---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0521HMA26H1
  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. -->

# G0521HMA26H1

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: 0.4153

## 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   | 1.4934          |
| 1.0624        | 0.18  | 20   | 0.7710          |
| 0.393         | 0.27  | 30   | 0.2162          |
| 0.1584        | 0.36  | 40   | 0.2425          |
| 0.1475        | 0.45  | 50   | 0.3888          |
| 0.1494        | 0.54  | 60   | 0.3249          |
| 0.1472        | 0.63  | 70   | 0.4650          |
| 0.6741        | 0.73  | 80   | 0.2848          |
| 0.1413        | 0.82  | 90   | 0.3718          |
| 0.1393        | 0.91  | 100  | 0.2967          |
| 0.1353        | 1.0   | 110  | 0.4193          |
| 0.1291        | 1.09  | 120  | 0.5094          |
| 0.121         | 1.18  | 130  | 0.3007          |
| 0.1249        | 1.27  | 140  | 0.2038          |
| 0.1256        | 1.36  | 150  | 0.1808          |
| 0.1223        | 1.45  | 160  | 0.2009          |
| 0.1147        | 1.54  | 170  | 0.3312          |
| 0.1162        | 1.63  | 180  | 0.2481          |
| 0.1168        | 1.72  | 190  | 0.2108          |
| 0.1127        | 1.81  | 200  | 0.4134          |
| 0.112         | 1.9   | 210  | 0.2823          |
| 0.1098        | 1.99  | 220  | 0.3958          |
| 0.0993        | 2.08  | 230  | 0.4361          |
| 0.101         | 2.18  | 240  | 0.5045          |
| 0.0935        | 2.27  | 250  | 0.3612          |
| 0.0961        | 2.36  | 260  | 0.3679          |
| 0.0941        | 2.45  | 270  | 0.3548          |
| 0.0892        | 2.54  | 280  | 0.3754          |
| 0.0866        | 2.63  | 290  | 0.3601          |
| 0.0914        | 2.72  | 300  | 0.3955          |
| 0.0947        | 2.81  | 310  | 0.4108          |
| 0.0942        | 2.9   | 320  | 0.4147          |
| 0.0941        | 2.99  | 330  | 0.4153          |


### Framework versions

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