Downloads · 30 days
9
3% of all-time downloads
gpt2_finetuned_with_schema
iffatN/gpt2_finetuned_with_schema
gpt2_finetuned_with_schema is a text generation model from iffatN. 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
334
Public
Repo size
47.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin510 MB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- gpt2
- Access
- Public
- Created
- Apr 21, 2023
- Updated
- Apr 21, 2023
- SHA
- 1b2e6f69
Try a prompt
Datasets
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. -->
gpt2_finetuned_with_schema
This model is a fine-tuned version of gpt2 on the wikisql dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.1059
- eval_runtime: 62.0026
- eval_samples_per_second: 135.817
- eval_steps_per_second: 33.966
- epoch: 2.0
- step: 3522
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- mit
- Created
- Apr 21, 2023
- Updated
- Apr 21, 2023