ALBADDAWI/ft-HuggingFaceH4-zephyr-7b-beta-qlora-v3

<!-- 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. -->

ft-HuggingFaceH4-zephyr-7b-beta-qlora-v3

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset. It achieves the following results on the evaluation set:

• —Loss: 3.2700

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: 0.0005
• —trainbatchsize: 16
• —evalbatchsize: 16
• —seed: 42
• —gradientaccumulationsteps: 5
• —totaltrainbatch_size: 80
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: constant
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 50
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —PEFT 0.9.0
• —Transformers 4.38.2
• —Pytorch 2.2.2+cu121
• —Datasets 2.18.0
• —Tokenizers 0.15.2