|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: protBERTbfd_AAV2_regressor |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# protBERTbfd_AAV2_regressor |
|
|
|
This model is a fine-tuned version of [Rostlab/prot_bert_bfd](https://huggingface.co/Rostlab/prot_bert_bfd) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0327 |
|
- Mse: 0.0327 |
|
- Rmse: 0.1808 |
|
- Mae: 0.0618 |
|
- R2: 0.8691 |
|
- Smape: 101.2324 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 64 |
|
- total_train_batch_size: 4096 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 200 |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mse | Rmse | Mae | R2 | Smape | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 58 | 0.0985 | 0.0985 | 0.3138 | 0.1707 | 0.6057 | 102.5806 | |
|
| No log | 2.0 | 116 | 0.0689 | 0.0689 | 0.2625 | 0.1432 | 0.7242 | 112.9846 | |
|
| No log | 3.0 | 174 | 0.0400 | 0.0400 | 0.1999 | 0.0859 | 0.8399 | 102.6132 | |
|
| No log | 4.0 | 232 | 0.0402 | 0.0402 | 0.2005 | 0.0745 | 0.8389 | 103.3228 | |
|
| No log | 5.0 | 290 | 0.0337 | 0.0337 | 0.1836 | 0.0665 | 0.8650 | 101.0925 | |
|
| No log | 6.0 | 348 | 0.0327 | 0.0327 | 0.1808 | 0.0618 | 0.8691 | 101.2324 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.0 |
|
- Pytorch 1.12.0+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
