---
license: apache-2.0
base_model: allenai/OLMo-1B
tags:
- generated_from_trainer
model-index:
- name: O0428HMA6
  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. -->

# O0428HMA6

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: 0.1537

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.4684        | 0.09  | 10   | 0.2658          |
| 0.176         | 0.18  | 20   | 0.1586          |
| 0.1482        | 0.27  | 30   | 0.1648          |
| 0.1537        | 0.36  | 40   | 0.1560          |
| 0.1513        | 0.45  | 50   | 0.1532          |
| 0.1524        | 0.54  | 60   | 0.1483          |
| 0.1561        | 0.63  | 70   | 0.1699          |
| 0.3903        | 0.73  | 80   | 2.6327          |
| 1.692         | 0.82  | 90   | 0.1612          |
| 3.4774        | 0.91  | 100  | 0.5470          |
| 0.5662        | 1.0   | 110  | 0.3429          |
| 2.9804        | 1.09  | 120  | 1.6472          |
| 3.087         | 1.18  | 130  | 3.2248          |
| 1.3303        | 1.27  | 140  | 1.4770          |
| 1.4895        | 1.36  | 150  | 0.5381          |
| 0.3974        | 1.45  | 160  | 0.3217          |
| 0.4325        | 1.54  | 170  | 0.9128          |
| 0.4121        | 1.63  | 180  | 0.2806          |
| 0.2431        | 1.72  | 190  | 0.2329          |
| 0.216         | 1.81  | 200  | 0.2063          |
| 0.2069        | 1.9   | 210  | 0.2249          |
| 0.2153        | 1.99  | 220  | 0.1920          |
| 0.1906        | 2.08  | 230  | 0.2070          |
| 0.1864        | 2.18  | 240  | 0.1844          |
| 0.1734        | 2.27  | 250  | 0.1766          |
| 0.1638        | 2.36  | 260  | 0.1677          |
| 0.1545        | 2.45  | 270  | 0.1604          |
| 0.1572        | 2.54  | 280  | 0.1569          |
| 0.1508        | 2.63  | 290  | 0.1577          |
| 0.1497        | 2.72  | 300  | 0.1537          |
| 0.1494        | 2.81  | 310  | 0.1526          |
| 0.148         | 2.9   | 320  | 0.1540          |
| 0.1483        | 2.99  | 330  | 0.1537          |


### Framework versions

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