Downloads · 30 days
7
10% of all-time downloads
jiangnan-gpt2
jiang-psy-infj/jiangnan-gpt2
jiangnan-gpt2 is a text generation model from jiang-psy-infj. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
71
Public
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin466 MB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- gpt2
- Access
- Public
- Created
- Aug 17, 2023
- Updated
- Aug 20, 2023
- SHA
- 384e5894
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
jiangnan-gpt2
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3111
Model description
causal language model, tokenizer based on Chinese words.
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: 0.0005
- train_batch_size: 70
- eval_batch_size: 55
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 560
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8773 | 0.3 | 2000 | 2.9219 |
| 2.6651 | 0.6 | 4000 | 2.6712 |
| 2.5012 | 0.9 | 6000 | 2.5307 |
| 2.3838 | 1.2 | 8000 | 2.4271 |
| 2.3019 | 1.5 | 10000 | 2.3489 |
| 2.2531 | 1.8 | 12000 | 2.3111 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- mit
- Languages
- zh
- Created
- Aug 17, 2023
- Updated
- Aug 20, 2023