---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-kl_01_05-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_05-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: 0.5387

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 73.5669       | 0.02  | 10   | 69.5838         |
| 46.1192       | 0.04  | 20   | 32.9319         |
| 13.5763       | 0.06  | 30   | 10.6437         |
| 5.6862        | 0.08  | 40   | 4.3509          |
| 2.8355        | 0.1   | 50   | 1.9914          |
| 1.4127        | 0.12  | 60   | 1.0386          |
| 1.139         | 0.14  | 70   | 0.8992          |
| 0.9191        | 0.16  | 80   | 0.7150          |
| 0.7454        | 0.18  | 90   | 0.7040          |
| 0.7465        | 0.2   | 100  | 0.6307          |
| 0.6444        | 0.22  | 110  | 0.6424          |
| 0.6783        | 0.24  | 120  | 0.6040          |
| 0.6724        | 0.26  | 130  | 0.6014          |
| 0.6898        | 0.28  | 140  | 0.6155          |
| 0.6583        | 0.3   | 150  | 0.5748          |
| 0.6234        | 0.32  | 160  | 0.5870          |
| 0.5572        | 0.34  | 170  | 0.5669          |
| 0.6596        | 0.36  | 180  | 0.5635          |
| 0.6763        | 0.38  | 190  | 0.5650          |
| 0.6112        | 0.4   | 200  | 0.5616          |
| 0.7173        | 0.42  | 210  | 0.5608          |
| 0.6714        | 0.44  | 220  | 0.5604          |
| 0.5898        | 0.46  | 230  | 0.5624          |
| 0.5849        | 0.48  | 240  | 0.5570          |
| 0.5825        | 0.5   | 250  | 0.5556          |
| 0.6123        | 0.52  | 260  | 0.5440          |
| 0.5956        | 0.54  | 270  | 0.5397          |
| 0.634         | 0.56  | 280  | 0.5404          |
| 0.6152        | 0.58  | 290  | 0.5387          |
| 0.5719        | 0.6   | 300  | 0.5396          |
| 0.587         | 0.62  | 310  | 0.5363          |
| 0.6913        | 0.64  | 320  | 0.5357          |
| 0.5504        | 0.66  | 330  | 0.5409          |
| 0.545         | 0.68  | 340  | 0.5359          |
| 0.558         | 0.7   | 350  | 0.5387          |


### Framework versions

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