---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-kl_01_05_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_05_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: 0.5409

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 73.5512       | 0.02  | 10   | 69.5664         |
| 46.0783       | 0.04  | 20   | 32.9183         |
| 13.5625       | 0.06  | 30   | 10.6417         |
| 6.8251        | 0.08  | 40   | 4.2115          |
| 3.5615        | 0.1   | 50   | 2.0291          |
| 1.4471        | 0.12  | 60   | 1.0824          |
| 1.1156        | 0.14  | 70   | 0.9043          |
| 0.9839        | 0.16  | 80   | 0.7788          |
| 0.75          | 0.18  | 90   | 0.6556          |
| 0.7311        | 0.2   | 100  | 0.6302          |
| 0.6331        | 0.22  | 110  | 0.6142          |
| 0.6426        | 0.24  | 120  | 0.6279          |
| 0.7058        | 0.26  | 130  | 0.5762          |
| 0.6443        | 0.28  | 140  | 0.5702          |
| 0.6437        | 0.3   | 150  | 0.5679          |
| 0.6041        | 0.32  | 160  | 0.5654          |
| 0.5403        | 0.34  | 170  | 0.5669          |
| 0.6511        | 0.36  | 180  | 0.5710          |
| 0.651         | 0.38  | 190  | 0.5604          |
| 0.6074        | 0.4   | 200  | 0.5608          |
| 0.7023        | 0.42  | 210  | 0.5603          |
| 0.6567        | 0.44  | 220  | 0.5581          |
| 0.5573        | 0.46  | 230  | 0.5606          |
| 0.5748        | 0.48  | 240  | 0.5573          |
| 0.5728        | 0.5   | 250  | 0.5559          |
| 0.6418        | 0.52  | 260  | 0.5447          |
| 0.5855        | 0.54  | 270  | 0.5406          |
| 0.6127        | 0.56  | 280  | 0.5423          |
| 0.6065        | 0.58  | 290  | 0.5415          |
| 0.5687        | 0.6   | 300  | 0.5409          |


### Framework versions

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