EtashGuha/gemma-simpo-reproductions

<!-- 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. -->

gemma-simpo-reproductions

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

• —Loss: 3.0558
• —Rewards/chosen: -17.0597
• —Rewards/rejected: -21.9498
• —Rewards/accuracies: 0.7584
• —Rewards/margins: 4.8901
• —Logps/rejected: -2.1950
• —Logps/chosen: -1.7060
• —Logits/rejected: -18.1137
• —Logits/chosen: -18.2041

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
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —gradientaccumulationsteps: 32
• —totaltrainbatch_size: 128
• —totalevalbatch_size: 4
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 1.0

Training results

Framework versions

• —Transformers 4.45.2
• —Pytorch 2.2.0+cu121
• —Datasets 3.0.0
• —Tokenizers 0.20.1