xlm_roberta_final2
This model is a fine-tuned version of pedramyazdipoor/persian_xlm_roberta_large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2361
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-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7048 | 0.1477 | 300 | 1.3828 |
| 1.4155 | 0.2953 | 600 | 1.3106 |
| 1.3612 | 0.4430 | 900 | 1.3065 |
| 1.4218 | 0.5907 | 1200 | 1.2196 |
| 1.3149 | 0.7384 | 1500 | 1.2361 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Downloads last month
- -
Model tree for MahdisHosseini/xlm_roberta_final2
Base model
pedramyazdipoor/persian_xlm_roberta_large