Fadri commited on
Commit
b785ddb
·
verified ·
1 Parent(s): e4566fa

End of training

Browse files
README.md CHANGED
@@ -21,8 +21,8 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [scratch](https://huggingface.co/scratch) on the mnist dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.0181
25
- - Accuracy: 0.9946
26
 
27
  ## Model description
28
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
- | 0.0684 | 1.0 | 422 | 0.0507 | 0.985 |
57
- | 0.0448 | 2.0 | 844 | 0.0355 | 0.9885 |
58
- | 0.0389 | 3.0 | 1266 | 0.0288 | 0.9908 |
59
- | 0.0299 | 4.0 | 1688 | 0.0277 | 0.9917 |
60
- | 0.0243 | 5.0 | 2110 | 0.0262 | 0.9922 |
61
 
62
 
63
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [scratch](https://huggingface.co/scratch) on the mnist dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.0182
25
+ - Accuracy: 0.9945
26
 
27
  ## Model description
28
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
+ | 0.0687 | 1.0 | 422 | 0.0511 | 0.9852 |
57
+ | 0.0453 | 2.0 | 844 | 0.0360 | 0.9883 |
58
+ | 0.0393 | 3.0 | 1266 | 0.0295 | 0.9907 |
59
+ | 0.0297 | 4.0 | 1688 | 0.0284 | 0.9915 |
60
+ | 0.0243 | 5.0 | 2110 | 0.0267 | 0.992 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4352641d6f9d186908af727d3cfe898bc133a2b2e17acc5bdf502a9875baef52
3
  size 6719112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aec947653975a8fd70f635205547d7612b81f6e3c9389a3e50d295415fc2211
3
  size 6719112
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPFeatureExtractor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
runs/Apr29_14-40-35_ip-10-192-12-206/events.out.tfevents.1745937635.ip-10-192-12-206.137877.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e6ff6069e9621b47ccb3600209ce72d12d446a600b26b8df241e2fdeb872ca
3
+ size 10724
runs/Apr29_14-40-35_ip-10-192-12-206/events.out.tfevents.1745937902.ip-10-192-12-206.137877.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc905e2d2f9a106fbe810cc7b427ea307cc761653a408895e2bf401a62ac9437
3
+ size 411
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0123f3bf2612298c0579f87bc2c11260951832231f43688767bfcbaabd88d4a1
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68fdc4416057f004800314bf45b623f668d97d44703cd58f19a81c962a34c1c5
3
  size 5368