|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2-kl_01_07_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_07_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: 0.5377 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 73.5948 | 0.02 | 10 | 69.5786 | |
|
| 46.1586 | 0.04 | 20 | 32.9619 | |
|
| 13.6007 | 0.06 | 30 | 10.6513 | |
|
| 6.8042 | 0.08 | 40 | 4.2289 | |
|
| 2.8577 | 0.1 | 50 | 2.1080 | |
|
| 1.447 | 0.12 | 60 | 1.1006 | |
|
| 1.2972 | 0.14 | 70 | 0.9296 | |
|
| 0.9482 | 0.16 | 80 | 0.7053 | |
|
| 0.7817 | 0.18 | 90 | 0.7118 | |
|
| 0.7763 | 0.2 | 100 | 0.6232 | |
|
| 0.6719 | 0.22 | 110 | 0.5972 | |
|
| 0.6852 | 0.24 | 120 | 0.5835 | |
|
| 0.7033 | 0.26 | 130 | 0.5850 | |
|
| 0.6782 | 0.28 | 140 | 0.5815 | |
|
| 0.6635 | 0.3 | 150 | 0.5757 | |
|
| 0.6405 | 0.32 | 160 | 0.5796 | |
|
| 0.5739 | 0.34 | 170 | 0.5705 | |
|
| 0.7139 | 0.36 | 180 | 0.5606 | |
|
| 0.6883 | 0.38 | 190 | 0.5592 | |
|
| 0.6429 | 0.4 | 200 | 0.5586 | |
|
| 0.7397 | 0.42 | 210 | 0.5511 | |
|
| 0.6993 | 0.44 | 220 | 0.5484 | |
|
| 0.5946 | 0.46 | 230 | 0.5515 | |
|
| 0.6172 | 0.48 | 240 | 0.5473 | |
|
| 0.6077 | 0.5 | 250 | 0.5442 | |
|
| 0.6148 | 0.52 | 260 | 0.5435 | |
|
| 0.6213 | 0.54 | 270 | 0.5425 | |
|
| 0.6431 | 0.56 | 280 | 0.5414 | |
|
| 0.6459 | 0.58 | 290 | 0.5392 | |
|
| 0.604 | 0.6 | 300 | 0.5394 | |
|
| 0.603 | 0.62 | 310 | 0.5368 | |
|
| 0.7207 | 0.64 | 320 | 0.5387 | |
|
| 0.5689 | 0.66 | 330 | 0.5407 | |
|
| 0.5721 | 0.68 | 340 | 0.5377 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.0.dev0 |
|
- Pytorch 1.12.0a0+bd13bc6 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
