Hugging Face's logo

Raihan004
/
Action_model

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Raihan004 commited on
Commit
afe7fca
•
1 Parent(s): bae8716

Model save

Browse files
Files changed (4) hide show
  1. README.md +68 -19
  2. model.safetensors +1 -1
  3. runs/Apr17_15-48-28_43f826248acb/events.out.tfevents.1713369257.43f826248acb.34.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -2,7 +2,6 @@
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
- - image-classification
6
  - generated_from_trainer
7
  datasets:
8
  - imagefolder
@@ -15,7 +14,7 @@ model-index:
15
  name: Image Classification
16
  type: image-classification
17
  dataset:
18
- name: action_class
19
  type: imagefolder
20
  config: default
21
  split: train
@@ -23,7 +22,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.7847619047619048
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # Action_model
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 action_class dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.7120
37
- - Accuracy: 0.7848
38
 
39
  ## Model description
40
 
@@ -59,25 +58,75 @@ The following hyperparameters were used during training:
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
- - num_epochs: 2
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 1.3489 | 0.16 | 100 | 1.2612 | 0.7 |
70
- | 1.0112 | 0.32 | 200 | 0.9050 | 0.7590 |
71
- | 0.7962 | 0.48 | 300 | 0.8522 | 0.7505 |
72
- | 0.6383 | 0.64 | 400 | 0.8676 | 0.7219 |
73
- | 0.6485 | 0.8 | 500 | 0.8052 | 0.7324 |
74
- | 0.5452 | 0.96 | 600 | 0.7120 | 0.7848 |
75
- | 0.4882 | 1.11 | 700 | 0.7478 | 0.7714 |
76
- | 0.3409 | 1.27 | 800 | 0.7311 | 0.7743 |
77
- | 0.4105 | 1.43 | 900 | 0.7353 | 0.7810 |
78
- | 0.4011 | 1.59 | 1000 | 0.8154 | 0.7457 |
79
- | 0.3493 | 1.75 | 1100 | 0.7398 | 0.7752 |
80
- | 0.3389 | 1.91 | 1200 | 0.7365 | 0.7676 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
 
82
 
83
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
 
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
 
14
  name: Image Classification
15
  type: image-classification
16
  dataset:
17
+ name: imagefolder
18
  type: imagefolder
19
  config: default
20
  split: train
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.7466666666666667
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # Action_model
32
 
33
+ 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.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.1523
36
+ - Accuracy: 0.7467
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 10
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.3291 | 0.16 | 100 | 1.1433 | 0.7457 |
69
+ | 0.9409 | 0.32 | 200 | 0.8621 | 0.7686 |
70
+ | 0.7815 | 0.48 | 300 | 0.7599 | 0.7676 |
71
+ | 0.6803 | 0.64 | 400 | 0.8861 | 0.7210 |
72
+ | 0.6277 | 0.8 | 500 | 0.8190 | 0.7305 |
73
+ | 0.5569 | 0.96 | 600 | 0.6443 | 0.7990 |
74
+ | 0.5029 | 1.11 | 700 | 0.7456 | 0.7676 |
75
+ | 0.3852 | 1.27 | 800 | 0.7609 | 0.7695 |
76
+ | 0.4065 | 1.43 | 900 | 0.7442 | 0.7705 |
77
+ | 0.4319 | 1.59 | 1000 | 0.8240 | 0.7543 |
78
+ | 0.4167 | 1.75 | 1100 | 0.8335 | 0.7571 |
79
+ | 0.3778 | 1.91 | 1200 | 0.8210 | 0.7667 |
80
+ | 0.3818 | 2.07 | 1300 | 0.8431 | 0.7486 |
81
+ | 0.3249 | 2.23 | 1400 | 0.9156 | 0.7276 |
82
+ | 0.2931 | 2.39 | 1500 | 0.8948 | 0.7371 |
83
+ | 0.2808 | 2.55 | 1600 | 0.9114 | 0.7467 |
84
+ | 0.2767 | 2.71 | 1700 | 0.8772 | 0.7590 |
85
+ | 0.3422 | 2.87 | 1800 | 0.8072 | 0.7676 |
86
+ | 0.2441 | 3.03 | 1900 | 0.9659 | 0.7381 |
87
+ | 0.2438 | 3.18 | 2000 | 0.7905 | 0.7924 |
88
+ | 0.3925 | 3.34 | 2100 | 0.9977 | 0.7305 |
89
+ | 0.263 | 3.5 | 2200 | 0.8677 | 0.7619 |
90
+ | 0.2585 | 3.66 | 2300 | 1.0279 | 0.7390 |
91
+ | 0.2523 | 3.82 | 2400 | 0.8742 | 0.7829 |
92
+ | 0.2322 | 3.98 | 2500 | 0.8817 | 0.7790 |
93
+ | 0.1948 | 4.14 | 2600 | 0.8387 | 0.7848 |
94
+ | 0.2318 | 4.3 | 2700 | 1.1542 | 0.7124 |
95
+ | 0.2184 | 4.46 | 2800 | 1.1387 | 0.7152 |
96
+ | 0.2484 | 4.62 | 2900 | 1.0976 | 0.7248 |
97
+ | 0.1575 | 4.78 | 3000 | 1.0478 | 0.7457 |
98
+ | 0.2028 | 4.94 | 3100 | 1.0374 | 0.7448 |
99
+ | 0.1173 | 5.1 | 3200 | 1.0067 | 0.7610 |
100
+ | 0.1313 | 5.25 | 3300 | 1.1971 | 0.7267 |
101
+ | 0.2142 | 5.41 | 3400 | 1.1455 | 0.74 |
102
+ | 0.1302 | 5.57 | 3500 | 1.0319 | 0.7629 |
103
+ | 0.2193 | 5.73 | 3600 | 0.9746 | 0.7733 |
104
+ | 0.1778 | 5.89 | 3700 | 1.0207 | 0.7552 |
105
+ | 0.1003 | 6.05 | 3800 | 1.0538 | 0.7638 |
106
+ | 0.1644 | 6.21 | 3900 | 1.1832 | 0.7305 |
107
+ | 0.1843 | 6.37 | 4000 | 1.0814 | 0.7495 |
108
+ | 0.129 | 6.53 | 4100 | 1.2479 | 0.72 |
109
+ | 0.17 | 6.69 | 4200 | 1.1575 | 0.7419 |
110
+ | 0.2184 | 6.85 | 4300 | 1.0946 | 0.7562 |
111
+ | 0.1506 | 7.01 | 4400 | 1.0580 | 0.7714 |
112
+ | 0.1099 | 7.17 | 4500 | 1.0479 | 0.7638 |
113
+ | 0.1226 | 7.32 | 4600 | 1.1307 | 0.7495 |
114
+ | 0.2122 | 7.48 | 4700 | 1.2838 | 0.7286 |
115
+ | 0.1565 | 7.64 | 4800 | 1.2040 | 0.7390 |
116
+ | 0.151 | 7.8 | 4900 | 1.2361 | 0.7429 |
117
+ | 0.0934 | 7.96 | 5000 | 1.1985 | 0.7457 |
118
+ | 0.1374 | 8.12 | 5100 | 1.1365 | 0.7495 |
119
+ | 0.1799 | 8.28 | 5200 | 1.1371 | 0.7581 |
120
+ | 0.1496 | 8.44 | 5300 | 1.1775 | 0.7429 |
121
+ | 0.0804 | 8.6 | 5400 | 1.1278 | 0.7562 |
122
+ | 0.12 | 8.76 | 5500 | 1.1210 | 0.7533 |
123
+ | 0.099 | 8.92 | 5600 | 1.1295 | 0.7486 |
124
+ | 0.1429 | 9.08 | 5700 | 1.2079 | 0.7390 |
125
+ | 0.0959 | 9.24 | 5800 | 1.1451 | 0.7476 |
126
+ | 0.0263 | 9.39 | 5900 | 1.1176 | 0.7514 |
127
+ | 0.0936 | 9.55 | 6000 | 1.1179 | 0.7533 |
128
+ | 0.1332 | 9.71 | 6100 | 1.1387 | 0.7486 |
129
+ | 0.071 | 9.87 | 6200 | 1.1523 | 0.7467 |
130
 
131
 
132
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e092f25460757f6e7cf8b9970d399547ecd83e34b7ff04cfaa4d8e6f78d55a5
3
  size 343248584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62faa2e5b8a3a31e455fcc990a986f000a21efc3e9603f74d88f7558ded49f80
3
  size 343248584
runs/Apr17_15-48-28_43f826248acb/events.out.tfevents.1713369257.43f826248acb.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9856a729f9c82842d73188590bbdeccd69d6f57a1587e8edf77349e569ca3699
3
+ size 97769
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1180ed796bb3cf15dda3e0346fe0d067efe07eeeb8dc59c43f5750c0d790dbaf
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34fdbe88bbadf111a47562e45e3b8a5dc649c10b26b418f408b2be7a922460c
3
  size 4920