---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: bnc_spoken_aochildes_log_rarity-mixed-seed
  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. -->

# bnc_spoken_aochildes_log_rarity-mixed-seed

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.1729

## 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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.3769        | 0.29  | 500   | 5.3515          |
| 5.065         | 0.59  | 1000  | 4.9413          |
| 4.7275        | 0.88  | 1500  | 4.7082          |
| 4.4708        | 1.18  | 2000  | 4.5784          |
| 4.3239        | 1.47  | 2500  | 4.4544          |
| 4.2171        | 1.77  | 3000  | 4.3623          |
| 4.1007        | 2.06  | 3500  | 4.2928          |
| 3.9212        | 2.36  | 4000  | 4.2540          |
| 3.901         | 2.65  | 4500  | 4.1964          |
| 3.8579        | 2.95  | 5000  | 4.1494          |
| 3.6469        | 3.24  | 5500  | 4.1546          |
| 3.6172        | 3.54  | 6000  | 4.1207          |
| 3.5878        | 3.83  | 6500  | 4.0930          |
| 3.4727        | 4.12  | 7000  | 4.0978          |
| 3.3469        | 4.42  | 7500  | 4.0968          |
| 3.3354        | 4.71  | 8000  | 4.0848          |
| 3.3186        | 5.01  | 8500  | 4.0809          |
| 3.1618        | 5.3   | 9000  | 4.0917          |
| 3.1612        | 5.6   | 9500  | 4.0911          |
| 3.1527        | 5.89  | 10000 | 4.0916          |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3