sam-paech/Quill-v0.9

<!-- 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-2-9b-it-gutenberg3

This model is a fine-tuned version of sam-paech/gutenberg3-orpo-exp02 on the sam-paech/gutenberg3-generalfiction-scifi-fantasy-romance-adventure-dpo dataset. It achieves the following results on the evaluation set:

• —Loss: 21.6407
• —Rewards/chosen: -27.5382
• —Rewards/rejected: -10.2163
• —Rewards/accuracies: 0.0
• —Rewards/margins: -17.3219
• —Logps/rejected: -1.0216
• —Logps/chosen: -2.7538

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-08
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 5
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 10
• —totalevalbatch_size: 5
• —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 4.45.2
• —Pytorch 2.2.0+cu121
• —Datasets 3.0.1
• —Tokenizers 0.20.1