metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
model-index:
- name: distilbert-base-uncased_reveal_ft_0920
results: []
distilbert-base-uncased_reveal_ft_0920
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2843
- Accuracy: 0.8937
- F1: 0.8779
- Precision: 0.6909
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
|---|---|---|---|---|---|---|
| 0.2967 | 1.0 | 341 | 0.3203 | 0.8975 | 0.8490 | 0.4487 |
| 0.2715 | 2.0 | 682 | 0.2838 | 0.8975 | 0.8492 | 0.6988 |
| 0.2388 | 3.0 | 1023 | 0.2808 | 0.9002 | 0.8733 | 0.7302 |
| 0.2157 | 4.0 | 1364 | 0.2843 | 0.8937 | 0.8779 | 0.6909 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.2.2
- Datasets 2.16.1
- Tokenizers 0.13.3