---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0513HMA4H
  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. -->

# G0513HMA4H

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: 0.1331

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 3.1824        | 0.09  | 10   | 2.8991          |
| 2.6535        | 0.18  | 20   | 2.2337          |
| 1.8658        | 0.27  | 30   | 1.4097          |
| 1.0771        | 0.36  | 40   | 0.6675          |
| 0.4164        | 0.45  | 50   | 0.2215          |
| 0.1854        | 0.54  | 60   | 0.1678          |
| 0.1586        | 0.63  | 70   | 0.1549          |
| 0.153         | 0.73  | 80   | 0.1504          |
| 0.1434        | 0.82  | 90   | 0.1510          |
| 0.1463        | 0.91  | 100  | 0.1488          |
| 0.1487        | 1.0   | 110  | 0.1499          |
| 0.1439        | 1.09  | 120  | 0.1488          |
| 0.1454        | 1.18  | 130  | 0.1481          |
| 0.1456        | 1.27  | 140  | 0.1468          |
| 0.148         | 1.36  | 150  | 0.1459          |
| 0.1426        | 1.45  | 160  | 0.1489          |
| 0.1441        | 1.54  | 170  | 0.1468          |
| 0.1447        | 1.63  | 180  | 0.1448          |
| 0.1456        | 1.72  | 190  | 0.1494          |
| 0.1454        | 1.81  | 200  | 0.1461          |
| 0.1448        | 1.9   | 210  | 0.1451          |
| 0.1454        | 1.99  | 220  | 0.1436          |
| 0.1406        | 2.08  | 230  | 0.1407          |
| 0.136         | 2.18  | 240  | 0.1395          |
| 0.1345        | 2.27  | 250  | 0.1406          |
| 0.1392        | 2.36  | 260  | 0.1384          |
| 0.1356        | 2.45  | 270  | 0.1367          |
| 0.1343        | 2.54  | 280  | 0.1357          |
| 0.1313        | 2.63  | 290  | 0.1344          |
| 0.13          | 2.72  | 300  | 0.1331          |
| 0.1356        | 2.81  | 310  | 0.1330          |
| 0.1338        | 2.9   | 320  | 0.1330          |
| 0.1323        | 2.99  | 330  | 0.1331          |


### Framework versions

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