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
84ed97c
·
verified ·
1 Parent(s): a141e82

itsLeen/swin-large-ai-or-not

Browse files
Files changed (7) hide show
  1. README.md +49 -10
  2. all_results.json +6 -6
  3. model.safetensors +1 -1
  4. runs/Oct29_15-53-34_d133ef931242/events.out.tfevents.1730217216.d133ef931242.303.0 +3 -0
  5. runs/Oct29_15-54-41_d133ef931242/events.out.tfevents.1730217282.d133ef931242.303.1 +3 -0
  6. train_results.json +6 -6
  7. 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: 0.2789
22
- - Accuracy: 0.9558
23
 
24
  ## Model description
25
 
@@ -39,25 +39,64 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 1e-05
42
- - train_batch_size: 8
43
  - eval_batch_size: 8
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
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | No log | 1.0 | 57 | 0.2138 | 0.9204 |
54
- | No log | 2.0 | 114 | 0.2483 | 0.9381 |
55
- | No log | 3.0 | 171 | 0.2920 | 0.9469 |
56
- | No log | 4.0 | 228 | 0.2789 | 0.9558 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
  - Transformers 4.44.2
62
  - Pytorch 2.5.0+cu121
 
63
  - 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: 0.2586
22
+ - Accuracy: 0.9667
23
 
24
  ## Model description
25
 
 
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
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 7
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 0.0327 | 0.1667 | 20 | 0.2187 | 0.975 |
54
+ | 0.3745 | 0.3333 | 40 | 0.5542 | 0.8917 |
55
+ | 0.0148 | 0.5 | 60 | 0.2031 | 0.9667 |
56
+ | 0.2762 | 0.6667 | 80 | 0.3867 | 0.95 |
57
+ | 0.1352 | 0.8333 | 100 | 0.2771 | 0.9667 |
58
+ | 0.2078 | 1.0 | 120 | 0.2782 | 0.9667 |
59
+ | 0.0784 | 1.1667 | 140 | 0.3109 | 0.9667 |
60
+ | 0.0786 | 1.3333 | 160 | 0.2338 | 0.975 |
61
+ | 0.0284 | 1.5 | 180 | 0.2686 | 0.9583 |
62
+ | 0.0493 | 1.6667 | 200 | 0.2244 | 0.975 |
63
+ | 0.023 | 1.8333 | 220 | 0.2154 | 0.9833 |
64
+ | 0.0035 | 2.0 | 240 | 0.2103 | 0.9833 |
65
+ | 0.0001 | 2.1667 | 260 | 0.2091 | 0.9667 |
66
+ | 0.0005 | 2.3333 | 280 | 0.3189 | 0.9583 |
67
+ | 0.022 | 2.5 | 300 | 0.2298 | 0.975 |
68
+ | 0.0016 | 2.6667 | 320 | 0.2199 | 0.9833 |
69
+ | 0.0009 | 2.8333 | 340 | 0.2301 | 0.975 |
70
+ | 0.0 | 3.0 | 360 | 0.2416 | 0.9667 |
71
+ | 0.0 | 3.1667 | 380 | 0.2517 | 0.9667 |
72
+ | 0.0 | 3.3333 | 400 | 0.2541 | 0.9667 |
73
+ | 0.0 | 3.5 | 420 | 0.2518 | 0.9667 |
74
+ | 0.0 | 3.6667 | 440 | 0.2483 | 0.9667 |
75
+ | 0.0001 | 3.8333 | 460 | 0.2442 | 0.9667 |
76
+ | 0.0 | 4.0 | 480 | 0.2406 | 0.9667 |
77
+ | 0.0 | 4.1667 | 500 | 0.2402 | 0.9667 |
78
+ | 0.0 | 4.3333 | 520 | 0.2398 | 0.9667 |
79
+ | 0.0 | 4.5 | 540 | 0.2461 | 0.9667 |
80
+ | 0.0686 | 4.6667 | 560 | 0.2567 | 0.9667 |
81
+ | 0.0 | 4.8333 | 580 | 0.2572 | 0.9667 |
82
+ | 0.0 | 5.0 | 600 | 0.2571 | 0.9667 |
83
+ | 0.0001 | 5.1667 | 620 | 0.2752 | 0.975 |
84
+ | 0.0002 | 5.3333 | 640 | 0.2621 | 0.9667 |
85
+ | 0.0001 | 5.5 | 660 | 0.2379 | 0.9667 |
86
+ | 0.0 | 5.6667 | 680 | 0.2453 | 0.9667 |
87
+ | 0.0 | 5.8333 | 700 | 0.2470 | 0.9667 |
88
+ | 0.0 | 6.0 | 720 | 0.2488 | 0.9667 |
89
+ | 0.0 | 6.1667 | 740 | 0.2492 | 0.9667 |
90
+ | 0.0003 | 6.3333 | 760 | 0.2536 | 0.9667 |
91
+ | 0.0 | 6.5 | 780 | 0.2566 | 0.9667 |
92
+ | 0.0 | 6.6667 | 800 | 0.2571 | 0.9667 |
93
+ | 0.0 | 6.8333 | 820 | 0.2585 | 0.9667 |
94
+ | 0.0 | 7.0 | 840 | 0.2586 | 0.9667 |
95
 
96
 
97
  ### Framework versions
98
 
99
  - Transformers 4.44.2
100
  - Pytorch 2.5.0+cu121
101
+ - Datasets 3.0.2
102
  - Tokenizers 0.19.1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 4.0,
3
- "total_flos": 1.410220001304576e+17,
4
- "train_loss": 0.16879116861443771,
5
- "train_runtime": 300.6842,
6
- "train_samples_per_second": 5.986,
7
- "train_steps_per_second": 0.758
8
  }
 
1
  {
2
+ "epoch": 7.0,
3
+ "total_flos": 2.6159581024199885e+17,
4
+ "train_loss": 0.033261351659027806,
5
+ "train_runtime": 1062.0855,
6
+ "train_samples_per_second": 3.144,
7
+ "train_steps_per_second": 0.791
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:464281578b838b0e748b6f5cf23cbbc149b6d43a656269b293bd3b3c20939bd5
3
  size 347498816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaac5af132f00a6629c92fe0da1810913be495e6c2c9f5ac1bc0a7271edd4150
3
  size 347498816
runs/Oct29_15-53-34_d133ef931242/events.out.tfevents.1730217216.d133ef931242.303.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a128b0a419bbace99527e633bab9d6596e4e42192b3537f7494339fc3215ab1
3
+ size 5222
runs/Oct29_15-54-41_d133ef931242/events.out.tfevents.1730217282.d133ef931242.303.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0917d473e5205c3e271dedc60f9f62f25c2a2ee14938d05c47f40c1251a5b89
3
+ size 27944
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 4.0,
3
- "total_flos": 1.410220001304576e+17,
4
- "train_loss": 0.16879116861443771,
5
- "train_runtime": 300.6842,
6
- "train_samples_per_second": 5.986,
7
- "train_steps_per_second": 0.758
8
  }
 
1
  {
2
+ "epoch": 7.0,
3
+ "total_flos": 2.6159581024199885e+17,
4
+ "train_loss": 0.033261351659027806,
5
+ "train_runtime": 1062.0855,
6
+ "train_samples_per_second": 3.144,
7
+ "train_steps_per_second": 0.791
8
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b26b6a9a473550d6db3198a7a972a01f4eddad3a856636ddd4fe87ef3fcf08fe
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4c5d4797cd5aec1556b77237d22a831a614fcc94388c51da3d531f00eb7bb9
3
  size 5176