xlm-roberta-base_pan_corr_5e-06
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0244
- Spearman Corr: 0.7659
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: 32
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
---|---|---|---|---|
No log | 0.85 | 200 | 0.0258 | 0.7651 |
No log | 1.69 | 400 | 0.0241 | 0.7668 |
0.0007 | 2.54 | 600 | 0.0254 | 0.7642 |
0.0007 | 3.38 | 800 | 0.0249 | 0.7668 |
0.0007 | 4.23 | 1000 | 0.0247 | 0.7614 |
0.0007 | 5.07 | 1200 | 0.0234 | 0.7675 |
0.0007 | 5.92 | 1400 | 0.0249 | 0.7660 |
0.0007 | 6.77 | 1600 | 0.0241 | 0.7653 |
0.0007 | 7.61 | 1800 | 0.0235 | 0.7663 |
0.0007 | 8.46 | 2000 | 0.0255 | 0.7692 |
0.0007 | 9.3 | 2200 | 0.0241 | 0.7680 |
0.0013 | 10.15 | 2400 | 0.0239 | 0.7660 |
0.0013 | 10.99 | 2600 | 0.0239 | 0.7655 |
0.0013 | 11.84 | 2800 | 0.0241 | 0.7671 |
0.0017 | 12.68 | 3000 | 0.0241 | 0.7633 |
0.0017 | 13.53 | 3200 | 0.0249 | 0.7658 |
0.0016 | 14.38 | 3400 | 0.0244 | 0.7673 |
0.0016 | 15.22 | 3600 | 0.0244 | 0.7659 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 5