codellama-code-completion-mojo

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

• Loss: 1.0127

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: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.77	1.0	50	1.2786
1.0433	2.0	100	1.0009
0.6979	3.0	150	0.9540
0.5164	4.0	200	1.0127

Framework versions

• PEFT 0.11.2.dev0
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1