---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0513HMAB1
  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. -->

# G0513HMAB1

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: 0.1352

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.926         | 0.09  | 10   | 1.9074          |
| 1.8937        | 0.18  | 20   | 1.8418          |
| 1.7669        | 0.27  | 30   | 1.6397          |
| 1.4926        | 0.36  | 40   | 1.2660          |
| 1.0153        | 0.45  | 50   | 0.6891          |
| 0.5171        | 0.54  | 60   | 0.3388          |
| 0.2538        | 0.63  | 70   | 0.1816          |
| 0.1674        | 0.73  | 80   | 0.1558          |
| 0.147         | 0.82  | 90   | 0.1501          |
| 0.1461        | 0.91  | 100  | 0.1470          |
| 0.1485        | 1.0   | 110  | 0.1488          |
| 0.1444        | 1.09  | 120  | 0.1460          |
| 0.1446        | 1.18  | 130  | 0.1469          |
| 0.1459        | 1.27  | 140  | 0.1454          |
| 0.1469        | 1.36  | 150  | 0.1441          |
| 0.1404        | 1.45  | 160  | 0.1456          |
| 0.142         | 1.54  | 170  | 0.1426          |
| 0.1418        | 1.63  | 180  | 0.1418          |
| 0.1429        | 1.72  | 190  | 0.1429          |
| 0.1401        | 1.81  | 200  | 0.1400          |
| 0.1415        | 1.9   | 210  | 0.1392          |
| 0.141         | 1.99  | 220  | 0.1395          |
| 0.1393        | 2.08  | 230  | 0.1376          |
| 0.137         | 2.18  | 240  | 0.1374          |
| 0.1349        | 2.27  | 250  | 0.1368          |
| 0.1392        | 2.36  | 260  | 0.1367          |
| 0.1369        | 2.45  | 270  | 0.1364          |
| 0.1337        | 2.54  | 280  | 0.1360          |
| 0.1322        | 2.63  | 290  | 0.1356          |
| 0.1341        | 2.72  | 300  | 0.1353          |
| 0.1349        | 2.81  | 310  | 0.1352          |
| 0.1343        | 2.9   | 320  | 0.1352          |
| 0.1365        | 2.99  | 330  | 0.1352          |


### Framework versions

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