klcsp/gemma7b-gpt4o_1k_closedqa-fft

<!-- 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. -->

gemma7b-gpt4o1kclosedqa-fft

This model is a fine-tuned version of google/gemma-7b on the llama-duo/synthclosedqadatasetdedup dataset. It achieves the following results on the evaluation set:

• —Loss: 5.6168

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: 0.0003
• —trainbatchsize: 2
• —evalbatchsize: 2
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 32
• —totalevalbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.45.1
• —Pytorch 2.4.1+cu121
• —Datasets 3.0.1
• —Tokenizers 0.20.0