g3-4b-it-creative-qlora
This model is a fine-tuned version of unsloth/gemma-3-4b-it on the ToastyPigeon/some-rp-extended, the allura-org/inkstructmix-v0.2.1a-system-reasoning-separated, the ToastyPigeon/unalign-v2, the ToastyPigeon/unalign-v2, the ToastyPigeon/synth-rp, the PocketDoc/Floyd-Text-Adventures and the ToastyPigeon/new-story-dataset datasets. It achieves the following results on the evaluation set:
- Loss: 2.7299
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: 3
- eval_batch_size: 3
- seed: 69
- gradient_accumulation_steps: 6
- total_train_batch_size: 18
- 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: cosine
- lr_scheduler_warmup_steps: 8
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5251 | 0.0034 | 1 | 4.6010 |
| 3.9623 | 0.1995 | 58 | 3.7722 |
| 2.8668 | 0.3991 | 116 | 3.2242 |
| 2.8385 | 0.5986 | 174 | 2.8821 |
| 2.7389 | 0.7982 | 232 | 2.7648 |
| 2.5117 | 0.9977 | 290 | 2.7299 |
Framework versions
- PEFT 0.15.0
- Transformers 4.51.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support