metadata
license: mit
base_model: xlnet-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fact_test_with_xlnet
results: []
fact_test_with_xlnet
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: 1.6043
- Accuracy: 0.672
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 310 | 0.9194 | 0.66 |
| 0.9336 | 2.0 | 620 | 0.8339 | 0.696 |
| 0.9336 | 3.0 | 930 | 1.1543 | 0.702 |
| 0.3955 | 4.0 | 1240 | 1.4356 | 0.682 |
| 0.1551 | 5.0 | 1550 | 1.6043 | 0.672 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2