---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0513HMA6H
  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. -->

# G0513HMA6H

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: 0.1240

## 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: 80
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.161         | 0.09  | 10   | 2.8226          |
| 2.4808        | 0.18  | 20   | 1.9257          |
| 1.4989        | 0.27  | 30   | 0.9749          |
| 0.6093        | 0.36  | 40   | 0.2572          |
| 0.1925        | 0.45  | 50   | 0.1591          |
| 0.1558        | 0.54  | 60   | 0.1523          |
| 0.1517        | 0.63  | 70   | 0.1497          |
| 0.1503        | 0.73  | 80   | 0.1487          |
| 0.1422        | 0.82  | 90   | 0.1499          |
| 0.1459        | 0.91  | 100  | 0.1487          |
| 0.1494        | 1.0   | 110  | 0.1495          |
| 0.1438        | 1.09  | 120  | 0.1499          |
| 0.1458        | 1.18  | 130  | 0.1472          |
| 0.1465        | 1.27  | 140  | 0.1463          |
| 0.1483        | 1.36  | 150  | 0.1464          |
| 0.1426        | 1.45  | 160  | 0.1480          |
| 0.1433        | 1.54  | 170  | 0.1450          |
| 0.1443        | 1.63  | 180  | 0.1440          |
| 0.1455        | 1.72  | 190  | 0.1495          |
| 0.1437        | 1.81  | 200  | 0.1439          |
| 0.1433        | 1.9   | 210  | 0.1398          |
| 0.1408        | 1.99  | 220  | 0.1387          |
| 0.1348        | 2.08  | 230  | 0.1340          |
| 0.1311        | 2.18  | 240  | 0.1334          |
| 0.1303        | 2.27  | 250  | 0.1297          |
| 0.1319        | 2.36  | 260  | 0.1285          |
| 0.1297        | 2.45  | 270  | 0.1291          |
| 0.129         | 2.54  | 280  | 0.1270          |
| 0.1247        | 2.63  | 290  | 0.1252          |
| 0.1251        | 2.72  | 300  | 0.1242          |
| 0.1299        | 2.81  | 310  | 0.1239          |
| 0.1271        | 2.9   | 320  | 0.1240          |
| 0.1269        | 2.99  | 330  | 0.1240          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0