metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Regression_xlnet_aug_MSEloss
results: []
Regression_xlnet_aug_MSEloss
This model is a fine-tuned version of xlnet-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4900
- Mse: 0.4900
- Mae: 0.5762
- R2: -0.0876
- Accuracy: 0.4533
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: 1e-12
- train_batch_size: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 263 | 0.4123 | 0.4123 | 0.5313 | 0.0379 | 0.4633 |
| 0.4874 | 2.0 | 526 | 0.4123 | 0.4123 | 0.5313 | 0.0379 | 0.4633 |
| 0.4874 | 3.0 | 789 | 0.4123 | 0.4123 | 0.5313 | 0.0379 | 0.4633 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3