Downloads · 30 days
5
16% of all-time downloads
10-swin-base-patch4-window12-384-finetuned-spiderTraining20-500
zkdeng/10-swin-base-patch4-window12-384-finetuned-spiderTraining20-500
10-swin-base-patch4-window12-384-finetuned-spiderTraining20-500 is a machine learning model from zkdeng. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
32
Public
Repo size
3.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin352 MB · 100%
At a glance
- License
- apache-2.0
- Model type
- swin
- Access
- Public
- Created
- Sep 13, 2024
- Updated
- Sep 13, 2024
- SHA
- 7c4008bb
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. -->
10-swin-base-patch4-window12-384-finetuned-spiderTraining20-500
This model is a fine-tuned version of microsoft/swin-base-patch4-window12-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3023
- Accuracy: 0.9339
- Precision: 0.9335
- Recall: 0.9314
- F1: 0.9313
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: 0.0005
- train_batch_size: 25
- eval_batch_size: 25
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 100
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.786 | 1.0 | 80 | 0.6341 | 0.7918 | 0.8135 | 0.7860 | 0.7830 |
| 0.6519 | 2.0 | 160 | 0.6522 | 0.7958 | 0.8177 | 0.7913 | 0.7840 |
| 0.6352 | 3.0 | 240 | 0.5289 | 0.8328 | 0.8473 | 0.8255 | 0.8258 |
| 0.4922 | 4.0 | 320 | 0.5681 | 0.8448 | 0.8680 | 0.8386 | 0.8396 |
| 0.3959 | 5.0 | 400 | 0.3896 | 0.8799 | 0.8816 | 0.8772 | 0.8755 |
| 0.3277 | 6.0 | 480 | 0.3588 | 0.9119 | 0.9073 | 0.9104 | 0.9080 |
| 0.284 | 7.0 | 560 | 0.3355 | 0.9099 | 0.9126 | 0.9066 | 0.9058 |
| 0.2075 | 8.0 | 640 | 0.2876 | 0.9289 | 0.9271 | 0.9287 | 0.9269 |
| 0.1751 | 9.0 | 720 | 0.2871 | 0.9349 | 0.9337 | 0.9320 | 0.9321 |
| 0.1923 | 10.0 | 800 | 0.3023 | 0.9339 | 0.9335 | 0.9314 | 0.9313 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
- Type
- swin
- License
- apache-2.0
- Created
- Sep 13, 2024
- Updated
- Sep 13, 2024