Downloads · 30 days
12
18% of all-time downloads
finetuned_gpt2-medium_sst2_negation0.0001_pretrainedTrue_epochs3
jhaochenz/finetuned_gpt2-medium_sst2_negation0.0001_pretrainedTrue_epochs3
finetuned_gpt2-medium_sst2_negation0.0001_pretrainedTrue_epochs3 is a text generation model from jhaochenz. 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
68
Public
Repo size
11.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- gpt2
- Access
- Public
- Created
- Jan 15, 2023
- Updated
- Jan 15, 2023
- SHA
- 5dab27ff
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. -->
finetuned_gpt2-medium_sst2_negation0.0001_pretrainedTrue_epochs3
This model is a fine-tuned version of gpt2-medium on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 3.0503
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2809 | 1.0 | 1322 | 2.8898 |
| 1.9683 | 2.0 | 2644 | 2.9770 |
| 1.8548 | 3.0 | 3966 | 3.0503 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.7.0
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- mit
- Created
- Jan 15, 2023
- Updated
- Jan 15, 2023