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
46dc68f
·
verified ·
1 Parent(s): 3f5bde0

itsLeen/swin-large-ai-or-nott

Browse files
Files changed (6) hide show
  1. README.md +15 -9
  2. all_results.json +6 -6
  3. model.safetensors +1 -1
  4. runs/Nov03_13-12-40_22c1df2da09d/events.out.tfevents.1730639562.22c1df2da09d.1016.0 +3 -0
  5. train_results.json +6 -6
  6. 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: 0.4799
22
- - Accuracy: 0.92
23
 
24
  ## Model description
25
 
@@ -38,27 +38,33 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 1e-07
42
- - train_batch_size: 32
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
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 0.8972 | 2.0 | 50 | 0.5104 | 0.905 |
55
- | 0.8229 | 4.0 | 100 | 0.4892 | 0.92 |
56
- | 0.7347 | 6.0 | 150 | 0.4799 | 0.92 |
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
  - Transformers 4.44.2
62
  - Pytorch 2.5.0+cu121
63
- - Datasets 3.1.0
64
  - 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: 0.3141
22
+ - Accuracy: 0.95
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 1e-05
42
+ - train_batch_size: 16
43
  - eval_batch_size: 8
44
  - seed: 42
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 20
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
+ | 0.3817 | 2.0 | 50 | 0.2489 | 0.92 |
57
+ | 0.0787 | 4.0 | 100 | 0.3381 | 0.92 |
58
+ | 0.0361 | 6.0 | 150 | 0.3256 | 0.93 |
59
+ | 0.012 | 8.0 | 200 | 0.3192 | 0.94 |
60
+ | 0.0062 | 10.0 | 250 | 0.2874 | 0.955 |
61
+ | 0.0026 | 12.0 | 300 | 0.3379 | 0.95 |
62
+ | 0.003 | 14.0 | 350 | 0.3620 | 0.945 |
63
+ | 0.003 | 16.0 | 400 | 0.3141 | 0.95 |
64
 
65
 
66
  ### Framework versions
67
 
68
  - Transformers 4.44.2
69
  - Pytorch 2.5.0+cu121
 
70
  - Tokenizers 0.19.1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 7.0,
3
- "total_flos": 4.387351115169792e+17,
4
- "train_loss": 0.8093985530308315,
5
- "train_runtime": 960.4895,
6
- "train_samples_per_second": 5.83,
7
- "train_steps_per_second": 0.182
8
  }
 
1
  {
2
+ "epoch": 16.0,
3
+ "total_flos": 1.0028231120388096e+18,
4
+ "train_loss": 0.06541787043213844,
5
+ "train_runtime": 1788.9812,
6
+ "train_samples_per_second": 8.944,
7
+ "train_steps_per_second": 0.279
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c08a0e4dd5e65dfd0ce0f61ebc68d962bd17c5e155889731ce969ab6b91e321b
3
  size 347498816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8616bc58b4fa8d256f08240e9a9e71c41273c61bd6a76d09081522507a72d6b3
3
  size 347498816
runs/Nov03_13-12-40_22c1df2da09d/events.out.tfevents.1730639562.22c1df2da09d.1016.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf831b4cba44ed9a8345f48c1fc4cb52602787c2dd7995831d64bb13e71411f
3
+ size 9833
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 7.0,
3
- "total_flos": 4.387351115169792e+17,
4
- "train_loss": 0.8093985530308315,
5
- "train_runtime": 960.4895,
6
- "train_samples_per_second": 5.83,
7
- "train_steps_per_second": 0.182
8
  }
 
1
  {
2
+ "epoch": 16.0,
3
+ "total_flos": 1.0028231120388096e+18,
4
+ "train_loss": 0.06541787043213844,
5
+ "train_runtime": 1788.9812,
6
+ "train_samples_per_second": 8.944,
7
+ "train_steps_per_second": 0.279
8
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64f88c3f38ddee37f2e76b9a8779e2a2c559d63f0a10617b165fe98fb0f22514
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a04433f297c998d5da5994ba9e737e1c5111cddbedd621134203217302a8966
3
  size 5176