metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: DEREXP
results: []
DEREXP
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0504
- Mse: 0.0504
- Mae: 0.2062
- R2: 0.9910
- Accuracy: 0.995
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
|---|---|---|---|---|---|---|---|
| 12.4633 | 1.0 | 625 | 0.0598 | 0.0598 | 0.2042 | 0.9893 | 0.975 |
| 0.2021 | 2.0 | 1250 | 0.0607 | 0.0607 | 0.2199 | 0.9892 | 0.99 |
| 0.1478 | 3.0 | 1875 | 0.0504 | 0.0504 | 0.2062 | 0.9910 | 0.995 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1