metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: toy
results: []
toy
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: 0.2041
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: 2
- eval_batch_size: 2
- 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 |
|---|---|---|---|
| 0.3125 | 1.0 | 923 | 0.2391 |
| 0.3287 | 2.0 | 1846 | 0.2306 |
| 0.1138 | 3.0 | 2769 | 0.1806 |
| 0.1219 | 4.0 | 3692 | 0.1858 |
| 0.0962 | 5.0 | 4615 | 0.1922 |
| 0.0526 | 6.0 | 5538 | 0.1963 |
| 0.0248 | 7.0 | 6461 | 0.1930 |
| 0.0004 | 8.0 | 7384 | 0.2153 |
| 0.0136 | 9.0 | 8307 | 0.2037 |
| 0.0002 | 10.0 | 9230 | 0.2041 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0
- Datasets 1.18.3
- Tokenizers 0.11.6