metadata
library_name: transformers
license: gemma
base_model: google/gemma-3-1b-it
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: gemma-3-1b-it_MED_NLI
results: []
gemma-3-1b-it_MED_NLI
This model is a fine-tuned version of google/gemma-3-1b-it on the zero_shot dataset. It achieves the following results on the evaluation set:
- Loss: 0.0177
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: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0331 | 0.1176 | 1000 | 0.0379 |
| 0.0299 | 0.2352 | 2000 | 0.0262 |
| 0.0251 | 0.3528 | 3000 | 0.0284 |
| 0.0213 | 0.4704 | 4000 | 0.0252 |
| 0.0264 | 0.5880 | 5000 | 0.0222 |
| 0.0183 | 0.7056 | 6000 | 0.0191 |
| 0.0171 | 0.8232 | 7000 | 0.0179 |
| 0.0185 | 0.9408 | 8000 | 0.0177 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.0