Hugging Face's logo

prithivMLmods
/
Mnist-Digits-SigLIP2

Image Classification
Transformers
Safetensors
English
siglip
Digits
Mnist
SigLIP2
0-t0-9
Number-Classification
Model card Files Community
prithivMLmods commited on
Commit
cef3eac
·
verified ·
1 Parent(s): b5ce0ed

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-1875/config.json +62 -0
  2. checkpoint-1875/model.safetensors +3 -0
  3. checkpoint-1875/optimizer.pt +3 -0
  4. checkpoint-1875/preprocessor_config.json +24 -0
  5. checkpoint-1875/rng_state.pth +3 -0
  6. checkpoint-1875/scheduler.pt +3 -0
  7. checkpoint-1875/trainer_state.json +65 -0
  8. checkpoint-1875/training_args.bin +3 -0
  9. config.json +62 -0
  10. model.safetensors +3 -0
  11. preprocessor_config.json +24 -0
  12. training_args.bin +3 -0
checkpoint-1875/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "0",
7
+ "1": "1",
8
+ "2": "2",
9
+ "3": "3",
10
+ "4": "4",
11
+ "5": "5",
12
+ "6": "6",
13
+ "7": "7",
14
+ "8": "8",
15
+ "9": "9"
16
+ },
17
+ "initializer_factor": 1.0,
18
+ "label2id": {
19
+ "0": 0,
20
+ "1": 1,
21
+ "2": 2,
22
+ "3": 3,
23
+ "4": 4,
24
+ "5": 5,
25
+ "6": 6,
26
+ "7": 7,
27
+ "8": 8,
28
+ "9": 9
29
+ },
30
+ "model_type": "siglip",
31
+ "problem_type": "single_label_classification",
32
+ "text_config": {
33
+ "attention_dropout": 0.0,
34
+ "hidden_act": "gelu_pytorch_tanh",
35
+ "hidden_size": 768,
36
+ "intermediate_size": 3072,
37
+ "layer_norm_eps": 1e-06,
38
+ "max_position_embeddings": 64,
39
+ "model_type": "siglip_text_model",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "projection_size": 768,
43
+ "torch_dtype": "float32",
44
+ "vocab_size": 256000
45
+ },
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.50.0",
48
+ "vision_config": {
49
+ "attention_dropout": 0.0,
50
+ "hidden_act": "gelu_pytorch_tanh",
51
+ "hidden_size": 768,
52
+ "image_size": 224,
53
+ "intermediate_size": 3072,
54
+ "layer_norm_eps": 1e-06,
55
+ "model_type": "siglip_vision_model",
56
+ "num_attention_heads": 12,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 12,
59
+ "patch_size": 16,
60
+ "torch_dtype": "float32"
61
+ }
62
+ }
checkpoint-1875/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28ce6798bfdad6a283dc20b51eb6d2d504c5b1c0e44ca68cce98dea2f48ff79
3
+ size 371592608
checkpoint-1875/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012ab04f46f21cdda441b0ac17abb4611cde9b5749a34ab44cd4060f13292701
3
+ size 686604922
checkpoint-1875/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-1875/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f2b3ac1c991d659109219935d886c6afab3ba720ceb1fdeba6003e7056c2020
3
+ size 14244
checkpoint-1875/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad567daa9e33941a58023e5194f13493b164c0d81a85e962b52a5ce57c34904
3
+ size 1064
checkpoint-1875/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1875,
3
+ "best_metric": 0.027827957645058632,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1875",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1875,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.26666666666666666,
14
+ "grad_norm": 10.099852561950684,
15
+ "learning_rate": 7.534246575342466e-06,
16
+ "loss": 0.3566,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.5333333333333333,
21
+ "grad_norm": 5.800719738006592,
22
+ "learning_rate": 4.7945205479452054e-06,
23
+ "loss": 0.0881,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.8,
28
+ "grad_norm": 0.3786800503730774,
29
+ "learning_rate": 2.0547945205479454e-06,
30
+ "loss": 0.0549,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_accuracy": 0.9927833333333334,
36
+ "eval_loss": 0.027827957645058632,
37
+ "eval_model_preparation_time": 0.0023,
38
+ "eval_runtime": 739.6755,
39
+ "eval_samples_per_second": 81.117,
40
+ "eval_steps_per_second": 10.14,
41
+ "step": 1875
42
+ }
43
+ ],
44
+ "logging_steps": 500,
45
+ "max_steps": 1875,
46
+ "num_input_tokens_seen": 0,
47
+ "num_train_epochs": 1,
48
+ "save_steps": 500,
49
+ "stateful_callbacks": {
50
+ "TrainerControl": {
51
+ "args": {
52
+ "should_epoch_stop": false,
53
+ "should_evaluate": false,
54
+ "should_log": false,
55
+ "should_save": true,
56
+ "should_training_stop": true
57
+ },
58
+ "attributes": {}
59
+ }
60
+ },
61
+ "total_flos": 5.02566312665088e+18,
62
+ "train_batch_size": 32,
63
+ "trial_name": null,
64
+ "trial_params": null
65
+ }
checkpoint-1875/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa26e4f32f2c0dea4691f20df0231475a0a2fa288f905d660d89b3db9b37c2c3
3
+ size 5304
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "0",
7
+ "1": "1",
8
+ "2": "2",
9
+ "3": "3",
10
+ "4": "4",
11
+ "5": "5",
12
+ "6": "6",
13
+ "7": "7",
14
+ "8": "8",
15
+ "9": "9"
16
+ },
17
+ "initializer_factor": 1.0,
18
+ "label2id": {
19
+ "0": 0,
20
+ "1": 1,
21
+ "2": 2,
22
+ "3": 3,
23
+ "4": 4,
24
+ "5": 5,
25
+ "6": 6,
26
+ "7": 7,
27
+ "8": 8,
28
+ "9": 9
29
+ },
30
+ "model_type": "siglip",
31
+ "problem_type": "single_label_classification",
32
+ "text_config": {
33
+ "attention_dropout": 0.0,
34
+ "hidden_act": "gelu_pytorch_tanh",
35
+ "hidden_size": 768,
36
+ "intermediate_size": 3072,
37
+ "layer_norm_eps": 1e-06,
38
+ "max_position_embeddings": 64,
39
+ "model_type": "siglip_text_model",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "projection_size": 768,
43
+ "torch_dtype": "float32",
44
+ "vocab_size": 256000
45
+ },
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.50.0",
48
+ "vision_config": {
49
+ "attention_dropout": 0.0,
50
+ "hidden_act": "gelu_pytorch_tanh",
51
+ "hidden_size": 768,
52
+ "image_size": 224,
53
+ "intermediate_size": 3072,
54
+ "layer_norm_eps": 1e-06,
55
+ "model_type": "siglip_vision_model",
56
+ "num_attention_heads": 12,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 12,
59
+ "patch_size": 16,
60
+ "torch_dtype": "float32"
61
+ }
62
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28ce6798bfdad6a283dc20b51eb6d2d504c5b1c0e44ca68cce98dea2f48ff79
3
+ size 371592608
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:fa26e4f32f2c0dea4691f20df0231475a0a2fa288f905d660d89b3db9b37c2c3
3
+ size 5304