mbiarreta commited on
Commit
464e199
·
verified ·
1 Parent(s): 5668165

Model save

Browse files
Files changed (2) hide show
  1. README.md +76 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: microsoft/swin-tiny-patch4-window7-224
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: swin-ena24
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # swin-ena24
18
+
19
+ 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.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1460
22
+ - Accuracy: 0.9695
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0002
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 2
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
54
+ | 1.679 | 0.1302 | 100 | 1.2075 | 0.6573 |
55
+ | 0.9674 | 0.2604 | 200 | 0.7625 | 0.7809 |
56
+ | 0.8194 | 0.3906 | 300 | 0.7240 | 0.7931 |
57
+ | 0.5756 | 0.5208 | 400 | 0.6613 | 0.8023 |
58
+ | 0.5796 | 0.6510 | 500 | 0.3928 | 0.8947 |
59
+ | 0.5275 | 0.7812 | 600 | 0.4274 | 0.8863 |
60
+ | 0.1931 | 0.9115 | 700 | 0.4006 | 0.8908 |
61
+ | 0.254 | 1.0417 | 800 | 0.2949 | 0.9237 |
62
+ | 0.1321 | 1.1719 | 900 | 0.2565 | 0.9420 |
63
+ | 0.1888 | 1.3021 | 1000 | 0.2155 | 0.9466 |
64
+ | 0.0558 | 1.4323 | 1100 | 0.2289 | 0.9420 |
65
+ | 0.0824 | 1.5625 | 1200 | 0.1732 | 0.9634 |
66
+ | 0.1455 | 1.6927 | 1300 | 0.1689 | 0.9649 |
67
+ | 0.1453 | 1.8229 | 1400 | 0.1596 | 0.9672 |
68
+ | 0.0403 | 1.9531 | 1500 | 0.1460 | 0.9695 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.48.3
74
+ - Pytorch 2.5.1+cu124
75
+ - Datasets 3.5.0
76
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d99dde7fe8206a16c8b345d24a4c58295ad4f60556faa3c42ad5f2135aaaa41f
3
  size 110404360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60b30293564a22f6feb6f44a3f4b44b00eff8e466b3f5af7ceabb3dd6bdf397
3
  size 110404360