Hugging Face's logo

prithivMLmods
/
PACS-DG-SigLIP2

Image Classification
Transformers
Safetensors
English
siglip
PACS-DG
Image-Classification
domain generalization
SigLIP2
Model card Files
xet
Community
1
prithivMLmods commited on
Commit
4d51f8c
·
verified ·
1 Parent(s): c03d88e

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-626/config.json +50 -0
  2. checkpoint-626/model.safetensors +3 -0
  3. checkpoint-626/optimizer.pt +3 -0
  4. checkpoint-626/preprocessor_config.json +24 -0
  5. checkpoint-626/rng_state.pth +3 -0
  6. checkpoint-626/scheduler.pt +3 -0
  7. checkpoint-626/trainer_state.json +61 -0
  8. checkpoint-626/training_args.bin +3 -0
  9. config.json +50 -0
  10. model.safetensors +3 -0
  11. preprocessor_config.json +24 -0
  12. training_args.bin +3 -0
checkpoint-626/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "art_painting",
7
+ "1": "cartoon",
8
+ "2": "photo",
9
+ "3": "sketch"
10
+ },
11
+ "initializer_factor": 1.0,
12
+ "label2id": {
13
+ "art_painting": 0,
14
+ "cartoon": 1,
15
+ "photo": 2,
16
+ "sketch": 3
17
+ },
18
+ "model_type": "siglip",
19
+ "problem_type": "single_label_classification",
20
+ "text_config": {
21
+ "attention_dropout": 0.0,
22
+ "hidden_act": "gelu_pytorch_tanh",
23
+ "hidden_size": 768,
24
+ "intermediate_size": 3072,
25
+ "layer_norm_eps": 1e-06,
26
+ "max_position_embeddings": 64,
27
+ "model_type": "siglip_text_model",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "projection_size": 768,
31
+ "torch_dtype": "float32",
32
+ "vocab_size": 256000
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.50.0",
36
+ "vision_config": {
37
+ "attention_dropout": 0.0,
38
+ "hidden_act": "gelu_pytorch_tanh",
39
+ "hidden_size": 768,
40
+ "image_size": 224,
41
+ "intermediate_size": 3072,
42
+ "layer_norm_eps": 1e-06,
43
+ "model_type": "siglip_vision_model",
44
+ "num_attention_heads": 12,
45
+ "num_channels": 3,
46
+ "num_hidden_layers": 12,
47
+ "patch_size": 16,
48
+ "torch_dtype": "float32"
49
+ }
50
+ }
checkpoint-626/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf7ceb3f5795cbb62a1f8cdeb770bd35720654ee1fac458f0a5ea2a06f4ac45
3
+ size 371574144
checkpoint-626/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de6dfb3d9fa1f2e8c37879fe48d1d2477954398ec7a47df8916333485919503
3
+ size 686568058
checkpoint-626/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-626/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af7f1aca0c7ec1ab19c4dba1071f1600e2942aed85e46ad836702afd54ffda2e
3
+ size 14244
checkpoint-626/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d020344d4cdb625fa3ccdabe828dfdae277b492bb5282dbb9f16edd7c73161
3
+ size 1064
checkpoint-626/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 626,
3
+ "best_metric": 0.13495254516601562,
4
+ "best_model_checkpoint": "siglip2-finetune-domain/checkpoint-626",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 626,
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": 0.9060154138724852,
15
+ "eval_loss": 0.2301129400730133,
16
+ "eval_model_preparation_time": 0.0026,
17
+ "eval_runtime": 131.0611,
18
+ "eval_samples_per_second": 76.232,
19
+ "eval_steps_per_second": 9.53,
20
+ "step": 313
21
+ },
22
+ {
23
+ "epoch": 1.5974440894568689,
24
+ "grad_norm": 2.59607195854187,
25
+ "learning_rate": 4.375e-05,
26
+ "loss": 0.3739,
27
+ "step": 500
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.9487538784906415,
32
+ "eval_loss": 0.13495254516601562,
33
+ "eval_model_preparation_time": 0.0026,
34
+ "eval_runtime": 131.817,
35
+ "eval_samples_per_second": 75.794,
36
+ "eval_steps_per_second": 9.475,
37
+ "step": 626
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 626,
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": 1.6736300739458335e+18,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-626/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0d4f8bc8c28cb45a881c9d831caa9213ca8e84784d63cc47e24bdee779b59f
3
+ size 5304
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "art_painting",
7
+ "1": "cartoon",
8
+ "2": "photo",
9
+ "3": "sketch"
10
+ },
11
+ "initializer_factor": 1.0,
12
+ "label2id": {
13
+ "art_painting": 0,
14
+ "cartoon": 1,
15
+ "photo": 2,
16
+ "sketch": 3
17
+ },
18
+ "model_type": "siglip",
19
+ "problem_type": "single_label_classification",
20
+ "text_config": {
21
+ "attention_dropout": 0.0,
22
+ "hidden_act": "gelu_pytorch_tanh",
23
+ "hidden_size": 768,
24
+ "intermediate_size": 3072,
25
+ "layer_norm_eps": 1e-06,
26
+ "max_position_embeddings": 64,
27
+ "model_type": "siglip_text_model",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "projection_size": 768,
31
+ "torch_dtype": "float32",
32
+ "vocab_size": 256000
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.50.0",
36
+ "vision_config": {
37
+ "attention_dropout": 0.0,
38
+ "hidden_act": "gelu_pytorch_tanh",
39
+ "hidden_size": 768,
40
+ "image_size": 224,
41
+ "intermediate_size": 3072,
42
+ "layer_norm_eps": 1e-06,
43
+ "model_type": "siglip_vision_model",
44
+ "num_attention_heads": 12,
45
+ "num_channels": 3,
46
+ "num_hidden_layers": 12,
47
+ "patch_size": 16,
48
+ "torch_dtype": "float32"
49
+ }
50
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf7ceb3f5795cbb62a1f8cdeb770bd35720654ee1fac458f0a5ea2a06f4ac45
3
+ size 371574144
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 sha256:9f0d4f8bc8c28cb45a881c9d831caa9213ca8e84784d63cc47e24bdee779b59f
3
+ size 5304