outputs
This model is a fine-tuned version of google/gemma-2-2b-it on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0013
- Model Preparation Time: 0.0212
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
|---|---|---|---|---|
| 1.1766 | 0.2002 | 390 | 1.2098 | 0.0212 |
| 1.2063 | 0.4003 | 780 | 1.1293 | 0.0212 |
| 1.063 | 0.6005 | 1170 | 1.0843 | 0.0212 |
| 1.0623 | 0.8006 | 1560 | 1.0545 | 0.0212 |
| 0.9728 | 1.0008 | 1950 | 1.0336 | 0.0212 |
| 0.9455 | 1.2009 | 2340 | 1.0228 | 0.0212 |
| 1.0184 | 1.4011 | 2730 | 1.0115 | 0.0212 |
| 0.9698 | 1.6012 | 3120 | 1.0042 | 0.0212 |
| 0.935 | 1.8014 | 3510 | 1.0013 | 0.0212 |
Framework versions
- PEFT 0.13.1
- Transformers 4.45.2
- Pytorch 2.2.1
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 2