llama3-8b-neural_ndcg-beta0.06-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: -412.9110
• Logits: -2.3852
• Rank Correct Batch: 37.1406
• Rank Pair Batch: 56.0
• Rank Accuracy Batch: 0.6632
• Ndcg: 0.9901

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
• train_batch_size: 1
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Logps	Logits	Rank Correct Batch	Rank Pair Batch	Rank Accuracy Batch	Ndcg
-0.9901	0.2672	125	-0.9892	-389.0790	-2.1794	35.9375	56.0	0.6417	0.9882
-0.9914	0.5344	250	-0.9905	-405.1916	-2.3368	36.8594	56.0	0.6582	0.9897
-0.9915	0.8016	375	-0.9909	-410.5014	-2.3648	36.8438	56.0	0.6579	0.9900

Framework versions

• Transformers 4.45.1
• Pytorch 2.6.0+cu126
• Datasets 2.19.1
• Tokenizers 0.20.3