update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: MultiLabel_V3
|
| 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 |
+
# MultiLabel_V3
|
| 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: 0.9683
|
| 20 |
+
- Accuracy: 0.7370
|
| 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: 0.0002
|
| 40 |
+
- train_batch_size: 16
|
| 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: 2
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 51 |
+
| 0.8572 | 0.1 | 100 | 1.1607 | 0.6466 |
|
| 52 |
+
| 0.8578 | 0.2 | 200 | 1.1956 | 0.6499 |
|
| 53 |
+
| 0.7362 | 0.3 | 300 | 1.1235 | 0.6885 |
|
| 54 |
+
| 0.8569 | 0.39 | 400 | 1.0460 | 0.6891 |
|
| 55 |
+
| 0.4851 | 0.49 | 500 | 1.1213 | 0.6891 |
|
| 56 |
+
| 0.7252 | 0.59 | 600 | 1.1512 | 0.6720 |
|
| 57 |
+
| 0.6333 | 0.69 | 700 | 1.1039 | 0.6913 |
|
| 58 |
+
| 0.6239 | 0.79 | 800 | 1.0636 | 0.7001 |
|
| 59 |
+
| 0.2768 | 0.89 | 900 | 1.0386 | 0.7073 |
|
| 60 |
+
| 0.4872 | 0.99 | 1000 | 1.0311 | 0.7062 |
|
| 61 |
+
| 0.3049 | 1.09 | 1100 | 1.0437 | 0.7155 |
|
| 62 |
+
| 0.1435 | 1.18 | 1200 | 1.0343 | 0.7222 |
|
| 63 |
+
| 0.2088 | 1.28 | 1300 | 1.0784 | 0.7194 |
|
| 64 |
+
| 0.4972 | 1.38 | 1400 | 1.1072 | 0.7166 |
|
| 65 |
+
| 0.3604 | 1.48 | 1500 | 1.0438 | 0.7150 |
|
| 66 |
+
| 0.2726 | 1.58 | 1600 | 1.0077 | 0.7293 |
|
| 67 |
+
| 0.3106 | 1.68 | 1700 | 1.0029 | 0.7326 |
|
| 68 |
+
| 0.3259 | 1.78 | 1800 | 0.9906 | 0.7310 |
|
| 69 |
+
| 0.3323 | 1.88 | 1900 | 0.9729 | 0.7359 |
|
| 70 |
+
| 0.2998 | 1.97 | 2000 | 0.9683 | 0.7370 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.26.1
|
| 76 |
+
- Pytorch 1.13.1+cu116
|
| 77 |
+
- Datasets 2.10.1
|
| 78 |
+
- Tokenizers 0.13.2
|