Hugging Face's logo

itsLeen
/
swin-large-ai-or-not

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
itsLeen commited on
Commit
3e33d6d
•
1 Parent(s): 07c1379

itsLeen/swin-large-ai-or-not

Browse files
Files changed (8) hide show
  1. README.md +14 -45
  2. all_results.json +5 -5
  3. model.safetensors +1 -1
  4. runs/Nov02_08-02-32_df6c36de6d15/events.out.tfevents.1730534555.df6c36de6d15.2759.0 +3 -0
  5. runs/Nov02_08-04-46_df6c36de6d15/events.out.tfevents.1730534688.df6c36de6d15.2759.1 +3 -0
  6. runs/Nov02_08-17-59_df6c36de6d15/events.out.tfevents.1730535480.df6c36de6d15.2759.2 +3 -0
  7. train_results.json +5 -5
  8. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [itsLeen/swin-large-ai-or-not](https://huggingface.co/itsLeen/swin-large-ai-or-not) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2628
22
- - Accuracy: 0.9583
23
 
24
  ## Model description
25
 
@@ -38,7 +38,7 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 1e-05
42
  - train_batch_size: 4
43
  - eval_batch_size: 8
44
  - seed: 42
@@ -50,52 +50,21 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
- | 0.0188 | 0.1667 | 20 | 0.2001 | 0.9833 |
54
- | 0.0042 | 0.3333 | 40 | 0.7105 | 0.9 |
55
- | 0.0006 | 0.5 | 60 | 0.2346 | 0.975 |
56
- | 0.2284 | 0.6667 | 80 | 0.8042 | 0.8833 |
57
- | 0.1805 | 0.8333 | 100 | 0.1862 | 0.9667 |
58
- | 0.2656 | 1.0 | 120 | 0.2883 | 0.9667 |
59
- | 0.1605 | 1.1667 | 140 | 0.2653 | 0.9667 |
60
- | 0.0328 | 1.3333 | 160 | 0.2375 | 0.975 |
61
- | 0.0006 | 1.5 | 180 | 0.3004 | 0.9667 |
62
- | 0.0681 | 1.6667 | 200 | 0.2590 | 0.975 |
63
- | 0.0004 | 1.8333 | 220 | 0.2436 | 0.975 |
64
- | 0.0001 | 2.0 | 240 | 0.2329 | 0.9583 |
65
- | 0.0 | 2.1667 | 260 | 0.2355 | 0.9583 |
66
- | 0.003 | 2.3333 | 280 | 0.2585 | 0.9583 |
67
- | 0.0018 | 2.5 | 300 | 0.2390 | 0.9583 |
68
- | 0.0051 | 2.6667 | 320 | 0.2616 | 0.975 |
69
- | 0.0017 | 2.8333 | 340 | 0.2648 | 0.975 |
70
- | 0.0206 | 3.0 | 360 | 0.2513 | 0.9667 |
71
- | 0.008 | 3.1667 | 380 | 0.2732 | 0.9583 |
72
- | 0.0 | 3.3333 | 400 | 0.2828 | 0.9583 |
73
- | 0.0002 | 3.5 | 420 | 0.3129 | 0.9667 |
74
- | 0.0002 | 3.6667 | 440 | 0.3141 | 0.9667 |
75
- | 0.0003 | 3.8333 | 460 | 0.2968 | 0.9667 |
76
- | 0.0202 | 4.0 | 480 | 0.2816 | 0.9667 |
77
- | 0.0011 | 4.1667 | 500 | 0.2612 | 0.9667 |
78
- | 0.0 | 4.3333 | 520 | 0.2553 | 0.975 |
79
- | 0.0001 | 4.5 | 540 | 0.2683 | 0.9583 |
80
- | 0.0004 | 4.6667 | 560 | 0.3086 | 0.9667 |
81
- | 0.0 | 4.8333 | 580 | 0.3180 | 0.9667 |
82
- | 0.0 | 5.0 | 600 | 0.3145 | 0.9667 |
83
- | 0.0001 | 5.1667 | 620 | 0.3021 | 0.9583 |
84
- | 0.0 | 5.3333 | 640 | 0.2854 | 0.9583 |
85
- | 0.0 | 5.5 | 660 | 0.2834 | 0.9583 |
86
- | 0.0 | 5.6667 | 680 | 0.2891 | 0.9583 |
87
- | 0.0 | 5.8333 | 700 | 0.2870 | 0.9583 |
88
- | 0.0 | 6.0 | 720 | 0.2862 | 0.9583 |
89
- | 0.0 | 6.1667 | 740 | 0.2862 | 0.9583 |
90
- | 0.0001 | 6.3333 | 760 | 0.2708 | 0.9583 |
91
- | 0.0 | 6.5 | 780 | 0.2657 | 0.9583 |
92
- | 0.0002 | 6.6667 | 800 | 0.2630 | 0.9583 |
93
- | 0.0 | 6.8333 | 820 | 0.2628 | 0.9583 |
94
- | 0.0 | 7.0 | 840 | 0.2628 | 0.9583 |
95
 
96
 
97
  ### Framework versions
98
 
99
  - Transformers 4.44.2
100
  - Pytorch 2.5.0+cu121
 
101
  - Tokenizers 0.19.1
 
18
 
19
  This model is a fine-tuned version of [itsLeen/swin-large-ai-or-not](https://huggingface.co/itsLeen/swin-large-ai-or-not) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1281
22
+ - Accuracy: 0.9744
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 1e-06
42
  - train_batch_size: 4
43
  - eval_batch_size: 8
44
  - seed: 42
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 0.5334 | 0.6452 | 100 | 0.2879 | 0.9615 |
54
+ | 0.6945 | 1.2903 | 200 | 0.2294 | 0.9615 |
55
+ | 0.4024 | 1.9355 | 300 | 0.1788 | 0.9679 |
56
+ | 0.3705 | 2.5806 | 400 | 0.1681 | 0.9744 |
57
+ | 0.1969 | 3.2258 | 500 | 0.1593 | 0.9744 |
58
+ | 0.2916 | 3.8710 | 600 | 0.1441 | 0.9744 |
59
+ | 0.1849 | 4.5161 | 700 | 0.1284 | 0.9744 |
60
+ | 0.185 | 5.1613 | 800 | 0.1347 | 0.9744 |
61
+ | 0.2097 | 5.8065 | 900 | 0.1315 | 0.9744 |
62
+ | 0.157 | 6.4516 | 1000 | 0.1281 | 0.9744 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
66
 
67
  - Transformers 4.44.2
68
  - Pytorch 2.5.0+cu121
69
+ - Datasets 3.1.0
70
  - Tokenizers 0.19.1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 7.0,
3
- "total_flos": 2.6159581024199885e+17,
4
- "train_loss": 0.024369950504204835,
5
- "train_runtime": 1052.9955,
6
- "train_samples_per_second": 3.171,
7
- "train_steps_per_second": 0.798
8
  }
 
1
  {
2
  "epoch": 7.0,
3
+ "total_flos": 3.400197114256589e+17,
4
+ "train_loss": 0.30842060141849076,
5
+ "train_runtime": 931.0574,
6
+ "train_samples_per_second": 4.661,
7
+ "train_steps_per_second": 1.165
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e17304544b279afcb2aab7e3739d45c57a4d14eca21c8485fbb64db83490482
3
  size 347498816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb36c8883f826c565e13ab40672a9fbd66980dccb15193471e4b7c00b1161870
3
  size 347498816
runs/Nov02_08-02-32_df6c36de6d15/events.out.tfevents.1730534555.df6c36de6d15.2759.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a5280f278b67ae28ba98586a32599023aca2638ef0f089509c4625db6871a1
3
+ size 6268
runs/Nov02_08-04-46_df6c36de6d15/events.out.tfevents.1730534688.df6c36de6d15.2759.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58120800100c2f4ce9f6e4cc341c519626fb87335a329de9abc5c635e2f430d7
3
+ size 8247
runs/Nov02_08-17-59_df6c36de6d15/events.out.tfevents.1730535480.df6c36de6d15.2759.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba3a987028f432d8cfa6ddce57020f45f0b8d0ab572acecfe232d7ffad40902
3
+ size 10908
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 7.0,
3
- "total_flos": 2.6159581024199885e+17,
4
- "train_loss": 0.024369950504204835,
5
- "train_runtime": 1052.9955,
6
- "train_samples_per_second": 3.171,
7
- "train_steps_per_second": 0.798
8
  }
 
1
  {
2
  "epoch": 7.0,
3
+ "total_flos": 3.400197114256589e+17,
4
+ "train_loss": 0.30842060141849076,
5
+ "train_runtime": 931.0574,
6
+ "train_samples_per_second": 4.661,
7
+ "train_steps_per_second": 1.165
8
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:005df697a6a8ab3293ac269b8878050c6b1e0e96d324ff7bfa814a244cd11273
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e358edee8df29903285d6a3b32b605e528c6285c3acfe3a34730e34594351637
3
  size 5176