Commit
•
07b37ad
1
Parent(s):
8da8c4f
Model save
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: microsoft/swin-tiny-patch4-window7-224
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: swin-tiny-patch4-window7-224-finetuned-eurosat
|
| 8 |
results: []
|
|
@@ -15,13 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
-
|
| 19 |
-
-
|
| 20 |
-
- eval_runtime: 111.9674
|
| 21 |
-
- eval_samples_per_second: 136.388
|
| 22 |
-
- eval_steps_per_second: 4.269
|
| 23 |
-
- epoch: 3.1413
|
| 24 |
-
- step: 3373
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -41,19 +38,35 @@ More information needed
|
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
- learning_rate: 5e-05
|
| 44 |
-
- train_batch_size:
|
| 45 |
-
- eval_batch_size:
|
| 46 |
- seed: 42
|
| 47 |
- gradient_accumulation_steps: 4
|
| 48 |
-
- total_train_batch_size:
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
- num_epochs: 10
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
-
- Transformers 4.
|
| 57 |
-
- Pytorch 2.
|
| 58 |
-
- Datasets 2.
|
| 59 |
-
- Tokenizers 0.
|
|
|
|
| 3 |
base_model: microsoft/swin-tiny-patch4-window7-224
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: swin-tiny-patch4-window7-224-finetuned-eurosat
|
| 10 |
results: []
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0675
|
| 21 |
+
- Accuracy: 0.9765
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 64
|
| 42 |
+
- eval_batch_size: 64
|
| 43 |
- seed: 42
|
| 44 |
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 256
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
- num_epochs: 10
|
| 50 |
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 0.2428 | 1.0 | 537 | 0.1768 | 0.9302 |
|
| 56 |
+
| 0.1877 | 2.0 | 1074 | 0.1141 | 0.9551 |
|
| 57 |
+
| 0.1574 | 3.0 | 1611 | 0.1359 | 0.9461 |
|
| 58 |
+
| 0.1412 | 4.0 | 2148 | 0.1245 | 0.9522 |
|
| 59 |
+
| 0.1289 | 5.0 | 2685 | 0.0774 | 0.9705 |
|
| 60 |
+
| 0.1116 | 6.0 | 3222 | 0.0889 | 0.9663 |
|
| 61 |
+
| 0.1091 | 7.0 | 3759 | 0.0800 | 0.9717 |
|
| 62 |
+
| 0.1096 | 8.0 | 4296 | 0.0665 | 0.9757 |
|
| 63 |
+
| 0.0996 | 9.0 | 4833 | 0.0708 | 0.9747 |
|
| 64 |
+
| 0.0992 | 10.0 | 5370 | 0.0675 | 0.9765 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
+
- Transformers 4.39.3
|
| 70 |
+
- Pytorch 2.1.2
|
| 71 |
+
- Datasets 2.18.0
|
| 72 |
+
- Tokenizers 0.15.2
|