alignment-handbook/mistral-7b-sft-constitutional-ai

<!-- 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-sft-constitutional-ai

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/cai-conversation-harmless and the HuggingFaceH4/ultrachat_200k datasets. It achieves the following results on the evaluation set:

• —Loss: 0.9344

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: 2e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 256
• —totalevalbatch_size: 64
• —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 4.36.2
• —Pytorch 2.1.2+cu121
• —Datasets 2.14.6
• —Tokenizers 0.15.1