Downloads · 30 days
15
3% of all-time downloads
PCT3F_new_wangchanberta-base-att-spm-uncased
Tonjk/PCT3F_new_wangchanberta-base-att-spm-uncased
PCT3F_new_wangchanberta-base-att-spm-uncased is a fill-mask model from Tonjk. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
455
Public
Parameters
110M
2.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors442 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- camembert
- Access
- Public
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023
- SHA
- f5269831
Try a prompt
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. -->
PCT3F_new_wangchanberta-base-att-spm-uncased
This model is a fine-tuned version of airesearch/wangchanberta-base-att-spm-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4920
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8872 | 1.0 | 4321 | 0.5377 |
| 0.5102 | 2.0 | 8642 | 0.4925 |
| 0.4445 | 3.0 | 12963 | 0.4779 |
| 0.4047 | 4.0 | 17284 | 0.4855 |
| 0.3802 | 5.0 | 21605 | 0.4920 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 1.17.0
- Tokenizers 0.14.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- camembert
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023