Commit
•
4ccc25a
1
Parent(s):
462d304
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/deit-tiny-patch16-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: smids_3x_deit_tiny_sgd_001_fold2
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: imagefolder
|
| 18 |
+
type: imagefolder
|
| 19 |
+
config: default
|
| 20 |
+
split: test
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8652246256239601
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# smids_3x_deit_tiny_sgd_001_fold2
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.3631
|
| 36 |
+
- Accuracy: 0.8652
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 0.001
|
| 56 |
+
- train_batch_size: 32
|
| 57 |
+
- eval_batch_size: 32
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 62 |
+
- num_epochs: 50
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 68 |
+
| 0.9177 | 1.0 | 225 | 0.8996 | 0.5691 |
|
| 69 |
+
| 0.6997 | 2.0 | 450 | 0.6912 | 0.7121 |
|
| 70 |
+
| 0.5229 | 3.0 | 675 | 0.5718 | 0.7671 |
|
| 71 |
+
| 0.5533 | 4.0 | 900 | 0.5111 | 0.8020 |
|
| 72 |
+
| 0.4272 | 5.0 | 1125 | 0.4697 | 0.8070 |
|
| 73 |
+
| 0.3877 | 6.0 | 1350 | 0.4425 | 0.8170 |
|
| 74 |
+
| 0.4004 | 7.0 | 1575 | 0.4203 | 0.8336 |
|
| 75 |
+
| 0.3661 | 8.0 | 1800 | 0.4043 | 0.8369 |
|
| 76 |
+
| 0.3402 | 9.0 | 2025 | 0.3983 | 0.8386 |
|
| 77 |
+
| 0.2899 | 10.0 | 2250 | 0.3839 | 0.8486 |
|
| 78 |
+
| 0.3594 | 11.0 | 2475 | 0.3760 | 0.8469 |
|
| 79 |
+
| 0.2789 | 12.0 | 2700 | 0.3717 | 0.8502 |
|
| 80 |
+
| 0.2808 | 13.0 | 2925 | 0.3681 | 0.8502 |
|
| 81 |
+
| 0.2912 | 14.0 | 3150 | 0.3664 | 0.8552 |
|
| 82 |
+
| 0.2944 | 15.0 | 3375 | 0.3661 | 0.8502 |
|
| 83 |
+
| 0.3273 | 16.0 | 3600 | 0.3677 | 0.8552 |
|
| 84 |
+
| 0.2474 | 17.0 | 3825 | 0.3614 | 0.8552 |
|
| 85 |
+
| 0.1928 | 18.0 | 4050 | 0.3628 | 0.8569 |
|
| 86 |
+
| 0.2096 | 19.0 | 4275 | 0.3553 | 0.8519 |
|
| 87 |
+
| 0.2614 | 20.0 | 4500 | 0.3573 | 0.8552 |
|
| 88 |
+
| 0.2898 | 21.0 | 4725 | 0.3557 | 0.8619 |
|
| 89 |
+
| 0.3219 | 22.0 | 4950 | 0.3582 | 0.8536 |
|
| 90 |
+
| 0.3025 | 23.0 | 5175 | 0.3562 | 0.8602 |
|
| 91 |
+
| 0.28 | 24.0 | 5400 | 0.3553 | 0.8569 |
|
| 92 |
+
| 0.2538 | 25.0 | 5625 | 0.3547 | 0.8569 |
|
| 93 |
+
| 0.2485 | 26.0 | 5850 | 0.3551 | 0.8586 |
|
| 94 |
+
| 0.2246 | 27.0 | 6075 | 0.3556 | 0.8619 |
|
| 95 |
+
| 0.2303 | 28.0 | 6300 | 0.3556 | 0.8602 |
|
| 96 |
+
| 0.2272 | 29.0 | 6525 | 0.3568 | 0.8619 |
|
| 97 |
+
| 0.2494 | 30.0 | 6750 | 0.3572 | 0.8602 |
|
| 98 |
+
| 0.1942 | 31.0 | 6975 | 0.3593 | 0.8619 |
|
| 99 |
+
| 0.2095 | 32.0 | 7200 | 0.3591 | 0.8619 |
|
| 100 |
+
| 0.2432 | 33.0 | 7425 | 0.3587 | 0.8619 |
|
| 101 |
+
| 0.2713 | 34.0 | 7650 | 0.3578 | 0.8586 |
|
| 102 |
+
| 0.1998 | 35.0 | 7875 | 0.3599 | 0.8619 |
|
| 103 |
+
| 0.2229 | 36.0 | 8100 | 0.3607 | 0.8586 |
|
| 104 |
+
| 0.2109 | 37.0 | 8325 | 0.3599 | 0.8619 |
|
| 105 |
+
| 0.1909 | 38.0 | 8550 | 0.3609 | 0.8602 |
|
| 106 |
+
| 0.1902 | 39.0 | 8775 | 0.3619 | 0.8586 |
|
| 107 |
+
| 0.2221 | 40.0 | 9000 | 0.3623 | 0.8586 |
|
| 108 |
+
| 0.1747 | 41.0 | 9225 | 0.3610 | 0.8586 |
|
| 109 |
+
| 0.1796 | 42.0 | 9450 | 0.3605 | 0.8602 |
|
| 110 |
+
| 0.1695 | 43.0 | 9675 | 0.3624 | 0.8619 |
|
| 111 |
+
| 0.2018 | 44.0 | 9900 | 0.3615 | 0.8619 |
|
| 112 |
+
| 0.2591 | 45.0 | 10125 | 0.3627 | 0.8602 |
|
| 113 |
+
| 0.2 | 46.0 | 10350 | 0.3630 | 0.8602 |
|
| 114 |
+
| 0.1903 | 47.0 | 10575 | 0.3635 | 0.8619 |
|
| 115 |
+
| 0.1709 | 48.0 | 10800 | 0.3630 | 0.8636 |
|
| 116 |
+
| 0.21 | 49.0 | 11025 | 0.3631 | 0.8636 |
|
| 117 |
+
| 0.168 | 50.0 | 11250 | 0.3631 | 0.8652 |
|
| 118 |
+
|
| 119 |
+
|
| 120 |
+
### Framework versions
|
| 121 |
+
|
| 122 |
+
- Transformers 4.32.1
|
| 123 |
+
- Pytorch 2.1.1+cu121
|
| 124 |
+
- Datasets 2.12.0
|
| 125 |
+
- Tokenizers 0.13.2
|