itsLeen/vit-large-ai-or-not
Browse files- README.md +13 -52
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,11 +1,9 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
-
base_model:
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
metrics:
|
| 8 |
-
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: vit-large-ai-or-not
|
| 11 |
results: []
|
|
@@ -16,10 +14,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# vit-large-ai-or-not
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
-
|
| 22 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -42,57 +45,15 @@ The following hyperparameters were used during training:
|
|
| 42 |
- train_batch_size: 8
|
| 43 |
- eval_batch_size: 8
|
| 44 |
- seed: 42
|
|
|
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
-
- num_epochs:
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
-
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 54 |
-
| 0.1089 | 0.1074 | 200 | 0.1756 | 0.9498 |
|
| 55 |
-
| 0.041 | 0.2148 | 400 | 0.2151 | 0.9503 |
|
| 56 |
-
| 0.0566 | 0.3222 | 600 | 0.2125 | 0.9511 |
|
| 57 |
-
| 0.1028 | 0.4296 | 800 | 0.2084 | 0.9450 |
|
| 58 |
-
| 0.1722 | 0.5371 | 1000 | 0.1658 | 0.9557 |
|
| 59 |
-
| 0.1486 | 0.6445 | 1200 | 0.1312 | 0.9595 |
|
| 60 |
-
| 0.1446 | 0.7519 | 1400 | 0.1634 | 0.9565 |
|
| 61 |
-
| 0.1281 | 0.8593 | 1600 | 0.1282 | 0.9654 |
|
| 62 |
-
| 0.1584 | 0.9667 | 1800 | 0.1295 | 0.9667 |
|
| 63 |
-
| 0.0549 | 1.0741 | 2000 | 0.1613 | 0.9670 |
|
| 64 |
-
| 0.0373 | 1.1815 | 2200 | 0.1344 | 0.9723 |
|
| 65 |
-
| 0.0293 | 1.2889 | 2400 | 0.1584 | 0.9699 |
|
| 66 |
-
| 0.0251 | 1.3963 | 2600 | 0.1704 | 0.9656 |
|
| 67 |
-
| 0.0249 | 1.5038 | 2800 | 0.1586 | 0.9699 |
|
| 68 |
-
| 0.0383 | 1.6112 | 3000 | 0.1467 | 0.9715 |
|
| 69 |
-
| 0.0213 | 1.7186 | 3200 | 0.1546 | 0.9734 |
|
| 70 |
-
| 0.0544 | 1.8260 | 3400 | 0.1671 | 0.9686 |
|
| 71 |
-
| 0.0401 | 1.9334 | 3600 | 0.1870 | 0.9656 |
|
| 72 |
-
| 0.0288 | 2.0408 | 3800 | 0.1981 | 0.9600 |
|
| 73 |
-
| 0.0078 | 2.1482 | 4000 | 0.1422 | 0.9748 |
|
| 74 |
-
| 0.0037 | 2.2556 | 4200 | 0.1775 | 0.9705 |
|
| 75 |
-
| 0.0035 | 2.3631 | 4400 | 0.1845 | 0.9705 |
|
| 76 |
-
| 0.0043 | 2.4705 | 4600 | 0.2001 | 0.9710 |
|
| 77 |
-
| 0.0049 | 2.5779 | 4800 | 0.2145 | 0.9689 |
|
| 78 |
-
| 0.01 | 2.6853 | 5000 | 0.1445 | 0.9750 |
|
| 79 |
-
| 0.0039 | 2.7927 | 5200 | 0.1509 | 0.9748 |
|
| 80 |
-
| 0.0055 | 2.9001 | 5400 | 0.1674 | 0.9748 |
|
| 81 |
-
| 0.0094 | 3.0075 | 5600 | 0.1569 | 0.9748 |
|
| 82 |
-
| 0.0018 | 3.1149 | 5800 | 0.1580 | 0.9753 |
|
| 83 |
-
| 0.0 | 3.2223 | 6000 | 0.1698 | 0.9761 |
|
| 84 |
-
| 0.0003 | 3.3298 | 6200 | 0.1606 | 0.9761 |
|
| 85 |
-
| 0.0034 | 3.4372 | 6400 | 0.1870 | 0.9737 |
|
| 86 |
-
| 0.0 | 3.5446 | 6600 | 0.1697 | 0.9756 |
|
| 87 |
-
| 0.0 | 3.6520 | 6800 | 0.1673 | 0.9750 |
|
| 88 |
-
| 0.0053 | 3.7594 | 7000 | 0.1644 | 0.9753 |
|
| 89 |
-
| 0.0 | 3.8668 | 7200 | 0.1676 | 0.9753 |
|
| 90 |
-
| 0.0013 | 3.9742 | 7400 | 0.1641 | 0.9761 |
|
| 91 |
-
|
| 92 |
-
|
| 93 |
### Framework versions
|
| 94 |
|
| 95 |
- Transformers 4.44.2
|
| 96 |
-
- Pytorch 2.
|
| 97 |
-
- Datasets 3.0.2
|
| 98 |
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
+
base_model: microsoft/swin-base-patch4-window7-224
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: vit-large-ai-or-not
|
| 9 |
results: []
|
|
|
|
| 14 |
|
| 15 |
# vit-large-ai-or-not
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- eval_loss: 0.1679
|
| 20 |
+
- eval_accuracy: 0.9801
|
| 21 |
+
- eval_runtime: 50.6302
|
| 22 |
+
- eval_samples_per_second: 73.553
|
| 23 |
+
- eval_steps_per_second: 9.204
|
| 24 |
+
- epoch: 7.9484
|
| 25 |
+
- step: 7400
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 45 |
- train_batch_size: 8
|
| 46 |
- eval_batch_size: 8
|
| 47 |
- seed: 42
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 16
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 30
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- Transformers 4.44.2
|
| 58 |
+
- Pytorch 2.5.0+cu121
|
|
|
|
| 59 |
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 347498816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a503ffd3fcc58dd4d65a07ba41b8cab1ebec8e20d847afe0406137eea75995e9
|
| 3 |
size 347498816
|