Hugging Face's logo

prithivMLmods
/
Document-Type-Detection

Image Classification
Transformers
Safetensors
English
siglip
Document
Classification
finance
Model card Files
xet
Community
prithivMLmods commited on
Commit
9d8e587
·
verified ·
1 Parent(s): 5d5a1ee

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-375/config.json +54 -0
  2. checkpoint-375/model.safetensors +3 -0
  3. checkpoint-375/optimizer.pt +3 -0
  4. checkpoint-375/preprocessor_config.json +24 -0
  5. checkpoint-375/rng_state.pth +3 -0
  6. checkpoint-375/scheduler.pt +3 -0
  7. checkpoint-375/trainer_state.json +44 -0
  8. checkpoint-375/training_args.bin +3 -0
  9. checkpoint-750/config.json +54 -0
  10. checkpoint-750/model.safetensors +3 -0
  11. checkpoint-750/optimizer.pt +3 -0
  12. checkpoint-750/preprocessor_config.json +24 -0
  13. checkpoint-750/rng_state.pth +3 -0
  14. checkpoint-750/scheduler.pt +3 -0
  15. checkpoint-750/trainer_state.json +61 -0
  16. checkpoint-750/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-375/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Advertisement-Doc",
7
+ "1": "Hand-Written-Doc",
8
+ "2": "Invoice-Doc",
9
+ "3": "Letter-Doc",
10
+ "4": "News-Article-Doc",
11
+ "5": "Resume-Doc"
12
+ },
13
+ "initializer_factor": 1.0,
14
+ "label2id": {
15
+ "Advertisement-Doc": 0,
16
+ "Hand-Written-Doc": 1,
17
+ "Invoice-Doc": 2,
18
+ "Letter-Doc": 3,
19
+ "News-Article-Doc": 4,
20
+ "Resume-Doc": 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-375/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153b16aefcb6144c1c2f4f3708fb7469ccb691693ce65882298edeeebf11be30
3
+ size 371580296
checkpoint-375/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36bf72c9edf93ca85448bea99a1a906c72193098b181f97ba43a4e88d5932c7
3
+ size 686580346
checkpoint-375/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-375/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11027277b6c51f59488df520020d383908a9f170baa7ea4bd0c166aa72cced2
3
+ size 14244
checkpoint-375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4d1140f5a0513989aca0dc1db73e181db90de91e412469cc8be792cca398dc
3
+ size 1064
checkpoint-375/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 375,
3
+ "best_metric": 0.7141851186752319,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-375",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 375,
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": 0.7595,
15
+ "eval_loss": 0.7141851186752319,
16
+ "eval_model_preparation_time": 0.0024,
17
+ "eval_runtime": 238.6163,
18
+ "eval_samples_per_second": 50.29,
19
+ "eval_steps_per_second": 6.286,
20
+ "step": 375
21
+ }
22
+ ],
23
+ "logging_steps": 500,
24
+ "max_steps": 750,
25
+ "num_input_tokens_seen": 0,
26
+ "num_train_epochs": 2,
27
+ "save_steps": 500,
28
+ "stateful_callbacks": {
29
+ "TrainerControl": {
30
+ "args": {
31
+ "should_epoch_stop": false,
32
+ "should_evaluate": false,
33
+ "should_log": false,
34
+ "should_save": true,
35
+ "should_training_stop": false
36
+ },
37
+ "attributes": {}
38
+ }
39
+ },
40
+ "total_flos": 1.00509928759296e+18,
41
+ "train_batch_size": 32,
42
+ "trial_name": null,
43
+ "trial_params": null
44
+ }
checkpoint-375/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95bb653dd97d78b7753ea82d077c8996b72fa1550f7010f4232616eb9770e680
3
+ size 5304
checkpoint-750/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Advertisement-Doc",
7
+ "1": "Hand-Written-Doc",
8
+ "2": "Invoice-Doc",
9
+ "3": "Letter-Doc",
10
+ "4": "News-Article-Doc",
11
+ "5": "Resume-Doc"
12
+ },
13
+ "initializer_factor": 1.0,
14
+ "label2id": {
15
+ "Advertisement-Doc": 0,
16
+ "Hand-Written-Doc": 1,
17
+ "Invoice-Doc": 2,
18
+ "Letter-Doc": 3,
19
+ "News-Article-Doc": 4,
20
+ "Resume-Doc": 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-750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768863c613164b0c06acc0257e7d74f31afaff3e7cdb6e4257ed9b46487fd835
3
+ size 371580296
checkpoint-750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09fcfcb82d6618f07692a67d528832dc543b254a8efc21045a3985586aba6c7
3
+ size 686580346
checkpoint-750/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-750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dfd1f9a2a29539f346868eb36a1b264e5fc13fdb515c6a844bf62e6abee8853
3
+ size 14244
checkpoint-750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab03192a60c4fb6ec6096a859424dfb24171c6b3fc801b38b85ab0fd723b1704
3
+ size 1064
checkpoint-750/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 750,
3
+ "best_metric": 0.3114723861217499,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-750",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 750,
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": 0.7595,
15
+ "eval_loss": 0.7141851186752319,
16
+ "eval_model_preparation_time": 0.0024,
17
+ "eval_runtime": 238.6163,
18
+ "eval_samples_per_second": 50.29,
19
+ "eval_steps_per_second": 6.286,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.3333333333333333,
24
+ "grad_norm": 6.521303653717041,
25
+ "learning_rate": 7.142857142857143e-05,
26
+ "loss": 0.8019,
27
+ "step": 500
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.9025,
32
+ "eval_loss": 0.3114723861217499,
33
+ "eval_model_preparation_time": 0.0024,
34
+ "eval_runtime": 240.645,
35
+ "eval_samples_per_second": 49.866,
36
+ "eval_steps_per_second": 6.233,
37
+ "step": 750
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 750,
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": 2.01019857518592e+18,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95bb653dd97d78b7753ea82d077c8996b72fa1550f7010f4232616eb9770e680
3
+ size 5304
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Advertisement-Doc",
7
+ "1": "Hand-Written-Doc",
8
+ "2": "Invoice-Doc",
9
+ "3": "Letter-Doc",
10
+ "4": "News-Article-Doc",
11
+ "5": "Resume-Doc"
12
+ },
13
+ "initializer_factor": 1.0,
14
+ "label2id": {
15
+ "Advertisement-Doc": 0,
16
+ "Hand-Written-Doc": 1,
17
+ "Invoice-Doc": 2,
18
+ "Letter-Doc": 3,
19
+ "News-Article-Doc": 4,
20
+ "Resume-Doc": 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 sha256:768863c613164b0c06acc0257e7d74f31afaff3e7cdb6e4257ed9b46487fd835
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 sha256:95bb653dd97d78b7753ea82d077c8996b72fa1550f7010f4232616eb9770e680
3
+ size 5304