xlmroberta_clir_back
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0152
- Spearman Corr: 0.8972
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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
---|---|---|---|---|
No log | 1.0 | 206 | 0.0300 | 0.6949 |
0.041 | 2.0 | 413 | 0.0230 | 0.7671 |
0.041 | 3.0 | 619 | 0.0183 | 0.8169 |
0.0219 | 4.0 | 826 | 0.0154 | 0.8516 |
0.0219 | 5.0 | 1032 | 0.0146 | 0.8698 |
0.0133 | 6.0 | 1239 | 0.0150 | 0.8869 |
0.0133 | 7.0 | 1445 | 0.0152 | 0.8972 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 5