---
license: apache-2.0
base_model: allenai/OLMo-1B
tags:
- generated_from_trainer
model-index:
- name: O0428HMA22
  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. -->

# O0428HMA22

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: 0.0467

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.4529        | 0.09  | 10   | 0.1637          |
| 0.1607        | 0.18  | 20   | 0.1594          |
| 0.1523        | 0.27  | 30   | 0.1619          |
| 0.1562        | 0.36  | 40   | 0.1498          |
| 0.1516        | 0.45  | 50   | 0.1536          |
| 0.1533        | 0.54  | 60   | 0.1494          |
| 0.1507        | 0.63  | 70   | 0.1481          |
| 0.1494        | 0.73  | 80   | 0.1566          |
| 0.1481        | 0.82  | 90   | 0.1476          |
| 0.1486        | 0.91  | 100  | 0.1493          |
| 0.1506        | 1.0   | 110  | 0.1496          |
| 0.1464        | 1.09  | 120  | 0.1483          |
| 0.1465        | 1.18  | 130  | 0.1523          |
| 0.148         | 1.27  | 140  | 0.1493          |
| 0.1512        | 1.36  | 150  | 0.1502          |
| 0.147         | 1.45  | 160  | 0.1495          |
| 0.1453        | 1.54  | 170  | 0.1470          |
| 0.1477        | 1.63  | 180  | 0.1460          |
| 0.1476        | 1.72  | 190  | 0.1500          |
| 0.145         | 1.81  | 200  | 0.1482          |
| 0.1483        | 1.9   | 210  | 0.1451          |
| 0.139         | 1.99  | 220  | 0.1258          |
| 0.0991        | 2.08  | 230  | 0.0957          |
| 0.1018        | 2.18  | 240  | 0.0760          |
| 0.0642        | 2.27  | 250  | 0.0672          |
| 0.0644        | 2.36  | 260  | 0.0607          |
| 0.0533        | 2.45  | 270  | 0.0558          |
| 0.0475        | 2.54  | 280  | 0.0542          |
| 0.0509        | 2.63  | 290  | 0.0499          |
| 0.0512        | 2.72  | 300  | 0.0486          |
| 0.0478        | 2.81  | 310  | 0.0488          |
| 0.0466        | 2.9   | 320  | 0.0471          |
| 0.0504        | 2.99  | 330  | 0.0467          |


### Framework versions

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