gemma3-27b-finetune

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: 0.1649

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: 8
  • 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
2.3649 0.1882 50 0.2670
2.0987 0.3765 100 0.2411
1.7172 0.5647 150 0.2212
1.6842 0.7529 200 0.2054
1.5273 0.9412 250 0.1960
1.3487 1.1280 300 0.1920
1.3797 1.3162 350 0.1861
1.3611 1.5045 400 0.1791
1.2523 1.6927 450 0.1838
1.2999 1.8809 500 0.1751
1.079 2.0678 550 0.1729
1.189 2.2560 600 0.1721
1.0816 2.4442 650 0.1699
1.0669 2.6325 700 0.1694
0.9985 2.8207 750 0.1649

Framework versions

  • PEFT 0.17.1
  • Transformers 4.56.2
  • Pytorch 2.8.0+cu128
  • Datasets 4.1.1
  • Tokenizers 0.22.1
Downloads last month
1
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for c-mohanraj/gemma3-27b-finetune

Adapter
(35)
this model