metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: mytest_trainer_base-cased
results: []
mytest_trainer_base-cased
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: 0.9503
- Rmse: 0.7134
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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 | Rmse |
|---|---|---|---|---|
| 0.9734 | 1.0 | 500 | 0.9593 | 0.9513 |
| 0.966 | 2.0 | 1000 | 0.9822 | 0.7134 |
| 0.9643 | 3.0 | 1500 | 0.9556 | 0.7134 |
| 0.9615 | 4.0 | 2000 | 0.9510 | 0.7134 |
| 0.959 | 5.0 | 2500 | 0.9540 | 0.7134 |
| 0.9572 | 6.0 | 3000 | 0.9503 | 0.7134 |
| 0.9571 | 7.0 | 3500 | 0.9760 | 0.7134 |
| 0.9561 | 8.0 | 4000 | 0.9534 | 0.7134 |
| 0.9526 | 9.0 | 4500 | 0.9500 | 0.7134 |
| 0.9527 | 10.0 | 5000 | 0.9503 | 0.7134 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3