---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-kl_001_04-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_04-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: 0.5604

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 73.5237       | 0.02  | 10   | 69.5834         |
| 46.0936       | 0.04  | 20   | 32.9841         |
| 13.5494       | 0.06  | 30   | 10.6508         |
| 6.7786        | 0.08  | 40   | 4.2309          |
| 3.5444        | 0.1   | 50   | 2.0264          |
| 1.4088        | 0.12  | 60   | 1.0764          |
| 1.0333        | 0.14  | 70   | 0.8561          |
| 0.8826        | 0.16  | 80   | 0.7578          |
| 0.7216        | 0.18  | 90   | 0.6627          |
| 0.7005        | 0.2   | 100  | 0.6215          |
| 0.6334        | 0.22  | 110  | 0.6000          |
| 0.6216        | 0.24  | 120  | 0.5858          |
| 0.6231        | 0.26  | 130  | 0.5915          |
| 0.622         | 0.28  | 140  | 0.5720          |
| 0.597         | 0.3   | 150  | 0.5694          |
| 0.5761        | 0.32  | 160  | 0.5654          |
| 0.514         | 0.34  | 170  | 0.5676          |
| 0.6263        | 0.36  | 180  | 0.5755          |
| 0.6266        | 0.38  | 190  | 0.5600          |
| 0.5743        | 0.4   | 200  | 0.5583          |
| 0.6755        | 0.42  | 210  | 0.5647          |
| 0.6305        | 0.44  | 220  | 0.5548          |
| 0.5329        | 0.46  | 230  | 0.5590          |
| 0.5465        | 0.48  | 240  | 0.5587          |
| 0.5494        | 0.5   | 250  | 0.5604          |


### Framework versions

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