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_16_e4
|
| 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_16_e4
|
| 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: 0.3598
|
| 20 |
+
- Accuracy: 0.9059
|
| 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: 4
|
| 46 |
+
- mixed_precision_training: Apex, opt level O1
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 3.7606 | 0.16 | 100 | 3.7839 | 0.1989 |
|
| 53 |
+
| 3.1072 | 0.31 | 200 | 3.0251 | 0.3285 |
|
| 54 |
+
| 2.4068 | 0.47 | 300 | 2.4380 | 0.4719 |
|
| 55 |
+
| 2.0881 | 0.63 | 400 | 2.0489 | 0.5412 |
|
| 56 |
+
| 1.6817 | 0.78 | 500 | 1.7968 | 0.6025 |
|
| 57 |
+
| 1.342 | 0.94 | 600 | 1.5044 | 0.6249 |
|
| 58 |
+
| 0.9343 | 1.1 | 700 | 1.1881 | 0.7132 |
|
| 59 |
+
| 0.9552 | 1.25 | 800 | 1.1064 | 0.7224 |
|
| 60 |
+
| 0.7265 | 1.41 | 900 | 0.9189 | 0.7768 |
|
| 61 |
+
| 0.6732 | 1.56 | 1000 | 0.9227 | 0.7606 |
|
| 62 |
+
| 0.5587 | 1.72 | 1100 | 0.7912 | 0.7903 |
|
| 63 |
+
| 0.6332 | 1.88 | 1200 | 0.7606 | 0.7945 |
|
| 64 |
+
| 0.3188 | 2.03 | 1300 | 0.6535 | 0.8288 |
|
| 65 |
+
| 0.3079 | 2.19 | 1400 | 0.5686 | 0.8577 |
|
| 66 |
+
| 0.2518 | 2.35 | 1500 | 0.5517 | 0.8577 |
|
| 67 |
+
| 0.2 | 2.5 | 1600 | 0.5277 | 0.8631 |
|
| 68 |
+
| 0.2032 | 2.66 | 1700 | 0.4841 | 0.8701 |
|
| 69 |
+
| 0.1555 | 2.82 | 1800 | 0.4578 | 0.8793 |
|
| 70 |
+
| 0.145 | 2.97 | 1900 | 0.4466 | 0.8755 |
|
| 71 |
+
| 0.0985 | 3.13 | 2000 | 0.4249 | 0.8867 |
|
| 72 |
+
| 0.0955 | 3.29 | 2100 | 0.3977 | 0.8932 |
|
| 73 |
+
| 0.0438 | 3.44 | 2200 | 0.3785 | 0.9036 |
|
| 74 |
+
| 0.0589 | 3.6 | 2300 | 0.3717 | 0.9017 |
|
| 75 |
+
| 0.0709 | 3.76 | 2400 | 0.3609 | 0.9052 |
|
| 76 |
+
| 0.0706 | 3.91 | 2500 | 0.3598 | 0.9059 |
|
| 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
|