Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string
gemma_outreach_first_level12
This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9830
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: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9238 | 1.0 | 32 | 2.1867 |
| 1.488 | 2.0 | 64 | 2.0711 |
| 1.3557 | 3.0 | 96 | 2.0691 |
| 1.1916 | 4.0 | 128 | 1.9726 |
| 1.1594 | 5.0 | 160 | 1.9830 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for KirubaLS/gemma_outreach_first_level12
Base model
google/gemma-2b