zephyr-ds

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3439
• Rewards/chosen: -1.1633
• Rewards/rejected: -3.5290
• Rewards/accuracies: 0.7420
• Rewards/margins: 2.3657
• Logps/rejected: -294.5901
• Logps/chosen: -295.8908
• Logits/rejected: -2.7390
• Logits/chosen: -2.7421
• Use Label: 9180.7998
• Pred Label: 6851.2002

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-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 16
• 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
0.333	1.0	955	0.3439	-1.1633	-3.5290	0.7420	2.3657	-294.5901	-295.8908	-2.7390	-2.7421	8950.7998	6581.2002

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.1+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1