metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: experiment_lr_20241214_130720
results: []
experiment_lr_20241214_130720
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0103
- Exact Match Accuracy: 0.8830
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: 16
- eval_batch_size: 16
- 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: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match Accuracy |
|---|---|---|---|---|
| 0.014 | 1.0 | 4594 | 0.0125 | 0.6134 |
| 0.0023 | 2.0 | 9188 | 0.0072 | 0.8473 |
| 0.0009 | 3.0 | 13782 | 0.0078 | 0.8711 |
| 0.0006 | 4.0 | 18376 | 0.0085 | 0.8711 |
| 0.0003 | 5.0 | 22970 | 0.0094 | 0.8685 |
| 0.0002 | 6.0 | 27564 | 0.0096 | 0.8771 |
| 0.0002 | 7.0 | 32158 | 0.0095 | 0.8824 |
| 0.0001 | 8.0 | 36752 | 0.0111 | 0.8744 |
| 0.0001 | 9.0 | 41346 | 0.0103 | 0.8830 |
| 0.0001 | 10.0 | 45940 | 0.0100 | 0.8824 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0