zephyr-7b-llm-science-exam
This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-alpha on the llm-science-exam dataset. It achieves the following results on the evaluation set:
- Loss: 1.3920
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8861 | 0.24 | 100 | 1.6360 |
| 1.6563 | 0.48 | 200 | 1.4566 |
| 1.5457 | 0.71 | 300 | 1.3980 |
| 1.4945 | 0.95 | 400 | 1.3920 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.0