metadata
license: mit
base_model: xlnet/xlnet-base-cased
tags:
- generated_from_trainer
model-index:
- name: xlnet_base_all
results: []
xlnet_base_all
This model is a fine-tuned version of xlnet/xlnet-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4611
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3162 | 1.0 | 1949 | 0.4187 |
| 0.1553 | 2.0 | 3898 | 0.3679 |
| 0.1649 | 3.0 | 5847 | 0.3724 |
| 0.2501 | 4.0 | 7796 | 0.3303 |
| 0.2847 | 5.0 | 9745 | 0.3959 |
| 0.2092 | 6.0 | 11694 | 0.4093 |
| 0.0744 | 7.0 | 13643 | 0.4144 |
| 0.0403 | 8.0 | 15592 | 0.4852 |
| 0.0003 | 9.0 | 17541 | 0.4603 |
| 0.0002 | 10.0 | 19490 | 0.4611 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1