metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
model-index:
- name: lifechart-deberta-classifier-hptuning
results: []
lifechart-deberta-classifier-hptuning
This model is a fine-tuned version of microsoft/deberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9622
- Macro F1: 0.7854
- Precision: 0.7750
- Recall: 0.8009
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: 2.0260649431134323e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.09915082219848009
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Precision | Recall |
|---|---|---|---|---|---|---|
| 2.0427 | 1.0 | 821 | 0.8925 | 0.7133 | 0.6744 | 0.7897 |
| 0.7423 | 2.0 | 1642 | 0.7529 | 0.7677 | 0.7333 | 0.8192 |
| 0.4454 | 3.0 | 2463 | 0.8392 | 0.7721 | 0.7592 | 0.7980 |
| 0.2746 | 4.0 | 3284 | 0.9407 | 0.7711 | 0.7626 | 0.7873 |
| 0.1817 | 5.0 | 4105 | 0.9622 | 0.7854 | 0.7750 | 0.8009 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4