---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0428HMA11
  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. -->

# G0428HMA11

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: 0.1108

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.7848        | 0.09  | 10   | 2.0338          |
| 1.5344        | 0.18  | 20   | 0.9449          |
| 0.5532        | 0.27  | 30   | 0.2231          |
| 0.1757        | 0.36  | 40   | 0.1577          |
| 0.151         | 0.45  | 50   | 0.1493          |
| 0.149         | 0.54  | 60   | 0.1492          |
| 0.1476        | 0.63  | 70   | 0.1472          |
| 0.1488        | 0.73  | 80   | 0.1479          |
| 0.1416        | 0.82  | 90   | 0.1485          |
| 0.1452        | 0.91  | 100  | 0.1475          |
| 0.1484        | 1.0   | 110  | 0.1486          |
| 0.1431        | 1.09  | 120  | 0.1476          |
| 0.1447        | 1.18  | 130  | 0.1481          |
| 0.1451        | 1.27  | 140  | 0.1469          |
| 0.1474        | 1.36  | 150  | 0.1455          |
| 0.1417        | 1.45  | 160  | 0.1463          |
| 0.1428        | 1.54  | 170  | 0.1426          |
| 0.1406        | 1.63  | 180  | 0.1370          |
| 0.1392        | 1.72  | 190  | 0.1435          |
| 0.1355        | 1.81  | 200  | 0.1343          |
| 0.1343        | 1.9   | 210  | 0.1318          |
| 0.1297        | 1.99  | 220  | 0.1237          |
| 0.1205        | 2.08  | 230  | 0.1239          |
| 0.1161        | 2.18  | 240  | 0.1210          |
| 0.1139        | 2.27  | 250  | 0.1177          |
| 0.1159        | 2.36  | 260  | 0.1159          |
| 0.1165        | 2.45  | 270  | 0.1150          |
| 0.111         | 2.54  | 280  | 0.1146          |
| 0.1049        | 2.63  | 290  | 0.1129          |
| 0.1055        | 2.72  | 300  | 0.1116          |
| 0.1108        | 2.81  | 310  | 0.1112          |
| 0.1117        | 2.9   | 320  | 0.1109          |
| 0.1116        | 2.99  | 330  | 0.1108          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1