Downloads · 30 days
4
14% of all-time downloads
10-finetuned-spiderTraining50-200
zkdeng/10-finetuned-spiderTraining50-200
10-finetuned-spiderTraining50-200 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
29
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin112 MB · 100%
At a glance
- License
- apache-2.0
- Model type
- convnextv2
- Access
- Public
- Created
- Aug 20, 2024
- Updated
- Aug 20, 2024
- SHA
- 71a8971e
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-finetuned-spiderTraining50-200
This model is a fine-tuned version of facebook/convnextv2-tiny-22k-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3858
- Accuracy: 0.8899
- Precision: 0.8906
- Recall: 0.8904
- F1: 0.8882
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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|---|---|---|
| 1.6006 | 1.0 | 125 | 1.3292 | 0.6246 | 0.6998 | 0.6230 | 0.6169 |
| 1.3122 | 2.0 | 250 | 1.0785 | 0.6747 | 0.7123 | 0.6769 | 0.6664 |
| 0.8869 | 3.0 | 375 | 0.9295 | 0.7367 | 0.7838 | 0.7398 | 0.7424 |
| 0.7394 | 4.0 | 500 | 0.6719 | 0.8078 | 0.8157 | 0.8089 | 0.8041 |
| 0.5704 | 5.0 | 625 | 0.6200 | 0.8198 | 0.8320 | 0.8265 | 0.8176 |
| 0.4273 | 6.0 | 750 | 0.5874 | 0.8338 | 0.8469 | 0.8338 | 0.8310 |
| 0.3289 | 7.0 | 875 | 0.5009 | 0.8549 | 0.8618 | 0.8523 | 0.8519 |
| 0.2828 | 8.0 | 1000 | 0.4697 | 0.8699 | 0.8728 | 0.8696 | 0.8677 |
| 0.2991 | 9.0 | 1125 | 0.4464 | 0.8639 | 0.8651 | 0.8653 | 0.8609 |
| 0.2108 | 10.0 | 1250 | 0.3858 | 0.8899 | 0.8906 | 0.8904 | 0.8882 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
- Type
- convnextv2
- License
- apache-2.0
- Created
- Aug 20, 2024
- Updated
- Aug 20, 2024