Commit ·
3e3d605
1
Parent(s): 4a4163d
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: vit-base-clothing-leafs-example-full-simple
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# vit-base-clothing-leafs-example-full-simple
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.0767
|
| 20 |
+
- Accuracy: 0.7045
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0001
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 5
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 52 |
+
| 1.5425 | 0.14 | 1000 | 1.2917 | 0.6362 |
|
| 53 |
+
| 1.2 | 0.28 | 2000 | 1.1728 | 0.6634 |
|
| 54 |
+
| 1.1415 | 0.41 | 3000 | 1.1331 | 0.6729 |
|
| 55 |
+
| 1.1054 | 0.55 | 4000 | 1.0928 | 0.6815 |
|
| 56 |
+
| 1.0592 | 0.69 | 5000 | 1.0824 | 0.6865 |
|
| 57 |
+
| 1.0516 | 0.83 | 6000 | 1.0709 | 0.6868 |
|
| 58 |
+
| 1.0335 | 0.97 | 7000 | 1.0542 | 0.6915 |
|
| 59 |
+
| 0.9049 | 1.11 | 8000 | 1.0505 | 0.6961 |
|
| 60 |
+
| 0.855 | 1.24 | 9000 | 1.0374 | 0.7003 |
|
| 61 |
+
| 0.8416 | 1.38 | 10000 | 1.0451 | 0.6988 |
|
| 62 |
+
| 0.8389 | 1.52 | 11000 | 1.0445 | 0.7002 |
|
| 63 |
+
| 0.8565 | 1.66 | 12000 | 1.0185 | 0.7032 |
|
| 64 |
+
| 0.8621 | 1.8 | 13000 | 1.0167 | 0.7044 |
|
| 65 |
+
| 0.8402 | 1.94 | 14000 | 1.0216 | 0.7033 |
|
| 66 |
+
| 0.7132 | 2.07 | 15000 | 1.0478 | 0.7062 |
|
| 67 |
+
| 0.5989 | 2.21 | 16000 | 1.0767 | 0.7045 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.29.2
|
| 73 |
+
- Pytorch 2.0.1
|
| 74 |
+
- Datasets 2.12.0
|
| 75 |
+
- Tokenizers 0.13.3
|