fine-tune-gemma-7b
This model is a fine-tuned version of google/gemma-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5002
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- training_steps: 150
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0244 | 10 | 1.7039 |
| No log | 0.0487 | 20 | 1.5506 |
| 1.6989 | 0.0731 | 30 | 1.5446 |
| 1.6989 | 0.0975 | 40 | 1.5375 |
| 1.5135 | 0.1219 | 50 | 1.5419 |
| 1.5135 | 0.1462 | 60 | 1.5533 |
| 1.5135 | 0.1706 | 70 | 1.5362 |
| 1.4875 | 0.1950 | 80 | 1.5241 |
| 1.4875 | 0.2193 | 90 | 1.5273 |
| 1.516 | 0.2437 | 100 | 1.5218 |
| 1.516 | 0.2681 | 110 | 1.5121 |
| 1.516 | 0.2924 | 120 | 1.5068 |
| 1.5041 | 0.3168 | 130 | 1.5059 |
| 1.5041 | 0.3412 | 140 | 1.5048 |
| 1.4515 | 0.3656 | 150 | 1.5002 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.0.0+nv23.05
- Datasets 2.15.0
- Tokenizers 0.19.1
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for kshitij1188/fine-tune-gemma-7b
Base model
google/gemma-7b