working

This model is a fine-tuned version of unsloth/gemma-2-9b-it-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3774
• Acc: 0.35
• Log Loss: 1.3774

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 20
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Acc	Log Loss
3.0058	1.0	10	1.8528	0.4	1.8527
2.9092	2.0	20	1.7207	0.45	1.7206
2.6161	3.0	30	1.5368	0.4	1.5367
2.3656	4.0	40	1.4192	0.35	1.4191
2.1831	5.0	50	1.3774	0.35	1.3774

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0