|
--- |
|
license: mit |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: Regression_xlnet_NOaug_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_NOaug_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: 0.1862 |
|
- Train Mae: 0.5631 |
|
- Train Mse: 0.4095 |
|
- Train R2-score: 0.8268 |
|
- Validation Loss: 0.1355 |
|
- Validation Mae: 0.5683 |
|
- Validation Mse: 0.3643 |
|
- Validation R2-score: 0.8811 |
|
- 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 | |
|
|:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:| |
|
| 0.1966 | 0.5177 | 0.3647 | 0.3590 | 0.1412 | 0.6460 | 0.4895 | 0.8850 | 0 | |
|
| 0.1804 | 0.5606 | 0.4181 | 0.8105 | 0.1540 | 0.6614 | 0.5259 | 0.8820 | 1 | |
|
| 0.2037 | 0.5676 | 0.4319 | 0.6885 | 0.1399 | 0.6439 | 0.4849 | 0.8849 | 2 | |
|
| 0.1833 | 0.5499 | 0.3954 | 0.8256 | 0.1804 | 0.6845 | 0.5879 | 0.8760 | 3 | |
|
| 0.1627 | 0.5412 | 0.3866 | 0.8022 | 0.1661 | 0.6729 | 0.5558 | 0.8793 | 4 | |
|
| 0.1822 | 0.5677 | 0.4178 | 0.7449 | 0.1327 | 0.6311 | 0.4580 | 0.8861 | 5 | |
|
| 0.2117 | 0.5798 | 0.4520 | 0.5186 | 0.1282 | 0.6187 | 0.4345 | 0.8866 | 6 | |
|
| 0.1843 | 0.5544 | 0.3998 | 0.5283 | 0.1272 | 0.6142 | 0.4265 | 0.8866 | 7 | |
|
| 0.2074 | 0.5906 | 0.4639 | 0.6729 | 0.1269 | 0.6127 | 0.4239 | 0.8865 | 8 | |
|
| 0.1756 | 0.5666 | 0.4032 | 0.8054 | 0.1272 | 0.5909 | 0.3908 | 0.8850 | 9 | |
|
| 0.1706 | 0.5452 | 0.3948 | 0.7999 | 0.1282 | 0.5862 | 0.3845 | 0.8844 | 10 | |
|
| 0.1727 | 0.5499 | 0.3928 | 0.8471 | 0.1453 | 0.6513 | 0.5021 | 0.8840 | 11 | |
|
| 0.1688 | 0.5467 | 0.3884 | 0.3339 | 0.1777 | 0.6823 | 0.5817 | 0.8766 | 12 | |
|
| 0.1625 | 0.5476 | 0.3918 | 0.5804 | 0.1483 | 0.6541 | 0.5098 | 0.8833 | 13 | |
|
| 0.1862 | 0.5631 | 0.4095 | 0.8268 | 0.1355 | 0.5683 | 0.3643 | 0.8811 | 14 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- TensorFlow 2.12.0 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|