prithivMLmods commited on
Commit
80229eb
·
verified ·
1 Parent(s): c474a69

Upload folder using huggingface_hub

Browse files
checkpoint-1566/config.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "\u0905",
7
+ "1": "\u0906",
8
+ "2": "\u0907",
9
+ "3": "\u0908",
10
+ "4": "\u0909",
11
+ "5": "\u090a",
12
+ "6": "\u090f",
13
+ "7": "\u0910",
14
+ "8": "\u0913",
15
+ "9": "\u0914",
16
+ "10": "\u0915",
17
+ "11": "\u0915\u094d\u0937",
18
+ "12": "\u0916",
19
+ "13": "\u0917",
20
+ "14": "\u0918",
21
+ "15": "\u091a",
22
+ "16": "\u091b",
23
+ "17": "\u091c",
24
+ "18": "\u091c\u094d\u091e",
25
+ "19": "\u091d",
26
+ "20": "\u091f",
27
+ "21": "\u0920",
28
+ "22": "\u0921",
29
+ "23": "\u0922",
30
+ "24": "\u0923",
31
+ "25": "\u0924",
32
+ "26": "\u0925",
33
+ "27": "\u0926",
34
+ "28": "\u0927",
35
+ "29": "\u0928",
36
+ "30": "\u092a",
37
+ "31": "\u092b",
38
+ "32": "\u092c",
39
+ "33": "\u092d",
40
+ "34": "\u092e",
41
+ "35": "\u092f",
42
+ "36": "\u0930",
43
+ "37": "\u0932",
44
+ "38": "\u0933",
45
+ "39": "\u0935",
46
+ "40": "\u0936",
47
+ "41": "\u0938",
48
+ "42": "\u0939"
49
+ },
50
+ "initializer_factor": 1.0,
51
+ "label2id": {
52
+ "\u0905": 0,
53
+ "\u0906": 1,
54
+ "\u0907": 2,
55
+ "\u0908": 3,
56
+ "\u0909": 4,
57
+ "\u090a": 5,
58
+ "\u090f": 6,
59
+ "\u0910": 7,
60
+ "\u0913": 8,
61
+ "\u0914": 9,
62
+ "\u0915": 10,
63
+ "\u0915\u094d\u0937": 11,
64
+ "\u0916": 12,
65
+ "\u0917": 13,
66
+ "\u0918": 14,
67
+ "\u091a": 15,
68
+ "\u091b": 16,
69
+ "\u091c": 17,
70
+ "\u091c\u094d\u091e": 18,
71
+ "\u091d": 19,
72
+ "\u091f": 20,
73
+ "\u0920": 21,
74
+ "\u0921": 22,
75
+ "\u0922": 23,
76
+ "\u0923": 24,
77
+ "\u0924": 25,
78
+ "\u0925": 26,
79
+ "\u0926": 27,
80
+ "\u0927": 28,
81
+ "\u0928": 29,
82
+ "\u092a": 30,
83
+ "\u092b": 31,
84
+ "\u092c": 32,
85
+ "\u092d": 33,
86
+ "\u092e": 34,
87
+ "\u092f": 35,
88
+ "\u0930": 36,
89
+ "\u0932": 37,
90
+ "\u0933": 38,
91
+ "\u0935": 39,
92
+ "\u0936": 40,
93
+ "\u0938": 41,
94
+ "\u0939": 42
95
+ },
96
+ "model_type": "siglip",
97
+ "problem_type": "single_label_classification",
98
+ "text_config": {
99
+ "attention_dropout": 0.0,
100
+ "hidden_act": "gelu_pytorch_tanh",
101
+ "hidden_size": 768,
102
+ "intermediate_size": 3072,
103
+ "layer_norm_eps": 1e-06,
104
+ "max_position_embeddings": 64,
105
+ "model_type": "siglip_text_model",
106
+ "num_attention_heads": 12,
107
+ "num_hidden_layers": 12,
108
+ "projection_size": 768,
109
+ "torch_dtype": "float32",
110
+ "vocab_size": 256000
111
+ },
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.50.0",
114
+ "vision_config": {
115
+ "attention_dropout": 0.0,
116
+ "hidden_act": "gelu_pytorch_tanh",
117
+ "hidden_size": 768,
118
+ "image_size": 224,
119
+ "intermediate_size": 3072,
120
+ "layer_norm_eps": 1e-06,
121
+ "model_type": "siglip_vision_model",
122
+ "num_attention_heads": 12,
123
+ "num_channels": 3,
124
+ "num_hidden_layers": 12,
125
+ "patch_size": 16,
126
+ "torch_dtype": "float32"
127
+ }
128
+ }
checkpoint-1566/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998638d185582b100934f96ec7d6ba8f2379625b25bce4f3f24f834648d18388
3
+ size 371694116
checkpoint-1566/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7a3757c59674339c6b4c72b3d9853e89f05102df93cf8089f39a21a22cc6fe
3
+ size 686807930
checkpoint-1566/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-1566/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b344f97c3525d640e1a6be6ecd6fb52ac2b4ecf26be4ad98ccc8f8a8bad10ae4
3
+ size 14244
checkpoint-1566/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af4351eab912a5bba46b7dc5123604ddf8595c520eae68e64469f680d78e413
3
+ size 1064
checkpoint-1566/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1566,
3
+ "best_metric": 0.33024775981903076,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1566",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1566,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.31928480204342274,
14
+ "grad_norm": 5.945098876953125,
15
+ "learning_rate": 0.00035158311345646437,
16
+ "loss": 2.9737,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.6385696040868455,
21
+ "grad_norm": 6.650278091430664,
22
+ "learning_rate": 0.0001866754617414248,
23
+ "loss": 1.602,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.9578544061302682,
28
+ "grad_norm": 4.597949504852295,
29
+ "learning_rate": 2.1767810026385228e-05,
30
+ "loss": 0.5841,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_accuracy": 0.9026727080380846,
36
+ "eval_loss": 0.33024775981903076,
37
+ "eval_model_preparation_time": 0.0023,
38
+ "eval_runtime": 620.5266,
39
+ "eval_samples_per_second": 80.736,
40
+ "eval_steps_per_second": 10.093,
41
+ "step": 1566
42
+ }
43
+ ],
44
+ "logging_steps": 500,
45
+ "max_steps": 1566,
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": 4.197493203467913e+18,
62
+ "train_batch_size": 32,
63
+ "trial_name": null,
64
+ "trial_params": null
65
+ }
checkpoint-1566/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612c403177e06b8bedd8811e6dea1df948cad37ad8afa6cedefa4a3426d7dd77
3
+ size 5304
config.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "\u0905",
7
+ "1": "\u0906",
8
+ "2": "\u0907",
9
+ "3": "\u0908",
10
+ "4": "\u0909",
11
+ "5": "\u090a",
12
+ "6": "\u090f",
13
+ "7": "\u0910",
14
+ "8": "\u0913",
15
+ "9": "\u0914",
16
+ "10": "\u0915",
17
+ "11": "\u0915\u094d\u0937",
18
+ "12": "\u0916",
19
+ "13": "\u0917",
20
+ "14": "\u0918",
21
+ "15": "\u091a",
22
+ "16": "\u091b",
23
+ "17": "\u091c",
24
+ "18": "\u091c\u094d\u091e",
25
+ "19": "\u091d",
26
+ "20": "\u091f",
27
+ "21": "\u0920",
28
+ "22": "\u0921",
29
+ "23": "\u0922",
30
+ "24": "\u0923",
31
+ "25": "\u0924",
32
+ "26": "\u0925",
33
+ "27": "\u0926",
34
+ "28": "\u0927",
35
+ "29": "\u0928",
36
+ "30": "\u092a",
37
+ "31": "\u092b",
38
+ "32": "\u092c",
39
+ "33": "\u092d",
40
+ "34": "\u092e",
41
+ "35": "\u092f",
42
+ "36": "\u0930",
43
+ "37": "\u0932",
44
+ "38": "\u0933",
45
+ "39": "\u0935",
46
+ "40": "\u0936",
47
+ "41": "\u0938",
48
+ "42": "\u0939"
49
+ },
50
+ "initializer_factor": 1.0,
51
+ "label2id": {
52
+ "\u0905": 0,
53
+ "\u0906": 1,
54
+ "\u0907": 2,
55
+ "\u0908": 3,
56
+ "\u0909": 4,
57
+ "\u090a": 5,
58
+ "\u090f": 6,
59
+ "\u0910": 7,
60
+ "\u0913": 8,
61
+ "\u0914": 9,
62
+ "\u0915": 10,
63
+ "\u0915\u094d\u0937": 11,
64
+ "\u0916": 12,
65
+ "\u0917": 13,
66
+ "\u0918": 14,
67
+ "\u091a": 15,
68
+ "\u091b": 16,
69
+ "\u091c": 17,
70
+ "\u091c\u094d\u091e": 18,
71
+ "\u091d": 19,
72
+ "\u091f": 20,
73
+ "\u0920": 21,
74
+ "\u0921": 22,
75
+ "\u0922": 23,
76
+ "\u0923": 24,
77
+ "\u0924": 25,
78
+ "\u0925": 26,
79
+ "\u0926": 27,
80
+ "\u0927": 28,
81
+ "\u0928": 29,
82
+ "\u092a": 30,
83
+ "\u092b": 31,
84
+ "\u092c": 32,
85
+ "\u092d": 33,
86
+ "\u092e": 34,
87
+ "\u092f": 35,
88
+ "\u0930": 36,
89
+ "\u0932": 37,
90
+ "\u0933": 38,
91
+ "\u0935": 39,
92
+ "\u0936": 40,
93
+ "\u0938": 41,
94
+ "\u0939": 42
95
+ },
96
+ "model_type": "siglip",
97
+ "problem_type": "single_label_classification",
98
+ "text_config": {
99
+ "attention_dropout": 0.0,
100
+ "hidden_act": "gelu_pytorch_tanh",
101
+ "hidden_size": 768,
102
+ "intermediate_size": 3072,
103
+ "layer_norm_eps": 1e-06,
104
+ "max_position_embeddings": 64,
105
+ "model_type": "siglip_text_model",
106
+ "num_attention_heads": 12,
107
+ "num_hidden_layers": 12,
108
+ "projection_size": 768,
109
+ "torch_dtype": "float32",
110
+ "vocab_size": 256000
111
+ },
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.50.0",
114
+ "vision_config": {
115
+ "attention_dropout": 0.0,
116
+ "hidden_act": "gelu_pytorch_tanh",
117
+ "hidden_size": 768,
118
+ "image_size": 224,
119
+ "intermediate_size": 3072,
120
+ "layer_norm_eps": 1e-06,
121
+ "model_type": "siglip_vision_model",
122
+ "num_attention_heads": 12,
123
+ "num_channels": 3,
124
+ "num_hidden_layers": 12,
125
+ "patch_size": 16,
126
+ "torch_dtype": "float32"
127
+ }
128
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998638d185582b100934f96ec7d6ba8f2379625b25bce4f3f24f834648d18388
3
+ size 371694116
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 sha256:612c403177e06b8bedd8811e6dea1df948cad37ad8afa6cedefa4a3426d7dd77
3
+ size 5304