simpo-train-large-wrong

<!-- 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. -->

simpo-train-large-wrong

This model is a fine-tuned version of google/gemma-2-9b-it on the jz666/gemma2-ultrafeedback-ppl-split dataset. It achieves the following results on the evaluation set:

• Loss: 4.5115
• Rewards/chosen: -5.4495
• Rewards/rejected: -6.3534
• Rewards/accuracies: 0.5963
• Rewards/margins: 0.9039
• Logps/rejected: -0.6353
• Logps/chosen: -0.5450
• Logits/rejected: -6.0010
• Logits/chosen: -6.2132

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: 8e-07
• train_batch_size: 2
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Framework versions

• Transformers 4.44.2
• Pytorch 2.7.0+cu128
• Datasets 2.18.0
• Tokenizers 0.19.1