---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-kl_001_03_hscnspecial-hs_cn
  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-kl_001_03_hscnspecial-hs_cn

This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5521

## 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: 8
- eval_batch_size: 4
- seed: 21
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 73.5197       | 0.02  | 10   | 69.5785         |
| 46.0808       | 0.04  | 20   | 32.9820         |
| 13.5502       | 0.06  | 30   | 10.6512         |
| 6.7525        | 0.08  | 40   | 4.2586          |
| 2.8056        | 0.1   | 50   | 2.0866          |
| 1.3788        | 0.12  | 60   | 1.1292          |
| 1.2289        | 0.14  | 70   | 0.9021          |
| 0.9622        | 0.16  | 80   | 0.7473          |
| 0.7371        | 0.18  | 90   | 0.6521          |
| 0.7113        | 0.2   | 100  | 0.6246          |
| 0.6374        | 0.22  | 110  | 0.6168          |
| 0.6234        | 0.24  | 120  | 0.5887          |
| 0.6292        | 0.26  | 130  | 0.5813          |
| 0.6154        | 0.28  | 140  | 0.5762          |
| 0.5948        | 0.3   | 150  | 0.5718          |
| 0.5784        | 0.32  | 160  | 0.5694          |
| 0.5132        | 0.34  | 170  | 0.5701          |
| 0.625         | 0.36  | 180  | 0.5649          |
| 0.6225        | 0.38  | 190  | 0.5578          |
| 0.5756        | 0.4   | 200  | 0.5559          |
| 0.6848        | 0.42  | 210  | 0.5547          |
| 0.6253        | 0.44  | 220  | 0.5502          |
| 0.5286        | 0.46  | 230  | 0.5511          |
| 0.5537        | 0.48  | 240  | 0.5483          |
| 0.5466        | 0.5   | 250  | 0.5512          |
| 0.5536        | 0.52  | 260  | 0.5467          |
| 0.5509        | 0.54  | 270  | 0.5446          |
| 0.5801        | 0.56  | 280  | 0.5524          |
| 0.5775        | 0.58  | 290  | 0.5440          |
| 0.5355        | 0.6   | 300  | 0.5414          |
| 0.5483        | 0.62  | 310  | 0.5445          |
| 0.6389        | 0.64  | 320  | 0.5420          |
| 0.506         | 0.66  | 330  | 0.5521          |


### Framework versions

- Transformers 4.29.0.dev0
- Pytorch 1.12.0a0+bd13bc6
- Datasets 2.12.0
- Tokenizers 0.13.3