hippocrate-lora-training-2024-2
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7579
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 300
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.817 | 0.5030 | 2000 | 0.8639 |
0.8933 | 1.0060 | 4000 | 0.7860 |
0.9076 | 1.5091 | 6000 | 0.7668 |
0.5954 | 2.0121 | 8000 | 0.7627 |
0.5311 | 2.5151 | 10000 | 0.7580 |
0.5863 | 3.0181 | 12000 | 0.7542 |
0.595 | 3.5211 | 14000 | 0.7579 |
Framework versions
- PEFT 0.12.0
- Transformers 4.45.0
- Pytorch 2.3.1+cu121
- Datasets 2.14.5
- Tokenizers 0.20.0
- Downloads last month
- 7
Model tree for DaijobuAI/hippocrate-lora-training-2024-2
Base model
meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct