Hugging Face's logo

prithivMLmods
/
Fashion-Product-Usage

Image Classification
Transformers
Safetensors
English
siglip
fashion
product
usage
Casual
Ethnic
Formal
Model card Files
xet
prithivMLmods commited on
Commit
11d28bc
·
verified ·
1 Parent(s): 8afadd0

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-1378/config.json +58 -0
  2. checkpoint-1378/model.safetensors +3 -0
  3. checkpoint-1378/optimizer.pt +3 -0
  4. checkpoint-1378/preprocessor_config.json +24 -0
  5. checkpoint-1378/rng_state.pth +3 -0
  6. checkpoint-1378/scheduler.pt +3 -0
  7. checkpoint-1378/trainer_state.json +58 -0
  8. checkpoint-1378/training_args.bin +3 -0
  9. checkpoint-2756/config.json +58 -0
  10. checkpoint-2756/model.safetensors +3 -0
  11. checkpoint-2756/optimizer.pt +3 -0
  12. checkpoint-2756/preprocessor_config.json +24 -0
  13. checkpoint-2756/rng_state.pth +3 -0
  14. checkpoint-2756/scheduler.pt +3 -0
  15. checkpoint-2756/trainer_state.json +89 -0
  16. checkpoint-2756/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-1378/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Casual",
7
+ "1": "Ethnic",
8
+ "2": "Formal",
9
+ "3": "Home",
10
+ "4": "Party",
11
+ "5": "Smart Casual",
12
+ "6": "Sports",
13
+ "7": "Travel"
14
+ },
15
+ "initializer_factor": 1.0,
16
+ "label2id": {
17
+ "Casual": 0,
18
+ "Ethnic": 1,
19
+ "Formal": 2,
20
+ "Home": 3,
21
+ "Party": 4,
22
+ "Smart Casual": 5,
23
+ "Sports": 6,
24
+ "Travel": 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-1378/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715afb0b4131c1502547e39d3d980c28d1326c29071f1409f5dc49b418d0e2a0
3
+ size 371586448
checkpoint-1378/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f649ee5ca8c9e2fe20eaa433cf9ebf3220a0c392863abb5c8af6917662c2858
3
+ size 686592634
checkpoint-1378/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-1378/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3800323adfbabbfee073f7c32c3d86bc0c9fd7937c41a132afa461c6c74cbe
3
+ size 14244
checkpoint-1378/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2f9dcade45b8d8773de525e316b5580ad7e0268f4b204751a07ebc271c81d0
3
+ size 1064
checkpoint-1378/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1378,
3
+ "best_metric": 0.6540075540542603,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1378",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1378,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.36284470246734396,
14
+ "grad_norm": 3.5291202068328857,
15
+ "learning_rate": 0.00016674057649667407,
16
+ "loss": 0.7979,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.7256894049346879,
21
+ "grad_norm": 5.995710372924805,
22
+ "learning_rate": 0.00012978566149297858,
23
+ "loss": 0.7031,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_accuracy": 0.7998502450535487,
29
+ "eval_loss": 0.6540075540542603,
30
+ "eval_model_preparation_time": 0.0024,
31
+ "eval_runtime": 538.706,
32
+ "eval_samples_per_second": 81.811,
33
+ "eval_steps_per_second": 10.226,
34
+ "step": 1378
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 2756,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 2,
41
+ "save_steps": 500,
42
+ "stateful_callbacks": {
43
+ "TrainerControl": {
44
+ "args": {
45
+ "should_epoch_stop": false,
46
+ "should_evaluate": false,
47
+ "should_log": false,
48
+ "should_save": true,
49
+ "should_training_stop": false
50
+ },
51
+ "attributes": {}
52
+ }
53
+ },
54
+ "total_flos": 3.6914558694311854e+18,
55
+ "train_batch_size": 32,
56
+ "trial_name": null,
57
+ "trial_params": null
58
+ }
checkpoint-1378/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-2756/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Casual",
7
+ "1": "Ethnic",
8
+ "2": "Formal",
9
+ "3": "Home",
10
+ "4": "Party",
11
+ "5": "Smart Casual",
12
+ "6": "Sports",
13
+ "7": "Travel"
14
+ },
15
+ "initializer_factor": 1.0,
16
+ "label2id": {
17
+ "Casual": 0,
18
+ "Ethnic": 1,
19
+ "Formal": 2,
20
+ "Home": 3,
21
+ "Party": 4,
22
+ "Smart Casual": 5,
23
+ "Sports": 6,
24
+ "Travel": 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-2756/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67aedfbd1bcba0b0828c4c25504878dce9db52376ff551143064f89b40c50bd7
3
+ size 371586448
checkpoint-2756/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a55f289f616fff148360e5ccfcadc0d193d70af67c1b8254e98004181aaa405
3
+ size 686592634
checkpoint-2756/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-2756/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6895266ce7775b656647ddf97f9b07ff3ff78add76255d92106d9353ec64e09
3
+ size 14244
checkpoint-2756/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d105dad7507619cb227e4051cae60fdd5d2447df00dfe640987ab94bee865e58
3
+ size 1064
checkpoint-2756/trainer_state.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2756,
3
+ "best_metric": 0.4510948061943054,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-2756",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2756,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.36284470246734396,
14
+ "grad_norm": 3.5291202068328857,
15
+ "learning_rate": 0.00016674057649667407,
16
+ "loss": 0.7979,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.7256894049346879,
21
+ "grad_norm": 5.995710372924805,
22
+ "learning_rate": 0.00012978566149297858,
23
+ "loss": 0.7031,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_accuracy": 0.7998502450535487,
29
+ "eval_loss": 0.6540075540542603,
30
+ "eval_model_preparation_time": 0.0024,
31
+ "eval_runtime": 538.706,
32
+ "eval_samples_per_second": 81.811,
33
+ "eval_steps_per_second": 10.226,
34
+ "step": 1378
35
+ },
36
+ {
37
+ "epoch": 1.0885341074020318,
38
+ "grad_norm": 3.6915018558502197,
39
+ "learning_rate": 9.283074648928308e-05,
40
+ "loss": 0.614,
41
+ "step": 1500
42
+ },
43
+ {
44
+ "epoch": 1.4513788098693758,
45
+ "grad_norm": 5.141565799713135,
46
+ "learning_rate": 5.587583148558758e-05,
47
+ "loss": 0.5564,
48
+ "step": 2000
49
+ },
50
+ {
51
+ "epoch": 1.8142235123367199,
52
+ "grad_norm": 2.352071523666382,
53
+ "learning_rate": 1.892091648189209e-05,
54
+ "loss": 0.5031,
55
+ "step": 2500
56
+ },
57
+ {
58
+ "epoch": 2.0,
59
+ "eval_accuracy": 0.8457750952986023,
60
+ "eval_loss": 0.4510948061943054,
61
+ "eval_model_preparation_time": 0.0024,
62
+ "eval_runtime": 536.7741,
63
+ "eval_samples_per_second": 82.105,
64
+ "eval_steps_per_second": 10.263,
65
+ "step": 2756
66
+ }
67
+ ],
68
+ "logging_steps": 500,
69
+ "max_steps": 2756,
70
+ "num_input_tokens_seen": 0,
71
+ "num_train_epochs": 2,
72
+ "save_steps": 500,
73
+ "stateful_callbacks": {
74
+ "TrainerControl": {
75
+ "args": {
76
+ "should_epoch_stop": false,
77
+ "should_evaluate": false,
78
+ "should_log": false,
79
+ "should_save": true,
80
+ "should_training_stop": true
81
+ },
82
+ "attributes": {}
83
+ }
84
+ },
85
+ "total_flos": 7.382911738862371e+18,
86
+ "train_batch_size": 32,
87
+ "trial_name": null,
88
+ "trial_params": null
89
+ }
checkpoint-2756/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": "Casual",
7
+ "1": "Ethnic",
8
+ "2": "Formal",
9
+ "3": "Home",
10
+ "4": "Party",
11
+ "5": "Smart Casual",
12
+ "6": "Sports",
13
+ "7": "Travel"
14
+ },
15
+ "initializer_factor": 1.0,
16
+ "label2id": {
17
+ "Casual": 0,
18
+ "Ethnic": 1,
19
+ "Formal": 2,
20
+ "Home": 3,
21
+ "Party": 4,
22
+ "Smart Casual": 5,
23
+ "Sports": 6,
24
+ "Travel": 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 sha256:67aedfbd1bcba0b0828c4c25504878dce9db52376ff551143064f89b40c50bd7
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