metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta-v3-base_finetuned_nostalgia
results: []
deberta-v3-base_finetuned_nostalgia
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3772
- Accuracy: 0.9379
- F1 Macro: 0.9288
- Accuracy Balanced: 0.9264
- F1 Micro: 0.9379
- Precision Macro: 0.9313
- Recall Macro: 0.9264
- Precision Micro: 0.9379
- Recall Micro: 0.9379
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: 64
- seed: 1984
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Accuracy Balanced | F1 Micro | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
---|---|---|---|---|---|---|---|---|---|---|---|
No log | 1.0 | 73 | 0.3903 | 0.8759 | 0.8470 | 0.8251 | 0.8759 | 0.8890 | 0.8251 | 0.8759 | 0.8759 |
No log | 2.0 | 146 | 0.2130 | 0.9103 | 0.8933 | 0.8783 | 0.9103 | 0.9149 | 0.8783 | 0.9103 | 0.9103 |
No log | 3.0 | 219 | 0.1253 | 0.9379 | 0.9288 | 0.9264 | 0.9379 | 0.9313 | 0.9264 | 0.9379 | 0.9379 |
No log | 4.0 | 292 | 0.2694 | 0.9310 | 0.9229 | 0.9324 | 0.9310 | 0.9154 | 0.9324 | 0.9310 | 0.9310 |
No log | 5.0 | 365 | 0.1924 | 0.9448 | 0.9370 | 0.9370 | 0.9448 | 0.9370 | 0.9370 | 0.9448 | 0.9448 |
No log | 6.0 | 438 | 0.2648 | 0.9379 | 0.9288 | 0.9264 | 0.9379 | 0.9313 | 0.9264 | 0.9379 | 0.9379 |
0.1908 | 7.0 | 511 | 0.3431 | 0.9379 | 0.9288 | 0.9264 | 0.9379 | 0.9313 | 0.9264 | 0.9379 | 0.9379 |
0.1908 | 8.0 | 584 | 0.3450 | 0.9379 | 0.9288 | 0.9264 | 0.9379 | 0.9313 | 0.9264 | 0.9379 | 0.9379 |
0.1908 | 9.0 | 657 | 0.3538 | 0.9379 | 0.9279 | 0.9209 | 0.9379 | 0.9362 | 0.9209 | 0.9379 | 0.9379 |
0.1908 | 10.0 | 730 | 0.3772 | 0.9379 | 0.9288 | 0.9264 | 0.9379 | 0.9313 | 0.9264 | 0.9379 | 0.9379 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1