mistral-7b-instruct-v0.2-rsimpo-full

<!-- 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-instruct-v0.2-rsimpo-full

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the princeton-nlp/mistral-instruct-ultrafeedback dataset. It achieves the following results on the evaluation set:

• Loss: 0.7976
• Rewards/chosen: -1.2291
• Rewards/rejected: -1.3244
• Rewards/accuracies: 0.5507
• Rewards/margins: 0.0955
• Agreement Weights/mean: 0.9696
• Agreement Weights/std: 0.0182
• Eta/annotator 0: 0.9730

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: 2
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 256
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Framework versions

• Transformers 4.46.3
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.20.3