metadata
license: apache-2.0
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
EvolCodeLlama-3.1-8B-Instruct
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct using QLoRA (4-bit precision) on the mlabonne/Evol-Instruct-Python-1k dataset. It achieves the following results on the evaluation set:
- Loss: 0.4057
Training:
It was trained on an A40 for more than 1 hour using Axolotl.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- 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: 100
- num_epochs: 3
The lose curves are as:
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1