metadata
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Model
results: []
Model
This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6196
- F1: 0.9295
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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.1769 | 1.0 | 1500 | 0.1696 | 0.9397 |
| 0.105 | 2.0 | 3000 | 0.1966 | 0.9324 |
| 0.0614 | 3.0 | 4500 | 0.3216 | 0.9178 |
| 0.0327 | 4.0 | 6000 | 0.5325 | 0.9226 |
| 0.0203 | 5.0 | 7500 | 0.7042 | 0.9025 |
| 0.0104 | 6.0 | 9000 | 0.5079 | 0.9277 |
| 0.0045 | 7.0 | 10500 | 0.6219 | 0.9267 |
| 0.0011 | 8.0 | 12000 | 0.6196 | 0.9295 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1