distilbert-yahoo
This model is a fine-tuned version of distilbert-base-uncased on the yahoo_answers_topics dataset. It achieves the following results on the evaluation set:
- Loss: 0.9117
- Accuracy: 0.7124
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: 5e-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
- training_steps: 30000
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.0424 | 0.03 | 5000 | 1.0730 | 0.6706 |
1.0143 | 0.06 | 10000 | 1.0225 | 0.6793 |
0.9683 | 0.09 | 15000 | 0.9732 | 0.6950 |
0.8925 | 0.11 | 20000 | 0.9442 | 0.7038 |
0.9407 | 0.14 | 25000 | 0.9212 | 0.7090 |
0.9463 | 0.17 | 30000 | 0.9117 | 0.7124 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 13
Finetuned from
Dataset used to train Prezily/distilbert-yahoo
Evaluation results
- Accuracy on yahoo_answers_topicstest set self-reported0.712