---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: gpt2_small
  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. -->

# gpt2_small

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 4.0095
- Accuracy: 0.8
- Precision: 0.25
- Recall: 0.0882
- F1: 0.1304
- D-index: 1.4492

## 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1600
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | D-index |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
| No log        | 1.0   | 200  | 1.4996          | 0.79     | 0.1667    | 0.0588 | 0.0870 | 1.4242  |
| No log        | 2.0   | 400  | 0.6186          | 0.79     | 0.2143    | 0.0882 | 0.125  | 1.4354  |
| 2.445         | 3.0   | 600  | 0.8246          | 0.825    | 0.0       | 0.0    | 0.0    | 1.4500  |
| 2.445         | 4.0   | 800  | 0.5725          | 0.81     | 0.0       | 0.0    | 0.0    | 1.4293  |
| 0.6727        | 5.0   | 1000 | 1.1303          | 0.82     | 0.25      | 0.0294 | 0.0526 | 1.4543  |
| 0.6727        | 6.0   | 1200 | 1.3270          | 0.82     | 0.3333    | 0.0588 | 0.1    | 1.4655  |
| 0.6727        | 7.0   | 1400 | 2.4838          | 0.82     | 0.0       | 0.0    | 0.0    | 1.4431  |
| 0.2813        | 8.0   | 1600 | 2.2778          | 0.79     | 0.2143    | 0.0882 | 0.125  | 1.4354  |
| 0.2813        | 9.0   | 1800 | 2.8120          | 0.82     | 0.25      | 0.0294 | 0.0526 | 1.4543  |
| 0.1174        | 10.0  | 2000 | 2.6462          | 0.795    | 0.1818    | 0.0588 | 0.0889 | 1.4312  |
| 0.1174        | 11.0  | 2200 | 3.1627          | 0.795    | 0.2308    | 0.0882 | 0.1277 | 1.4423  |
| 0.1174        | 12.0  | 2400 | 3.3766          | 0.795    | 0.2308    | 0.0882 | 0.1277 | 1.4423  |
| 0.0319        | 13.0  | 2600 | 3.6674          | 0.8      | 0.2857    | 0.1176 | 0.1667 | 1.4603  |
| 0.0319        | 14.0  | 2800 | 3.4900          | 0.78     | 0.1875    | 0.0882 | 0.12   | 1.4216  |
| 0.0136        | 15.0  | 3000 | 3.7351          | 0.795    | 0.1818    | 0.0588 | 0.0889 | 1.4312  |
| 0.0136        | 16.0  | 3200 | 3.8282          | 0.8      | 0.25      | 0.0882 | 0.1304 | 1.4492  |
| 0.0136        | 17.0  | 3400 | 3.9465          | 0.8      | 0.25      | 0.0882 | 0.1304 | 1.4492  |
| 0.0002        | 18.0  | 3600 | 4.0329          | 0.8      | 0.25      | 0.0882 | 0.1304 | 1.4492  |
| 0.0002        | 19.0  | 3800 | 3.9581          | 0.795    | 0.2308    | 0.0882 | 0.1277 | 1.4423  |
| 0.0015        | 20.0  | 4000 | 4.0095          | 0.8      | 0.25      | 0.0882 | 0.1304 | 1.4492  |


### Framework versions

- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3