xlm-roberta-base_arb_loss_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: 0.0250
- Spearman Corr: 0.7543
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 | 0.0250 | 0.7524 |
No log | 1.69 | 400 | 0.0251 | 0.7477 |
0.0062 | 2.54 | 600 | 0.0252 | 0.7496 |
0.0062 | 3.38 | 800 | 0.0265 | 0.7428 |
0.0064 | 4.23 | 1000 | 0.0261 | 0.7512 |
0.0064 | 5.07 | 1200 | 0.0261 | 0.7537 |
0.0064 | 5.92 | 1400 | 0.0252 | 0.7528 |
0.0068 | 6.77 | 1600 | 0.0258 | 0.7468 |
0.0068 | 7.61 | 1800 | 0.0250 | 0.7543 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 7