metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: CS221-xlm-roberta-large-finetuned-semeval-2
results: []
CS221-xlm-roberta-large-finetuned-semeval-2
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4312
- F1: 0.7476
- Roc Auc: 0.8101
- Accuracy: 0.4531
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 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 |
|---|---|---|---|---|---|---|
| 0.5734 | 1.0 | 139 | 0.5795 | 0.4593 | 0.6262 | 0.1516 |
| 0.4662 | 2.0 | 278 | 0.4728 | 0.5379 | 0.6777 | 0.3032 |
| 0.4162 | 3.0 | 417 | 0.4079 | 0.7009 | 0.7751 | 0.4152 |
| 0.3298 | 4.0 | 556 | 0.4313 | 0.6911 | 0.7683 | 0.3736 |
| 0.2603 | 5.0 | 695 | 0.4033 | 0.7355 | 0.8020 | 0.4296 |
| 0.1685 | 6.0 | 834 | 0.4312 | 0.7476 | 0.8101 | 0.4531 |
| 0.1225 | 7.0 | 973 | 0.4752 | 0.7326 | 0.7979 | 0.4242 |
| 0.1152 | 8.0 | 1112 | 0.5029 | 0.7362 | 0.8019 | 0.4224 |
| 0.0681 | 9.0 | 1251 | 0.5362 | 0.7406 | 0.8049 | 0.4278 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0