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
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 5
• gradient_accumulation_steps: 2
• total_train_batch_size: 10
• total_eval_batch_size: 5
• 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 4.45.2
• Pytorch 2.2.0+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1