Hugging Face's logo

dima806
/
ai_vs_human_generated_image_detection

Image Classification
Transformers
Safetensors
vit
Model card Files
xet
Community
1
dima806 commited on
Commit
f34fc3b
·
verified ·
1 Parent(s): f9eb011

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-3000/config.json +32 -0
  2. checkpoint-3000/model.safetensors +3 -0
  3. checkpoint-3000/optimizer.pt +3 -0
  4. checkpoint-3000/preprocessor_config.json +23 -0
  5. checkpoint-3000/rng_state.pth +3 -0
  6. checkpoint-3000/scheduler.pt +3 -0
  7. checkpoint-3000/trainer_state.json +95 -0
  8. checkpoint-3000/training_args.bin +3 -0
  9. config.json +32 -0
  10. model.safetensors +3 -0
  11. preprocessor_config.json +23 -0
  12. training_args.bin +3 -0
checkpoint-3000/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "human",
13
+ "1": "AI-generated"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "AI-generated": 1,
20
+ "human": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.48.1"
32
+ }
checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871b68ec78bb3255291c2611c94384a915cdfad8aebe36b12c079f5f6102fce5
3
+ size 343223968
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a0f89581ddbc4f22d5201d323f1d80964c1697fa7dd0af117d4089e5be209c
3
+ size 686568890
checkpoint-3000/preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b0151a0763df93bf00e608e1f851c6826d363ffa2e3218494cfcfb632219ca
3
+ size 14244
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94cced5fc82e8af08be18947f0e2aace7bd071ff7b098185030ddf84d640a76
3
+ size 1064
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.11322234570980072,
3
+ "best_model_checkpoint": "ai_vs_human_generated_image_detection/checkpoint-3000",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.3333333333333333,
13
+ "grad_norm": 0.953800618648529,
14
+ "learning_rate": 2.5423728813559323e-06,
15
+ "loss": 0.4979,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.6666666666666666,
20
+ "grad_norm": 1.084754228591919,
21
+ "learning_rate": 2.033898305084746e-06,
22
+ "loss": 0.146,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "grad_norm": 12.670453071594238,
28
+ "learning_rate": 1.5254237288135592e-06,
29
+ "loss": 0.1073,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "eval_accuracy": 0.9691056910569106,
35
+ "eval_loss": 0.14485515654087067,
36
+ "eval_model_preparation_time": 0.0038,
37
+ "eval_runtime": 428.2517,
38
+ "eval_samples_per_second": 74.676,
39
+ "eval_steps_per_second": 9.336,
40
+ "step": 1500
41
+ },
42
+ {
43
+ "epoch": 1.3333333333333333,
44
+ "grad_norm": 2.258631467819214,
45
+ "learning_rate": 1.016949152542373e-06,
46
+ "loss": 0.0859,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 1.6666666666666665,
51
+ "grad_norm": 4.437932014465332,
52
+ "learning_rate": 5.084745762711865e-07,
53
+ "loss": 0.0785,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 2.0,
58
+ "grad_norm": 0.19989100098609924,
59
+ "learning_rate": 0.0,
60
+ "loss": 0.0762,
61
+ "step": 3000
62
+ },
63
+ {
64
+ "epoch": 2.0,
65
+ "eval_accuracy": 0.9722639149468417,
66
+ "eval_loss": 0.11322234570980072,
67
+ "eval_model_preparation_time": 0.0038,
68
+ "eval_runtime": 432.331,
69
+ "eval_samples_per_second": 73.971,
70
+ "eval_steps_per_second": 9.248,
71
+ "step": 3000
72
+ }
73
+ ],
74
+ "logging_steps": 500,
75
+ "max_steps": 3000,
76
+ "num_input_tokens_seen": 0,
77
+ "num_train_epochs": 2,
78
+ "save_steps": 500,
79
+ "stateful_callbacks": {
80
+ "TrainerControl": {
81
+ "args": {
82
+ "should_epoch_stop": false,
83
+ "should_evaluate": false,
84
+ "should_log": false,
85
+ "should_save": true,
86
+ "should_training_stop": true
87
+ },
88
+ "attributes": {}
89
+ }
90
+ },
91
+ "total_flos": 7.434581483623956e+18,
92
+ "train_batch_size": 32,
93
+ "trial_name": null,
94
+ "trial_params": null
95
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a58791d1445928df8775da8fea14195f443d87f2ecf20bccfef5db1511bf1a
3
+ size 5304
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "human",
13
+ "1": "AI-generated"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "AI-generated": 1,
20
+ "human": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
+ "qkv_bias": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.48.1"
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871b68ec78bb3255291c2611c94384a915cdfad8aebe36b12c079f5f6102fce5
3
+ size 343223968
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a58791d1445928df8775da8fea14195f443d87f2ecf20bccfef5db1511bf1a
3
+ size 5304