Llama-2-code-python

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0589

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: 2e-05
• train_batch_size: 6
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.612	0.3183	30	1.6686
1.4094	0.6366	60	1.4388
1.2172	0.9549	90	1.2583
1.0647	1.2732	120	1.1357
1.0144	1.5915	150	1.0771
1.0622	1.9098	180	1.0643
1.045	2.2281	210	1.0599
1.0739	2.5464	240	1.0588
1.0306	2.8647	270	1.0589

Framework versions

• PEFT 0.11.1
• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1