chchen/Llama-3.1-8B-Instruct-KTO-100

<!-- 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. -->

Llama-3.1-8B-Instruct-KTO-100

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the bctnoncotkto100 dataset. It achieves the following results on the evaluation set:

• —Loss: 0.4997
• —Rewards/chosen: 0.0050
• —Logps/chosen: -17.0744
• —Logits/chosen: -5053702.8571
• —Rewards/rejected: 0.0078
• —Logps/rejected: -23.8299
• —Logits/rejected: -7957526.6667
• —Rewards/margins: -0.0028
• —Kl: 0.0

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: 5e-06
• —trainbatchsize: 2
• —evalbatchsize: 2
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 16
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 10.0

Training results

Framework versions

• —PEFT 0.12.0
• —Transformers 4.46.1
• —Pytorch 2.5.1+cu124
• —Datasets 3.1.0
• —Tokenizers 0.20.3