---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0521HMA26H5
  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. -->

# G0521HMA26H5

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: 0.1040

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.753         | 0.09  | 10   | 1.3225          |
| 0.9976        | 0.18  | 20   | 0.4776          |
| 0.3118        | 0.27  | 30   | 0.1654          |
| 0.1527        | 0.36  | 40   | 0.1543          |
| 0.1481        | 0.45  | 50   | 0.1486          |
| 0.1472        | 0.54  | 60   | 0.1495          |
| 0.1545        | 0.63  | 70   | 0.1452          |
| 0.1467        | 0.73  | 80   | 0.1473          |
| 0.1381        | 0.82  | 90   | 0.1348          |
| 0.1314        | 0.91  | 100  | 0.1327          |
| 0.1316        | 1.0   | 110  | 0.1324          |
| 0.1212        | 1.09  | 120  | 0.1323          |
| 0.1135        | 1.18  | 130  | 0.1179          |
| 0.1188        | 1.27  | 140  | 0.1166          |
| 0.1193        | 1.36  | 150  | 0.1179          |
| 0.1153        | 1.45  | 160  | 0.1126          |
| 0.1145        | 1.54  | 170  | 0.1137          |
| 0.1075        | 1.63  | 180  | 0.1109          |
| 0.1148        | 1.72  | 190  | 0.1136          |
| 0.1126        | 1.81  | 200  | 0.1056          |
| 0.1092        | 1.9   | 210  | 0.1042          |
| 0.1065        | 1.99  | 220  | 0.1044          |
| 0.0961        | 2.08  | 230  | 0.1060          |
| 0.0973        | 2.18  | 240  | 0.1027          |
| 0.0926        | 2.27  | 250  | 0.1055          |
| 0.09          | 2.36  | 260  | 0.1084          |
| 0.0916        | 2.45  | 270  | 0.1066          |
| 0.0859        | 2.54  | 280  | 0.1057          |
| 0.0842        | 2.63  | 290  | 0.1042          |
| 0.0855        | 2.72  | 300  | 0.1044          |
| 0.0876        | 2.81  | 310  | 0.1045          |
| 0.0895        | 2.9   | 320  | 0.1041          |
| 0.0896        | 2.99  | 330  | 0.1040          |


### Framework versions

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