metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned
results: []
distilbert-base-uncased-finetuned
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: 1.0396
- Accuracy: 0.9000
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.34 | 1.0 | 10500 | 0.3049 | 0.8909 |
| 0.2648 | 2.0 | 21000 | 0.3869 | 0.8980 |
| 0.203 | 3.0 | 31500 | 0.4494 | 0.8969 |
| 0.1493 | 4.0 | 42000 | 0.5825 | 0.8958 |
| 0.1103 | 5.0 | 52500 | 0.6355 | 0.8983 |
| 0.0642 | 6.0 | 63000 | 0.7923 | 0.8981 |
| 0.0593 | 7.0 | 73500 | 0.8063 | 0.8969 |
| 0.0274 | 8.0 | 84000 | 0.8779 | 0.8997 |
| 0.0142 | 9.0 | 94500 | 0.9841 | 0.8993 |
| 0.0137 | 10.0 | 105000 | 1.0396 | 0.9000 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3