Downloads · 30 days
8
4% of all-time downloads
mt5-small-task2-dataset2
ZhiguangHan/mt5-small-task2-dataset2
mt5-small-task2-dataset2 is a machine learning model from ZhiguangHan. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
218
Public
Parameters
300M
31.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 98%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- mt5
- Access
- Public
- Created
- Dec 9, 2023
- Updated
- Jan 22, 2024
- SHA
- e94a6bef
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. -->
mt5-small-task2-dataset2
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4320
- Accuracy: 0.37
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: 5.6e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 7.018 | 1.0 | 250 | 1.2234 | 0.014 |
| 1.6684 | 2.0 | 500 | 0.8157 | 0.124 |
| 1.0289 | 3.0 | 750 | 0.6527 | 0.222 |
| 0.8021 | 4.0 | 1000 | 0.5877 | 0.282 |
| 0.6964 | 5.0 | 1250 | 0.5360 | 0.3 |
| 0.6252 | 6.0 | 1500 | 0.5118 | 0.32 |
| 0.5828 | 7.0 | 1750 | 0.4899 | 0.318 |
| 0.5436 | 8.0 | 2000 | 0.4718 | 0.35 |
| 0.5232 | 9.0 | 2250 | 0.4625 | 0.34 |
| 0.5005 | 10.0 | 2500 | 0.4556 | 0.342 |
| 0.4789 | 11.0 | 2750 | 0.4436 | 0.356 |
| 0.4733 | 12.0 | 3000 | 0.4379 | 0.356 |
| 0.4651 | 13.0 | 3250 | 0.4347 | 0.366 |
| 0.4591 | 14.0 | 3500 | 0.4320 | 0.37 |
| 0.4508 | 15.0 | 3750 | 0.4320 | 0.37 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Tokenizers 0.15.0
- Library
- transformers
- Type
- mt5
- License
- apache-2.0
- Created
- Dec 9, 2023
- Updated
- Jan 22, 2024