zephyr-7b-UC-0

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: 0.1374
• Rewards/chosen: -4.8195
• Rewards/rejected: -11.6393
• Rewards/accuracies: 0.8670
• Rewards/margins: 6.8198
• Logps/rejected: -263.2084
• Logps/chosen: -230.3513
• Logits/rejected: -2.6736
• Logits/chosen: -2.7815

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: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 16
• 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
0.1537	0.62	500	0.1480	-3.7578	-9.9780	0.8564	6.2202	-246.5951	-219.7342	-2.7077	-2.7809

Framework versions

• Transformers 4.36.1
• Pytorch 2.0.1+cu117
• Datasets 2.16.1
• Tokenizers 0.15.0