---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0513HMAB3
  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. -->

# G0513HMAB3

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: 0.1174

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.9144        | 0.09  | 10   | 1.8171          |
| 1.6608        | 0.18  | 20   | 1.4138          |
| 1.2059        | 0.27  | 30   | 0.9062          |
| 0.6819        | 0.36  | 40   | 0.4067          |
| 0.2762        | 0.45  | 50   | 0.1792          |
| 0.1622        | 0.54  | 60   | 0.1512          |
| 0.1503        | 0.63  | 70   | 0.1473          |
| 0.1496        | 0.73  | 80   | 0.1468          |
| 0.1422        | 0.82  | 90   | 0.1453          |
| 0.1426        | 0.91  | 100  | 0.1438          |
| 0.142         | 1.0   | 110  | 0.1436          |
| 0.1382        | 1.09  | 120  | 0.1390          |
| 0.134         | 1.18  | 130  | 0.1356          |
| 0.1342        | 1.27  | 140  | 0.1369          |
| 0.1391        | 1.36  | 150  | 0.1356          |
| 0.1326        | 1.45  | 160  | 0.1313          |
| 0.129         | 1.54  | 170  | 0.1287          |
| 0.1302        | 1.63  | 180  | 0.1276          |
| 0.1316        | 1.72  | 190  | 0.1297          |
| 0.1269        | 1.81  | 200  | 0.1252          |
| 0.1271        | 1.9   | 210  | 0.1229          |
| 0.1242        | 1.99  | 220  | 0.1229          |
| 0.1193        | 2.08  | 230  | 0.1212          |
| 0.1226        | 2.18  | 240  | 0.1216          |
| 0.1172        | 2.27  | 250  | 0.1213          |
| 0.1202        | 2.36  | 260  | 0.1198          |
| 0.1173        | 2.45  | 270  | 0.1200          |
| 0.112         | 2.54  | 280  | 0.1186          |
| 0.1126        | 2.63  | 290  | 0.1182          |
| 0.1152        | 2.72  | 300  | 0.1175          |
| 0.1133        | 2.81  | 310  | 0.1174          |
| 0.117         | 2.9   | 320  | 0.1175          |
| 0.1177        | 2.99  | 330  | 0.1174          |


### Framework versions

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