Commit
•
5bfdb1f
1
Parent(s):
25806ee
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: BERT_full-6_tokenized
|
| 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 |
+
# BERT_full-6_tokenized
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [armheb/DNA_bert_6](https://huggingface.co/armheb/DNA_bert_6) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.0362
|
| 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: 2e-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 |
+
- num_epochs: 25
|
| 42 |
+
- mixed_precision_training: Native AMP
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 0.0775 | 1.0 | 284 | 0.0411 |
|
| 49 |
+
| 0.0428 | 2.0 | 568 | 0.0393 |
|
| 50 |
+
| 0.0395 | 3.0 | 852 | 0.0396 |
|
| 51 |
+
| 0.0395 | 4.0 | 1136 | 0.0374 |
|
| 52 |
+
| 0.0379 | 5.0 | 1420 | 0.0379 |
|
| 53 |
+
| 0.037 | 6.0 | 1704 | 0.0399 |
|
| 54 |
+
| 0.0368 | 7.0 | 1988 | 0.0382 |
|
| 55 |
+
| 0.0378 | 8.0 | 2272 | 0.0378 |
|
| 56 |
+
| 0.0365 | 9.0 | 2556 | 0.0362 |
|
| 57 |
+
| 0.0374 | 10.0 | 2840 | 0.0359 |
|
| 58 |
+
| 0.0372 | 11.0 | 3124 | 0.0373 |
|
| 59 |
+
| 0.0358 | 12.0 | 3408 | 0.0378 |
|
| 60 |
+
| 0.0361 | 13.0 | 3692 | 0.0385 |
|
| 61 |
+
| 0.0364 | 14.0 | 3976 | 0.0383 |
|
| 62 |
+
| 0.035 | 15.0 | 4260 | 0.0376 |
|
| 63 |
+
| 0.035 | 16.0 | 4544 | 0.0376 |
|
| 64 |
+
| 0.036 | 17.0 | 4828 | 0.0388 |
|
| 65 |
+
| 0.0365 | 18.0 | 5112 | 0.0372 |
|
| 66 |
+
| 0.0355 | 19.0 | 5396 | 0.0363 |
|
| 67 |
+
| 0.0349 | 20.0 | 5680 | 0.0378 |
|
| 68 |
+
| 0.0345 | 21.0 | 5964 | 0.0377 |
|
| 69 |
+
| 0.0349 | 22.0 | 6248 | 0.0372 |
|
| 70 |
+
| 0.035 | 23.0 | 6532 | 0.0374 |
|
| 71 |
+
| 0.0351 | 24.0 | 6816 | 0.0379 |
|
| 72 |
+
| 0.0351 | 25.0 | 7100 | 0.0374 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.23.1
|
| 78 |
+
- Pytorch 1.12.1+cu113
|
| 79 |
+
- Datasets 2.6.1
|
| 80 |
+
- Tokenizers 0.13.1
|