metadata
library_name: peft
license: gemma
base_model: google/gemma-2-9b
tags:
- base_model:adapter:google/gemma-2-9b
- lora
- transformers
model-index:
- name: Gemma_StereoDetect_Model
results: []
Gemma_StereoDetect_Model
This model is a fine-tuned version of google/gemma-2-9b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1845
- Pearson: 0.9725
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson |
|---|---|---|---|---|
| No log | 1.0 | 190 | 0.2128 | 0.9568 |
| No log | 2.0 | 380 | 0.1953 | 0.9564 |
| 0.2912 | 3.0 | 570 | 0.1950 | 0.9694 |
| 0.2912 | 4.0 | 760 | 0.1864 | 0.9713 |
| 0.2912 | 5.0 | 950 | 0.1845 | 0.9725 |
Framework versions
- PEFT 0.17.1
- Transformers 4.56.0
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 4.0.0
- Tokenizers 0.22.0