chatbot-arena-20240726

This model is a fine-tuned version of unsloth/gemma-2-9b-it-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9601
• Acc: 0.5312
• Log Loss: 0.9601

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 30
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Acc	Log Loss
1.1335	0.2195	100	1.0572	0.4740	1.0572
1.0353	0.4391	200	1.1517	0.4740	1.1517
0.9498	0.6586	300	0.9858	0.5182	0.9858
0.9488	0.8782	400	0.9601	0.5312	0.9601

Framework versions

• PEFT 0.11.1
• Transformers 4.43.3
• Pytorch 2.1.1+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1