update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- protein language model
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- train
|
| 8 |
+
metrics:
|
| 9 |
+
- spearmanr
|
| 10 |
+
model-index:
|
| 11 |
+
- name: tape-fluorescence-prediction-tape-fluorescence-evotuning-DistilProtBert
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Text Classification
|
| 15 |
+
type: text-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: cradle-bio/tape-fluorescence
|
| 18 |
+
type: train
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Spearmanr
|
| 21 |
+
type: spearmanr
|
| 22 |
+
value: 0.3011866489457721
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# tape-fluorescence-prediction-tape-fluorescence-evotuning-DistilProtBert
|
| 29 |
+
|
| 30 |
+
This model is a fine-tuned version of [thundaa/tape-fluorescence-evotuning-DistilProtBert](https://huggingface.co/thundaa/tape-fluorescence-evotuning-DistilProtBert) on the cradle-bio/tape-fluorescence dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.6667
|
| 33 |
+
- Spearmanr: 0.3012
|
| 34 |
+
|
| 35 |
+
## Model description
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training and evaluation data
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training procedure
|
| 48 |
+
|
| 49 |
+
### Training hyperparameters
|
| 50 |
+
|
| 51 |
+
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 5e-05
|
| 53 |
+
- train_batch_size: 32
|
| 54 |
+
- eval_batch_size: 32
|
| 55 |
+
- seed: 42
|
| 56 |
+
- gradient_accumulation_steps: 128
|
| 57 |
+
- total_train_batch_size: 4096
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- num_epochs: 5
|
| 61 |
+
- mixed_precision_training: Native AMP
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Spearmanr |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
| 67 |
+
| 9.0152 | 0.85 | 4 | 4.9739 | -0.0152 |
|
| 68 |
+
| 4.0359 | 1.85 | 8 | 2.1126 | 0.0919 |
|
| 69 |
+
| 1.7594 | 2.85 | 12 | 0.9896 | 0.0973 |
|
| 70 |
+
| 0.9771 | 3.85 | 16 | 0.6949 | 0.3219 |
|
| 71 |
+
| 0.7046 | 4.85 | 20 | 0.6667 | 0.3012 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.18.0
|
| 77 |
+
- Pytorch 1.11.0
|
| 78 |
+
- Datasets 2.1.0
|
| 79 |
+
- Tokenizers 0.12.1
|