xlm-roberta-base_kin_loss_2e-05
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: 0.0212
- Spearman Corr: 0.7789
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: 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 | 0.89 | 200 | 0.0204 | 0.7803 |
No log | 1.78 | 400 | 0.0212 | 0.7812 |
0.0005 | 2.67 | 600 | 0.0218 | 0.7836 |
0.0005 | 3.56 | 800 | 0.0212 | 0.7810 |
0.0004 | 4.45 | 1000 | 0.0212 | 0.7799 |
0.0004 | 5.35 | 1200 | 0.0214 | 0.7792 |
0.0005 | 6.24 | 1400 | 0.0208 | 0.7774 |
0.0005 | 7.13 | 1600 | 0.0210 | 0.7804 |
0.0005 | 8.02 | 1800 | 0.0212 | 0.7789 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 4