metadata
license: mit
base_model: facebook/esm2_t30_150M_UR50D
tags:
- generated_from_trainer
model-index:
- name: model_checkpoint
results: []
model_checkpoint
This model is a fine-tuned version of facebook/esm2_t30_150M_UR50D on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8311
- Mse: 0.8311
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse |
|---|---|---|---|---|
| No log | 1.0 | 146 | 1.5425 | 1.5425 |
| No log | 2.0 | 292 | 1.2182 | 1.2182 |
| No log | 3.0 | 438 | 1.2270 | 1.2270 |
| 1.7883 | 4.0 | 584 | 1.0496 | 1.0496 |
| 1.7883 | 5.0 | 730 | 1.0828 | 1.0828 |
| 1.7883 | 6.0 | 876 | 0.9050 | 0.9050 |
| 0.9949 | 7.0 | 1022 | 0.8451 | 0.8451 |
| 0.9949 | 8.0 | 1168 | 0.9760 | 0.9760 |
| 0.9949 | 9.0 | 1314 | 0.8303 | 0.8303 |
| 0.9949 | 10.0 | 1460 | 0.8311 | 0.8311 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cpu
- Datasets 2.18.0
- Tokenizers 0.15.2