yangzhao02/llama3-8b-neural_ndcg-beta0.04-tau1.0

<!-- 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-neural_ndcg-beta0.04-tau1.0

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the yangzhao02/ListUltraFeedback dataset. It achieves the following results on the evaluation set:

• —Loss: -0.9909
• —Logps: -445.2650
• —Logits: -2.4577
• —Rank Correct Batch: 37.5935
• —Rank Pair Batch: 56.0
• —Rank Accuracy Batch: 0.6713
• —Ndcg: 0.9904

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-07
• —trainbatchsize: 1
• —evalbatchsize: 2
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 16
• —totaltrainbatch_size: 128
• —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 2.6.0+cu126
• —Datasets 2.19.1
• —Tokenizers 0.20.3