Hugging Face's logo

prithivMLmods
/
open-scene-detection

Image Classification
Transformers
Safetensors
English
siglip
SigLIP2
Scene-Detection
buildings
forest
glacier
mountain
sea
street
Model card Files
xet
Community
prithivMLmods commited on
Commit
0432fd4
·
verified ·
1 Parent(s): 950abd6

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-1022/config.json +54 -0
  2. checkpoint-1022/model.safetensors +3 -0
  3. checkpoint-1022/optimizer.pt +3 -0
  4. checkpoint-1022/preprocessor_config.json +24 -0
  5. checkpoint-1022/rng_state.pth +3 -0
  6. checkpoint-1022/scheduler.pt +3 -0
  7. checkpoint-1022/trainer_state.json +68 -0
  8. checkpoint-1022/training_args.bin +3 -0
  9. checkpoint-511/config.json +54 -0
  10. checkpoint-511/model.safetensors +3 -0
  11. checkpoint-511/optimizer.pt +3 -0
  12. checkpoint-511/preprocessor_config.json +24 -0
  13. checkpoint-511/rng_state.pth +3 -0
  14. checkpoint-511/scheduler.pt +3 -0
  15. checkpoint-511/trainer_state.json +51 -0
  16. checkpoint-511/training_args.bin +3 -0
  17. config.json +54 -0
  18. model.safetensors +3 -0
  19. preprocessor_config.json +24 -0
  20. training_args.bin +3 -0
checkpoint-1022/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "buildings",
7
+ "1": "forest",
8
+ "2": "glacier",
9
+ "3": "mountain",
10
+ "4": "sea",
11
+ "5": "street"
12
+ },
13
+ "initializer_factor": 1.0,
14
+ "label2id": {
15
+ "buildings": 0,
16
+ "forest": 1,
17
+ "glacier": 2,
18
+ "mountain": 3,
19
+ "sea": 4,
20
+ "street": 5
21
+ },
22
+ "model_type": "siglip",
23
+ "problem_type": "single_label_classification",
24
+ "text_config": {
25
+ "attention_dropout": 0.0,
26
+ "hidden_act": "gelu_pytorch_tanh",
27
+ "hidden_size": 768,
28
+ "intermediate_size": 3072,
29
+ "layer_norm_eps": 1e-06,
30
+ "max_position_embeddings": 64,
31
+ "model_type": "siglip_text_model",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "projection_size": 768,
35
+ "torch_dtype": "float32",
36
+ "vocab_size": 256000
37
+ },
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.50.0",
40
+ "vision_config": {
41
+ "attention_dropout": 0.0,
42
+ "hidden_act": "gelu_pytorch_tanh",
43
+ "hidden_size": 768,
44
+ "image_size": 224,
45
+ "intermediate_size": 3072,
46
+ "layer_norm_eps": 1e-06,
47
+ "model_type": "siglip_vision_model",
48
+ "num_attention_heads": 12,
49
+ "num_channels": 3,
50
+ "num_hidden_layers": 12,
51
+ "patch_size": 16,
52
+ "torch_dtype": "float32"
53
+ }
54
+ }
checkpoint-1022/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:890bc5317e2e20e96ba1f6fb75e6cedd6e987560e23b2de18ada3a01cb5b1d28
3
+ size 371580296
checkpoint-1022/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c860c779ea0794b74e315426bb5ea2e1425afc3b1133017827e5ba601a0f06
3
+ size 686580346
checkpoint-1022/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-1022/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699ea8beb0a624c033e25786e6c72caa924d8b24ce794da347b42f6277c3560d
3
+ size 14244
checkpoint-1022/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d603898764e83c173904b892f14818a4417c1961b34f57963560995eef22ab
3
+ size 1064
checkpoint-1022/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1022,
3
+ "best_metric": 0.08018568158149719,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1022",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1022,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9784735812133072,
14
+ "grad_norm": 10.443733215332031,
15
+ "learning_rate": 1.0740740740740742e-05,
16
+ "loss": 0.3064,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.9588865096359743,
22
+ "eval_loss": 0.11907291412353516,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 205.0429,
25
+ "eval_samples_per_second": 79.715,
26
+ "eval_steps_per_second": 9.969,
27
+ "step": 511
28
+ },
29
+ {
30
+ "epoch": 1.9569471624266144,
31
+ "grad_norm": 3.556680917739868,
32
+ "learning_rate": 4.526748971193416e-07,
33
+ "loss": 0.1325,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.9727745487916795,
39
+ "eval_loss": 0.08018568158149719,
40
+ "eval_model_preparation_time": 0.0024,
41
+ "eval_runtime": 203.1892,
42
+ "eval_samples_per_second": 80.442,
43
+ "eval_steps_per_second": 10.06,
44
+ "step": 1022
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 1022,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 2,
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": true
60
+ },
61
+ "attributes": {}
62
+ }
63
+ },
64
+ "total_flos": 2.738057975951155e+18,
65
+ "train_batch_size": 32,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-1022/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:566011f5604bed061f658701cef40a0c715a83fe851a5dcfea9ade31ab9b8d4f
3
+ size 5304
checkpoint-511/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "buildings",
7
+ "1": "forest",
8
+ "2": "glacier",
9
+ "3": "mountain",
10
+ "4": "sea",
11
+ "5": "street"
12
+ },
13
+ "initializer_factor": 1.0,
14
+ "label2id": {
15
+ "buildings": 0,
16
+ "forest": 1,
17
+ "glacier": 2,
18
+ "mountain": 3,
19
+ "sea": 4,
20
+ "street": 5
21
+ },
22
+ "model_type": "siglip",
23
+ "problem_type": "single_label_classification",
24
+ "text_config": {
25
+ "attention_dropout": 0.0,
26
+ "hidden_act": "gelu_pytorch_tanh",
27
+ "hidden_size": 768,
28
+ "intermediate_size": 3072,
29
+ "layer_norm_eps": 1e-06,
30
+ "max_position_embeddings": 64,
31
+ "model_type": "siglip_text_model",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "projection_size": 768,
35
+ "torch_dtype": "float32",
36
+ "vocab_size": 256000
37
+ },
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.50.0",
40
+ "vision_config": {
41
+ "attention_dropout": 0.0,
42
+ "hidden_act": "gelu_pytorch_tanh",
43
+ "hidden_size": 768,
44
+ "image_size": 224,
45
+ "intermediate_size": 3072,
46
+ "layer_norm_eps": 1e-06,
47
+ "model_type": "siglip_vision_model",
48
+ "num_attention_heads": 12,
49
+ "num_channels": 3,
50
+ "num_hidden_layers": 12,
51
+ "patch_size": 16,
52
+ "torch_dtype": "float32"
53
+ }
54
+ }
checkpoint-511/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97108a9b10a2085494b942419fcede2037445d57d3ed1c4906ada78e1e527f6a
3
+ size 371580296
checkpoint-511/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f86a30dcc658df2ca09a86c134651f32d93eb2ab25cd179632e5fc125dad736
3
+ size 686580346
checkpoint-511/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-511/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ffa69372ffc1fb5e762e6132d15345ab1c8154c72a0876f1d843d16491e212f
3
+ size 14244
checkpoint-511/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679eb184daaf5577d17ba73b95cc09490dceb635d1c2c8d2c9596fd477a4efd4
3
+ size 1064
checkpoint-511/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 511,
3
+ "best_metric": 0.11907291412353516,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-511",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 511,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9784735812133072,
14
+ "grad_norm": 10.443733215332031,
15
+ "learning_rate": 1.0740740740740742e-05,
16
+ "loss": 0.3064,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.9588865096359743,
22
+ "eval_loss": 0.11907291412353516,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 205.0429,
25
+ "eval_samples_per_second": 79.715,
26
+ "eval_steps_per_second": 9.969,
27
+ "step": 511
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 1022,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
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": 1.3690289879755776e+18,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-511/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:566011f5604bed061f658701cef40a0c715a83fe851a5dcfea9ade31ab9b8d4f
3
+ size 5304
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "buildings",
7
+ "1": "forest",
8
+ "2": "glacier",
9
+ "3": "mountain",
10
+ "4": "sea",
11
+ "5": "street"
12
+ },
13
+ "initializer_factor": 1.0,
14
+ "label2id": {
15
+ "buildings": 0,
16
+ "forest": 1,
17
+ "glacier": 2,
18
+ "mountain": 3,
19
+ "sea": 4,
20
+ "street": 5
21
+ },
22
+ "model_type": "siglip",
23
+ "problem_type": "single_label_classification",
24
+ "text_config": {
25
+ "attention_dropout": 0.0,
26
+ "hidden_act": "gelu_pytorch_tanh",
27
+ "hidden_size": 768,
28
+ "intermediate_size": 3072,
29
+ "layer_norm_eps": 1e-06,
30
+ "max_position_embeddings": 64,
31
+ "model_type": "siglip_text_model",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "projection_size": 768,
35
+ "torch_dtype": "float32",
36
+ "vocab_size": 256000
37
+ },
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.50.0",
40
+ "vision_config": {
41
+ "attention_dropout": 0.0,
42
+ "hidden_act": "gelu_pytorch_tanh",
43
+ "hidden_size": 768,
44
+ "image_size": 224,
45
+ "intermediate_size": 3072,
46
+ "layer_norm_eps": 1e-06,
47
+ "model_type": "siglip_vision_model",
48
+ "num_attention_heads": 12,
49
+ "num_channels": 3,
50
+ "num_hidden_layers": 12,
51
+ "patch_size": 16,
52
+ "torch_dtype": "float32"
53
+ }
54
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:890bc5317e2e20e96ba1f6fb75e6cedd6e987560e23b2de18ada3a01cb5b1d28
3
+ size 371580296
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 sha256:566011f5604bed061f658701cef40a0c715a83fe851a5dcfea9ade31ab9b8d4f
3
+ size 5304