llama-duo/llama3-8b-coding-gpt4o-100k

<!-- 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. -->

llama3-8b-coding-gpt4o-100k

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the llama-duo/synthcodingdataset_dedup dataset. It achieves the following results on the evaluation set:

• —Loss: 1.5174

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: 0.002
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 128
• —totalevalbatch_size: 64
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 10

Training results

Framework versions

• —PEFT 0.12.0
• —Transformers 4.44.0
• —Pytorch 2.2.0+cu121
• —Datasets 2.20.0
• —Tokenizers 0.19.1