dmis-lab/mistral-7b-olaph

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

mistral-7b-wo-kqa_golden-iter-dpo-step2

This model is a fine-tuned version of Minbyul/mistral-7b-wo-kqa_golden-iter-sft-step1 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

• —Loss: 0.5463
• —Rewards/chosen: -0.5234
• —Rewards/rejected: -1.3980
• —Rewards/accuracies: 0.8125
• —Rewards/margins: 0.8746
• —Logps/rejected: -518.7740
• —Logps/chosen: -233.3091
• —Logits/rejected: -3.7466
• —Logits/chosen: -3.9181

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
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 64
• —totalevalbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.39.0.dev0
• —Pytorch 2.1.2
• —Datasets 2.14.6
• —Tokenizers 0.15.2