Downloads · 30 days
4
9% of all-time downloads
t5_large-qg-ap-nopeft
tiagoblima/t5_large-qg-ap-nopeft
t5_large-qg-ap-nopeft is a machine learning model from tiagoblima. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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
43
Public
Parameters
738M
14.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3 GB · 100%
At a glance
- Library
- transformers
- License
- mit
- Model type
- t5
- Access
- Public
- Created
- Jan 6, 2024
- Updated
- Jan 6, 2024
- SHA
- f9b12bbd
Base models
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. -->
t5_large-qg-ap-nopeft
This model is a fine-tuned version of unicamp-dl/ptt5-large-t5-vocab on the tiagoblima/qg_squad_v1_pt dataset. It achieves the following results on the evaluation set:
- Loss: 1.1994
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1714 | 1.0 | 808 | 1.2385 |
| 1.0782 | 2.0 | 1616 | 1.2066 |
| 1.0064 | 3.0 | 2424 | 1.1994 |
| 0.9555 | 4.0 | 3232 | 1.2031 |
| 0.9261 | 5.0 | 4040 | 1.2048 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Library
- transformers
- Type
- t5
- License
- mit
- Created
- Jan 6, 2024
- Updated
- Jan 6, 2024