Increased the number of training epochs. Accuracty and F1 score would benefit from yet further training.
a29c2e4
verified
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-wine
results: []
distilbert-base-uncased-finetuned-wine
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9082
- Accuracy: 0.7314
- F1: 0.7222
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.6559 | 1.0 | 1101 | 1.0917 | 0.6792 | 0.6623 |
| 1.0185 | 2.0 | 2202 | 0.9466 | 0.7214 | 0.7103 |
| 0.8851 | 3.0 | 3303 | 0.9082 | 0.7314 | 0.7222 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1