xlnet-case-12
This model is a fine-tuned version of amr8ta/xlnet-case-12 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3324
- Accuracy: 0.9
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 224
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 44 | 0.3948 | 0.8733 |
No log | 2.0 | 88 | 0.3324 | 0.9 |
No log | 3.0 | 132 | 0.3904 | 0.8933 |
No log | 4.0 | 176 | 0.3734 | 0.9133 |
No log | 5.0 | 220 | 0.4815 | 0.9 |
No log | 6.0 | 264 | 0.4847 | 0.9 |
No log | 7.0 | 308 | 0.4912 | 0.9 |
No log | 8.0 | 352 | 0.4946 | 0.9 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 0