Hugging Face's logo

itsLeen
/
realFake-img

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
itsLeen commited on
Commit
d46744b
•
1 Parent(s): 9a06b5f

Model save

Browse files
Files changed (5) hide show
  1. README.md +8 -46
  2. model.safetensors +2 -2
  3. runs/Sep24_13-48-12_37647b9c0688/events.out.tfevents.1727185800.37647b9c0688.3797.0 +3 -0
  4. runs/Sep24_13-50-15_37647b9c0688/events.out.tfevents.1727185828.37647b9c0688.3797.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -3,7 +3,6 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224
5
  tags:
6
- - image-classification
7
  - generated_from_trainer
8
  metrics:
9
  - accuracy
@@ -17,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # realFake-img
19
 
20
- This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the ai_real_images dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0819
23
- - Accuracy: 0.9785
24
 
25
  ## Model description
26
 
@@ -45,57 +44,20 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 10
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
- | 0.2578 | 0.2525 | 100 | 0.1594 | 0.9418 |
56
- | 0.0944 | 0.5051 | 200 | 0.2243 | 0.9373 |
57
- | 0.1747 | 0.7576 | 300 | 0.2472 | 0.9293 |
58
- | 0.1328 | 1.0101 | 400 | 0.1774 | 0.9338 |
59
- | 0.1918 | 1.2626 | 500 | 0.1282 | 0.9570 |
60
- | 0.169 | 1.5152 | 600 | 0.2247 | 0.9346 |
61
- | 0.2595 | 1.7677 | 700 | 0.1785 | 0.9445 |
62
- | 0.0911 | 2.0202 | 800 | 0.1353 | 0.9534 |
63
- | 0.0548 | 2.2727 | 900 | 0.1998 | 0.9472 |
64
- | 0.1399 | 2.5253 | 1000 | 0.1971 | 0.9445 |
65
- | 0.2001 | 2.7778 | 1100 | 0.2479 | 0.9373 |
66
- | 0.0976 | 3.0303 | 1200 | 0.1601 | 0.9499 |
67
- | 0.1291 | 3.2828 | 1300 | 0.1607 | 0.9588 |
68
- | 0.0721 | 3.5354 | 1400 | 0.1822 | 0.9588 |
69
- | 0.0592 | 3.7879 | 1500 | 0.1255 | 0.9624 |
70
- | 0.0964 | 4.0404 | 1600 | 0.1620 | 0.9543 |
71
- | 0.0738 | 4.2929 | 1700 | 0.1279 | 0.9651 |
72
- | 0.0504 | 4.5455 | 1800 | 0.1624 | 0.9588 |
73
- | 0.0972 | 4.7980 | 1900 | 0.1579 | 0.9624 |
74
- | 0.0456 | 5.0505 | 2000 | 0.1965 | 0.9490 |
75
- | 0.0334 | 5.3030 | 2100 | 0.1652 | 0.9570 |
76
- | 0.0242 | 5.5556 | 2200 | 0.1182 | 0.9749 |
77
- | 0.0715 | 5.8081 | 2300 | 0.1250 | 0.9651 |
78
- | 0.0407 | 6.0606 | 2400 | 0.1172 | 0.9696 |
79
- | 0.0003 | 6.3131 | 2500 | 0.0819 | 0.9785 |
80
- | 0.0072 | 6.5657 | 2600 | 0.1406 | 0.9714 |
81
- | 0.0183 | 6.8182 | 2700 | 0.1152 | 0.9749 |
82
- | 0.0021 | 7.0707 | 2800 | 0.1368 | 0.9731 |
83
- | 0.046 | 7.3232 | 2900 | 0.0900 | 0.9794 |
84
- | 0.033 | 7.5758 | 3000 | 0.1014 | 0.9785 |
85
- | 0.0354 | 7.8283 | 3100 | 0.0968 | 0.9767 |
86
- | 0.0026 | 8.0808 | 3200 | 0.1217 | 0.9731 |
87
- | 0.0002 | 8.3333 | 3300 | 0.0828 | 0.9794 |
88
- | 0.0006 | 8.5859 | 3400 | 0.0926 | 0.9794 |
89
- | 0.0006 | 8.8384 | 3500 | 0.1001 | 0.9794 |
90
- | 0.0006 | 9.0909 | 3600 | 0.0863 | 0.9848 |
91
- | 0.0633 | 9.3434 | 3700 | 0.0911 | 0.9803 |
92
- | 0.0009 | 9.5960 | 3800 | 0.0941 | 0.9821 |
93
- | 0.0247 | 9.8485 | 3900 | 0.0988 | 0.9785 |
94
 
95
 
96
  ### Framework versions
97
 
98
  - Transformers 4.44.2
99
- - Pytorch 2.4.0+cu121
100
- - Datasets 2.21.0
101
  - Tokenizers 0.19.1
 
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224
5
  tags:
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
 
16
 
17
  # realFake-img
18
 
19
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3400
22
+ - Accuracy: 0.8425
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 4
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:------:|:----:|:---------------:|:--------:|
54
+ | 0.3732 | 1.9231 | 100 | 0.4088 | 0.7945 |
55
+ | 0.1451 | 3.8462 | 200 | 0.3400 | 0.8425 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
59
 
60
  - Transformers 4.44.2
61
+ - Pytorch 2.4.1+cu121
62
+ - Datasets 3.0.0
63
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f41508a1be5071cec6928232738f3de3bcdc41ce4598a2a58f2613004a6409cb
3
- size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33da5abc04f7b115e193f7059f53c2aad4581aae49d924d31d3f6858cab55f07
3
+ size 346293856
runs/Sep24_13-48-12_37647b9c0688/events.out.tfevents.1727185800.37647b9c0688.3797.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3167e4b355a48c390d9ee139ae2f84eed853ac0d8e154f36b787c0181807b3b8
3
+ size 5086
runs/Sep24_13-50-15_37647b9c0688/events.out.tfevents.1727185828.37647b9c0688.3797.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c873c4fda76c3f208ed9e2e6afd434df8bf53311e4b6730592410fac5426a6
3
+ size 10093
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93e6eb44065ffcb1aacf2660e126ba36b49f18377071489c44b6c19b7b9ba491
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03254cee2fd469747a3f589c4004c4ac370813bbeffd183f30a0081908102830
3
  size 5176