llama-3.1-8b-instruct-single-judge

<!-- 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-single-judge

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the simonycl/llama3.1-ultrafeedback-annotate-single-judge dataset. It achieves the following results on the evaluation set:

• Loss: 0.6271
• Rewards/chosen: -2.1270
• Rewards/rejected: -2.3796
• Rewards/accuracies: 0.6351
• Rewards/margins: 0.2526
• Logps/rejected: -511.8614
• Logps/chosen: -475.5936
• Logits/rejected: -2.7554
• Logits/chosen: -2.8606

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: 2
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• 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

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1