Hugging Face's logo

tinutmap
/
categorAI_img

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
tinutmap commited on
Commit
ca2db63
·
verified ·
1 Parent(s): c573d08

End of training

Browse files
Files changed (4) hide show
  1. README.md +30 -25
  2. config.json +12 -10
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.8220338983050848
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.7045
37
- - Accuracy: 0.8220
38
 
39
  ## Model description
40
 
@@ -66,28 +66,33 @@ The following hyperparameters were used during training:
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | No log | 1.0 | 5 | 1.7291 | 0.3305 |
72
- | 6.2488 | 2.0 | 10 | 1.5994 | 0.6525 |
73
- | 6.2488 | 3.0 | 15 | 1.4457 | 0.6610 |
74
- | 5.1908 | 4.0 | 20 | 1.3022 | 0.6780 |
75
- | 5.1908 | 5.0 | 25 | 1.2008 | 0.7373 |
76
- | 4.2158 | 6.0 | 30 | 1.0729 | 0.7627 |
77
- | 4.2158 | 7.0 | 35 | 1.0047 | 0.7627 |
78
- | 3.6538 | 8.0 | 40 | 0.9829 | 0.7627 |
79
- | 3.6538 | 9.0 | 45 | 0.9142 | 0.7881 |
80
- | 2.9918 | 10.0 | 50 | 0.8212 | 0.8475 |
81
- | 2.9918 | 11.0 | 55 | 0.8235 | 0.8220 |
82
- | 2.69 | 12.0 | 60 | 0.7868 | 0.8136 |
83
- | 2.69 | 13.0 | 65 | 0.7657 | 0.8305 |
84
- | 2.4838 | 14.0 | 70 | 0.7228 | 0.8220 |
85
- | 2.4838 | 15.0 | 75 | 0.7381 | 0.8390 |
86
- | 2.2227 | 16.0 | 80 | 0.7062 | 0.8559 |
87
- | 2.2227 | 17.0 | 85 | 0.6916 | 0.8729 |
88
- | 2.1415 | 18.0 | 90 | 0.6925 | 0.8220 |
89
- | 2.1415 | 19.0 | 95 | 0.6786 | 0.8390 |
90
- | 1.9954 | 20.0 | 100 | 0.7045 | 0.8220 |
 
 
 
 
 
91
 
92
 
93
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.8378378378378378
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.7080
37
+ - Accuracy: 0.8378
38
 
39
  ## Model description
40
 
 
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
71
+ | No log | 0.9091 | 5 | 1.8872 | 0.3784 |
72
+ | 7.7979 | 1.9091 | 10 | 1.7777 | 0.6419 |
73
+ | 7.7979 | 2.9091 | 15 | 1.6224 | 0.6622 |
74
+ | 6.9519 | 3.9091 | 20 | 1.4667 | 0.6959 |
75
+ | 6.9519 | 4.9091 | 25 | 1.3353 | 0.7365 |
76
+ | 5.7562 | 5.9091 | 30 | 1.2522 | 0.7703 |
77
+ | 5.7562 | 6.9091 | 35 | 1.1617 | 0.7838 |
78
+ | 4.7446 | 7.9091 | 40 | 1.0967 | 0.7635 |
79
+ | 4.7446 | 8.9091 | 45 | 1.0362 | 0.7568 |
80
+ | 4.0655 | 9.9091 | 50 | 0.9349 | 0.8108 |
81
+ | 4.0655 | 10.9091 | 55 | 0.9393 | 0.7905 |
82
+ | 3.5041 | 11.9091 | 60 | 0.8859 | 0.7838 |
83
+ | 3.5041 | 12.9091 | 65 | 0.9039 | 0.7770 |
84
+ | 3.0788 | 13.9091 | 70 | 0.8123 | 0.8041 |
85
+ | 3.0788 | 14.9091 | 75 | 0.7946 | 0.8243 |
86
+ | 2.7461 | 15.9091 | 80 | 0.8003 | 0.8311 |
87
+ | 2.7461 | 16.9091 | 85 | 0.8101 | 0.7703 |
88
+ | 2.4988 | 17.9091 | 90 | 0.7111 | 0.8176 |
89
+ | 2.4988 | 18.9091 | 95 | 0.7439 | 0.8243 |
90
+ | 2.3122 | 19.9091 | 100 | 0.7542 | 0.7905 |
91
+ | 2.3122 | 20.9091 | 105 | 0.7323 | 0.8311 |
92
+ | 2.3408 | 21.9091 | 110 | 0.7175 | 0.8243 |
93
+ | 2.3408 | 22.9091 | 115 | 0.7652 | 0.8041 |
94
+ | 2.2846 | 23.9091 | 120 | 0.7211 | 0.8176 |
95
+ | 2.2846 | 24.9091 | 125 | 0.7080 | 0.8378 |
96
 
97
 
98
  ### Framework versions
config.json CHANGED
@@ -10,22 +10,24 @@
10
  "hidden_size": 768,
11
  "id2label": {
12
  "0": "accessories",
13
- "1": "panels",
14
- "2": "seat",
15
- "3": "storage",
16
- "4": "table",
17
- "5": "work surfaces"
 
18
  },
19
  "image_size": 224,
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
  "accessories": "0",
24
- "panels": "1",
25
- "seat": "2",
26
- "storage": "3",
27
- "table": "4",
28
- "work surfaces": "5"
 
29
  },
30
  "layer_norm_eps": 1e-12,
31
  "model_type": "vit",
 
10
  "hidden_size": 768,
11
  "id2label": {
12
  "0": "accessories",
13
+ "1": "light",
14
+ "2": "panels",
15
+ "3": "seat",
16
+ "4": "storage",
17
+ "5": "table",
18
+ "6": "work surfaces"
19
  },
20
  "image_size": 224,
21
  "initializer_range": 0.02,
22
  "intermediate_size": 3072,
23
  "label2id": {
24
  "accessories": "0",
25
+ "light": "1",
26
+ "panels": "2",
27
+ "seat": "3",
28
+ "storage": "4",
29
+ "table": "5",
30
+ "work surfaces": "6"
31
  },
32
  "layer_norm_eps": 1e-12,
33
  "model_type": "vit",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9135059a50788efdf75c7e89bed2be79fa38f11f4529a78677e3a69603d86f2
3
- size 343236280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295ad3e4a44a10b9c41694001ac05cedce879fbb1f9ffc7918386c7761c8e316
3
+ size 343239356
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df3681e4cb310e0e82e16b9f884dc594cf8ce160f9b5d2c0372b7c196a013d78
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d734840f32c8cdc7335aca3f8d60422caff2bb0ed40b19a57fa76a32b8cb4c
3
  size 5304