---
license: gemma
base_model: google/gemma-2b-it
tags:
- generated_from_trainer
model-index:
- name: logs
  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. -->

# logs

This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6511

## 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: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.1035        | 0.08  | 112  | 3.1213          |
| 3.0698        | 0.17  | 224  | 3.0171          |
| 3.0451        | 0.25  | 336  | 2.9717          |
| 2.8939        | 0.33  | 448  | 2.9336          |
| 2.8892        | 0.42  | 560  | 2.9099          |
| 2.8566        | 0.5   | 672  | 2.8757          |
| 2.8654        | 0.58  | 784  | 2.8486          |
| 2.8261        | 0.67  | 896  | 2.8291          |
| 2.8868        | 0.75  | 1008 | 2.7998          |
| 2.819         | 0.84  | 1120 | 2.7781          |
| 2.8064        | 0.92  | 1232 | 2.7543          |
| 2.761         | 1.0   | 1344 | 2.7338          |
| 2.3883        | 1.09  | 1456 | 2.7416          |
| 2.3511        | 1.17  | 1568 | 2.7239          |
| 2.3174        | 1.25  | 1680 | 2.7140          |
| 2.3234        | 1.34  | 1792 | 2.7004          |
| 2.3364        | 1.42  | 1904 | 2.6826          |
| 2.3079        | 1.5   | 2016 | 2.6718          |
| 2.2965        | 1.59  | 2128 | 2.6649          |
| 2.2233        | 1.67  | 2240 | 2.6626          |
| 2.2199        | 1.75  | 2352 | 2.6590          |
| 2.3126        | 1.84  | 2464 | 2.6526          |
| 2.2602        | 1.92  | 2576 | 2.6513          |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.0.0+cu117
- Datasets 2.16.0
- Tokenizers 0.15.0