llama-3.1-8b-instruct-agg-judge

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the simonycl/llama3.1-ultrafeedback-annotate-judge-5 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6230
• Rewards/chosen: -3.4404
• Rewards/rejected: -3.9038
• Rewards/accuracies: 0.6371
• Rewards/margins: 0.4633
• Logps/rejected: -664.0687
• Logps/chosen: -606.6761
• Logits/rejected: -3.0895
• Logits/chosen: -3.2065

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

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.4978	0.8442	400	0.6230	-3.4404	-3.9038	0.6371	0.4633	-664.0687	-606.6761	-3.0895	-3.2065

Framework versions

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