32 | 220000 | 1.7570 |
|
| 59 |
+
| 1.7585 | 73.44 | 240000 | 1.7442 |
|
| 60 |
+
| 1.7554 | 79.56 | 260000 | 1.7556 |
|
| 61 |
+
| 1.7515 | 85.68 | 280000 | 1.7505 |
|
| 62 |
+
| 1.7483 | 91.8 | 300000 | 1.7463 |
|
| 63 |
+
| 1.745 | 97.92 | 320000 | 1.7425 |
|
| 64 |
+
| 1.7427 | 104.04 | 340000 | 1.7425 |
|
| 65 |
+
| 1.7398 | 110.16 | 360000 | 1.7359 |
|
| 66 |
+
| 1.7377 | 116.28 | 380000 | 1.7369 |
|
| 67 |
+
| 1.7349 | 122.4 | 400000 | 1.7340 |
|
| 68 |
+
| 1.7325 | 128.52 | 420000 | 1.7313 |
|
| 69 |
+
| 1.731 | 134.64 | 440000 | 1.7256 |
|
| 70 |
+
| 1.7286 | 140.76 | 460000 | 1.7238 |
|
| 71 |
+
| 1.7267 | 146.88 | 480000 | 1.7324 |
|
| 72 |
+
| 1.7247 | 153.0 | 500000 | 1.7247 |
|
| 73 |
+
| 1.7228 | 159.12 | 520000 | 1.7185 |
|
| 74 |
+
| 1.7209 | 165.24 | 540000 | 1.7166 |
|
| 75 |
+
| 1.7189 | 171.36 | 560000 | 1.7206 |
|
| 76 |
+
| 1.7181 | 177.48 | 580000 | 1.7190 |
|
| 77 |
+
| 1.7159 | 183.6 | 600000 | 1.7194 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.19.2
|
| 83 |
+
- Pytorch 1.11.0
|
| 84 |
+
- Datasets 2.2.2
|
| 85 |
+
- Tokenizers 0.12.1
|