metadata
library_name: transformers
license: mit
base_model: xlnet/xlnet-large-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: sentiment-XLNnet-2025_II
results: []
sentiment-XLNnet-2025_II
This model is a fine-tuned version of xlnet/xlnet-large-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5971
- F1 Macro: 0.7693
- F1 Weighted: 0.7732
- Accuracy: 0.7721
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: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 0.7148 | 1.0 | 164 | 0.6885 | 0.3818 | 0.3498 | 0.4558 |
| 0.6764 | 2.0 | 328 | 0.6087 | 0.6659 | 0.6695 | 0.6677 |
| 0.6066 | 3.0 | 492 | 0.5459 | 0.7364 | 0.7459 | 0.7515 |
| 0.4872 | 4.0 | 656 | 0.5602 | 0.7572 | 0.7650 | 0.7683 |
| 0.386 | 5.0 | 820 | 0.5875 | 0.7701 | 0.7768 | 0.7790 |
| 0.2853 | 6.0 | 984 | 0.6121 | 0.7798 | 0.7841 | 0.7835 |
| 0.2407 | 7.0 | 1148 | 0.9999 | 0.7620 | 0.7690 | 0.7713 |
| 0.1793 | 8.0 | 1312 | 1.1289 | 0.7721 | 0.7786 | 0.7805 |
| 0.1414 | 9.0 | 1476 | 1.2392 | 0.7615 | 0.7660 | 0.7652 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1