---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0515HMA9H
  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. -->

# G0515HMA9H

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: 0.1309

## 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.2171        | 0.09  | 10   | 2.8982          |
| 2.6882        | 0.18  | 20   | 2.2647          |
| 1.8484        | 0.27  | 30   | 1.3286          |
| 0.9274        | 0.36  | 40   | 0.4311          |
| 0.2813        | 0.45  | 50   | 0.1829          |
| 0.1669        | 0.54  | 60   | 0.1548          |
| 0.153         | 0.63  | 70   | 0.1492          |
| 0.1515        | 0.73  | 80   | 0.1494          |
| 0.1428        | 0.82  | 90   | 0.1492          |
| 0.1454        | 0.91  | 100  | 0.1488          |
| 0.1497        | 1.0   | 110  | 0.1486          |
| 0.1434        | 1.09  | 120  | 0.1489          |
| 0.145         | 1.18  | 130  | 0.1479          |
| 0.1455        | 1.27  | 140  | 0.1470          |
| 0.1485        | 1.36  | 150  | 0.1464          |
| 0.1421        | 1.45  | 160  | 0.1494          |
| 0.1446        | 1.54  | 170  | 0.1463          |
| 0.1448        | 1.63  | 180  | 0.1449          |
| 0.1462        | 1.72  | 190  | 0.1491          |
| 0.1455        | 1.81  | 200  | 0.1469          |
| 0.1471        | 1.9   | 210  | 0.1459          |
| 0.146         | 1.99  | 220  | 0.1460          |
| 0.1423        | 2.08  | 230  | 0.1442          |
| 0.136         | 2.18  | 240  | 0.1406          |
| 0.1376        | 2.27  | 250  | 0.1414          |
| 0.1378        | 2.36  | 260  | 0.1390          |
| 0.1353        | 2.45  | 270  | 0.1366          |
| 0.1322        | 2.54  | 280  | 0.1349          |
| 0.13          | 2.63  | 290  | 0.1321          |
| 0.1292        | 2.72  | 300  | 0.1310          |
| 0.1317        | 2.81  | 310  | 0.1307          |
| 0.1315        | 2.9   | 320  | 0.1309          |
| 0.1299        | 2.99  | 330  | 0.1309          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1