---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0428HMA26
  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. -->

# G0428HMA26

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: 0.1123

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.48          | 0.09  | 10   | 1.3998          |
| 0.7559        | 0.18  | 20   | 0.2139          |
| 0.1722        | 0.27  | 30   | 0.1588          |
| 0.1516        | 0.36  | 40   | 0.1510          |
| 0.1466        | 0.45  | 50   | 0.1478          |
| 0.1473        | 0.54  | 60   | 0.1488          |
| 0.148         | 0.63  | 70   | 0.1479          |
| 0.1505        | 0.73  | 80   | 0.1491          |
| 0.1423        | 0.82  | 90   | 0.1494          |
| 0.1466        | 0.91  | 100  | 0.1490          |
| 0.1486        | 1.0   | 110  | 0.1487          |
| 0.1603        | 1.09  | 120  | 0.1975          |
| 0.298         | 1.18  | 130  | 0.6268          |
| 0.362         | 1.27  | 140  | 0.1486          |
| 0.1493        | 1.36  | 150  | 0.1485          |
| 0.1402        | 1.45  | 160  | 0.1469          |
| 0.1442        | 1.54  | 170  | 0.1431          |
| 0.1346        | 1.63  | 180  | 0.1396          |
| 0.1405        | 1.72  | 190  | 0.1378          |
| 0.132         | 1.81  | 200  | 0.1358          |
| 0.1309        | 1.9   | 210  | 0.1311          |
| 0.1266        | 1.99  | 220  | 0.1243          |
| 0.119         | 2.08  | 230  | 0.1219          |
| 0.1183        | 2.18  | 240  | 0.1208          |
| 0.114         | 2.27  | 250  | 0.1188          |
| 0.1129        | 2.36  | 260  | 0.1212          |
| 0.1152        | 2.45  | 270  | 0.1179          |
| 0.105         | 2.54  | 280  | 0.1157          |
| 0.106         | 2.63  | 290  | 0.1125          |
| 0.1033        | 2.72  | 300  | 0.1127          |
| 0.1074        | 2.81  | 310  | 0.1123          |
| 0.1098        | 2.9   | 320  | 0.1123          |
| 0.1091        | 2.99  | 330  | 0.1123          |


### Framework versions

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