Hugging Face's logo

prithivMLmods
/
Face-Confidence-SigLIP2

Image Classification
Transformers
Safetensors
English
siglip
text-generation-inference
Model card Files
xet
Community
prithivMLmods commited on
Commit
f4b575a
·
verified ·
1 Parent(s): 573488d

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. checkpoint-1078/config.json +46 -0
  2. checkpoint-1078/model.safetensors +3 -0
  3. checkpoint-1078/optimizer.pt +3 -0
  4. checkpoint-1078/preprocessor_config.json +24 -0
  5. checkpoint-1078/rng_state.pth +3 -0
  6. checkpoint-1078/scheduler.pt +3 -0
  7. checkpoint-1078/trainer_state.json +68 -0
  8. checkpoint-1078/training_args.bin +3 -0
  9. checkpoint-1617/config.json +46 -0
  10. checkpoint-1617/model.safetensors +3 -0
  11. checkpoint-1617/optimizer.pt +3 -0
  12. checkpoint-1617/preprocessor_config.json +24 -0
  13. checkpoint-1617/rng_state.pth +3 -0
  14. checkpoint-1617/scheduler.pt +3 -0
  15. checkpoint-1617/trainer_state.json +85 -0
  16. checkpoint-1617/training_args.bin +3 -0
  17. checkpoint-2156/config.json +46 -0
  18. checkpoint-2156/model.safetensors +3 -0
  19. checkpoint-2156/optimizer.pt +3 -0
  20. checkpoint-2156/preprocessor_config.json +24 -0
  21. checkpoint-2156/rng_state.pth +3 -0
  22. checkpoint-2156/scheduler.pt +3 -0
  23. checkpoint-2156/trainer_state.json +102 -0
  24. checkpoint-2156/training_args.bin +3 -0
  25. checkpoint-539/config.json +46 -0
  26. checkpoint-539/model.safetensors +3 -0
  27. checkpoint-539/optimizer.pt +3 -0
  28. checkpoint-539/preprocessor_config.json +24 -0
  29. checkpoint-539/rng_state.pth +3 -0
  30. checkpoint-539/scheduler.pt +3 -0
  31. checkpoint-539/trainer_state.json +51 -0
  32. checkpoint-539/training_args.bin +3 -0
  33. config.json +46 -0
  34. model.safetensors +3 -0
  35. preprocessor_config.json +24 -0
  36. training_args.bin +3 -0
checkpoint-1078/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "confident",
7
+ "1": "unconfident"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "confident": 0,
12
+ "unconfident": 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-1078/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6560e53402ca01a4389ac0327e8e606c3a39c6686fe97e23de601d339ae405e1
3
+ size 371567992
checkpoint-1078/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f681cae6156a5e0b2aaeb363dbaef008fe5b87b7d107108dc2268e161c68c14
3
+ size 686556235
checkpoint-1078/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-1078/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fcb359678c5ae6d1c327d06c6a34475e30ed74fb525da7ce2a36d76d3dd2ec1
3
+ size 14645
checkpoint-1078/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fae8d79b6269829aa01df41855f50e3bd7515b7972f837dd84fcf39967a1c31
3
+ size 1465
checkpoint-1078/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1078,
3
+ "best_metric": 0.37225112318992615,
4
+ "best_model_checkpoint": "face-confidence/checkpoint-1078",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1078,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9276437847866419,
14
+ "grad_norm": 6.720329761505127,
15
+ "learning_rate": 1.5726495726495726e-05,
16
+ "loss": 0.4994,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8189497518070191,
22
+ "eval_loss": 0.3962201476097107,
23
+ "eval_model_preparation_time": 0.0025,
24
+ "eval_runtime": 141.0014,
25
+ "eval_samples_per_second": 81.439,
26
+ "eval_steps_per_second": 10.184,
27
+ "step": 539
28
+ },
29
+ {
30
+ "epoch": 1.8552875695732838,
31
+ "grad_norm": 8.098552703857422,
32
+ "learning_rate": 1.0978157644824312e-05,
33
+ "loss": 0.4083,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.8331446486109901,
39
+ "eval_loss": 0.37225112318992615,
40
+ "eval_model_preparation_time": 0.0025,
41
+ "eval_runtime": 139.7716,
42
+ "eval_samples_per_second": 82.155,
43
+ "eval_steps_per_second": 10.274,
44
+ "step": 1078
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 2156,
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": 2.885209320052556e+18,
65
+ "train_batch_size": 32,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-1078/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebac92433010be2bcd166a9c8d0f0b5c25e7cfa6b3f6aa8d546bcec4c80ff5a5
3
+ size 5713
checkpoint-1617/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "confident",
7
+ "1": "unconfident"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "confident": 0,
12
+ "unconfident": 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-1617/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:346dd5e4eda86c5184383d062cd0af8f4631176df7ec36dab1679144a300127b
3
+ size 371567992
checkpoint-1617/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9fce0e5639014e5234a35912bfd1faaa2dba8cd192db868a6c5e3ceb119346a
3
+ size 686556235
checkpoint-1617/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-1617/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d2fb9c6db10fc63b6607702ea6575096693c0662c2780db0433af05b4774e35
3
+ size 14645
checkpoint-1617/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d4095dd1812a134c51f6fd196c73db0dd7ed152138125e99f20386e9410e48
3
+ size 1465
checkpoint-1617/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1617,
3
+ "best_metric": 0.33761295676231384,
4
+ "best_model_checkpoint": "face-confidence/checkpoint-1617",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1617,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9276437847866419,
14
+ "grad_norm": 6.720329761505127,
15
+ "learning_rate": 1.5726495726495726e-05,
16
+ "loss": 0.4994,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8189497518070191,
22
+ "eval_loss": 0.3962201476097107,
23
+ "eval_model_preparation_time": 0.0025,
24
+ "eval_runtime": 141.0014,
25
+ "eval_samples_per_second": 81.439,
26
+ "eval_steps_per_second": 10.184,
27
+ "step": 539
28
+ },
29
+ {
30
+ "epoch": 1.8552875695732838,
31
+ "grad_norm": 8.098552703857422,
32
+ "learning_rate": 1.0978157644824312e-05,
33
+ "loss": 0.4083,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.8331446486109901,
39
+ "eval_loss": 0.37225112318992615,
40
+ "eval_model_preparation_time": 0.0025,
41
+ "eval_runtime": 139.7716,
42
+ "eval_samples_per_second": 82.155,
43
+ "eval_steps_per_second": 10.274,
44
+ "step": 1078
45
+ },
46
+ {
47
+ "epoch": 2.782931354359926,
48
+ "grad_norm": 13.027604103088379,
49
+ "learning_rate": 6.229819563152897e-06,
50
+ "loss": 0.3556,
51
+ "step": 1500
52
+ },
53
+ {
54
+ "epoch": 3.0,
55
+ "eval_accuracy": 0.8531742575981887,
56
+ "eval_loss": 0.33761295676231384,
57
+ "eval_model_preparation_time": 0.0025,
58
+ "eval_runtime": 139.2575,
59
+ "eval_samples_per_second": 82.459,
60
+ "eval_steps_per_second": 10.312,
61
+ "step": 1617
62
+ }
63
+ ],
64
+ "logging_steps": 500,
65
+ "max_steps": 2156,
66
+ "num_input_tokens_seen": 0,
67
+ "num_train_epochs": 4,
68
+ "save_steps": 500,
69
+ "stateful_callbacks": {
70
+ "TrainerControl": {
71
+ "args": {
72
+ "should_epoch_stop": false,
73
+ "should_evaluate": false,
74
+ "should_log": false,
75
+ "should_save": true,
76
+ "should_training_stop": false
77
+ },
78
+ "attributes": {}
79
+ }
80
+ },
81
+ "total_flos": 4.3278139800788337e+18,
82
+ "train_batch_size": 32,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }
checkpoint-1617/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebac92433010be2bcd166a9c8d0f0b5c25e7cfa6b3f6aa8d546bcec4c80ff5a5
3
+ size 5713
checkpoint-2156/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "confident",
7
+ "1": "unconfident"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "confident": 0,
12
+ "unconfident": 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-2156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18123dc046e4fa3f30322fdc2d3c683bee5e5407e97a29d977eb80c474736a88
3
+ size 371567992
checkpoint-2156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6c2dbf642858673a3d7ba0d4eaa8ba7507f7283d98cd6ee6fe903d7581db0b
3
+ size 686556235
checkpoint-2156/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-2156/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8cd7fe39d1833160de27b177c23985162119980c8cf641ed13eebc22163d29a
3
+ size 14645
checkpoint-2156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219ff6749bd1e591eda030f47263717e87bfe55a8b920a22cb5a95dc1a04d769
3
+ size 1465
checkpoint-2156/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2156,
3
+ "best_metric": 0.3237510919570923,
4
+ "best_model_checkpoint": "face-confidence/checkpoint-2156",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2156,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9276437847866419,
14
+ "grad_norm": 6.720329761505127,
15
+ "learning_rate": 1.5726495726495726e-05,
16
+ "loss": 0.4994,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8189497518070191,
22
+ "eval_loss": 0.3962201476097107,
23
+ "eval_model_preparation_time": 0.0025,
24
+ "eval_runtime": 141.0014,
25
+ "eval_samples_per_second": 81.439,
26
+ "eval_steps_per_second": 10.184,
27
+ "step": 539
28
+ },
29
+ {
30
+ "epoch": 1.8552875695732838,
31
+ "grad_norm": 8.098552703857422,
32
+ "learning_rate": 1.0978157644824312e-05,
33
+ "loss": 0.4083,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.8331446486109901,
39
+ "eval_loss": 0.37225112318992615,
40
+ "eval_model_preparation_time": 0.0025,
41
+ "eval_runtime": 139.7716,
42
+ "eval_samples_per_second": 82.155,
43
+ "eval_steps_per_second": 10.274,
44
+ "step": 1078
45
+ },
46
+ {
47
+ "epoch": 2.782931354359926,
48
+ "grad_norm": 13.027604103088379,
49
+ "learning_rate": 6.229819563152897e-06,
50
+ "loss": 0.3556,
51
+ "step": 1500
52
+ },
53
+ {
54
+ "epoch": 3.0,
55
+ "eval_accuracy": 0.8531742575981887,
56
+ "eval_loss": 0.33761295676231384,
57
+ "eval_model_preparation_time": 0.0025,
58
+ "eval_runtime": 139.2575,
59
+ "eval_samples_per_second": 82.459,
60
+ "eval_steps_per_second": 10.312,
61
+ "step": 1617
62
+ },
63
+ {
64
+ "epoch": 3.7105751391465676,
65
+ "grad_norm": 11.10226821899414,
66
+ "learning_rate": 1.4814814814814815e-06,
67
+ "loss": 0.3085,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "eval_accuracy": 0.8599669076025429,
73
+ "eval_loss": 0.3237510919570923,
74
+ "eval_model_preparation_time": 0.0025,
75
+ "eval_runtime": 139.6031,
76
+ "eval_samples_per_second": 82.255,
77
+ "eval_steps_per_second": 10.286,
78
+ "step": 2156
79
+ }
80
+ ],
81
+ "logging_steps": 500,
82
+ "max_steps": 2156,
83
+ "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 4,
85
+ "save_steps": 500,
86
+ "stateful_callbacks": {
87
+ "TrainerControl": {
88
+ "args": {
89
+ "should_epoch_stop": false,
90
+ "should_evaluate": false,
91
+ "should_log": false,
92
+ "should_save": true,
93
+ "should_training_stop": true
94
+ },
95
+ "attributes": {}
96
+ }
97
+ },
98
+ "total_flos": 5.770418640105112e+18,
99
+ "train_batch_size": 32,
100
+ "trial_name": null,
101
+ "trial_params": null
102
+ }
checkpoint-2156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebac92433010be2bcd166a9c8d0f0b5c25e7cfa6b3f6aa8d546bcec4c80ff5a5
3
+ size 5713
checkpoint-539/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "confident",
7
+ "1": "unconfident"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "confident": 0,
12
+ "unconfident": 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-539/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c1326c09471cbef65e02feb5e750b0169c9ab65f4cdda92bb404a323f2c1b5
3
+ size 371567992
checkpoint-539/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f2917daa54d667ad86865cd2092da03cd0565f80d79f7a539c300b7cf8c485
3
+ size 686556235
checkpoint-539/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-539/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e63b022cfa0bdc4604aaaa3e84c559a10b79670453f801cfd456ce54ebbef9
3
+ size 14645
checkpoint-539/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2492312a2487b8c38da50c7fdc36c9ed7e9a449465619d05b037596a3a5bbe
3
+ size 1465
checkpoint-539/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 539,
3
+ "best_metric": 0.3962201476097107,
4
+ "best_model_checkpoint": "face-confidence/checkpoint-539",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 539,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9276437847866419,
14
+ "grad_norm": 6.720329761505127,
15
+ "learning_rate": 1.5726495726495726e-05,
16
+ "loss": 0.4994,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8189497518070191,
22
+ "eval_loss": 0.3962201476097107,
23
+ "eval_model_preparation_time": 0.0025,
24
+ "eval_runtime": 141.0014,
25
+ "eval_samples_per_second": 81.439,
26
+ "eval_steps_per_second": 10.184,
27
+ "step": 539
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 2156,
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": 1.442604660026278e+18,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-539/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebac92433010be2bcd166a9c8d0f0b5c25e7cfa6b3f6aa8d546bcec4c80ff5a5
3
+ size 5713
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "confident",
7
+ "1": "unconfident"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "confident": 0,
12
+ "unconfident": 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 sha256:18123dc046e4fa3f30322fdc2d3c683bee5e5407e97a29d977eb80c474736a88
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:ebac92433010be2bcd166a9c8d0f0b5c25e7cfa6b3f6aa8d546bcec4c80ff5a5
3
+ size 5713