Hugging Face's logo

prithivMLmods
/
3D-Printed-Or-Not-SigLIP2

Image Classification
Transformers
Safetensors
English
siglip
3D-Printed-Or-Not
SigLIP2
Image-Classification
Model card Files
xet
Community
prithivMLmods commited on
Commit
ef05982
·
verified ·
1 Parent(s): 0a4f88d

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-1610/config.json +46 -0
  2. checkpoint-1610/model.safetensors +3 -0
  3. checkpoint-1610/optimizer.pt +3 -0
  4. checkpoint-1610/preprocessor_config.json +24 -0
  5. checkpoint-1610/rng_state.pth +3 -0
  6. checkpoint-1610/scheduler.pt +3 -0
  7. checkpoint-1610/trainer_state.json +65 -0
  8. checkpoint-1610/training_args.bin +3 -0
  9. checkpoint-3220/config.json +46 -0
  10. checkpoint-3220/model.safetensors +3 -0
  11. checkpoint-3220/optimizer.pt +3 -0
  12. checkpoint-3220/preprocessor_config.json +24 -0
  13. checkpoint-3220/rng_state.pth +3 -0
  14. checkpoint-3220/scheduler.pt +3 -0
  15. checkpoint-3220/trainer_state.json +96 -0
  16. checkpoint-3220/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-1610/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "3D Printed",
7
+ "1": "Not 3D Printed"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "3D Printed": 0,
12
+ "Not 3D Printed": 1
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-1610/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19f41c11ef5518b8c2b6378ecfae9a3752360a2e3cd1aa880545bf07effaec2
3
+ size 371567992
checkpoint-1610/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce957601720d7d0e39ced43ff91722293cfbab94cae88028a1ba8dbcf4db85d9
3
+ size 686555770
checkpoint-1610/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-1610/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c83da6df814eca8b43ed154c9a2955977b59de9c93f918feeaa93dd911a3b962
3
+ size 14244
checkpoint-1610/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:190d207ec15c1cec6ef61ec0a870fdf0bd4ae1806ff0a0eb963c29f8102af4b1
3
+ size 1064
checkpoint-1610/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1610,
3
+ "best_metric": 0.341511070728302,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1610",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1610,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.3105590062111801,
14
+ "grad_norm": 10.944823265075684,
15
+ "learning_rate": 0.000171608832807571,
16
+ "loss": 0.5863,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.6211180124223602,
21
+ "grad_norm": 2.011547088623047,
22
+ "learning_rate": 0.00014006309148264986,
23
+ "loss": 0.4362,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.9316770186335404,
28
+ "grad_norm": 2.089695453643799,
29
+ "learning_rate": 0.0001085173501577287,
30
+ "loss": 0.3845,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_accuracy": 0.8420419254658386,
36
+ "eval_loss": 0.341511070728302,
37
+ "eval_model_preparation_time": 0.0027,
38
+ "eval_runtime": 649.0357,
39
+ "eval_samples_per_second": 79.379,
40
+ "eval_steps_per_second": 9.922,
41
+ "step": 1610
42
+ }
43
+ ],
44
+ "logging_steps": 500,
45
+ "max_steps": 3220,
46
+ "num_input_tokens_seen": 0,
47
+ "num_train_epochs": 2,
48
+ "save_steps": 500,
49
+ "stateful_callbacks": {
50
+ "TrainerControl": {
51
+ "args": {
52
+ "should_epoch_stop": false,
53
+ "should_evaluate": false,
54
+ "should_log": false,
55
+ "should_save": true,
56
+ "should_training_stop": false
57
+ },
58
+ "attributes": {}
59
+ }
60
+ },
61
+ "total_flos": 4.315083144713994e+18,
62
+ "train_batch_size": 32,
63
+ "trial_name": null,
64
+ "trial_params": null
65
+ }
checkpoint-1610/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5371dc4f3b7759a694db9f7dd1b77d5c2e28b4074a617a682427c213e9fb3ec6
3
+ size 5304
checkpoint-3220/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "3D Printed",
7
+ "1": "Not 3D Printed"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "3D Printed": 0,
12
+ "Not 3D Printed": 1
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-3220/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb2666f6b893c3d8e5fc3ad5beaf925be923189e89b7add16636c71e059f0402
3
+ size 371567992
checkpoint-3220/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b671a710b66899f233487bf975301078df8d9a3d4aac3e3d3504af38c24b8d
3
+ size 686555770
checkpoint-3220/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-3220/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9446115e4bf1555672f75daf67a36586a95178e3f5d568367fe223af8eb64b
3
+ size 14244
checkpoint-3220/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e0ad9f294e8ca829dfac0c54c11791f28839c1b3958b94f659deeeac45e22c7
3
+ size 1064
checkpoint-3220/trainer_state.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3220,
3
+ "best_metric": 0.16810201108455658,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-3220",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3220,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.3105590062111801,
14
+ "grad_norm": 10.944823265075684,
15
+ "learning_rate": 0.000171608832807571,
16
+ "loss": 0.5863,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.6211180124223602,
21
+ "grad_norm": 2.011547088623047,
22
+ "learning_rate": 0.00014006309148264986,
23
+ "loss": 0.4362,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.9316770186335404,
28
+ "grad_norm": 2.089695453643799,
29
+ "learning_rate": 0.0001085173501577287,
30
+ "loss": 0.3845,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_accuracy": 0.8420419254658386,
36
+ "eval_loss": 0.341511070728302,
37
+ "eval_model_preparation_time": 0.0027,
38
+ "eval_runtime": 649.0357,
39
+ "eval_samples_per_second": 79.379,
40
+ "eval_steps_per_second": 9.922,
41
+ "step": 1610
42
+ },
43
+ {
44
+ "epoch": 1.2422360248447206,
45
+ "grad_norm": 3.238433837890625,
46
+ "learning_rate": 7.697160883280758e-05,
47
+ "loss": 0.3316,
48
+ "step": 2000
49
+ },
50
+ {
51
+ "epoch": 1.5527950310559007,
52
+ "grad_norm": 1.6037983894348145,
53
+ "learning_rate": 4.5425867507886435e-05,
54
+ "loss": 0.2701,
55
+ "step": 2500
56
+ },
57
+ {
58
+ "epoch": 1.8633540372670807,
59
+ "grad_norm": 1.9789021015167236,
60
+ "learning_rate": 1.38801261829653e-05,
61
+ "loss": 0.2114,
62
+ "step": 3000
63
+ },
64
+ {
65
+ "epoch": 2.0,
66
+ "eval_accuracy": 0.9234277950310559,
67
+ "eval_loss": 0.16810201108455658,
68
+ "eval_model_preparation_time": 0.0027,
69
+ "eval_runtime": 651.5076,
70
+ "eval_samples_per_second": 79.078,
71
+ "eval_steps_per_second": 9.885,
72
+ "step": 3220
73
+ }
74
+ ],
75
+ "logging_steps": 500,
76
+ "max_steps": 3220,
77
+ "num_input_tokens_seen": 0,
78
+ "num_train_epochs": 2,
79
+ "save_steps": 500,
80
+ "stateful_callbacks": {
81
+ "TrainerControl": {
82
+ "args": {
83
+ "should_epoch_stop": false,
84
+ "should_evaluate": false,
85
+ "should_log": false,
86
+ "should_save": true,
87
+ "should_training_stop": true
88
+ },
89
+ "attributes": {}
90
+ }
91
+ },
92
+ "total_flos": 8.630166289427988e+18,
93
+ "train_batch_size": 32,
94
+ "trial_name": null,
95
+ "trial_params": null
96
+ }
checkpoint-3220/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5371dc4f3b7759a694db9f7dd1b77d5c2e28b4074a617a682427c213e9fb3ec6
3
+ size 5304
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "3D Printed",
7
+ "1": "Not 3D Printed"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "3D Printed": 0,
12
+ "Not 3D Printed": 1
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:bb2666f6b893c3d8e5fc3ad5beaf925be923189e89b7add16636c71e059f0402
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 sha256:5371dc4f3b7759a694db9f7dd1b77d5c2e28b4074a617a682427c213e9fb3ec6
3
+ size 5304