single-gpu-27b

This model is a fine-tuned version of google/gemma-3-27b-it on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1766

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.6974	0.7529	200	0.2047
1.3425	1.5045	400	0.1809
1.0936	2.2560	600	0.1766

Framework versions

• PEFT 0.17.0
• Transformers 4.56.1
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.22.0