---
base_model: google/gemma-2b
library_name: peft
license: gemma
metrics:
- accuracy
tags:
- trl
- reward-trainer
- generated_from_trainer
model-index:
- name: run
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# run

This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4823
- Accuracy: 0.75

## 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: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.6406        | 0.1773 | 25   | 0.5870          | 0.6806   |
| 0.5156        | 0.3546 | 50   | 0.5284          | 0.7292   |
| 0.6289        | 0.5319 | 75   | 0.4963          | 0.7639   |
| 0.4766        | 0.7092 | 100  | 0.4715          | 0.7639   |
| 0.3594        | 0.8865 | 125  | 0.4581          | 0.7431   |
| 0.4082        | 1.0638 | 150  | 0.4663          | 0.75     |
| 0.3262        | 1.2411 | 175  | 0.4452          | 0.7569   |
| 0.3594        | 1.4184 | 200  | 0.4306          | 0.75     |
| 0.4033        | 1.5957 | 225  | 0.4411          | 0.7639   |
| 0.3789        | 1.7730 | 250  | 0.4331          | 0.7708   |
| 0.293         | 1.9504 | 275  | 0.4652          | 0.7569   |
| 0.3555        | 2.1277 | 300  | 0.4356          | 0.7569   |
| 0.4375        | 2.3050 | 325  | 0.4415          | 0.7569   |
| 0.377         | 2.4823 | 350  | 0.4525          | 0.7292   |
| 0.3633        | 2.6596 | 375  | 0.4505          | 0.7708   |
| 0.2461        | 2.8369 | 400  | 0.4581          | 0.7431   |
| 0.3115        | 3.0142 | 425  | 0.4499          | 0.7361   |
| 0.3896        | 3.1915 | 450  | 0.4421          | 0.75     |
| 0.373         | 3.3688 | 475  | 0.4602          | 0.7569   |
| 0.2415        | 3.5461 | 500  | 0.4537          | 0.7639   |
| 0.334         | 3.7234 | 525  | 0.4650          | 0.7569   |
| 0.3662        | 3.9007 | 550  | 0.4750          | 0.7569   |
| 0.3232        | 4.0780 | 575  | 0.4778          | 0.7361   |
| 0.3369        | 4.2553 | 600  | 0.4709          | 0.75     |
| 0.5273        | 4.4326 | 625  | 0.4780          | 0.75     |
| 0.3623        | 4.6099 | 650  | 0.4839          | 0.75     |
| 0.2148        | 4.7872 | 675  | 0.4855          | 0.7431   |
| 0.3604        | 4.9645 | 700  | 0.4823          | 0.75     |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1