Hugging Face's logo

prithivMLmods
/
Indian-Western-Food-34

Image Classification
Transformers
Safetensors
English
siglip
food
class
biology
indian
western
Model card Files
xet
Community
prithivMLmods commited on
Commit
9ee6ac1
·
verified ·
1 Parent(s): 4e1fb6d

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. checkpoint-1494/config.json +110 -0
  2. checkpoint-1494/model.safetensors +3 -0
  3. checkpoint-1494/optimizer.pt +3 -0
  4. checkpoint-1494/preprocessor_config.json +24 -0
  5. checkpoint-1494/rng_state.pth +3 -0
  6. checkpoint-1494/scheduler.pt +3 -0
  7. checkpoint-1494/trainer_state.json +68 -0
  8. checkpoint-1494/training_args.bin +3 -0
  9. checkpoint-2241/config.json +110 -0
  10. checkpoint-2241/model.safetensors +3 -0
  11. checkpoint-2241/optimizer.pt +3 -0
  12. checkpoint-2241/preprocessor_config.json +24 -0
  13. checkpoint-2241/rng_state.pth +3 -0
  14. checkpoint-2241/scheduler.pt +3 -0
  15. checkpoint-2241/trainer_state.json +92 -0
  16. checkpoint-2241/training_args.bin +3 -0
  17. checkpoint-2988/config.json +110 -0
  18. checkpoint-2988/model.safetensors +3 -0
  19. checkpoint-2988/optimizer.pt +3 -0
  20. checkpoint-2988/preprocessor_config.json +24 -0
  21. checkpoint-2988/rng_state.pth +3 -0
  22. checkpoint-2988/scheduler.pt +3 -0
  23. checkpoint-2988/trainer_state.json +109 -0
  24. checkpoint-2988/training_args.bin +3 -0
  25. checkpoint-747/config.json +110 -0
  26. checkpoint-747/model.safetensors +3 -0
  27. checkpoint-747/optimizer.pt +3 -0
  28. checkpoint-747/preprocessor_config.json +24 -0
  29. checkpoint-747/rng_state.pth +3 -0
  30. checkpoint-747/scheduler.pt +3 -0
  31. checkpoint-747/trainer_state.json +51 -0
  32. checkpoint-747/training_args.bin +3 -0
  33. config.json +110 -0
  34. model.safetensors +3 -0
  35. preprocessor_config.json +24 -0
  36. training_args.bin +3 -0
checkpoint-1494/config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Baked Potato",
7
+ "1": "Crispy Chicken",
8
+ "2": "Donut",
9
+ "3": "Fries",
10
+ "4": "Hot Dog",
11
+ "5": "Sandwich",
12
+ "6": "Taco",
13
+ "7": "Taquito",
14
+ "8": "Apple Pie",
15
+ "9": "Burger",
16
+ "10": "Butter Naan",
17
+ "11": "Chai",
18
+ "12": "Chapati",
19
+ "13": "Cheesecake",
20
+ "14": "Chicken Curry",
21
+ "15": "Chole Bhature",
22
+ "16": "Dal Makhani",
23
+ "17": "Dhokla",
24
+ "18": "Fried Rice",
25
+ "19": "Ice Cream",
26
+ "20": "Idli",
27
+ "21": "Jalebi",
28
+ "22": "Kaathi Rolls",
29
+ "23": "Kadai Paneer",
30
+ "24": "Kulfi",
31
+ "25": "Masala Dosa",
32
+ "26": "Momos",
33
+ "27": "Omelette",
34
+ "28": "Paani Puri",
35
+ "29": "Pakode",
36
+ "30": "Pav Bhaji",
37
+ "31": "Pizza",
38
+ "32": "Samosa",
39
+ "33": "Sushi"
40
+ },
41
+ "initializer_factor": 1.0,
42
+ "label2id": {
43
+ "Apple Pie": 8,
44
+ "Baked Potato": 0,
45
+ "Burger": 9,
46
+ "Butter Naan": 10,
47
+ "Chai": 11,
48
+ "Chapati": 12,
49
+ "Cheesecake": 13,
50
+ "Chicken Curry": 14,
51
+ "Chole Bhature": 15,
52
+ "Crispy Chicken": 1,
53
+ "Dal Makhani": 16,
54
+ "Dhokla": 17,
55
+ "Donut": 2,
56
+ "Fried Rice": 18,
57
+ "Fries": 3,
58
+ "Hot Dog": 4,
59
+ "Ice Cream": 19,
60
+ "Idli": 20,
61
+ "Jalebi": 21,
62
+ "Kaathi Rolls": 22,
63
+ "Kadai Paneer": 23,
64
+ "Kulfi": 24,
65
+ "Masala Dosa": 25,
66
+ "Momos": 26,
67
+ "Omelette": 27,
68
+ "Paani Puri": 28,
69
+ "Pakode": 29,
70
+ "Pav Bhaji": 30,
71
+ "Pizza": 31,
72
+ "Samosa": 32,
73
+ "Sandwich": 5,
74
+ "Sushi": 33,
75
+ "Taco": 6,
76
+ "Taquito": 7
77
+ },
78
+ "model_type": "siglip",
79
+ "problem_type": "single_label_classification",
80
+ "text_config": {
81
+ "attention_dropout": 0.0,
82
+ "hidden_act": "gelu_pytorch_tanh",
83
+ "hidden_size": 768,
84
+ "intermediate_size": 3072,
85
+ "layer_norm_eps": 1e-06,
86
+ "max_position_embeddings": 64,
87
+ "model_type": "siglip_text_model",
88
+ "num_attention_heads": 12,
89
+ "num_hidden_layers": 12,
90
+ "projection_size": 768,
91
+ "torch_dtype": "float32",
92
+ "vocab_size": 256000
93
+ },
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.50.0",
96
+ "vision_config": {
97
+ "attention_dropout": 0.0,
98
+ "hidden_act": "gelu_pytorch_tanh",
99
+ "hidden_size": 768,
100
+ "image_size": 224,
101
+ "intermediate_size": 3072,
102
+ "layer_norm_eps": 1e-06,
103
+ "model_type": "siglip_vision_model",
104
+ "num_attention_heads": 12,
105
+ "num_channels": 3,
106
+ "num_hidden_layers": 12,
107
+ "patch_size": 16,
108
+ "torch_dtype": "float32"
109
+ }
110
+ }
checkpoint-1494/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560c794e2d80e8802c31ccaac2a199f04ec5ba60de771929dc18621fabdaac0b
3
+ size 371666432
checkpoint-1494/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e34f15b6f12a9152ac3d53621af8c1cc77bc26819307a6e8363eeb34a0398eb
3
+ size 686752634
checkpoint-1494/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-1494/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e13587f5636554f85164ae95fed3c20e934deb854fcc8b175069bf8909f10c
3
+ size 14244
checkpoint-1494/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304d1b8df6ef7958f3b50c14a52d3c5c4a69f545cdd98ccae04cd5f13d59781d
3
+ size 1064
checkpoint-1494/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1494,
3
+ "best_metric": 0.1536320447921753,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1494",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1494,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6693440428380187,
14
+ "grad_norm": 38.35798263549805,
15
+ "learning_rate": 2.5405037440435672e-06,
16
+ "loss": 1.3068,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.939136262723579,
22
+ "eval_loss": 0.28792640566825867,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 460.2975,
25
+ "eval_samples_per_second": 51.864,
26
+ "eval_steps_per_second": 12.968,
27
+ "step": 747
28
+ },
29
+ {
30
+ "epoch": 1.3386880856760375,
31
+ "grad_norm": 27.482799530029297,
32
+ "learning_rate": 2.029952348536419e-06,
33
+ "loss": 0.311,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.9621748418715704,
39
+ "eval_loss": 0.1536320447921753,
40
+ "eval_model_preparation_time": 0.0024,
41
+ "eval_runtime": 461.078,
42
+ "eval_samples_per_second": 51.776,
43
+ "eval_steps_per_second": 12.946,
44
+ "step": 1494
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 2988,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 4,
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": false
60
+ },
61
+ "attributes": {}
62
+ }
63
+ },
64
+ "total_flos": 4.000051065885106e+18,
65
+ "train_batch_size": 32,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-1494/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c72e8d1fb4783fc60417c45a864c19da3b014e0ded8c82006ea1defcd597e61
3
+ size 5304
checkpoint-2241/config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Baked Potato",
7
+ "1": "Crispy Chicken",
8
+ "2": "Donut",
9
+ "3": "Fries",
10
+ "4": "Hot Dog",
11
+ "5": "Sandwich",
12
+ "6": "Taco",
13
+ "7": "Taquito",
14
+ "8": "Apple Pie",
15
+ "9": "Burger",
16
+ "10": "Butter Naan",
17
+ "11": "Chai",
18
+ "12": "Chapati",
19
+ "13": "Cheesecake",
20
+ "14": "Chicken Curry",
21
+ "15": "Chole Bhature",
22
+ "16": "Dal Makhani",
23
+ "17": "Dhokla",
24
+ "18": "Fried Rice",
25
+ "19": "Ice Cream",
26
+ "20": "Idli",
27
+ "21": "Jalebi",
28
+ "22": "Kaathi Rolls",
29
+ "23": "Kadai Paneer",
30
+ "24": "Kulfi",
31
+ "25": "Masala Dosa",
32
+ "26": "Momos",
33
+ "27": "Omelette",
34
+ "28": "Paani Puri",
35
+ "29": "Pakode",
36
+ "30": "Pav Bhaji",
37
+ "31": "Pizza",
38
+ "32": "Samosa",
39
+ "33": "Sushi"
40
+ },
41
+ "initializer_factor": 1.0,
42
+ "label2id": {
43
+ "Apple Pie": 8,
44
+ "Baked Potato": 0,
45
+ "Burger": 9,
46
+ "Butter Naan": 10,
47
+ "Chai": 11,
48
+ "Chapati": 12,
49
+ "Cheesecake": 13,
50
+ "Chicken Curry": 14,
51
+ "Chole Bhature": 15,
52
+ "Crispy Chicken": 1,
53
+ "Dal Makhani": 16,
54
+ "Dhokla": 17,
55
+ "Donut": 2,
56
+ "Fried Rice": 18,
57
+ "Fries": 3,
58
+ "Hot Dog": 4,
59
+ "Ice Cream": 19,
60
+ "Idli": 20,
61
+ "Jalebi": 21,
62
+ "Kaathi Rolls": 22,
63
+ "Kadai Paneer": 23,
64
+ "Kulfi": 24,
65
+ "Masala Dosa": 25,
66
+ "Momos": 26,
67
+ "Omelette": 27,
68
+ "Paani Puri": 28,
69
+ "Pakode": 29,
70
+ "Pav Bhaji": 30,
71
+ "Pizza": 31,
72
+ "Samosa": 32,
73
+ "Sandwich": 5,
74
+ "Sushi": 33,
75
+ "Taco": 6,
76
+ "Taquito": 7
77
+ },
78
+ "model_type": "siglip",
79
+ "problem_type": "single_label_classification",
80
+ "text_config": {
81
+ "attention_dropout": 0.0,
82
+ "hidden_act": "gelu_pytorch_tanh",
83
+ "hidden_size": 768,
84
+ "intermediate_size": 3072,
85
+ "layer_norm_eps": 1e-06,
86
+ "max_position_embeddings": 64,
87
+ "model_type": "siglip_text_model",
88
+ "num_attention_heads": 12,
89
+ "num_hidden_layers": 12,
90
+ "projection_size": 768,
91
+ "torch_dtype": "float32",
92
+ "vocab_size": 256000
93
+ },
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.50.0",
96
+ "vision_config": {
97
+ "attention_dropout": 0.0,
98
+ "hidden_act": "gelu_pytorch_tanh",
99
+ "hidden_size": 768,
100
+ "image_size": 224,
101
+ "intermediate_size": 3072,
102
+ "layer_norm_eps": 1e-06,
103
+ "model_type": "siglip_vision_model",
104
+ "num_attention_heads": 12,
105
+ "num_channels": 3,
106
+ "num_hidden_layers": 12,
107
+ "patch_size": 16,
108
+ "torch_dtype": "float32"
109
+ }
110
+ }
checkpoint-2241/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7f7de673291aa64db83c8ddedea84444f3a364e37243652c5c1cb216f79591
3
+ size 371666432
checkpoint-2241/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836abb39b90deaf5f0298f6150cbf844a1702b1f0551f2435f06d6f443fe753f
3
+ size 686752634
checkpoint-2241/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-2241/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:228231e3a69e8bb6e041a818d73bdd329217a957638cfb475622a565bb77ef87
3
+ size 14244
checkpoint-2241/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec4339fc0f463d134c46dfbfa25b04f1a1abb8479445098997e77694db235d1
3
+ size 1064
checkpoint-2241/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2241,
3
+ "best_metric": 0.10924265533685684,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-2241",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2241,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6693440428380187,
14
+ "grad_norm": 38.35798263549805,
15
+ "learning_rate": 2.5405037440435672e-06,
16
+ "loss": 1.3068,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.939136262723579,
22
+ "eval_loss": 0.28792640566825867,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 460.2975,
25
+ "eval_samples_per_second": 51.864,
26
+ "eval_steps_per_second": 12.968,
27
+ "step": 747
28
+ },
29
+ {
30
+ "epoch": 1.3386880856760375,
31
+ "grad_norm": 27.482799530029297,
32
+ "learning_rate": 2.029952348536419e-06,
33
+ "loss": 0.311,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.9621748418715704,
39
+ "eval_loss": 0.1536320447921753,
40
+ "eval_model_preparation_time": 0.0024,
41
+ "eval_runtime": 461.078,
42
+ "eval_samples_per_second": 51.776,
43
+ "eval_steps_per_second": 12.946,
44
+ "step": 1494
45
+ },
46
+ {
47
+ "epoch": 2.0080321285140563,
48
+ "grad_norm": 24.544109344482422,
49
+ "learning_rate": 1.5194009530292717e-06,
50
+ "loss": 0.2148,
51
+ "step": 1500
52
+ },
53
+ {
54
+ "epoch": 2.677376171352075,
55
+ "grad_norm": 21.47413444519043,
56
+ "learning_rate": 1.0088495575221239e-06,
57
+ "loss": 0.1599,
58
+ "step": 2000
59
+ },
60
+ {
61
+ "epoch": 3.0,
62
+ "eval_accuracy": 0.9705525070162946,
63
+ "eval_loss": 0.10924265533685684,
64
+ "eval_model_preparation_time": 0.0024,
65
+ "eval_runtime": 460.2769,
66
+ "eval_samples_per_second": 51.867,
67
+ "eval_steps_per_second": 12.968,
68
+ "step": 2241
69
+ }
70
+ ],
71
+ "logging_steps": 500,
72
+ "max_steps": 2988,
73
+ "num_input_tokens_seen": 0,
74
+ "num_train_epochs": 4,
75
+ "save_steps": 500,
76
+ "stateful_callbacks": {
77
+ "TrainerControl": {
78
+ "args": {
79
+ "should_epoch_stop": false,
80
+ "should_evaluate": false,
81
+ "should_log": false,
82
+ "should_save": true,
83
+ "should_training_stop": false
84
+ },
85
+ "attributes": {}
86
+ }
87
+ },
88
+ "total_flos": 6.000076598827659e+18,
89
+ "train_batch_size": 32,
90
+ "trial_name": null,
91
+ "trial_params": null
92
+ }
checkpoint-2241/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c72e8d1fb4783fc60417c45a864c19da3b014e0ded8c82006ea1defcd597e61
3
+ size 5304
checkpoint-2988/config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Baked Potato",
7
+ "1": "Crispy Chicken",
8
+ "2": "Donut",
9
+ "3": "Fries",
10
+ "4": "Hot Dog",
11
+ "5": "Sandwich",
12
+ "6": "Taco",
13
+ "7": "Taquito",
14
+ "8": "Apple Pie",
15
+ "9": "Burger",
16
+ "10": "Butter Naan",
17
+ "11": "Chai",
18
+ "12": "Chapati",
19
+ "13": "Cheesecake",
20
+ "14": "Chicken Curry",
21
+ "15": "Chole Bhature",
22
+ "16": "Dal Makhani",
23
+ "17": "Dhokla",
24
+ "18": "Fried Rice",
25
+ "19": "Ice Cream",
26
+ "20": "Idli",
27
+ "21": "Jalebi",
28
+ "22": "Kaathi Rolls",
29
+ "23": "Kadai Paneer",
30
+ "24": "Kulfi",
31
+ "25": "Masala Dosa",
32
+ "26": "Momos",
33
+ "27": "Omelette",
34
+ "28": "Paani Puri",
35
+ "29": "Pakode",
36
+ "30": "Pav Bhaji",
37
+ "31": "Pizza",
38
+ "32": "Samosa",
39
+ "33": "Sushi"
40
+ },
41
+ "initializer_factor": 1.0,
42
+ "label2id": {
43
+ "Apple Pie": 8,
44
+ "Baked Potato": 0,
45
+ "Burger": 9,
46
+ "Butter Naan": 10,
47
+ "Chai": 11,
48
+ "Chapati": 12,
49
+ "Cheesecake": 13,
50
+ "Chicken Curry": 14,
51
+ "Chole Bhature": 15,
52
+ "Crispy Chicken": 1,
53
+ "Dal Makhani": 16,
54
+ "Dhokla": 17,
55
+ "Donut": 2,
56
+ "Fried Rice": 18,
57
+ "Fries": 3,
58
+ "Hot Dog": 4,
59
+ "Ice Cream": 19,
60
+ "Idli": 20,
61
+ "Jalebi": 21,
62
+ "Kaathi Rolls": 22,
63
+ "Kadai Paneer": 23,
64
+ "Kulfi": 24,
65
+ "Masala Dosa": 25,
66
+ "Momos": 26,
67
+ "Omelette": 27,
68
+ "Paani Puri": 28,
69
+ "Pakode": 29,
70
+ "Pav Bhaji": 30,
71
+ "Pizza": 31,
72
+ "Samosa": 32,
73
+ "Sandwich": 5,
74
+ "Sushi": 33,
75
+ "Taco": 6,
76
+ "Taquito": 7
77
+ },
78
+ "model_type": "siglip",
79
+ "problem_type": "single_label_classification",
80
+ "text_config": {
81
+ "attention_dropout": 0.0,
82
+ "hidden_act": "gelu_pytorch_tanh",
83
+ "hidden_size": 768,
84
+ "intermediate_size": 3072,
85
+ "layer_norm_eps": 1e-06,
86
+ "max_position_embeddings": 64,
87
+ "model_type": "siglip_text_model",
88
+ "num_attention_heads": 12,
89
+ "num_hidden_layers": 12,
90
+ "projection_size": 768,
91
+ "torch_dtype": "float32",
92
+ "vocab_size": 256000
93
+ },
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.50.0",
96
+ "vision_config": {
97
+ "attention_dropout": 0.0,
98
+ "hidden_act": "gelu_pytorch_tanh",
99
+ "hidden_size": 768,
100
+ "image_size": 224,
101
+ "intermediate_size": 3072,
102
+ "layer_norm_eps": 1e-06,
103
+ "model_type": "siglip_vision_model",
104
+ "num_attention_heads": 12,
105
+ "num_channels": 3,
106
+ "num_hidden_layers": 12,
107
+ "patch_size": 16,
108
+ "torch_dtype": "float32"
109
+ }
110
+ }
checkpoint-2988/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148fff53df3208491e46353170b6e6d7f8b49d2ee064cabda2608b194a64435e
3
+ size 371666432
checkpoint-2988/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5145b6f77597ae372bba1dbbf636a1ef7c65046707433d312a5bf9f86e4f697
3
+ size 686752634
checkpoint-2988/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-2988/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91dcbda3ac6a1b7db3a923fa20a7041200b635ceb8455e2019ae7098b53c3c05
3
+ size 14244
checkpoint-2988/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ab2117a878b298547a48a72a8dd8facc2794e050754f08f9dcec69967342a4
3
+ size 1064
checkpoint-2988/trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2988,
3
+ "best_metric": 0.09974350035190582,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-2988",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2988,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6693440428380187,
14
+ "grad_norm": 38.35798263549805,
15
+ "learning_rate": 2.5405037440435672e-06,
16
+ "loss": 1.3068,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.939136262723579,
22
+ "eval_loss": 0.28792640566825867,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 460.2975,
25
+ "eval_samples_per_second": 51.864,
26
+ "eval_steps_per_second": 12.968,
27
+ "step": 747
28
+ },
29
+ {
30
+ "epoch": 1.3386880856760375,
31
+ "grad_norm": 27.482799530029297,
32
+ "learning_rate": 2.029952348536419e-06,
33
+ "loss": 0.311,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.9621748418715704,
39
+ "eval_loss": 0.1536320447921753,
40
+ "eval_model_preparation_time": 0.0024,
41
+ "eval_runtime": 461.078,
42
+ "eval_samples_per_second": 51.776,
43
+ "eval_steps_per_second": 12.946,
44
+ "step": 1494
45
+ },
46
+ {
47
+ "epoch": 2.0080321285140563,
48
+ "grad_norm": 24.544109344482422,
49
+ "learning_rate": 1.5194009530292717e-06,
50
+ "loss": 0.2148,
51
+ "step": 1500
52
+ },
53
+ {
54
+ "epoch": 2.677376171352075,
55
+ "grad_norm": 21.47413444519043,
56
+ "learning_rate": 1.0088495575221239e-06,
57
+ "loss": 0.1599,
58
+ "step": 2000
59
+ },
60
+ {
61
+ "epoch": 3.0,
62
+ "eval_accuracy": 0.9705525070162946,
63
+ "eval_loss": 0.10924265533685684,
64
+ "eval_model_preparation_time": 0.0024,
65
+ "eval_runtime": 460.2769,
66
+ "eval_samples_per_second": 51.867,
67
+ "eval_steps_per_second": 12.968,
68
+ "step": 2241
69
+ },
70
+ {
71
+ "epoch": 3.3467202141900936,
72
+ "grad_norm": 30.689044952392578,
73
+ "learning_rate": 4.982981620149761e-07,
74
+ "loss": 0.1314,
75
+ "step": 2500
76
+ },
77
+ {
78
+ "epoch": 4.0,
79
+ "eval_accuracy": 0.9728563649310937,
80
+ "eval_loss": 0.09974350035190582,
81
+ "eval_model_preparation_time": 0.0024,
82
+ "eval_runtime": 459.1401,
83
+ "eval_samples_per_second": 51.995,
84
+ "eval_steps_per_second": 13.0,
85
+ "step": 2988
86
+ }
87
+ ],
88
+ "logging_steps": 500,
89
+ "max_steps": 2988,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 4,
92
+ "save_steps": 500,
93
+ "stateful_callbacks": {
94
+ "TrainerControl": {
95
+ "args": {
96
+ "should_epoch_stop": false,
97
+ "should_evaluate": false,
98
+ "should_log": false,
99
+ "should_save": true,
100
+ "should_training_stop": true
101
+ },
102
+ "attributes": {}
103
+ }
104
+ },
105
+ "total_flos": 8.000102131770212e+18,
106
+ "train_batch_size": 32,
107
+ "trial_name": null,
108
+ "trial_params": null
109
+ }
checkpoint-2988/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c72e8d1fb4783fc60417c45a864c19da3b014e0ded8c82006ea1defcd597e61
3
+ size 5304
checkpoint-747/config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Baked Potato",
7
+ "1": "Crispy Chicken",
8
+ "2": "Donut",
9
+ "3": "Fries",
10
+ "4": "Hot Dog",
11
+ "5": "Sandwich",
12
+ "6": "Taco",
13
+ "7": "Taquito",
14
+ "8": "Apple Pie",
15
+ "9": "Burger",
16
+ "10": "Butter Naan",
17
+ "11": "Chai",
18
+ "12": "Chapati",
19
+ "13": "Cheesecake",
20
+ "14": "Chicken Curry",
21
+ "15": "Chole Bhature",
22
+ "16": "Dal Makhani",
23
+ "17": "Dhokla",
24
+ "18": "Fried Rice",
25
+ "19": "Ice Cream",
26
+ "20": "Idli",
27
+ "21": "Jalebi",
28
+ "22": "Kaathi Rolls",
29
+ "23": "Kadai Paneer",
30
+ "24": "Kulfi",
31
+ "25": "Masala Dosa",
32
+ "26": "Momos",
33
+ "27": "Omelette",
34
+ "28": "Paani Puri",
35
+ "29": "Pakode",
36
+ "30": "Pav Bhaji",
37
+ "31": "Pizza",
38
+ "32": "Samosa",
39
+ "33": "Sushi"
40
+ },
41
+ "initializer_factor": 1.0,
42
+ "label2id": {
43
+ "Apple Pie": 8,
44
+ "Baked Potato": 0,
45
+ "Burger": 9,
46
+ "Butter Naan": 10,
47
+ "Chai": 11,
48
+ "Chapati": 12,
49
+ "Cheesecake": 13,
50
+ "Chicken Curry": 14,
51
+ "Chole Bhature": 15,
52
+ "Crispy Chicken": 1,
53
+ "Dal Makhani": 16,
54
+ "Dhokla": 17,
55
+ "Donut": 2,
56
+ "Fried Rice": 18,
57
+ "Fries": 3,
58
+ "Hot Dog": 4,
59
+ "Ice Cream": 19,
60
+ "Idli": 20,
61
+ "Jalebi": 21,
62
+ "Kaathi Rolls": 22,
63
+ "Kadai Paneer": 23,
64
+ "Kulfi": 24,
65
+ "Masala Dosa": 25,
66
+ "Momos": 26,
67
+ "Omelette": 27,
68
+ "Paani Puri": 28,
69
+ "Pakode": 29,
70
+ "Pav Bhaji": 30,
71
+ "Pizza": 31,
72
+ "Samosa": 32,
73
+ "Sandwich": 5,
74
+ "Sushi": 33,
75
+ "Taco": 6,
76
+ "Taquito": 7
77
+ },
78
+ "model_type": "siglip",
79
+ "problem_type": "single_label_classification",
80
+ "text_config": {
81
+ "attention_dropout": 0.0,
82
+ "hidden_act": "gelu_pytorch_tanh",
83
+ "hidden_size": 768,
84
+ "intermediate_size": 3072,
85
+ "layer_norm_eps": 1e-06,
86
+ "max_position_embeddings": 64,
87
+ "model_type": "siglip_text_model",
88
+ "num_attention_heads": 12,
89
+ "num_hidden_layers": 12,
90
+ "projection_size": 768,
91
+ "torch_dtype": "float32",
92
+ "vocab_size": 256000
93
+ },
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.50.0",
96
+ "vision_config": {
97
+ "attention_dropout": 0.0,
98
+ "hidden_act": "gelu_pytorch_tanh",
99
+ "hidden_size": 768,
100
+ "image_size": 224,
101
+ "intermediate_size": 3072,
102
+ "layer_norm_eps": 1e-06,
103
+ "model_type": "siglip_vision_model",
104
+ "num_attention_heads": 12,
105
+ "num_channels": 3,
106
+ "num_hidden_layers": 12,
107
+ "patch_size": 16,
108
+ "torch_dtype": "float32"
109
+ }
110
+ }
checkpoint-747/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49644d578d2fff9d71fbad635d940a64c6474c7fd2ab163734c70069cd531897
3
+ size 371666432
checkpoint-747/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:947a68eff2920172107ba1774dbcc64bd6f0a7c44ed01baa97bfba9258a933ed
3
+ size 686752634
checkpoint-747/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-747/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e90841bf5306dcf1bb378a829d2cc6fd05409fe58813885cad2f3a22559409be
3
+ size 14244
checkpoint-747/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb286b9a63a0a89957cef43ea7ab76df687f88d3187a7202c3dd5e8c01c694e
3
+ size 1064
checkpoint-747/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 747,
3
+ "best_metric": 0.28792640566825867,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-747",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 747,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6693440428380187,
14
+ "grad_norm": 38.35798263549805,
15
+ "learning_rate": 2.5405037440435672e-06,
16
+ "loss": 1.3068,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.939136262723579,
22
+ "eval_loss": 0.28792640566825867,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 460.2975,
25
+ "eval_samples_per_second": 51.864,
26
+ "eval_steps_per_second": 12.968,
27
+ "step": 747
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 2988,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
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": 2.000025532942553e+18,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-747/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c72e8d1fb4783fc60417c45a864c19da3b014e0ded8c82006ea1defcd597e61
3
+ size 5304
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Baked Potato",
7
+ "1": "Crispy Chicken",
8
+ "2": "Donut",
9
+ "3": "Fries",
10
+ "4": "Hot Dog",
11
+ "5": "Sandwich",
12
+ "6": "Taco",
13
+ "7": "Taquito",
14
+ "8": "Apple Pie",
15
+ "9": "Burger",
16
+ "10": "Butter Naan",
17
+ "11": "Chai",
18
+ "12": "Chapati",
19
+ "13": "Cheesecake",
20
+ "14": "Chicken Curry",
21
+ "15": "Chole Bhature",
22
+ "16": "Dal Makhani",
23
+ "17": "Dhokla",
24
+ "18": "Fried Rice",
25
+ "19": "Ice Cream",
26
+ "20": "Idli",
27
+ "21": "Jalebi",
28
+ "22": "Kaathi Rolls",
29
+ "23": "Kadai Paneer",
30
+ "24": "Kulfi",
31
+ "25": "Masala Dosa",
32
+ "26": "Momos",
33
+ "27": "Omelette",
34
+ "28": "Paani Puri",
35
+ "29": "Pakode",
36
+ "30": "Pav Bhaji",
37
+ "31": "Pizza",
38
+ "32": "Samosa",
39
+ "33": "Sushi"
40
+ },
41
+ "initializer_factor": 1.0,
42
+ "label2id": {
43
+ "Apple Pie": 8,
44
+ "Baked Potato": 0,
45
+ "Burger": 9,
46
+ "Butter Naan": 10,
47
+ "Chai": 11,
48
+ "Chapati": 12,
49
+ "Cheesecake": 13,
50
+ "Chicken Curry": 14,
51
+ "Chole Bhature": 15,
52
+ "Crispy Chicken": 1,
53
+ "Dal Makhani": 16,
54
+ "Dhokla": 17,
55
+ "Donut": 2,
56
+ "Fried Rice": 18,
57
+ "Fries": 3,
58
+ "Hot Dog": 4,
59
+ "Ice Cream": 19,
60
+ "Idli": 20,
61
+ "Jalebi": 21,
62
+ "Kaathi Rolls": 22,
63
+ "Kadai Paneer": 23,
64
+ "Kulfi": 24,
65
+ "Masala Dosa": 25,
66
+ "Momos": 26,
67
+ "Omelette": 27,
68
+ "Paani Puri": 28,
69
+ "Pakode": 29,
70
+ "Pav Bhaji": 30,
71
+ "Pizza": 31,
72
+ "Samosa": 32,
73
+ "Sandwich": 5,
74
+ "Sushi": 33,
75
+ "Taco": 6,
76
+ "Taquito": 7
77
+ },
78
+ "model_type": "siglip",
79
+ "problem_type": "single_label_classification",
80
+ "text_config": {
81
+ "attention_dropout": 0.0,
82
+ "hidden_act": "gelu_pytorch_tanh",
83
+ "hidden_size": 768,
84
+ "intermediate_size": 3072,
85
+ "layer_norm_eps": 1e-06,
86
+ "max_position_embeddings": 64,
87
+ "model_type": "siglip_text_model",
88
+ "num_attention_heads": 12,
89
+ "num_hidden_layers": 12,
90
+ "projection_size": 768,
91
+ "torch_dtype": "float32",
92
+ "vocab_size": 256000
93
+ },
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.50.0",
96
+ "vision_config": {
97
+ "attention_dropout": 0.0,
98
+ "hidden_act": "gelu_pytorch_tanh",
99
+ "hidden_size": 768,
100
+ "image_size": 224,
101
+ "intermediate_size": 3072,
102
+ "layer_norm_eps": 1e-06,
103
+ "model_type": "siglip_vision_model",
104
+ "num_attention_heads": 12,
105
+ "num_channels": 3,
106
+ "num_hidden_layers": 12,
107
+ "patch_size": 16,
108
+ "torch_dtype": "float32"
109
+ }
110
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148fff53df3208491e46353170b6e6d7f8b49d2ee064cabda2608b194a64435e
3
+ size 371666432
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 sha256:6c72e8d1fb4783fc60417c45a864c19da3b014e0ded8c82006ea1defcd597e61
3
+ size 5304