Commit
•
c053326
1
Parent(s):
674bbaa
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- snacks
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: vit-snacks
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: snacks
|
| 17 |
+
type: snacks
|
| 18 |
+
args: default
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.9392670157068063
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# vit-snacks
|
| 29 |
+
|
| 30 |
+
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 snacks dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.2782
|
| 33 |
+
- Accuracy: 0.9393
|
| 34 |
+
|
| 35 |
+
## Model description
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training and evaluation data
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training procedure
|
| 48 |
+
|
| 49 |
+
### Training hyperparameters
|
| 50 |
+
|
| 51 |
+
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 0.0002
|
| 53 |
+
- train_batch_size: 16
|
| 54 |
+
- eval_batch_size: 8
|
| 55 |
+
- seed: 42
|
| 56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 57 |
+
- lr_scheduler_type: linear
|
| 58 |
+
- num_epochs: 5
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 64 |
+
| 0.8724 | 0.33 | 100 | 0.9118 | 0.8670 |
|
| 65 |
+
| 0.5628 | 0.66 | 200 | 0.6873 | 0.8471 |
|
| 66 |
+
| 0.4421 | 0.99 | 300 | 0.4995 | 0.8691 |
|
| 67 |
+
| 0.2837 | 1.32 | 400 | 0.4008 | 0.9026 |
|
| 68 |
+
| 0.1645 | 1.65 | 500 | 0.3702 | 0.9058 |
|
| 69 |
+
| 0.1604 | 1.98 | 600 | 0.3981 | 0.8921 |
|
| 70 |
+
| 0.0498 | 2.31 | 700 | 0.3185 | 0.9204 |
|
| 71 |
+
| 0.0406 | 2.64 | 800 | 0.3427 | 0.9141 |
|
| 72 |
+
| 0.1049 | 2.97 | 900 | 0.3444 | 0.9173 |
|
| 73 |
+
| 0.0272 | 3.3 | 1000 | 0.3168 | 0.9246 |
|
| 74 |
+
| 0.0186 | 3.63 | 1100 | 0.3142 | 0.9288 |
|
| 75 |
+
| 0.0203 | 3.96 | 1200 | 0.2931 | 0.9298 |
|
| 76 |
+
| 0.007 | 4.29 | 1300 | 0.2754 | 0.9393 |
|
| 77 |
+
| 0.0072 | 4.62 | 1400 | 0.2778 | 0.9403 |
|
| 78 |
+
| 0.0073 | 4.95 | 1500 | 0.2782 | 0.9393 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.20.1
|
| 84 |
+
- Pytorch 1.11.0+cu113
|
| 85 |
+
- Datasets 2.3.2
|
| 86 |
+
- Tokenizers 0.12.1
|