This model is a fine-tuned version of [Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT] on the dataset HuggingFaceH4/ultrafeedback_binarized with the DPO trainer. It is part of the WeniGPT project for Weni.
It achieves the following results on the evaluation set:
{'eval_loss': 1.9277071952819824, 'eval_runtime': 94.1066, 'eval_samples_per_second': 2.125, 'eval_steps_per_second': 0.531, 'eval_rewards/chosen': 18.78862190246582, 'eval_rewards/rejected': 13.151841163635254, 'eval_rewards/accuracies': 0.5350000262260437, 'eval_rewards/margins': 5.63677978515625, 'eval_logps/rejected': -329.4024658203125, 'eval_logps/chosen': -334.51287841796875, 'eval_logits/rejected': -2.746166467666626, 'eval_logits/chosen': -2.7368459701538086, 'epoch': 7.96}
Intended uses & limitations
This model has not been trained to avoid specific intructions.
Training procedure
Finetuning was done on the model Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT with the following prompt:
