metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: DSC_xlm-roberta-large_finetuned
results: []
DSC_xlm-roberta-large_finetuned
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: 1.0981
- Accuracy: 0.35
- F1 Macro: 0.1728
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 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: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 1.1194 | 1.0 | 350 | 1.1025 | 0.3293 | 0.1651 |
| 1.1063 | 2.0 | 700 | 1.0981 | 0.35 | 0.1728 |
| 1.1026 | 3.0 | 1050 | 1.0987 | 0.35 | 0.1728 |
| 1.1043 | 4.0 | 1400 | 1.0986 | 0.35 | 0.1728 |
| 1.1023 | 5.0 | 1750 | 1.1013 | 0.35 | 0.1728 |
| 1.1025 | 6.0 | 2100 | 1.0996 | 0.3293 | 0.1651 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2