metadata
library_name: peft
license: gemma
base_model: google/gemma-3-4b-it
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: amharic_gemma_sum_lora_normalized
results: []
amharic_gemma_sum_lora_normalized
This model is a fine-tuned version of google/gemma-3-4b-it on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2718
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4595 | 0.4913 | 400 | 1.4549 |
| 1.3466 | 0.9826 | 800 | 1.3604 |
| 1.2949 | 1.4729 | 1200 | 1.3128 |
| 1.2699 | 1.9642 | 1600 | 1.2859 |
| 1.224 | 2.4544 | 2000 | 1.2747 |
| 1.2466 | 2.9457 | 2400 | 1.2718 |
Framework versions
- PEFT 0.14.1.dev0
- Transformers 4.57.1
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.22.1