Hugging Face's logo

fayetitchenal
/
segformer_finetuned_full_110324

TensorBoard
Safetensors
segformer
Model card Files Metrics Community
fayetitchenal commited on
Commit
bb7de0d
·
verified ·
1 Parent(s): de3a91c

Training in progress, step 6750, checkpoint

Browse files
Files changed (7) hide show
  1. checkpoint-6750/config.json +92 -0
  2. checkpoint-6750/model.safetensors +3 -0
  3. checkpoint-6750/optimizer.pt +3 -0
  4. checkpoint-6750/rng_state.pth +3 -0
  5. checkpoint-6750/scheduler.pt +3 -0
  6. checkpoint-6750/trainer_state.json +150 -0
  7. checkpoint-6750/training_args.bin +3 -0
checkpoint-6750/config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nvidia/mit-b5",
3
+ "architectures": [
4
+ "SegformerForSemanticSegmentation"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout_prob": 0.1,
8
+ "decoder_hidden_size": 768,
9
+ "depths": [
10
+ 3,
11
+ 6,
12
+ 40,
13
+ 3
14
+ ],
15
+ "downsampling_rates": [
16
+ 1,
17
+ 4,
18
+ 8,
19
+ 16
20
+ ],
21
+ "drop_path_rate": 0.1,
22
+ "hidden_act": "gelu",
23
+ "hidden_dropout_prob": 0.0,
24
+ "hidden_sizes": [
25
+ 64,
26
+ 128,
27
+ 320,
28
+ 512
29
+ ],
30
+ "id2label": {
31
+ "0": "background",
32
+ "1": "double_plant",
33
+ "2": "drydown",
34
+ "3": "endrow",
35
+ "4": "nutrient_deficiency",
36
+ "5": "planter_skip",
37
+ "6": "water",
38
+ "7": "waterway",
39
+ "8": "weed_cluster"
40
+ },
41
+ "image_size": 224,
42
+ "initializer_range": 0.02,
43
+ "label2id": {
44
+ "background": 0,
45
+ "double_plant": 1,
46
+ "drydown": 2,
47
+ "endrow": 3,
48
+ "nutrient_deficiency": 4,
49
+ "planter_skip": 5,
50
+ "water": 6,
51
+ "waterway": 7,
52
+ "weed_cluster": 8
53
+ },
54
+ "layer_norm_eps": 1e-06,
55
+ "mlp_ratios": [
56
+ 4,
57
+ 4,
58
+ 4,
59
+ 4
60
+ ],
61
+ "model_type": "segformer",
62
+ "num_attention_heads": [
63
+ 1,
64
+ 2,
65
+ 5,
66
+ 8
67
+ ],
68
+ "num_channels": 4,
69
+ "num_encoder_blocks": 4,
70
+ "patch_sizes": [
71
+ 7,
72
+ 3,
73
+ 3,
74
+ 3
75
+ ],
76
+ "reshape_last_stage": true,
77
+ "semantic_loss_ignore_index": 255,
78
+ "sr_ratios": [
79
+ 8,
80
+ 4,
81
+ 2,
82
+ 1
83
+ ],
84
+ "strides": [
85
+ 4,
86
+ 2,
87
+ 2,
88
+ 2
89
+ ],
90
+ "torch_dtype": "float32",
91
+ "transformers_version": "4.40.2"
92
+ }
checkpoint-6750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd7894ebc1264a8bcfd597f3b17faf4f7cefa8b58f245ef973c245f0ac50996
3
+ size 338562516
checkpoint-6750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f84947970e552ffabfbe429853900b1c1be0117da117381b7530447cf7c7e5
3
+ size 677518143
checkpoint-6750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f50b1aea084348a049d7ee3b160a857c65ecdc014a1660a2749bc518499c2ff
3
+ size 14575
checkpoint-6750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702e63bad1f9b9cd9db29eac8eb56da4a694a9c22f928b76ab0895383a24025d
3
+ size 563
checkpoint-6750/trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9799528301886795,
5
+ "eval_steps": 2250,
6
+ "global_step": 6750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.589622641509434,
13
+ "grad_norm": 9.137022018432617,
14
+ "learning_rate": 2.9481132075471702e-05,
15
+ "loss": 2.8435,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 1.179245283018868,
20
+ "grad_norm": 6.052332401275635,
21
+ "learning_rate": 5.8962264150943403e-05,
22
+ "loss": 1.791,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.3266509433962264,
27
+ "eval_accuracy_background": 0.6658729859800179,
28
+ "eval_accuracy_double_plant": 0.44796971861142204,
29
+ "eval_accuracy_drydown": 0.838452272819733,
30
+ "eval_accuracy_endrow": 0.6564099936974693,
31
+ "eval_accuracy_nutrient_deficiency": 0.5255760511997533,
32
+ "eval_accuracy_planter_skip": 0.7062276764551357,
33
+ "eval_accuracy_water": 0.9873387227342924,
34
+ "eval_accuracy_waterway": 0.5770296385642565,
35
+ "eval_accuracy_weed_cluster": 0.4428120632960455,
36
+ "eval_iou_background": 0.5904190410028399,
37
+ "eval_iou_double_plant": 0.21713659970128166,
38
+ "eval_iou_drydown": 0.5191145408680865,
39
+ "eval_iou_endrow": 0.146705809299966,
40
+ "eval_iou_nutrient_deficiency": 0.3433700256479391,
41
+ "eval_iou_planter_skip": 0.19867844175237825,
42
+ "eval_iou_water": 0.3151796347651091,
43
+ "eval_iou_waterway": 0.17710299517028666,
44
+ "eval_iou_weed_cluster": 0.2871479144864637,
45
+ "eval_loss": 1.6307891607284546,
46
+ "eval_mean_accuracy": 0.6497432359286807,
47
+ "eval_mean_iou": 0.31053944474381673,
48
+ "eval_overall_accuracy": 0.6703095203666921,
49
+ "eval_runtime": 550.4413,
50
+ "eval_samples_per_second": 15.489,
51
+ "eval_steps_per_second": 0.485,
52
+ "step": 2250
53
+ },
54
+ {
55
+ "epoch": 1.7688679245283019,
56
+ "grad_norm": 10.023482322692871,
57
+ "learning_rate": 8.84433962264151e-05,
58
+ "loss": 1.5821,
59
+ "step": 3000
60
+ },
61
+ {
62
+ "epoch": 2.358490566037736,
63
+ "grad_norm": 3.805853843688965,
64
+ "learning_rate": 9.990216178505835e-05,
65
+ "loss": 1.4645,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.6533018867924527,
70
+ "eval_accuracy_background": 0.6928149295345922,
71
+ "eval_accuracy_double_plant": 0.520600810240665,
72
+ "eval_accuracy_drydown": 0.9041661302317083,
73
+ "eval_accuracy_endrow": 0.41216652623141536,
74
+ "eval_accuracy_nutrient_deficiency": 0.5572999343661789,
75
+ "eval_accuracy_planter_skip": 0.5885655971148109,
76
+ "eval_accuracy_water": 0.9012349964392468,
77
+ "eval_accuracy_waterway": 0.5122856732827319,
78
+ "eval_accuracy_weed_cluster": 0.3529035479823603,
79
+ "eval_iou_background": 0.6154372685119965,
80
+ "eval_iou_double_plant": 0.286691279808622,
81
+ "eval_iou_drydown": 0.5005889595647872,
82
+ "eval_iou_endrow": 0.23071917367118422,
83
+ "eval_iou_nutrient_deficiency": 0.34903960157986247,
84
+ "eval_iou_planter_skip": 0.3404743586046269,
85
+ "eval_iou_water": 0.4866735755203849,
86
+ "eval_iou_waterway": 0.17740336931417308,
87
+ "eval_iou_weed_cluster": 0.25445442999377565,
88
+ "eval_loss": 1.6076184511184692,
89
+ "eval_mean_accuracy": 0.6046709050470789,
90
+ "eval_mean_iou": 0.36016466850771256,
91
+ "eval_overall_accuracy": 0.6938899108737494,
92
+ "eval_runtime": 529.8506,
93
+ "eval_samples_per_second": 16.091,
94
+ "eval_steps_per_second": 0.504,
95
+ "step": 4500
96
+ },
97
+ {
98
+ "epoch": 2.94811320754717,
99
+ "grad_norm": 3.9986305236816406,
100
+ "learning_rate": 9.931699497285711e-05,
101
+ "loss": 1.3957,
102
+ "step": 5000
103
+ },
104
+ {
105
+ "epoch": 3.5377358490566038,
106
+ "grad_norm": 2.7372334003448486,
107
+ "learning_rate": 9.821001342355031e-05,
108
+ "loss": 1.3124,
109
+ "step": 6000
110
+ },
111
+ {
112
+ "epoch": 3.9799528301886795,
113
+ "eval_accuracy_background": 0.6307230231497055,
114
+ "eval_accuracy_double_plant": 0.48486363452173786,
115
+ "eval_accuracy_drydown": 0.8612367898895216,
116
+ "eval_accuracy_endrow": 0.5075110635399532,
117
+ "eval_accuracy_nutrient_deficiency": 0.6861430352037324,
118
+ "eval_accuracy_planter_skip": 0.6031976315027698,
119
+ "eval_accuracy_water": 0.9802194342104156,
120
+ "eval_accuracy_waterway": 0.48897799511586637,
121
+ "eval_accuracy_weed_cluster": 0.556708376519504,
122
+ "eval_iou_background": 0.5741567963414517,
123
+ "eval_iou_double_plant": 0.2860919486620036,
124
+ "eval_iou_drydown": 0.5029587941632667,
125
+ "eval_iou_endrow": 0.22521629078173816,
126
+ "eval_iou_nutrient_deficiency": 0.3596590524564408,
127
+ "eval_iou_planter_skip": 0.3023475517768152,
128
+ "eval_iou_water": 0.41466030404934484,
129
+ "eval_iou_waterway": 0.11905712637247004,
130
+ "eval_iou_weed_cluster": 0.3161136298740651,
131
+ "eval_loss": 1.6003777980804443,
132
+ "eval_mean_accuracy": 0.6443978870725785,
133
+ "eval_mean_iou": 0.34447349938639954,
134
+ "eval_overall_accuracy": 0.6672287911844751,
135
+ "eval_runtime": 529.5311,
136
+ "eval_samples_per_second": 16.101,
137
+ "eval_steps_per_second": 0.504,
138
+ "step": 6750
139
+ }
140
+ ],
141
+ "logging_steps": 1000,
142
+ "max_steps": 33920,
143
+ "num_input_tokens_seen": 0,
144
+ "num_train_epochs": 20,
145
+ "save_steps": 2250,
146
+ "total_flos": 1.1495460697287111e+20,
147
+ "train_batch_size": 32,
148
+ "trial_name": null,
149
+ "trial_params": null
150
+ }
checkpoint-6750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f718e0633b4eda2deeb786176aa261e6cae5f387b8ef2e8fb286f958ed2885d
3
+ size 4539