|
--- |
|
license: mit |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: Regression_xlnet_aug_CustomLoss |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
# Regression_xlnet_aug_CustomLoss |
|
|
|
This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.3652 |
|
- Train Mae: 0.5686 |
|
- Train Mse: 0.4521 |
|
- Train R2-score: 0.7022 |
|
- Validation Loss: 0.3538 |
|
- Validation Mae: 0.5478 |
|
- Validation Mse: 0.4335 |
|
- Validation R2-score: 0.7272 |
|
- Epoch: 14 |
|
|
|
## 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: |
|
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False} |
|
- training_precision: float32 |
|
|
|
### Training results |
|
|
|
| Train Loss | Train Mae | Train Mse | Train R2-score | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Epoch | |
|
|:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:| |
|
| 0.3976 | 0.5843 | 0.4994 | 0.6170 | 0.3698 | 0.6232 | 0.4576 | 0.5391 | 0 | |
|
| 0.3938 | 0.5830 | 0.4901 | 0.5860 | 0.4330 | 0.6806 | 0.5537 | 0.2841 | 1 | |
|
| 0.3822 | 0.5739 | 0.4691 | -2.6800 | 0.3660 | 0.5198 | 0.4614 | 0.7579 | 2 | |
|
| 0.3716 | 0.5723 | 0.4607 | -0.3420 | 0.3541 | 0.5461 | 0.4343 | 0.7295 | 3 | |
|
| 0.3852 | 0.5794 | 0.4793 | 0.6654 | 0.3524 | 0.5654 | 0.4288 | 0.6982 | 4 | |
|
| 0.3826 | 0.5782 | 0.4787 | 0.5114 | 0.3584 | 0.5991 | 0.4374 | 0.6172 | 5 | |
|
| 0.3817 | 0.5746 | 0.4754 | 0.6431 | 0.3569 | 0.5945 | 0.4348 | 0.6304 | 6 | |
|
| 0.3705 | 0.5689 | 0.4541 | 0.6679 | 0.3621 | 0.5210 | 0.4528 | 0.7540 | 7 | |
|
| 0.3719 | 0.5654 | 0.4567 | 0.6807 | 0.3544 | 0.5446 | 0.4350 | 0.7315 | 8 | |
|
| 0.3752 | 0.5698 | 0.4638 | 0.6324 | 0.3571 | 0.5343 | 0.4413 | 0.7433 | 9 | |
|
| 0.3773 | 0.5714 | 0.4655 | 0.7523 | 0.3534 | 0.5787 | 0.4294 | 0.6701 | 10 | |
|
| 0.3651 | 0.5615 | 0.4490 | 0.6223 | 0.3766 | 0.5372 | 0.4846 | 0.7600 | 11 | |
|
| 0.3706 | 0.5649 | 0.4529 | 0.5998 | 0.3525 | 0.5683 | 0.4286 | 0.6924 | 12 | |
|
| 0.3779 | 0.5687 | 0.4619 | 0.6900 | 0.3532 | 0.5771 | 0.4291 | 0.6737 | 13 | |
|
| 0.3652 | 0.5686 | 0.4521 | 0.7022 | 0.3538 | 0.5478 | 0.4335 | 0.7272 | 14 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- TensorFlow 2.12.0 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
