prithivMLmods commited on
Commit
90b6c75
·
verified ·
1 Parent(s): 70dce93

Upload folder using huggingface_hub

Browse files
checkpoint-2198/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "high",
7
+ "1": "low",
8
+ "2": "moderate",
9
+ "3": "non-burnable",
10
+ "4": "very_high",
11
+ "5": "very_low",
12
+ "6": "water"
13
+ },
14
+ "initializer_factor": 1.0,
15
+ "label2id": {
16
+ "high": 0,
17
+ "low": 1,
18
+ "moderate": 2,
19
+ "non-burnable": 3,
20
+ "very_high": 4,
21
+ "very_low": 5,
22
+ "water": 6
23
+ },
24
+ "model_type": "siglip",
25
+ "problem_type": "single_label_classification",
26
+ "text_config": {
27
+ "attention_dropout": 0.0,
28
+ "hidden_act": "gelu_pytorch_tanh",
29
+ "hidden_size": 768,
30
+ "intermediate_size": 3072,
31
+ "layer_norm_eps": 1e-06,
32
+ "max_position_embeddings": 64,
33
+ "model_type": "siglip_text_model",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "projection_size": 768,
37
+ "torch_dtype": "float32",
38
+ "vocab_size": 256000
39
+ },
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.50.0",
42
+ "vision_config": {
43
+ "attention_dropout": 0.0,
44
+ "hidden_act": "gelu_pytorch_tanh",
45
+ "hidden_size": 768,
46
+ "image_size": 224,
47
+ "intermediate_size": 3072,
48
+ "layer_norm_eps": 1e-06,
49
+ "model_type": "siglip_vision_model",
50
+ "num_attention_heads": 12,
51
+ "num_channels": 3,
52
+ "num_hidden_layers": 12,
53
+ "patch_size": 16,
54
+ "torch_dtype": "float32"
55
+ }
56
+ }
checkpoint-2198/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6281091ff5c0fe9bd7983cc1ce080bd70427dc708f2e46d7ad32a52dc0ee7492
3
+ size 371583372
checkpoint-2198/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f91323c2914267114842e3480f4ca3c1c9be012f6f05fadd5a660acb8f8ccc9
3
+ size 686586490
checkpoint-2198/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-2198/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f7ea8883c164178080363baee98398c7a8d1e1a522fd334729e8f0d56e1b69a
3
+ size 14244
checkpoint-2198/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e32a9c6bef3ed656c949f069fb2e36bc4cc2d0f6fa32eea032204726059cbe
3
+ size 1064
checkpoint-2198/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2198,
3
+ "best_metric": 1.0199397802352905,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-2198",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2198,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.22747952684258416,
14
+ "grad_norm": 30.234283447265625,
15
+ "learning_rate": 1.7929130234698574e-06,
16
+ "loss": 1.2741,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.4549590536851683,
21
+ "grad_norm": 22.959794998168945,
22
+ "learning_rate": 1.5628163828808099e-06,
23
+ "loss": 1.1086,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.6824385805277525,
28
+ "grad_norm": 22.508281707763672,
29
+ "learning_rate": 1.3327197422917624e-06,
30
+ "loss": 1.0646,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.9099181073703366,
35
+ "grad_norm": 23.277908325195312,
36
+ "learning_rate": 1.102623101702715e-06,
37
+ "loss": 1.0494,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.5876782642078173,
43
+ "eval_loss": 1.0199397802352905,
44
+ "eval_model_preparation_time": 0.0025,
45
+ "eval_runtime": 1231.0032,
46
+ "eval_samples_per_second": 57.133,
47
+ "eval_steps_per_second": 7.142,
48
+ "step": 2198
49
+ }
50
+ ],
51
+ "logging_steps": 500,
52
+ "max_steps": 4396,
53
+ "num_input_tokens_seen": 0,
54
+ "num_train_epochs": 2,
55
+ "save_steps": 500,
56
+ "stateful_callbacks": {
57
+ "TrainerControl": {
58
+ "args": {
59
+ "should_epoch_stop": false,
60
+ "should_evaluate": false,
61
+ "should_log": false,
62
+ "should_save": true,
63
+ "should_training_stop": false
64
+ },
65
+ "attributes": {}
66
+ }
67
+ },
68
+ "total_flos": 5.890852013733292e+18,
69
+ "train_batch_size": 32,
70
+ "trial_name": null,
71
+ "trial_params": null
72
+ }
checkpoint-2198/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82b36bb262e454f8e5c5fe3efc83cadeb46f932ed1ecf2e64afcef391dc64f0
3
+ size 5304
checkpoint-4396/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "high",
7
+ "1": "low",
8
+ "2": "moderate",
9
+ "3": "non-burnable",
10
+ "4": "very_high",
11
+ "5": "very_low",
12
+ "6": "water"
13
+ },
14
+ "initializer_factor": 1.0,
15
+ "label2id": {
16
+ "high": 0,
17
+ "low": 1,
18
+ "moderate": 2,
19
+ "non-burnable": 3,
20
+ "very_high": 4,
21
+ "very_low": 5,
22
+ "water": 6
23
+ },
24
+ "model_type": "siglip",
25
+ "problem_type": "single_label_classification",
26
+ "text_config": {
27
+ "attention_dropout": 0.0,
28
+ "hidden_act": "gelu_pytorch_tanh",
29
+ "hidden_size": 768,
30
+ "intermediate_size": 3072,
31
+ "layer_norm_eps": 1e-06,
32
+ "max_position_embeddings": 64,
33
+ "model_type": "siglip_text_model",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "projection_size": 768,
37
+ "torch_dtype": "float32",
38
+ "vocab_size": 256000
39
+ },
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.50.0",
42
+ "vision_config": {
43
+ "attention_dropout": 0.0,
44
+ "hidden_act": "gelu_pytorch_tanh",
45
+ "hidden_size": 768,
46
+ "image_size": 224,
47
+ "intermediate_size": 3072,
48
+ "layer_norm_eps": 1e-06,
49
+ "model_type": "siglip_vision_model",
50
+ "num_attention_heads": 12,
51
+ "num_channels": 3,
52
+ "num_hidden_layers": 12,
53
+ "patch_size": 16,
54
+ "torch_dtype": "float32"
55
+ }
56
+ }
checkpoint-4396/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa8028d94b788509b18a5c60b04fe826f76be8583df7f70f9bd236ca2c2bcf7d
3
+ size 371583372
checkpoint-4396/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7dad23017f9b67247fff6781aebfddf8b84a6b449b067e527cb2d7e4f314d5
3
+ size 686586490
checkpoint-4396/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-4396/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e2709858db832dff17362cebc52149213793092c6ab9d2bc8b36eabe6f30966
3
+ size 14244
checkpoint-4396/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f583943f9826b26cabb09f2981f523d0b21e37f5df49172661800c73d9aaa7f9
3
+ size 1064
checkpoint-4396/trainer_state.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 4396,
3
+ "best_metric": 0.9813332557678223,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-4396",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4396,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.22747952684258416,
14
+ "grad_norm": 30.234283447265625,
15
+ "learning_rate": 1.7929130234698574e-06,
16
+ "loss": 1.2741,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.4549590536851683,
21
+ "grad_norm": 22.959794998168945,
22
+ "learning_rate": 1.5628163828808099e-06,
23
+ "loss": 1.1086,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.6824385805277525,
28
+ "grad_norm": 22.508281707763672,
29
+ "learning_rate": 1.3327197422917624e-06,
30
+ "loss": 1.0646,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.9099181073703366,
35
+ "grad_norm": 23.277908325195312,
36
+ "learning_rate": 1.102623101702715e-06,
37
+ "loss": 1.0494,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.5876782642078173,
43
+ "eval_loss": 1.0199397802352905,
44
+ "eval_model_preparation_time": 0.0025,
45
+ "eval_runtime": 1231.0032,
46
+ "eval_samples_per_second": 57.133,
47
+ "eval_steps_per_second": 7.142,
48
+ "step": 2198
49
+ },
50
+ {
51
+ "epoch": 1.1373976342129208,
52
+ "grad_norm": 25.28997802734375,
53
+ "learning_rate": 8.725264611136677e-07,
54
+ "loss": 1.0211,
55
+ "step": 2500
56
+ },
57
+ {
58
+ "epoch": 1.364877161055505,
59
+ "grad_norm": 23.57412338256836,
60
+ "learning_rate": 6.424298205246204e-07,
61
+ "loss": 0.9994,
62
+ "step": 3000
63
+ },
64
+ {
65
+ "epoch": 1.5923566878980893,
66
+ "grad_norm": 31.955904006958008,
67
+ "learning_rate": 4.123331799355729e-07,
68
+ "loss": 0.9899,
69
+ "step": 3500
70
+ },
71
+ {
72
+ "epoch": 1.8198362147406733,
73
+ "grad_norm": 23.125858306884766,
74
+ "learning_rate": 1.8223653934652553e-07,
75
+ "loss": 0.9761,
76
+ "step": 4000
77
+ },
78
+ {
79
+ "epoch": 2.0,
80
+ "eval_accuracy": 0.6032190641395686,
81
+ "eval_loss": 0.9813332557678223,
82
+ "eval_model_preparation_time": 0.0025,
83
+ "eval_runtime": 1219.9593,
84
+ "eval_samples_per_second": 57.65,
85
+ "eval_steps_per_second": 7.207,
86
+ "step": 4396
87
+ }
88
+ ],
89
+ "logging_steps": 500,
90
+ "max_steps": 4396,
91
+ "num_input_tokens_seen": 0,
92
+ "num_train_epochs": 2,
93
+ "save_steps": 500,
94
+ "stateful_callbacks": {
95
+ "TrainerControl": {
96
+ "args": {
97
+ "should_epoch_stop": false,
98
+ "should_evaluate": false,
99
+ "should_log": false,
100
+ "should_save": true,
101
+ "should_training_stop": true
102
+ },
103
+ "attributes": {}
104
+ }
105
+ },
106
+ "total_flos": 1.1781704027466584e+19,
107
+ "train_batch_size": 32,
108
+ "trial_name": null,
109
+ "trial_params": null
110
+ }
checkpoint-4396/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82b36bb262e454f8e5c5fe3efc83cadeb46f932ed1ecf2e64afcef391dc64f0
3
+ size 5304
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "high",
7
+ "1": "low",
8
+ "2": "moderate",
9
+ "3": "non-burnable",
10
+ "4": "very_high",
11
+ "5": "very_low",
12
+ "6": "water"
13
+ },
14
+ "initializer_factor": 1.0,
15
+ "label2id": {
16
+ "high": 0,
17
+ "low": 1,
18
+ "moderate": 2,
19
+ "non-burnable": 3,
20
+ "very_high": 4,
21
+ "very_low": 5,
22
+ "water": 6
23
+ },
24
+ "model_type": "siglip",
25
+ "problem_type": "single_label_classification",
26
+ "text_config": {
27
+ "attention_dropout": 0.0,
28
+ "hidden_act": "gelu_pytorch_tanh",
29
+ "hidden_size": 768,
30
+ "intermediate_size": 3072,
31
+ "layer_norm_eps": 1e-06,
32
+ "max_position_embeddings": 64,
33
+ "model_type": "siglip_text_model",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "projection_size": 768,
37
+ "torch_dtype": "float32",
38
+ "vocab_size": 256000
39
+ },
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.50.0",
42
+ "vision_config": {
43
+ "attention_dropout": 0.0,
44
+ "hidden_act": "gelu_pytorch_tanh",
45
+ "hidden_size": 768,
46
+ "image_size": 224,
47
+ "intermediate_size": 3072,
48
+ "layer_norm_eps": 1e-06,
49
+ "model_type": "siglip_vision_model",
50
+ "num_attention_heads": 12,
51
+ "num_channels": 3,
52
+ "num_hidden_layers": 12,
53
+ "patch_size": 16,
54
+ "torch_dtype": "float32"
55
+ }
56
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa8028d94b788509b18a5c60b04fe826f76be8583df7f70f9bd236ca2c2bcf7d
3
+ size 371583372
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:b82b36bb262e454f8e5c5fe3efc83cadeb46f932ed1ecf2e64afcef391dc64f0
3
+ size 5304