---
license: gemma
base_model: google/gemma-2b
tags:
- generated_from_trainer
model-index:
- name: GOLM2
  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. -->

# GOLM2

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: 0.1067

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7996        | 0.09  | 10   | 1.4594          |
| 0.9949        | 0.18  | 20   | 0.5804          |
| 0.3011        | 0.27  | 30   | 0.1728          |
| 0.1527        | 0.36  | 40   | 0.1498          |
| 0.1447        | 0.45  | 50   | 0.1491          |
| 0.1451        | 0.54  | 60   | 0.1476          |
| 0.142         | 0.63  | 70   | 0.1447          |
| 0.1422        | 0.73  | 80   | 0.1415          |
| 0.1304        | 0.82  | 90   | 0.1346          |
| 0.1241        | 0.91  | 100  | 0.1294          |
| 0.1263        | 1.0   | 110  | 0.1294          |
| 0.1163        | 1.09  | 120  | 0.1235          |
| 0.1091        | 1.18  | 130  | 0.1217          |
| 0.1143        | 1.27  | 140  | 0.1201          |
| 0.1131        | 1.36  | 150  | 0.1149          |
| 0.1127        | 1.45  | 160  | 0.1158          |
| 0.1087        | 1.54  | 170  | 0.1139          |
| 0.1086        | 1.63  | 180  | 0.1125          |
| 0.1069        | 1.72  | 190  | 0.1120          |
| 0.1027        | 1.81  | 200  | 0.1119          |
| 0.1037        | 1.9   | 210  | 0.1109          |
| 0.1072        | 1.99  | 220  | 0.1116          |
| 0.0896        | 2.08  | 230  | 0.1104          |
| 0.0918        | 2.18  | 240  | 0.1096          |
| 0.0828        | 2.27  | 250  | 0.1071          |
| 0.0861        | 2.36  | 260  | 0.1080          |
| 0.0853        | 2.45  | 270  | 0.1093          |
| 0.0809        | 2.54  | 280  | 0.1084          |
| 0.0782        | 2.63  | 290  | 0.1076          |
| 0.0814        | 2.72  | 300  | 0.1072          |
| 0.0849        | 2.81  | 310  | 0.1074          |
| 0.0838        | 2.9   | 320  | 0.1070          |
| 0.0864        | 2.99  | 330  | 0.1067          |


### Framework versions

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