---
license: apache-2.0
base_model: allenai/OLMo-1B
tags:
- generated_from_trainer
model-index:
- name: O0428HMA9
  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. -->

# O0428HMA9

This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0545

## 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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6202        | 0.09  | 10   | 0.2442          |
| 0.1807        | 0.18  | 20   | 0.1525          |
| 0.1486        | 0.27  | 30   | 0.1701          |
| 0.1564        | 0.36  | 40   | 0.1538          |
| 0.1507        | 0.45  | 50   | 0.1492          |
| 0.1511        | 0.54  | 60   | 0.1474          |
| 0.1491        | 0.63  | 70   | 0.1472          |
| 0.1496        | 0.73  | 80   | 0.1551          |
| 0.1466        | 0.82  | 90   | 0.1500          |
| 0.1496        | 0.91  | 100  | 0.1495          |
| 0.1516        | 1.0   | 110  | 0.1463          |
| 0.1509        | 1.09  | 120  | 0.1321          |
| 0.3642        | 1.18  | 130  | 0.2426          |
| 0.179         | 1.27  | 140  | 0.1081          |
| 0.1519        | 1.36  | 150  | 0.1300          |
| 0.272         | 1.45  | 160  | 0.0911          |
| 0.0746        | 1.54  | 170  | 0.0694          |
| 0.0657        | 1.63  | 180  | 0.0619          |
| 0.0678        | 1.72  | 190  | 0.0584          |
| 0.0578        | 1.81  | 200  | 0.0592          |
| 0.0577        | 1.9   | 210  | 0.0612          |
| 0.0599        | 1.99  | 220  | 0.0554          |
| 0.0587        | 2.08  | 230  | 0.0568          |
| 0.0538        | 2.18  | 240  | 0.0564          |
| 0.0562        | 2.27  | 250  | 0.0581          |
| 0.0591        | 2.36  | 260  | 0.0568          |
| 0.0537        | 2.45  | 270  | 0.0551          |
| 0.0523        | 2.54  | 280  | 0.0557          |
| 0.0548        | 2.63  | 290  | 0.0566          |
| 0.056         | 2.72  | 300  | 0.0545          |
| 0.0569        | 2.81  | 310  | 0.0543          |
| 0.0584        | 2.9   | 320  | 0.0545          |
| 0.0604        | 2.99  | 330  | 0.0545          |


### Framework versions

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