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_Fruitfly
|
| 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_Fruitfly
|
| 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: 1.7137
|
| 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 |
+
| 4.5584 | 5.36 | 20000 | 1.9795 |
|
| 49 |
+
| 1.9682 | 10.73 | 40000 | 1.8618 |
|
| 50 |
+
| 1.8692 | 16.09 | 60000 | 1.8273 |
|
| 51 |
+
| 1.8339 | 21.45 | 80000 | 1.8076 |
|
| 52 |
+
| 1.8208 | 26.82 | 100000 | 1.8073 |
|
| 53 |
+
| 1.8105 | 32.18 | 120000 | 1.7925 |
|
| 54 |
+
| 1.8022 | 37.54 | 140000 | 1.7909 |
|
| 55 |
+
| 1.7955 | 42.91 | 160000 | 1.7836 |
|
| 56 |
+
| 1.7907 | 48.27 | 180000 | 1.7769 |
|
| 57 |
+
| 1.7849 | 53.63 | 200000 | 1.7755 |
|
| 58 |
+
| 1.7805 | 59.0 | 220000 | 1.7677 |
|
| 59 |
+
| 1.7769 | 64.36 | 240000 | 1.7690 |
|
| 60 |
+
| 1.7723 | 69.72 | 260000 | 1.7614 |
|
| 61 |
+
| 1.7689 | 75.09 | 280000 | 1.7586 |
|
| 62 |
+
| 1.7646 | 80.45 | 300000 | 1.7523 |
|
| 63 |
+
| 1.7607 | 85.81 | 320000 | 1.7484 |
|
| 64 |
+
| 1.7572 | 91.18 | 340000 | 1.7458 |
|
| 65 |
+
| 1.754 | 96.54 | 360000 | 1.7460 |
|
| 66 |
+
| 1.7498 | 101.9 | 380000 | 1.7326 |
|
| 67 |
+
| 1.7463 | 107.27 | 400000 | 1.7377 |
|
| 68 |
+
| 1.7438 | 112.63 | 420000 | 1.7318 |
|
| 69 |
+
| 1.7406 | 117.99 | 440000 | 1.7342 |
|
| 70 |
+
| 1.7383 | 123.36 | 460000 | 1.7339 |
|
| 71 |
+
| 1.7348 | 128.72 | 480000 | 1.7244 |
|
| 72 |
+
| 1.7324 | 134.08 | 500000 | 1.7236 |
|
| 73 |
+
| 1.7289 | 139.45 | 520000 | 1.7155 |
|
| 74 |
+
| 1.7268 | 144.81 | 540000 | 1.7254 |
|
| 75 |
+
| 1.725 | 150.17 | 560000 | 1.7191 |
|
| 76 |
+
| 1.7221 | 155.54 | 580000 | 1.7147 |
|
| 77 |
+
| 1.7209 | 160.9 | 600000 | 1.7137 |
|
| 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
|