---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: aochildes-cbt-log-rarity
  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. -->

# aochildes-cbt-log-rarity

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: 4.1483

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.3649        | 0.29  | 500   | 5.3433          |
| 5.0506        | 0.59  | 1000  | 4.9337          |
| 4.7079        | 0.88  | 1500  | 4.6957          |
| 4.4512        | 1.17  | 2000  | 4.5593          |
| 4.3031        | 1.47  | 2500  | 4.4458          |
| 4.2085        | 1.76  | 3000  | 4.3418          |
| 4.0809        | 2.05  | 3500  | 4.2739          |
| 3.9047        | 2.35  | 4000  | 4.2277          |
| 3.8846        | 2.64  | 4500  | 4.1774          |
| 3.8392        | 2.93  | 5000  | 4.1313          |
| 3.6392        | 3.23  | 5500  | 4.1305          |
| 3.6016        | 3.52  | 6000  | 4.1020          |
| 3.5828        | 3.81  | 6500  | 4.0709          |
| 3.4733        | 4.11  | 7000  | 4.0797          |
| 3.3271        | 4.4   | 7500  | 4.0758          |
| 3.3228        | 4.69  | 8000  | 4.0635          |
| 3.3147        | 4.99  | 8500  | 4.0528          |
| 3.154         | 5.28  | 9000  | 4.0692          |
| 3.1461        | 5.58  | 9500  | 4.0692          |
| 3.1416        | 5.87  | 10000 | 4.0684          |


### Framework versions

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