---
license: apache-2.0
base_model: allenai/OLMo-1B
tags:
- generated_from_trainer
model-index:
- name: O0506TEST4
  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. -->

# O0506TEST4

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: 0.1571

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 3.0648        | 0.09  | 10   | 0.3333          |
| 0.2162        | 0.18  | 20   | 0.1599          |
| 0.1543        | 0.27  | 30   | 0.1590          |
| 0.156         | 0.36  | 40   | 0.1528          |
| 0.1499        | 0.45  | 50   | 0.1497          |
| 0.1524        | 0.54  | 60   | 0.1513          |
| 0.1499        | 0.63  | 70   | 0.1484          |
| 0.1488        | 0.73  | 80   | 0.1535          |
| 0.1478        | 0.82  | 90   | 0.1494          |
| 0.1478        | 0.91  | 100  | 0.1522          |
| 0.1511        | 1.0   | 110  | 0.1511          |
| 0.1465        | 1.09  | 120  | 0.1502          |
| 0.1454        | 1.18  | 130  | 0.1467          |
| 0.615         | 1.27  | 140  | 0.1920          |
| 5.4883        | 1.36  | 150  | 4.4845          |
| 1.4468        | 1.45  | 160  | 0.4784          |
| 0.3848        | 1.54  | 170  | 0.3101          |
| 0.3022        | 1.63  | 180  | 0.3316          |
| 0.2716        | 1.72  | 190  | 0.2528          |
| 0.2376        | 1.81  | 200  | 0.2176          |
| 0.1874        | 1.9   | 210  | 0.1744          |
| 0.1817        | 1.99  | 220  | 0.1734          |
| 0.1673        | 2.08  | 230  | 0.1810          |
| 0.1646        | 2.18  | 240  | 0.1609          |
| 0.1565        | 2.27  | 250  | 0.1599          |
| 0.1545        | 2.36  | 260  | 0.1606          |
| 0.1527        | 2.45  | 270  | 0.1590          |
| 0.1537        | 2.54  | 280  | 0.1579          |
| 0.1502        | 2.63  | 290  | 0.1596          |
| 0.154         | 2.72  | 300  | 0.1569          |
| 0.1522        | 2.81  | 310  | 0.1570          |
| 0.1519        | 2.9   | 320  | 0.1570          |
| 0.1534        | 2.99  | 330  | 0.1571          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0