---
library_name: transformers
license: mit
base_model: openai-community/gpt2-medium
tags:
- generated_from_trainer
model-index:
- name: simplewiki_upsampled_tom
  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. -->

[<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/ptsvil/tom-training/runs/keqgv1un)
# simplewiki_upsampled_tom

This model is a fine-tuned version of [openai-community/gpt2-medium](https://huggingface.co/openai-community/gpt2-medium) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1560

## 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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 4.0268        | 0.5387 | 20   | 3.4559          |
| 3.3888        | 1.0774 | 40   | 3.2204          |
| 3.2608        | 1.6162 | 60   | 3.1798          |
| 3.0763        | 2.1549 | 80   | 3.1624          |
| 3.0912        | 2.6936 | 100  | 3.1531          |


### Framework versions

- Transformers 4.44.1
- Pytorch 2.2.2
- Datasets 2.18.0
- Tokenizers 0.19.1