Hugging Face's logo

prithivMLmods
/
Anime-Classification-v1.0

Image Classification
Transformers
Safetensors
English
siglip
Anime
SigLIP2
Image-Detection
3D
Comic
Illustration
Bangumi
Model card Files
xet
Community
prithivMLmods commited on
Commit
e9f65cb
·
verified ·
1 Parent(s): 04244bd

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-1336/config.json +50 -0
  2. checkpoint-1336/model.safetensors +3 -0
  3. checkpoint-1336/optimizer.pt +3 -0
  4. checkpoint-1336/preprocessor_config.json +24 -0
  5. checkpoint-1336/rng_state.pth +3 -0
  6. checkpoint-1336/scheduler.pt +3 -0
  7. checkpoint-1336/trainer_state.json +68 -0
  8. checkpoint-1336/training_args.bin +3 -0
  9. checkpoint-668/config.json +50 -0
  10. checkpoint-668/model.safetensors +3 -0
  11. checkpoint-668/optimizer.pt +3 -0
  12. checkpoint-668/preprocessor_config.json +24 -0
  13. checkpoint-668/rng_state.pth +3 -0
  14. checkpoint-668/scheduler.pt +3 -0
  15. checkpoint-668/trainer_state.json +51 -0
  16. checkpoint-668/training_args.bin +3 -0
  17. config.json +50 -0
  18. model.safetensors +3 -0
  19. preprocessor_config.json +24 -0
  20. training_args.bin +3 -0
checkpoint-1336/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "3D",
7
+ "1": "Bangumi",
8
+ "2": "Comic",
9
+ "3": "Illustration"
10
+ },
11
+ "initializer_factor": 1.0,
12
+ "label2id": {
13
+ "3D": 0,
14
+ "Bangumi": 1,
15
+ "Comic": 2,
16
+ "Illustration": 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-1336/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e656b7ca20e67cce4a2256739615752e658af0870bcbe13d80970eb4fe1d368c
3
+ size 371574144
checkpoint-1336/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3103aa04211e160bbc365c0748c5809a78fc00372a5ba9ff5d6e3b70050d7461
3
+ size 686568058
checkpoint-1336/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-1336/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8bf85d7675f86b66172289f2cc48c017012034347fdb144a100446356f55539
3
+ size 14244
checkpoint-1336/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647df9cd6527878eec5eadd2c4c005832bc4f801f8161e81cccb11eb7549b952
3
+ size 1064
checkpoint-1336/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1336,
3
+ "best_metric": 0.36932608485221863,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1336",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1336,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7485029940119761,
14
+ "grad_norm": 6.10602331161499,
15
+ "learning_rate": 0.00013001555209953344,
16
+ "loss": 0.8424,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7876760398633791,
22
+ "eval_loss": 0.5560755133628845,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 452.724,
25
+ "eval_samples_per_second": 47.21,
26
+ "eval_steps_per_second": 5.902,
27
+ "step": 668
28
+ },
29
+ {
30
+ "epoch": 1.4970059880239521,
31
+ "grad_norm": 5.458612442016602,
32
+ "learning_rate": 5.225505443234837e-05,
33
+ "loss": 0.5875,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.8647826697234829,
39
+ "eval_loss": 0.36932608485221863,
40
+ "eval_model_preparation_time": 0.0024,
41
+ "eval_runtime": 444.0839,
42
+ "eval_samples_per_second": 48.128,
43
+ "eval_steps_per_second": 6.017,
44
+ "step": 1336
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 1336,
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": 3.580271801665929e+18,
65
+ "train_batch_size": 32,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-1336/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39454ed40a71658b1148c56f44bc70e76793ae64c389f854bb5ec8952778439
3
+ size 5304
checkpoint-668/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "3D",
7
+ "1": "Bangumi",
8
+ "2": "Comic",
9
+ "3": "Illustration"
10
+ },
11
+ "initializer_factor": 1.0,
12
+ "label2id": {
13
+ "3D": 0,
14
+ "Bangumi": 1,
15
+ "Comic": 2,
16
+ "Illustration": 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-668/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052cdf2536dee23665179cec44fb33fddcc29cb1a03a3e90a4b27411143b1031
3
+ size 371574144
checkpoint-668/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347607504d291513c30b00ab312d8804e000a858aa2829cb91f88dd41b94fddb
3
+ size 686568058
checkpoint-668/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-668/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e21a609470d81776f815cbaec32a1e1da2dfbf4721ecd8a0a9fb6c6116a796
3
+ size 14244
checkpoint-668/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de7c905f6e39599116793bc6608acec2ea84bf53339ad619997caed83519c80
3
+ size 1064
checkpoint-668/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 668,
3
+ "best_metric": 0.5560755133628845,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-668",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 668,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7485029940119761,
14
+ "grad_norm": 6.10602331161499,
15
+ "learning_rate": 0.00013001555209953344,
16
+ "loss": 0.8424,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7876760398633791,
22
+ "eval_loss": 0.5560755133628845,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 452.724,
25
+ "eval_samples_per_second": 47.21,
26
+ "eval_steps_per_second": 5.902,
27
+ "step": 668
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 1336,
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": 1.7901359008329646e+18,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-668/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39454ed40a71658b1148c56f44bc70e76793ae64c389f854bb5ec8952778439
3
+ size 5304
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "3D",
7
+ "1": "Bangumi",
8
+ "2": "Comic",
9
+ "3": "Illustration"
10
+ },
11
+ "initializer_factor": 1.0,
12
+ "label2id": {
13
+ "3D": 0,
14
+ "Bangumi": 1,
15
+ "Comic": 2,
16
+ "Illustration": 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:e656b7ca20e67cce4a2256739615752e658af0870bcbe13d80970eb4fe1d368c
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:d39454ed40a71658b1148c56f44bc70e76793ae64c389f854bb5ec8952778439
3
+ size 5304