cagrigungor commited on
Commit
640f8d2
·
verified ·
1 Parent(s): a3a017b
checkpoint-1891/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "dtype": "float32",
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "nowildfire",
13
+ "1": "wildfire"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "nowildfire": 0,
20
+ "wildfire": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "pooler_act": "tanh",
29
+ "pooler_output_size": 768,
30
+ "problem_type": "single_label_classification",
31
+ "qkv_bias": true,
32
+ "transformers_version": "4.57.3"
33
+ }
checkpoint-1891/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff03041800d5ae8c6b2ca91e51a256e763dfad85476d092a60686ba2b7c40b3
3
+ size 343223968
checkpoint-1891/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599425bf7bfba134f7b34845c8a467adbc0352874693e3ddc0c994b7eb166de6
3
+ size 686572107
checkpoint-1891/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
checkpoint-1891/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad539edef10f0571f1a7d7b4f8507ebe219f08474f973535f5a48b85ebf11cf
3
+ size 1383
checkpoint-1891/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a09d3d94b1d5ff39386a4bf86325efffb8e57eda3b97bfe8fd7cad482ef4189
3
+ size 1465
checkpoint-1891/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1891,
3
+ "best_metric": 0.9876190476190476,
4
+ "best_model_checkpoint": "./fire-prediction/checkpoint-1891",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1891,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.26441036488630354,
14
+ "grad_norm": 2.7893362045288086,
15
+ "learning_rate": 4.5601974264057816e-05,
16
+ "loss": 0.112,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.5288207297726071,
21
+ "grad_norm": 0.06084805727005005,
22
+ "learning_rate": 4.1195134849286097e-05,
23
+ "loss": 0.0631,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7932310946589106,
28
+ "grad_norm": 0.015775278210639954,
29
+ "learning_rate": 3.678829543451437e-05,
30
+ "loss": 0.0523,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_accuracy": 0.9876190476190476,
36
+ "eval_loss": 0.04352619871497154,
37
+ "eval_runtime": 60.3464,
38
+ "eval_samples_per_second": 104.397,
39
+ "eval_steps_per_second": 6.529,
40
+ "step": 1891
41
+ }
42
+ ],
43
+ "logging_steps": 500,
44
+ "max_steps": 5673,
45
+ "num_input_tokens_seen": 0,
46
+ "num_train_epochs": 3,
47
+ "save_steps": 500,
48
+ "stateful_callbacks": {
49
+ "TrainerControl": {
50
+ "args": {
51
+ "should_epoch_stop": false,
52
+ "should_evaluate": false,
53
+ "should_log": false,
54
+ "should_save": true,
55
+ "should_training_stop": false
56
+ },
57
+ "attributes": {}
58
+ }
59
+ },
60
+ "total_flos": 2.344132685841408e+18,
61
+ "train_batch_size": 16,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
checkpoint-1891/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc67be2c03ad928ae3615baa5690e1b9d3973d4a014149c9bb48d8d6f74383b
3
+ size 5841
checkpoint-3782/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "dtype": "float32",
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "nowildfire",
13
+ "1": "wildfire"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "nowildfire": 0,
20
+ "wildfire": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "pooler_act": "tanh",
29
+ "pooler_output_size": 768,
30
+ "problem_type": "single_label_classification",
31
+ "qkv_bias": true,
32
+ "transformers_version": "4.57.3"
33
+ }
checkpoint-3782/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff28a311b3267696acc33ec512a1878d1f54ecbb8a42df99a1327b130818598f
3
+ size 343223968
checkpoint-3782/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:996e3b65528099905dc17a3d3b0e0dd39d63225d9fd29a0bc089a4a929fde8b4
3
+ size 686572107
checkpoint-3782/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
3
+ size 14645
checkpoint-3782/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f280770ce4b57994cd7747c6ad5cfb5f038a562c0ee35fb27a45ad968223c1
3
+ size 1383
checkpoint-3782/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f20a0cf4a88ac106610d1f23ab23b974d4b9a3ed66e76a14773c1b18f1c71b
3
+ size 1465
checkpoint-3782/trainer_state.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3782,
3
+ "best_metric": 0.9957142857142857,
4
+ "best_model_checkpoint": "./fire-prediction/checkpoint-3782",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3782,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.26441036488630354,
14
+ "grad_norm": 2.7893362045288086,
15
+ "learning_rate": 4.5601974264057816e-05,
16
+ "loss": 0.112,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.5288207297726071,
21
+ "grad_norm": 0.06084805727005005,
22
+ "learning_rate": 4.1195134849286097e-05,
23
+ "loss": 0.0631,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7932310946589106,
28
+ "grad_norm": 0.015775278210639954,
29
+ "learning_rate": 3.678829543451437e-05,
30
+ "loss": 0.0523,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_accuracy": 0.9876190476190476,
36
+ "eval_loss": 0.04352619871497154,
37
+ "eval_runtime": 60.3464,
38
+ "eval_samples_per_second": 104.397,
39
+ "eval_steps_per_second": 6.529,
40
+ "step": 1891
41
+ },
42
+ {
43
+ "epoch": 1.0576414595452142,
44
+ "grad_norm": 0.008536307141184807,
45
+ "learning_rate": 3.238145601974264e-05,
46
+ "loss": 0.0364,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 1.3220518244315178,
51
+ "grad_norm": 0.000655231240671128,
52
+ "learning_rate": 2.7974616604970916e-05,
53
+ "loss": 0.0115,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 1.5864621893178212,
58
+ "grad_norm": 0.004304015543311834,
59
+ "learning_rate": 2.356777719019919e-05,
60
+ "loss": 0.0149,
61
+ "step": 3000
62
+ },
63
+ {
64
+ "epoch": 1.8508725542041247,
65
+ "grad_norm": 0.002045305911451578,
66
+ "learning_rate": 1.9160937775427465e-05,
67
+ "loss": 0.0151,
68
+ "step": 3500
69
+ },
70
+ {
71
+ "epoch": 2.0,
72
+ "eval_accuracy": 0.9957142857142857,
73
+ "eval_loss": 0.017194285988807678,
74
+ "eval_runtime": 39.5065,
75
+ "eval_samples_per_second": 159.468,
76
+ "eval_steps_per_second": 9.973,
77
+ "step": 3782
78
+ }
79
+ ],
80
+ "logging_steps": 500,
81
+ "max_steps": 5673,
82
+ "num_input_tokens_seen": 0,
83
+ "num_train_epochs": 3,
84
+ "save_steps": 500,
85
+ "stateful_callbacks": {
86
+ "TrainerControl": {
87
+ "args": {
88
+ "should_epoch_stop": false,
89
+ "should_evaluate": false,
90
+ "should_log": false,
91
+ "should_save": true,
92
+ "should_training_stop": false
93
+ },
94
+ "attributes": {}
95
+ }
96
+ },
97
+ "total_flos": 4.688265371682816e+18,
98
+ "train_batch_size": 16,
99
+ "trial_name": null,
100
+ "trial_params": null
101
+ }
checkpoint-3782/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc67be2c03ad928ae3615baa5690e1b9d3973d4a014149c9bb48d8d6f74383b
3
+ size 5841
checkpoint-5673/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "dtype": "float32",
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "nowildfire",
13
+ "1": "wildfire"
14
+ },
15
+ "image_size": 224,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "nowildfire": 0,
20
+ "wildfire": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "model_type": "vit",
24
+ "num_attention_heads": 12,
25
+ "num_channels": 3,
26
+ "num_hidden_layers": 12,
27
+ "patch_size": 16,
28
+ "pooler_act": "tanh",
29
+ "pooler_output_size": 768,
30
+ "problem_type": "single_label_classification",
31
+ "qkv_bias": true,
32
+ "transformers_version": "4.57.3"
33
+ }
checkpoint-5673/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cac99bd121fdf210c548bce2193d1498b28ee516d7cbf0133e7b7a63fa6b0ea
3
+ size 343223968
checkpoint-5673/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ffc16675fa2e0a04d5ad68c6003cc53693d8bc9dc72c444234a11c79c45e00c
3
+ size 686572107
checkpoint-5673/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
3
+ size 14645
checkpoint-5673/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1899efd0805f6329c71dbd0894b89b43862f83d8a89a6df00facdf815ea5ce4b
3
+ size 1383
checkpoint-5673/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985b65608b96b912f38ca98b4c277427b18ec689f5630e5068a61e6fa05ff096
3
+ size 1465
checkpoint-5673/trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 5673,
3
+ "best_metric": 0.9971428571428571,
4
+ "best_model_checkpoint": "./fire-prediction/checkpoint-5673",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 5673,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.26441036488630354,
14
+ "grad_norm": 2.7893362045288086,
15
+ "learning_rate": 4.5601974264057816e-05,
16
+ "loss": 0.112,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.5288207297726071,
21
+ "grad_norm": 0.06084805727005005,
22
+ "learning_rate": 4.1195134849286097e-05,
23
+ "loss": 0.0631,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7932310946589106,
28
+ "grad_norm": 0.015775278210639954,
29
+ "learning_rate": 3.678829543451437e-05,
30
+ "loss": 0.0523,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_accuracy": 0.9876190476190476,
36
+ "eval_loss": 0.04352619871497154,
37
+ "eval_runtime": 60.3464,
38
+ "eval_samples_per_second": 104.397,
39
+ "eval_steps_per_second": 6.529,
40
+ "step": 1891
41
+ },
42
+ {
43
+ "epoch": 1.0576414595452142,
44
+ "grad_norm": 0.008536307141184807,
45
+ "learning_rate": 3.238145601974264e-05,
46
+ "loss": 0.0364,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 1.3220518244315178,
51
+ "grad_norm": 0.000655231240671128,
52
+ "learning_rate": 2.7974616604970916e-05,
53
+ "loss": 0.0115,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 1.5864621893178212,
58
+ "grad_norm": 0.004304015543311834,
59
+ "learning_rate": 2.356777719019919e-05,
60
+ "loss": 0.0149,
61
+ "step": 3000
62
+ },
63
+ {
64
+ "epoch": 1.8508725542041247,
65
+ "grad_norm": 0.002045305911451578,
66
+ "learning_rate": 1.9160937775427465e-05,
67
+ "loss": 0.0151,
68
+ "step": 3500
69
+ },
70
+ {
71
+ "epoch": 2.0,
72
+ "eval_accuracy": 0.9957142857142857,
73
+ "eval_loss": 0.017194285988807678,
74
+ "eval_runtime": 39.5065,
75
+ "eval_samples_per_second": 159.468,
76
+ "eval_steps_per_second": 9.973,
77
+ "step": 3782
78
+ },
79
+ {
80
+ "epoch": 2.1152829190904283,
81
+ "grad_norm": 0.0005648525548167527,
82
+ "learning_rate": 1.4754098360655739e-05,
83
+ "loss": 0.009,
84
+ "step": 4000
85
+ },
86
+ {
87
+ "epoch": 2.379693283976732,
88
+ "grad_norm": 0.002387133426964283,
89
+ "learning_rate": 1.0347258945884013e-05,
90
+ "loss": 0.0036,
91
+ "step": 4500
92
+ },
93
+ {
94
+ "epoch": 2.6441036488630356,
95
+ "grad_norm": 0.0003914125554729253,
96
+ "learning_rate": 5.940419531112287e-06,
97
+ "loss": 0.0022,
98
+ "step": 5000
99
+ },
100
+ {
101
+ "epoch": 2.908514013749339,
102
+ "grad_norm": 0.00033830569009296596,
103
+ "learning_rate": 1.5335801163405607e-06,
104
+ "loss": 0.0013,
105
+ "step": 5500
106
+ },
107
+ {
108
+ "epoch": 3.0,
109
+ "eval_accuracy": 0.9971428571428571,
110
+ "eval_loss": 0.012723890133202076,
111
+ "eval_runtime": 38.9372,
112
+ "eval_samples_per_second": 161.799,
113
+ "eval_steps_per_second": 10.119,
114
+ "step": 5673
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 5673,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 3,
121
+ "save_steps": 500,
122
+ "stateful_callbacks": {
123
+ "TrainerControl": {
124
+ "args": {
125
+ "should_epoch_stop": false,
126
+ "should_evaluate": false,
127
+ "should_log": false,
128
+ "should_save": true,
129
+ "should_training_stop": true
130
+ },
131
+ "attributes": {}
132
+ }
133
+ },
134
+ "total_flos": 7.032398057524224e+18,
135
+ "train_batch_size": 16,
136
+ "trial_name": null,
137
+ "trial_params": null
138
+ }
checkpoint-5673/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc67be2c03ad928ae3615baa5690e1b9d3973d4a014149c9bb48d8d6f74383b
3
+ size 5841