---
license: apache-2.0
base_model: allenai/OLMo-1B
tags:
- generated_from_trainer
model-index:
- name: O0430HMA14
  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. -->

# O0430HMA14

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: 0.0186

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.558         | 0.09  | 10   | 0.2938          |
| 0.1782        | 0.18  | 20   | 0.1518          |
| 0.1488        | 0.27  | 30   | 0.1634          |
| 0.1562        | 0.36  | 40   | 0.1549          |
| 0.1523        | 0.45  | 50   | 0.1528          |
| 0.1532        | 0.54  | 60   | 0.1495          |
| 0.1487        | 0.63  | 70   | 0.1476          |
| 0.1493        | 0.73  | 80   | 0.1547          |
| 0.148         | 0.82  | 90   | 0.1499          |
| 0.1487        | 0.91  | 100  | 0.1516          |
| 0.1516        | 1.0   | 110  | 0.1509          |
| 0.1464        | 1.09  | 120  | 0.1491          |
| 0.2792        | 1.18  | 130  | 2.5830          |
| 1.2568        | 1.27  | 140  | 0.1547          |
| 0.1824        | 1.36  | 150  | 0.1368          |
| 0.341         | 1.45  | 160  | 0.3759          |
| 0.1732        | 1.54  | 170  | 0.0789          |
| 0.444         | 1.63  | 180  | 0.0761          |
| 0.0692        | 1.72  | 190  | 0.0591          |
| 0.0553        | 1.81  | 200  | 0.0601          |
| 0.0576        | 1.9   | 210  | 0.0560          |
| 0.0578        | 1.99  | 220  | 0.0525          |
| 0.0498        | 2.08  | 230  | 0.0459          |
| 0.0412        | 2.18  | 240  | 0.0334          |
| 0.0359        | 2.27  | 250  | 0.0302          |
| 0.0315        | 2.36  | 260  | 0.0261          |
| 0.0254        | 2.45  | 270  | 0.0243          |
| 0.0179        | 2.54  | 280  | 0.0219          |
| 0.0251        | 2.63  | 290  | 0.0211          |
| 0.0226        | 2.72  | 300  | 0.0195          |
| 0.0216        | 2.81  | 310  | 0.0197          |
| 0.0231        | 2.9   | 320  | 0.0186          |
| 0.0224        | 2.99  | 330  | 0.0186          |


### Framework versions

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