---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0521HMA26H7
  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. -->

# G0521HMA26H7

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: 0.0990

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7533        | 0.09  | 10   | 1.3592          |
| 0.9791        | 0.18  | 20   | 0.4708          |
| 0.2914        | 0.27  | 30   | 0.1584          |
| 0.1518        | 0.36  | 40   | 0.1514          |
| 0.1476        | 0.45  | 50   | 0.1479          |
| 0.1477        | 0.54  | 60   | 0.1477          |
| 0.146         | 0.63  | 70   | 0.1451          |
| 0.1467        | 0.73  | 80   | 0.1468          |
| 0.1387        | 0.82  | 90   | 0.1401          |
| 0.1342        | 0.91  | 100  | 0.1306          |
| 0.1353        | 1.0   | 110  | 0.1319          |
| 0.1235        | 1.09  | 120  | 0.1225          |
| 0.114         | 1.18  | 130  | 0.1180          |
| 0.1184        | 1.27  | 140  | 0.1166          |
| 0.1203        | 1.36  | 150  | 0.1177          |
| 0.1158        | 1.45  | 160  | 0.1090          |
| 0.1112        | 1.54  | 170  | 0.1058          |
| 0.1095        | 1.63  | 180  | 0.1067          |
| 0.11          | 1.72  | 190  | 0.1082          |
| 0.1109        | 1.81  | 200  | 0.1044          |
| 0.1118        | 1.9   | 210  | 0.1044          |
| 0.1072        | 1.99  | 220  | 0.1023          |
| 0.0934        | 2.08  | 230  | 0.1022          |
| 0.0938        | 2.18  | 240  | 0.1023          |
| 0.0896        | 2.27  | 250  | 0.1004          |
| 0.0917        | 2.36  | 260  | 0.1014          |
| 0.0909        | 2.45  | 270  | 0.1004          |
| 0.0848        | 2.54  | 280  | 0.0992          |
| 0.0833        | 2.63  | 290  | 0.0999          |
| 0.0845        | 2.72  | 300  | 0.0995          |
| 0.0872        | 2.81  | 310  | 0.0993          |
| 0.0895        | 2.9   | 320  | 0.0990          |
| 0.0872        | 2.99  | 330  | 0.0990          |


### Framework versions

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