metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- deBERTa
- sequence-classification
- generated_from_trainer
datasets:
- banking77
metrics:
- accuracy
model-index:
- name: banking77-deBERTa-v3-base
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: banking77
type: banking77
config: default
split: train
args: default
metrics:
- type: accuracy
value: 0.9195402298850575
name: Accuracy
banking77-deBERTa-v3-base
This model is a fine-tuned version of microsoft/deberta-v3-base on the banking77 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3281
- Accuracy: 0.9195
- F1 Macro: 0.9170
- Precision Macro: 0.9222
- Recall Macro: 0.9159
- F1 Weighted: 0.9194
- Precision Weighted: 0.9229
- Recall Weighted: 0.9195
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | F1 Weighted | Precision Weighted | Recall Weighted |
|---|---|---|---|---|---|---|---|---|---|---|
| 3.4666 | 1.0 | 501 | 3.1762 | 0.3548 | 0.2479 | 0.3016 | 0.3195 | 0.2774 | 0.3421 | 0.3548 |
| 1.2538 | 2.0 | 1002 | 1.0122 | 0.8141 | 0.7625 | 0.8091 | 0.7795 | 0.7946 | 0.8291 | 0.8141 |
| 0.5576 | 3.0 | 1503 | 0.4823 | 0.8941 | 0.8797 | 0.9012 | 0.8786 | 0.8915 | 0.9021 | 0.8941 |
| 0.3544 | 4.0 | 2004 | 0.3625 | 0.9110 | 0.9090 | 0.9170 | 0.9084 | 0.9108 | 0.9172 | 0.9110 |
| 0.2603 | 5.0 | 2505 | 0.3281 | 0.9195 | 0.9170 | 0.9222 | 0.9159 | 0.9194 | 0.9229 | 0.9195 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1