---
tags:
- generated_from_trainer
datasets:
- roneneldan/TinyStories
metrics:
- accuracy
model-index:
- name: gpt2_u030_tiny-stories_1024_dpos
  results:
  - task:
      name: Causal Language Modeling
      type: text-generation
    dataset:
      name: roneneldan/TinyStories
      type: roneneldan/TinyStories
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6788553562327562
---

<!-- 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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/scads-nlp/morph-gpt_gpt2_tiny-stories_dpos/runs/s3ht4a0t)
# gpt2_u030_tiny-stories_1024_dpos

This model is a fine-tuned version of [](https://huggingface.co/) on the roneneldan/TinyStories dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2107
- Accuracy: 0.6789

## 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
| 2.92          | 0.0523 | 1000  | 2.4566          | 0.4470   |
| 1.9818        | 0.1046 | 2000  | 1.8089          | 0.5672   |
| 1.7321        | 0.1570 | 3000  | 1.6133          | 0.6021   |
| 1.6137        | 0.2093 | 4000  | 1.5171          | 0.6195   |
| 1.5353        | 0.2616 | 5000  | 1.4516          | 0.6312   |
| 1.4845        | 0.3139 | 6000  | 1.4056          | 0.6400   |
| 1.4443        | 0.3662 | 7000  | 1.3718          | 0.6466   |
| 1.4118        | 0.4186 | 8000  | 1.3420          | 0.6525   |
| 1.3878        | 0.4709 | 9000  | 1.3189          | 0.6569   |
| 1.3661        | 0.5232 | 10000 | 1.2988          | 0.6608   |
| 1.3485        | 0.5755 | 11000 | 1.2834          | 0.6639   |
| 1.3326        | 0.6278 | 12000 | 1.2675          | 0.6669   |
| 1.319         | 0.6802 | 13000 | 1.2555          | 0.6694   |
| 1.3068        | 0.7325 | 14000 | 1.2440          | 0.6719   |
| 1.2932        | 0.7848 | 15000 | 1.2350          | 0.6737   |
| 1.2868        | 0.8371 | 16000 | 1.2263          | 0.6755   |
| 1.2791        | 0.8894 | 17000 | 1.2193          | 0.6771   |
| 1.2725        | 0.9418 | 18000 | 1.2141          | 0.6780   |
| 1.2711        | 0.9941 | 19000 | 1.2108          | 0.6788   |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1