Hugging Face's logo

prithivMLmods
/
AIorNot-SigLIP2

Image Classification
Transformers
Safetensors
English
siglip
SigLIP2
AI-vs-Real
art
Model card Files
xet
Community
prithivMLmods commited on
Commit
4e177d0
·
verified ·
1 Parent(s): f1519d9

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-1164/config.json +46 -0
  2. checkpoint-1164/model.safetensors +3 -0
  3. checkpoint-1164/optimizer.pt +3 -0
  4. checkpoint-1164/preprocessor_config.json +24 -0
  5. checkpoint-1164/rng_state.pth +3 -0
  6. checkpoint-1164/scheduler.pt +3 -0
  7. checkpoint-1164/trainer_state.json +68 -0
  8. checkpoint-1164/training_args.bin +3 -0
  9. checkpoint-582/config.json +46 -0
  10. checkpoint-582/model.safetensors +3 -0
  11. checkpoint-582/optimizer.pt +3 -0
  12. checkpoint-582/preprocessor_config.json +24 -0
  13. checkpoint-582/rng_state.pth +3 -0
  14. checkpoint-582/scheduler.pt +3 -0
  15. checkpoint-582/trainer_state.json +51 -0
  16. checkpoint-582/training_args.bin +3 -0
  17. config.json +46 -0
  18. model.safetensors +3 -0
  19. preprocessor_config.json +24 -0
  20. training_args.bin +3 -0
checkpoint-1164/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Real",
7
+ "1": "AI"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "AI": 1,
12
+ "Real": 0
13
+ },
14
+ "model_type": "siglip",
15
+ "problem_type": "single_label_classification",
16
+ "text_config": {
17
+ "attention_dropout": 0.0,
18
+ "hidden_act": "gelu_pytorch_tanh",
19
+ "hidden_size": 768,
20
+ "intermediate_size": 3072,
21
+ "layer_norm_eps": 1e-06,
22
+ "max_position_embeddings": 64,
23
+ "model_type": "siglip_text_model",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "projection_size": 768,
27
+ "torch_dtype": "float32",
28
+ "vocab_size": 256000
29
+ },
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.50.0",
32
+ "vision_config": {
33
+ "attention_dropout": 0.0,
34
+ "hidden_act": "gelu_pytorch_tanh",
35
+ "hidden_size": 768,
36
+ "image_size": 224,
37
+ "intermediate_size": 3072,
38
+ "layer_norm_eps": 1e-06,
39
+ "model_type": "siglip_vision_model",
40
+ "num_attention_heads": 12,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 12,
43
+ "patch_size": 16,
44
+ "torch_dtype": "float32"
45
+ }
46
+ }
checkpoint-1164/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8560c44d0f9fbe9a939a3dbbff4c2d88047b073beeb1410e7afc2b567e6628f4
3
+ size 371567992
checkpoint-1164/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b715982592db256aabfd32721cf8140adcded1e00b628e00d5786a7555ac087b
3
+ size 686555770
checkpoint-1164/preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
checkpoint-1164/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1ea2b46dd598770f6017019352d426285ae77cb2430efb5a4f47c28041949b
3
+ size 14244
checkpoint-1164/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cfdeba37894edaf4ac8f41c28ab878995c1e016d8abb743ab1d91009fe2dd2a
3
+ size 1064
checkpoint-1164/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1164,
3
+ "best_metric": 0.2065684199333191,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1164",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1164,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8591065292096219,
14
+ "grad_norm": 3.2585995197296143,
15
+ "learning_rate": 0.00011921005385996409,
16
+ "loss": 0.5338,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8734020840047266,
22
+ "eval_loss": 0.3001032769680023,
23
+ "eval_model_preparation_time": 0.0027,
24
+ "eval_runtime": 277.2698,
25
+ "eval_samples_per_second": 67.148,
26
+ "eval_steps_per_second": 8.396,
27
+ "step": 582
28
+ },
29
+ {
30
+ "epoch": 1.718213058419244,
31
+ "grad_norm": 3.363511562347412,
32
+ "learning_rate": 2.9443447037701977e-05,
33
+ "loss": 0.3278,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.9149210441508218,
39
+ "eval_loss": 0.2065684199333191,
40
+ "eval_model_preparation_time": 0.0027,
41
+ "eval_runtime": 280.2892,
42
+ "eval_samples_per_second": 66.424,
43
+ "eval_steps_per_second": 8.306,
44
+ "step": 1164
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 1164,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 2,
51
+ "save_steps": 500,
52
+ "stateful_callbacks": {
53
+ "TrainerControl": {
54
+ "args": {
55
+ "should_epoch_stop": false,
56
+ "should_evaluate": false,
57
+ "should_log": false,
58
+ "should_save": true,
59
+ "should_training_stop": true
60
+ },
61
+ "attributes": {}
62
+ }
63
+ },
64
+ "total_flos": 3.1187196424023736e+18,
65
+ "train_batch_size": 32,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-1164/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206d195b28a5a4e1f61804a2eec06b109a4be9fa8d841f4d552fca404cebe15f
3
+ size 5304
checkpoint-582/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Real",
7
+ "1": "AI"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "AI": 1,
12
+ "Real": 0
13
+ },
14
+ "model_type": "siglip",
15
+ "problem_type": "single_label_classification",
16
+ "text_config": {
17
+ "attention_dropout": 0.0,
18
+ "hidden_act": "gelu_pytorch_tanh",
19
+ "hidden_size": 768,
20
+ "intermediate_size": 3072,
21
+ "layer_norm_eps": 1e-06,
22
+ "max_position_embeddings": 64,
23
+ "model_type": "siglip_text_model",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "projection_size": 768,
27
+ "torch_dtype": "float32",
28
+ "vocab_size": 256000
29
+ },
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.50.0",
32
+ "vision_config": {
33
+ "attention_dropout": 0.0,
34
+ "hidden_act": "gelu_pytorch_tanh",
35
+ "hidden_size": 768,
36
+ "image_size": 224,
37
+ "intermediate_size": 3072,
38
+ "layer_norm_eps": 1e-06,
39
+ "model_type": "siglip_vision_model",
40
+ "num_attention_heads": 12,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 12,
43
+ "patch_size": 16,
44
+ "torch_dtype": "float32"
45
+ }
46
+ }
checkpoint-582/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caae1250ebfd11db56e18ed1a1132fd0ac6104ab9922fbcafbaf79c63a81dbc6
3
+ size 371567992
checkpoint-582/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e566e2828377d9bd353e9cf879944f45d205b370ae74761452403ec038900cc6
3
+ size 686555770
checkpoint-582/preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
checkpoint-582/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aef95b588f2fa4f74aa3445276067460b3f96dbe1913e7b6087b3f3ed691c48
3
+ size 14244
checkpoint-582/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5461f1d8cc6a2eddb196f32da43cf9fb09101eead2a8748d00fe8a8e3e51b19b
3
+ size 1064
checkpoint-582/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 582,
3
+ "best_metric": 0.3001032769680023,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-582",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 582,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8591065292096219,
14
+ "grad_norm": 3.2585995197296143,
15
+ "learning_rate": 0.00011921005385996409,
16
+ "loss": 0.5338,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8734020840047266,
22
+ "eval_loss": 0.3001032769680023,
23
+ "eval_model_preparation_time": 0.0027,
24
+ "eval_runtime": 277.2698,
25
+ "eval_samples_per_second": 67.148,
26
+ "eval_steps_per_second": 8.396,
27
+ "step": 582
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 1164,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "stateful_callbacks": {
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
39
+ "should_evaluate": false,
40
+ "should_log": false,
41
+ "should_save": true,
42
+ "should_training_stop": false
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 1.5593598212011868e+18,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-582/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206d195b28a5a4e1f61804a2eec06b109a4be9fa8d841f4d552fca404cebe15f
3
+ size 5304
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Real",
7
+ "1": "AI"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "AI": 1,
12
+ "Real": 0
13
+ },
14
+ "model_type": "siglip",
15
+ "problem_type": "single_label_classification",
16
+ "text_config": {
17
+ "attention_dropout": 0.0,
18
+ "hidden_act": "gelu_pytorch_tanh",
19
+ "hidden_size": 768,
20
+ "intermediate_size": 3072,
21
+ "layer_norm_eps": 1e-06,
22
+ "max_position_embeddings": 64,
23
+ "model_type": "siglip_text_model",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "projection_size": 768,
27
+ "torch_dtype": "float32",
28
+ "vocab_size": 256000
29
+ },
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.50.0",
32
+ "vision_config": {
33
+ "attention_dropout": 0.0,
34
+ "hidden_act": "gelu_pytorch_tanh",
35
+ "hidden_size": 768,
36
+ "image_size": 224,
37
+ "intermediate_size": 3072,
38
+ "layer_norm_eps": 1e-06,
39
+ "model_type": "siglip_vision_model",
40
+ "num_attention_heads": 12,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 12,
43
+ "patch_size": 16,
44
+ "torch_dtype": "float32"
45
+ }
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8560c44d0f9fbe9a939a3dbbff4c2d88047b073beeb1410e7afc2b567e6628f4
3
+ size 371567992
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206d195b28a5a4e1f61804a2eec06b109a4be9fa8d841f4d552fca404cebe15f
3
+ size 5304