news_classification
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the 20 News Group dataset. It achieves the following results on the evaluation set:
- Loss: 1.4061
- Balanced Accuracy: 0.5117
- Accuracy: 0.53
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: 0.0001
- 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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy | Accuracy |
---|---|---|---|---|---|
2.4925 | 1.0 | 25 | 1.7238 | 0.4608 | 0.475 |
1.2815 | 2.0 | 50 | 1.4959 | 0.5185 | 0.535 |
0.7958 | 3.0 | 75 | 1.4061 | 0.5117 | 0.53 |
Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for bakanaims/llama-3-8b-20-news-group
Base model
meta-llama/Meta-Llama-3-8B