llama-3-8b-instruct-armorm-judge

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the simonycl/Llama-3-8B-Instruct-ultrafeedback-armorm-annotate dataset. It achieves the following results on the evaluation set:

• Loss: 0.4834
• Rewards/chosen: -2.9573
• Rewards/rejected: -4.4536
• Rewards/accuracies: 0.7760
• Rewards/margins: 1.4963
• Logps/rejected: -597.7948
• Logps/chosen: -448.3257
• Logits/rejected: -0.6484
• Logits/chosen: -0.6989

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: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 32
• total_train_batch_size: 128
• total_eval_batch_size: 4
• 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
0.5062	0.8529	400	0.4834	-2.9573	-4.4536	0.7760	1.4963	-597.7948	-448.3257	-0.6484	-0.6989

Framework versions

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