metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test_linsearch_only_abstract
results: []
test_linsearch_only_abstract
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2716
- Accuracy: 0.6508
- F1 Macro: 0.5942
- Precision Macro: 0.6170
- Recall Macro: 0.5858
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 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro |
|---|---|---|---|---|---|---|---|
| 1.2232 | 1.0 | 2466 | 1.1574 | 0.6405 | 0.5484 | 0.5538 | 0.5608 |
| 1.0386 | 2.0 | 4932 | 1.0934 | 0.6497 | 0.5631 | 0.5712 | 0.5642 |
| 0.9215 | 3.0 | 7398 | 1.0725 | 0.6634 | 0.5933 | 0.5950 | 0.5970 |
| 0.8026 | 4.0 | 9864 | 1.0994 | 0.6532 | 0.5817 | 0.5905 | 0.5796 |
| 0.6754 | 5.0 | 12330 | 1.1462 | 0.6558 | 0.5838 | 0.5934 | 0.5806 |
| 0.5958 | 6.0 | 14796 | 1.2077 | 0.6537 | 0.5857 | 0.5963 | 0.5813 |
| 0.4924 | 7.0 | 17262 | 1.2716 | 0.6508 | 0.5942 | 0.6170 | 0.5858 |
| 0.4165 | 8.0 | 19728 | 1.3450 | 0.6450 | 0.5938 | 0.6037 | 0.5923 |
| 0.3599 | 9.0 | 22194 | 1.4048 | 0.6412 | 0.5906 | 0.6077 | 0.5812 |
| 0.3262 | 10.0 | 24660 | 1.4422 | 0.6389 | 0.5941 | 0.6032 | 0.5894 |
Framework versions
- Transformers 4.50.1
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1