slavamarcin/saiga_llama3_8b_Qdora_4bit_purpose

<!-- 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. -->

saigallama38b-qdora-4bit_purpose

This model is a fine-tuned version of IlyaGusev/saiga_llama3_8b on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 0.9495

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: 1e-05
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 2
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 1

Training results

Framework versions

• —PEFT 0.11.2.dev0
• —Transformers 4.38.2
• —Pytorch 2.3.0+cu121
• —Datasets 2.19.1
• —Tokenizers 0.15.2