metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-base_pan_loss_5e-06
results: []
xlm-roberta-base_pan_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: 0.0245
- Spearman Corr: 0.7682
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 | 0.0232 | 0.7677 |
| No log | 1.69 | 400 | 0.0279 | 0.7686 |
| 0.0011 | 2.54 | 600 | 0.0229 | 0.7636 |
| 0.0011 | 3.38 | 800 | 0.0240 | 0.7676 |
| 0.0009 | 4.23 | 1000 | 0.0237 | 0.7664 |
| 0.0009 | 5.07 | 1200 | 0.0239 | 0.7677 |
| 0.0009 | 5.92 | 1400 | 0.0236 | 0.7678 |
| 0.0007 | 6.77 | 1600 | 0.0248 | 0.7646 |
| 0.0007 | 7.61 | 1800 | 0.0231 | 0.7647 |
| 0.0006 | 8.46 | 2000 | 0.0256 | 0.7671 |
| 0.0006 | 9.3 | 2200 | 0.0245 | 0.7682 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2