metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
model-index:
- name: microsoft-deberta-v3-large
results: []
microsoft-deberta-v3-large
This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5698
- Pearson R: 0.8241
- Spearman R: 0.8276
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson R | Spearman R |
|---|---|---|---|---|---|
| 0.6835 | 1.0 | 719 | 0.6543 | 0.5224 | 0.5221 |
| 0.6489 | 2.0 | 1438 | 0.6053 | 0.7743 | 0.7848 |
| 0.6408 | 3.0 | 2157 | 0.6005 | 0.7826 | 0.7938 |
| 0.6288 | 4.0 | 2876 | 0.5970 | 0.7778 | 0.7792 |
| 0.6138 | 5.0 | 3595 | 0.6643 | 0.7622 | 0.7814 |
| 0.6044 | 6.0 | 4314 | 0.6048 | 0.8059 | 0.8135 |
| 0.597 | 7.0 | 5033 | 0.5865 | 0.8243 | 0.8307 |
| 0.5946 | 8.0 | 5752 | 0.5702 | 0.8170 | 0.8236 |
| 0.5915 | 9.0 | 6471 | 0.5738 | 0.8211 | 0.8242 |
| 0.5891 | 10.0 | 7190 | 0.5698 | 0.8241 | 0.8276 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0