annaluiza/codellama-instruct-mojo

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

codellama-instruct-mojo

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

• —Loss: 1.0479

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
• —trainbatchsize: 2
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 4
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: constant
• —lrschedulerwarmup_ratio: 0.03
• —num_epochs: 5
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —PEFT 0.12.1.dev0
• —Transformers 4.41.2
• —Pytorch 2.3.1+cu121
• —Datasets 2.19.2
• —Tokenizers 0.19.1