xlm-roberta-base_original_esp-hau-eng_train_spearman_corr
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: 0.0293
- Spearman Corr: 0.7485
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 | 1.45 | 200 | 0.0269 | 0.6960 |
0.0444 | 2.91 | 400 | 0.0266 | 0.7221 |
0.0247 | 4.36 | 600 | 0.0258 | 0.7535 |
0.0247 | 5.82 | 800 | 0.0297 | 0.7543 |
0.0188 | 7.27 | 1000 | 0.0263 | 0.7520 |
0.0144 | 8.73 | 1200 | 0.0283 | 0.7540 |
0.0115 | 10.18 | 1400 | 0.0289 | 0.7519 |
0.0115 | 11.64 | 1600 | 0.0277 | 0.7510 |
0.0091 | 13.09 | 1800 | 0.0258 | 0.7605 |
0.0078 | 14.55 | 2000 | 0.0287 | 0.7540 |
0.0064 | 16.0 | 2200 | 0.0278 | 0.7506 |
0.0064 | 17.45 | 2400 | 0.0309 | 0.7539 |
0.0054 | 18.91 | 2600 | 0.0287 | 0.7469 |
0.0049 | 20.36 | 2800 | 0.0284 | 0.7478 |
0.0049 | 21.82 | 3000 | 0.0286 | 0.7469 |
0.0045 | 23.27 | 3200 | 0.0289 | 0.7439 |
0.004 | 24.73 | 3400 | 0.0293 | 0.7485 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 7