metadata
library_name: transformers
license: mit
base_model: xlnet/xlnet-large-cased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: cs221-xlnet-large-cased-eng-finetuned-remove-neutral-20-epochs
results: []
cs221-xlnet-large-cased-eng-finetuned-remove-neutral-20-epochs
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: 0.4332
- F1: 0.78
- Roc Auc: 0.8345
- Accuracy: 0.4901
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.5992 | 1.0 | 64 | 0.5778 | 0.4728 | 0.6331 | 0.1897 |
| 0.5534 | 2.0 | 128 | 0.4896 | 0.6557 | 0.7409 | 0.3004 |
| 0.4278 | 3.0 | 192 | 0.4141 | 0.7192 | 0.7893 | 0.3775 |
| 0.357 | 4.0 | 256 | 0.4215 | 0.7112 | 0.7818 | 0.4209 |
| 0.2832 | 5.0 | 320 | 0.3839 | 0.7644 | 0.8258 | 0.4289 |
| 0.2142 | 6.0 | 384 | 0.3746 | 0.7745 | 0.8293 | 0.4881 |
| 0.1625 | 7.0 | 448 | 0.4357 | 0.7704 | 0.8269 | 0.4763 |
| 0.1169 | 8.0 | 512 | 0.4332 | 0.78 | 0.8345 | 0.4901 |
| 0.0805 | 9.0 | 576 | 0.5132 | 0.7714 | 0.8320 | 0.4526 |
| 0.0624 | 10.0 | 640 | 0.4989 | 0.7735 | 0.8298 | 0.4625 |
| 0.0509 | 11.0 | 704 | 0.5205 | 0.7736 | 0.8315 | 0.4644 |
| 0.0294 | 12.0 | 768 | 0.5289 | 0.7767 | 0.8322 | 0.4763 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0