---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: G0428HMA22
  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. -->

# G0428HMA22

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: 0.1053

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.5672        | 0.09  | 10   | 1.5723          |
| 0.95          | 0.18  | 20   | 0.3053          |
| 0.1975        | 0.27  | 30   | 0.1617          |
| 0.1542        | 0.36  | 40   | 0.1482          |
| 0.1465        | 0.45  | 50   | 0.1487          |
| 0.148         | 0.54  | 60   | 0.1489          |
| 0.1482        | 0.63  | 70   | 0.1472          |
| 0.1491        | 0.73  | 80   | 0.1474          |
| 0.1423        | 0.82  | 90   | 0.1480          |
| 0.1448        | 0.91  | 100  | 0.1481          |
| 0.1481        | 1.0   | 110  | 0.1487          |
| 0.1439        | 1.09  | 120  | 0.1480          |
| 0.1453        | 1.18  | 130  | 0.1486          |
| 0.1463        | 1.27  | 140  | 0.1457          |
| 0.1462        | 1.36  | 150  | 0.1437          |
| 0.1372        | 1.45  | 160  | 0.1387          |
| 0.1398        | 1.54  | 170  | 0.1416          |
| 0.133         | 1.63  | 180  | 0.1324          |
| 0.1316        | 1.72  | 190  | 0.1315          |
| 0.1279        | 1.81  | 200  | 0.1283          |
| 0.1273        | 1.9   | 210  | 0.1243          |
| 0.1232        | 1.99  | 220  | 0.1185          |
| 0.1129        | 2.08  | 230  | 0.1186          |
| 0.1112        | 2.18  | 240  | 0.1143          |
| 0.1046        | 2.27  | 250  | 0.1138          |
| 0.1075        | 2.36  | 260  | 0.1122          |
| 0.1088        | 2.45  | 270  | 0.1098          |
| 0.1046        | 2.54  | 280  | 0.1102          |
| 0.0971        | 2.63  | 290  | 0.1084          |
| 0.0994        | 2.72  | 300  | 0.1072          |
| 0.1019        | 2.81  | 310  | 0.1058          |
| 0.1021        | 2.9   | 320  | 0.1054          |
| 0.1068        | 2.99  | 330  | 0.1053          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1