---
license: apache-2.0
base_model: allenai/OLMo-1B
tags:
- generated_from_trainer
model-index:
- name: O0428HMA11
  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. -->

# O0428HMA11

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: 0.0353

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6441        | 0.09  | 10   | 0.2795          |
| 0.1859        | 0.18  | 20   | 0.1565          |
| 0.1509        | 0.27  | 30   | 0.1657          |
| 0.1581        | 0.36  | 40   | 0.1509          |
| 0.1497        | 0.45  | 50   | 0.1504          |
| 0.1514        | 0.54  | 60   | 0.1496          |
| 0.1497        | 0.63  | 70   | 0.1472          |
| 0.1487        | 0.73  | 80   | 0.1529          |
| 0.1465        | 0.82  | 90   | 0.1488          |
| 0.149         | 0.91  | 100  | 0.1478          |
| 0.1511        | 1.0   | 110  | 0.1483          |
| 0.1438        | 1.09  | 120  | 0.1352          |
| 0.1382        | 1.18  | 130  | 0.1203          |
| 0.59          | 1.27  | 140  | 2.9085          |
| 0.602         | 1.36  | 150  | 1.5195          |
| 6.4792        | 1.45  | 160  | 5.2383          |
| 2.3451        | 1.54  | 170  | 0.7049          |
| 1.0846        | 1.63  | 180  | 0.6462          |
| 0.5224        | 1.72  | 190  | 0.3806          |
| 0.3875        | 1.81  | 200  | 0.2835          |
| 0.2533        | 1.9   | 210  | 0.2670          |
| 0.2265        | 1.99  | 220  | 0.2117          |
| 0.1544        | 2.08  | 230  | 0.1180          |
| 0.1085        | 2.18  | 240  | 0.0898          |
| 0.0812        | 2.27  | 250  | 0.0735          |
| 0.0721        | 2.36  | 260  | 0.0757          |
| 0.0719        | 2.45  | 270  | 0.0617          |
| 0.0545        | 2.54  | 280  | 0.0565          |
| 0.0479        | 2.63  | 290  | 0.0479          |
| 0.0458        | 2.72  | 300  | 0.0403          |
| 0.0316        | 2.81  | 310  | 0.0371          |
| 0.0298        | 2.9   | 320  | 0.0362          |
| 0.0346        | 2.99  | 330  | 0.0353          |


### Framework versions

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