---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-kl_01_06_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_01_06_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: 0.5434

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 73.5734       | 0.02  | 10   | 69.5788         |
| 46.1373       | 0.04  | 20   | 32.9663         |
| 13.5782       | 0.06  | 30   | 10.6413         |
| 6.8512        | 0.08  | 40   | 4.2326          |
| 3.5656        | 0.1   | 50   | 2.0355          |
| 1.4777        | 0.12  | 60   | 1.0854          |
| 1.0982        | 0.14  | 70   | 0.8590          |
| 0.9299        | 0.16  | 80   | 0.8011          |
| 0.7663        | 0.18  | 90   | 0.7395          |
| 0.7731        | 0.2   | 100  | 0.6091          |
| 0.6341        | 0.22  | 110  | 0.6048          |
| 0.6659        | 0.24  | 120  | 0.5985          |
| 0.6741        | 0.26  | 130  | 0.5786          |
| 0.6632        | 0.28  | 140  | 0.5795          |
| 0.6483        | 0.3   | 150  | 0.5862          |
| 0.6445        | 0.32  | 160  | 0.5703          |
| 0.5508        | 0.34  | 170  | 0.5656          |
| 0.7139        | 0.36  | 180  | 0.5628          |
| 0.6662        | 0.38  | 190  | 0.5556          |
| 0.6166        | 0.4   | 200  | 0.5553          |
| 0.7288        | 0.42  | 210  | 0.5551          |
| 0.6741        | 0.44  | 220  | 0.5528          |
| 0.5773        | 0.46  | 230  | 0.5566          |
| 0.5935        | 0.48  | 240  | 0.5559          |
| 0.5889        | 0.5   | 250  | 0.5513          |
| 0.6015        | 0.52  | 260  | 0.5447          |
| 0.6026        | 0.54  | 270  | 0.5408          |
| 0.6295        | 0.56  | 280  | 0.5449          |
| 0.6315        | 0.58  | 290  | 0.5417          |
| 0.5773        | 0.6   | 300  | 0.5434          |


### Framework versions

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