Hugging Face's logo

prithivMLmods
/
Geometric-Shapes-Classification

Image Classification
Transformers
Safetensors
English
siglip
Shapes
Geometric
SigLIP2
art
Model card Files Community
prithivMLmods commited on
Commit
01d09d9
·
verified ·
1 Parent(s): 638374f

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-375/config.json +58 -0
  2. checkpoint-375/model.safetensors +3 -0
  3. checkpoint-375/optimizer.pt +3 -0
  4. checkpoint-375/preprocessor_config.json +24 -0
  5. checkpoint-375/rng_state.pth +3 -0
  6. checkpoint-375/scheduler.pt +3 -0
  7. checkpoint-375/trainer_state.json +44 -0
  8. checkpoint-375/training_args.bin +3 -0
  9. checkpoint-750/config.json +58 -0
  10. checkpoint-750/model.safetensors +3 -0
  11. checkpoint-750/optimizer.pt +3 -0
  12. checkpoint-750/preprocessor_config.json +24 -0
  13. checkpoint-750/rng_state.pth +3 -0
  14. checkpoint-750/scheduler.pt +3 -0
  15. checkpoint-750/trainer_state.json +61 -0
  16. checkpoint-750/training_args.bin +3 -0
  17. config.json +58 -0
  18. model.safetensors +3 -0
  19. preprocessor_config.json +24 -0
  20. training_args.bin +3 -0
checkpoint-375/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Circle \u25ef",
7
+ "1": "Kite \u2b30",
8
+ "2": "Parallelogram \u25b0",
9
+ "3": "Rectangle \u25ad",
10
+ "4": "Rhombus \u25c6",
11
+ "5": "Square \u25fc",
12
+ "6": "Trapezoid \u23e2",
13
+ "7": "Triangle \u25b2"
14
+ },
15
+ "initializer_factor": 1.0,
16
+ "label2id": {
17
+ "Circle \u25ef": 0,
18
+ "Kite \u2b30": 1,
19
+ "Parallelogram \u25b0": 2,
20
+ "Rectangle \u25ad": 3,
21
+ "Rhombus \u25c6": 4,
22
+ "Square \u25fc": 5,
23
+ "Trapezoid \u23e2": 6,
24
+ "Triangle \u25b2": 7
25
+ },
26
+ "model_type": "siglip",
27
+ "problem_type": "single_label_classification",
28
+ "text_config": {
29
+ "attention_dropout": 0.0,
30
+ "hidden_act": "gelu_pytorch_tanh",
31
+ "hidden_size": 768,
32
+ "intermediate_size": 3072,
33
+ "layer_norm_eps": 1e-06,
34
+ "max_position_embeddings": 64,
35
+ "model_type": "siglip_text_model",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "projection_size": 768,
39
+ "torch_dtype": "float32",
40
+ "vocab_size": 256000
41
+ },
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.50.3",
44
+ "vision_config": {
45
+ "attention_dropout": 0.0,
46
+ "hidden_act": "gelu_pytorch_tanh",
47
+ "hidden_size": 768,
48
+ "image_size": 224,
49
+ "intermediate_size": 3072,
50
+ "layer_norm_eps": 1e-06,
51
+ "model_type": "siglip_vision_model",
52
+ "num_attention_heads": 12,
53
+ "num_channels": 3,
54
+ "num_hidden_layers": 12,
55
+ "patch_size": 16,
56
+ "torch_dtype": "float32"
57
+ }
58
+ }
checkpoint-375/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59774861a5253ee8a2685bef62a6aa8e016c2bc57d6ec515be051100f5ae5f43
3
+ size 371586448
checkpoint-375/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa188c598b29736f377f9dffe4bd270589b44c7bc79b653779c972bc68163aab
3
+ size 686592634
checkpoint-375/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-375/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11027277b6c51f59488df520020d383908a9f170baa7ea4bd0c166aa72cced2
3
+ size 14244
checkpoint-375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4d1140f5a0513989aca0dc1db73e181db90de91e412469cc8be792cca398dc
3
+ size 1064
checkpoint-375/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 375,
3
+ "best_metric": 0.5122714638710022,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-375",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 375,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.85325,
15
+ "eval_loss": 0.5122714638710022,
16
+ "eval_model_preparation_time": 0.0023,
17
+ "eval_runtime": 142.4763,
18
+ "eval_samples_per_second": 84.225,
19
+ "eval_steps_per_second": 10.528,
20
+ "step": 375
21
+ }
22
+ ],
23
+ "logging_steps": 500,
24
+ "max_steps": 750,
25
+ "num_input_tokens_seen": 0,
26
+ "num_train_epochs": 2,
27
+ "save_steps": 500,
28
+ "stateful_callbacks": {
29
+ "TrainerControl": {
30
+ "args": {
31
+ "should_epoch_stop": false,
32
+ "should_evaluate": false,
33
+ "should_log": false,
34
+ "should_save": true,
35
+ "should_training_stop": false
36
+ },
37
+ "attributes": {}
38
+ }
39
+ },
40
+ "total_flos": 1.005115956461568e+18,
41
+ "train_batch_size": 32,
42
+ "trial_name": null,
43
+ "trial_params": null
44
+ }
checkpoint-375/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-750/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Circle \u25ef",
7
+ "1": "Kite \u2b30",
8
+ "2": "Parallelogram \u25b0",
9
+ "3": "Rectangle \u25ad",
10
+ "4": "Rhombus \u25c6",
11
+ "5": "Square \u25fc",
12
+ "6": "Trapezoid \u23e2",
13
+ "7": "Triangle \u25b2"
14
+ },
15
+ "initializer_factor": 1.0,
16
+ "label2id": {
17
+ "Circle \u25ef": 0,
18
+ "Kite \u2b30": 1,
19
+ "Parallelogram \u25b0": 2,
20
+ "Rectangle \u25ad": 3,
21
+ "Rhombus \u25c6": 4,
22
+ "Square \u25fc": 5,
23
+ "Trapezoid \u23e2": 6,
24
+ "Triangle \u25b2": 7
25
+ },
26
+ "model_type": "siglip",
27
+ "problem_type": "single_label_classification",
28
+ "text_config": {
29
+ "attention_dropout": 0.0,
30
+ "hidden_act": "gelu_pytorch_tanh",
31
+ "hidden_size": 768,
32
+ "intermediate_size": 3072,
33
+ "layer_norm_eps": 1e-06,
34
+ "max_position_embeddings": 64,
35
+ "model_type": "siglip_text_model",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "projection_size": 768,
39
+ "torch_dtype": "float32",
40
+ "vocab_size": 256000
41
+ },
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.50.3",
44
+ "vision_config": {
45
+ "attention_dropout": 0.0,
46
+ "hidden_act": "gelu_pytorch_tanh",
47
+ "hidden_size": 768,
48
+ "image_size": 224,
49
+ "intermediate_size": 3072,
50
+ "layer_norm_eps": 1e-06,
51
+ "model_type": "siglip_vision_model",
52
+ "num_attention_heads": 12,
53
+ "num_channels": 3,
54
+ "num_hidden_layers": 12,
55
+ "patch_size": 16,
56
+ "torch_dtype": "float32"
57
+ }
58
+ }
checkpoint-750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a134585cac12e3065d395f47c8f7a50916ed236e6752f94152d5b1466ed6631c
3
+ size 371586448
checkpoint-750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7b8773667c165c9b7ea1d9ea7b20c1d7ff46c21735b0201c4284ee44a97853
3
+ size 686592634
checkpoint-750/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-750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dfd1f9a2a29539f346868eb36a1b264e5fc13fdb515c6a844bf62e6abee8853
3
+ size 14244
checkpoint-750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab03192a60c4fb6ec6096a859424dfb24171c6b3fc801b38b85ab0fd723b1704
3
+ size 1064
checkpoint-750/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 750,
3
+ "best_metric": 0.03016640432178974,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-750",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 750,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.85325,
15
+ "eval_loss": 0.5122714638710022,
16
+ "eval_model_preparation_time": 0.0023,
17
+ "eval_runtime": 142.4763,
18
+ "eval_samples_per_second": 84.225,
19
+ "eval_steps_per_second": 10.528,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.3333333333333333,
24
+ "grad_norm": 6.622213840484619,
25
+ "learning_rate": 7.142857142857143e-05,
26
+ "loss": 0.4962,
27
+ "step": 500
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.99075,
32
+ "eval_loss": 0.03016640432178974,
33
+ "eval_model_preparation_time": 0.0023,
34
+ "eval_runtime": 141.9262,
35
+ "eval_samples_per_second": 84.551,
36
+ "eval_steps_per_second": 10.569,
37
+ "step": 750
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 750,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 2,
44
+ "save_steps": 500,
45
+ "stateful_callbacks": {
46
+ "TrainerControl": {
47
+ "args": {
48
+ "should_epoch_stop": false,
49
+ "should_evaluate": false,
50
+ "should_log": false,
51
+ "should_save": true,
52
+ "should_training_stop": true
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 2.010231912923136e+18,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-750/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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Circle \u25ef",
7
+ "1": "Kite \u2b30",
8
+ "2": "Parallelogram \u25b0",
9
+ "3": "Rectangle \u25ad",
10
+ "4": "Rhombus \u25c6",
11
+ "5": "Square \u25fc",
12
+ "6": "Trapezoid \u23e2",
13
+ "7": "Triangle \u25b2"
14
+ },
15
+ "initializer_factor": 1.0,
16
+ "label2id": {
17
+ "Circle \u25ef": 0,
18
+ "Kite \u2b30": 1,
19
+ "Parallelogram \u25b0": 2,
20
+ "Rectangle \u25ad": 3,
21
+ "Rhombus \u25c6": 4,
22
+ "Square \u25fc": 5,
23
+ "Trapezoid \u23e2": 6,
24
+ "Triangle \u25b2": 7
25
+ },
26
+ "model_type": "siglip",
27
+ "problem_type": "single_label_classification",
28
+ "text_config": {
29
+ "attention_dropout": 0.0,
30
+ "hidden_act": "gelu_pytorch_tanh",
31
+ "hidden_size": 768,
32
+ "intermediate_size": 3072,
33
+ "layer_norm_eps": 1e-06,
34
+ "max_position_embeddings": 64,
35
+ "model_type": "siglip_text_model",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "projection_size": 768,
39
+ "torch_dtype": "float32",
40
+ "vocab_size": 256000
41
+ },
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.50.3",
44
+ "vision_config": {
45
+ "attention_dropout": 0.0,
46
+ "hidden_act": "gelu_pytorch_tanh",
47
+ "hidden_size": 768,
48
+ "image_size": 224,
49
+ "intermediate_size": 3072,
50
+ "layer_norm_eps": 1e-06,
51
+ "model_type": "siglip_vision_model",
52
+ "num_attention_heads": 12,
53
+ "num_channels": 3,
54
+ "num_hidden_layers": 12,
55
+ "patch_size": 16,
56
+ "torch_dtype": "float32"
57
+ }
58
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a134585cac12e3065d395f47c8f7a50916ed236e6752f94152d5b1466ed6631c
3
+ size 371586448
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