update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: exper_batch_32_e8
|
| 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 |
+
# exper_batch_32_e8
|
| 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: 0.3520
|
| 20 |
+
- Accuracy: 0.9113
|
| 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: 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: 8
|
| 46 |
+
- mixed_precision_training: Apex, opt level O1
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 3.3787 | 0.31 | 100 | 3.3100 | 0.3566 |
|
| 53 |
+
| 2.3975 | 0.62 | 200 | 2.3196 | 0.5717 |
|
| 54 |
+
| 1.5578 | 0.94 | 300 | 1.6764 | 0.6461 |
|
| 55 |
+
| 1.0291 | 1.25 | 400 | 1.1713 | 0.7463 |
|
| 56 |
+
| 0.8185 | 1.56 | 500 | 0.9292 | 0.7953 |
|
| 57 |
+
| 0.6181 | 1.88 | 600 | 0.7732 | 0.8169 |
|
| 58 |
+
| 0.3873 | 2.19 | 700 | 0.6877 | 0.8277 |
|
| 59 |
+
| 0.2979 | 2.5 | 800 | 0.6250 | 0.8404 |
|
| 60 |
+
| 0.2967 | 2.81 | 900 | 0.6151 | 0.8365 |
|
| 61 |
+
| 0.1874 | 3.12 | 1000 | 0.5401 | 0.8608 |
|
| 62 |
+
| 0.2232 | 3.44 | 1100 | 0.5032 | 0.8712 |
|
| 63 |
+
| 0.1109 | 3.75 | 1200 | 0.4635 | 0.8774 |
|
| 64 |
+
| 0.0539 | 4.06 | 1300 | 0.4495 | 0.8843 |
|
| 65 |
+
| 0.0668 | 4.38 | 1400 | 0.4273 | 0.8951 |
|
| 66 |
+
| 0.0567 | 4.69 | 1500 | 0.4427 | 0.8867 |
|
| 67 |
+
| 0.0285 | 5.0 | 1600 | 0.4092 | 0.8955 |
|
| 68 |
+
| 0.0473 | 5.31 | 1700 | 0.3720 | 0.9071 |
|
| 69 |
+
| 0.0225 | 5.62 | 1800 | 0.3691 | 0.9063 |
|
| 70 |
+
| 0.0196 | 5.94 | 1900 | 0.3775 | 0.9048 |
|
| 71 |
+
| 0.0173 | 6.25 | 2000 | 0.3641 | 0.9040 |
|
| 72 |
+
| 0.0092 | 6.56 | 2100 | 0.3551 | 0.9090 |
|
| 73 |
+
| 0.008 | 6.88 | 2200 | 0.3591 | 0.9125 |
|
| 74 |
+
| 0.0072 | 7.19 | 2300 | 0.3542 | 0.9121 |
|
| 75 |
+
| 0.007 | 7.5 | 2400 | 0.3532 | 0.9106 |
|
| 76 |
+
| 0.007 | 7.81 | 2500 | 0.3520 | 0.9113 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.19.4
|
| 82 |
+
- Pytorch 1.5.1
|
| 83 |
+
- Datasets 2.3.2
|
| 84 |
+
- Tokenizers 0.12.1
|