zephyr-7b-dpo-full

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4309
• Rewards/chosen: 1.2748
• Rewards/rejected: -0.1475
• Rewards/accuracies: 0.7460
• Rewards/margins: 1.4222
• Logps/rejected: -313.7914
• Logps/chosen: -342.4030
• Logits/rejected: -1.3735
• Logits/chosen: -1.3773
• Use Label: 5751.2222
• Pred Label: 2268.7778

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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• 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	Use Label	Pred Label
0.4503	1.0	955	0.4309	1.2748	-0.1475	0.7460	1.4222	-313.7914	-342.4030	-1.3735	-1.3773	5590.2222	2177.7778

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.1+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1