joe611 commited on
Commit
6c471d0
1 Parent(s): fc2233c

Training in progress, epoch 1, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/detr-resnet-50",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "DetrForObjectDetection"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auxiliary_loss": false,
10
+ "backbone": "resnet50",
11
+ "backbone_config": null,
12
+ "backbone_kwargs": {
13
+ "in_chans": 3,
14
+ "out_indices": [
15
+ 1,
16
+ 2,
17
+ 3,
18
+ 4
19
+ ]
20
+ },
21
+ "bbox_cost": 5,
22
+ "bbox_loss_coefficient": 5,
23
+ "class_cost": 1,
24
+ "classifier_dropout": 0.0,
25
+ "d_model": 256,
26
+ "decoder_attention_heads": 8,
27
+ "decoder_ffn_dim": 2048,
28
+ "decoder_layerdrop": 0.0,
29
+ "decoder_layers": 6,
30
+ "dice_loss_coefficient": 1,
31
+ "dilation": false,
32
+ "dropout": 0.1,
33
+ "encoder_attention_heads": 8,
34
+ "encoder_ffn_dim": 2048,
35
+ "encoder_layerdrop": 0.0,
36
+ "encoder_layers": 6,
37
+ "eos_coefficient": 0.1,
38
+ "giou_cost": 2,
39
+ "giou_loss_coefficient": 2,
40
+ "id2label": {
41
+ "0": "chicken",
42
+ "1": "duck",
43
+ "2": "plant"
44
+ },
45
+ "init_std": 0.02,
46
+ "init_xavier_std": 1.0,
47
+ "is_encoder_decoder": true,
48
+ "label2id": {
49
+ "chicken": 0,
50
+ "duck": 1,
51
+ "plant": 2
52
+ },
53
+ "mask_loss_coefficient": 1,
54
+ "max_position_embeddings": 1024,
55
+ "model_type": "detr",
56
+ "num_channels": 3,
57
+ "num_hidden_layers": 6,
58
+ "num_queries": 100,
59
+ "position_embedding_type": "sine",
60
+ "scale_embedding": false,
61
+ "torch_dtype": "float32",
62
+ "transformers_version": "4.46.2",
63
+ "use_pretrained_backbone": true,
64
+ "use_timm_backbone": true
65
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a8ea70030be138aa75b02645a583c09e8ada1badfa7d50a8e75dcf24286c8a
3
+ size 166496880
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c89ef86117ee9d983bc1c015365e036682915d1a8c7504ee84ce611317f1f854
3
+ size 330495866
last-checkpoint/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_annotations": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "format": "coco_detection",
8
+ "image_mean": [
9
+ 0.485,
10
+ 0.456,
11
+ 0.406
12
+ ],
13
+ "image_processor_type": "DetrImageProcessor",
14
+ "image_std": [
15
+ 0.229,
16
+ 0.224,
17
+ 0.225
18
+ ],
19
+ "pad_size": {
20
+ "height": 480,
21
+ "width": 480
22
+ },
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 480,
27
+ "width": 480
28
+ }
29
+ }
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80102c2ed7116fe515826ab6f9a361c705e0bd357c30f1258bdcf26128f862e8
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7173c0fe85cede5b9a4816598dcc9e1616999a7e5656401e0a94269cd8bf4cd3
3
+ size 1064
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.49143648147583,
3
+ "best_model_checkpoint": "chickens-composite-201616161616-150-epochs-w-transform-metrics-test-shfld/checkpoint-500",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "grad_norm": 75.97504425048828,
14
+ "learning_rate": 9.99999605215876e-06,
15
+ "loss": 2.1001,
16
+ "step": 30
17
+ },
18
+ {
19
+ "epoch": 0.12,
20
+ "grad_norm": 325.9894104003906,
21
+ "learning_rate": 9.999984208641271e-06,
22
+ "loss": 1.9809,
23
+ "step": 60
24
+ },
25
+ {
26
+ "epoch": 0.18,
27
+ "grad_norm": 368.0644836425781,
28
+ "learning_rate": 9.999964469466236e-06,
29
+ "loss": 1.9328,
30
+ "step": 90
31
+ },
32
+ {
33
+ "epoch": 0.24,
34
+ "grad_norm": 135.25502014160156,
35
+ "learning_rate": 9.99993683466483e-06,
36
+ "loss": 1.638,
37
+ "step": 120
38
+ },
39
+ {
40
+ "epoch": 0.3,
41
+ "grad_norm": 9.217020988464355,
42
+ "learning_rate": 9.999901304280686e-06,
43
+ "loss": 1.77,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.36,
48
+ "grad_norm": 332.27508544921875,
49
+ "learning_rate": 9.999857878369917e-06,
50
+ "loss": 1.7866,
51
+ "step": 180
52
+ },
53
+ {
54
+ "epoch": 0.42,
55
+ "grad_norm": 46.90544509887695,
56
+ "learning_rate": 9.999806557001092e-06,
57
+ "loss": 1.6174,
58
+ "step": 210
59
+ },
60
+ {
61
+ "epoch": 0.48,
62
+ "grad_norm": 56.86224365234375,
63
+ "learning_rate": 9.99974734025526e-06,
64
+ "loss": 1.7012,
65
+ "step": 240
66
+ },
67
+ {
68
+ "epoch": 0.54,
69
+ "grad_norm": 81.79679870605469,
70
+ "learning_rate": 9.99968022822593e-06,
71
+ "loss": 1.7739,
72
+ "step": 270
73
+ },
74
+ {
75
+ "epoch": 0.6,
76
+ "grad_norm": 68.52080535888672,
77
+ "learning_rate": 9.999605221019082e-06,
78
+ "loss": 1.5547,
79
+ "step": 300
80
+ },
81
+ {
82
+ "epoch": 0.66,
83
+ "grad_norm": 78.40971374511719,
84
+ "learning_rate": 9.99952231875316e-06,
85
+ "loss": 1.3662,
86
+ "step": 330
87
+ },
88
+ {
89
+ "epoch": 0.72,
90
+ "grad_norm": 58.15324020385742,
91
+ "learning_rate": 9.999431521559081e-06,
92
+ "loss": 1.4828,
93
+ "step": 360
94
+ },
95
+ {
96
+ "epoch": 0.78,
97
+ "grad_norm": 26.653955459594727,
98
+ "learning_rate": 9.999332829580227e-06,
99
+ "loss": 1.4824,
100
+ "step": 390
101
+ },
102
+ {
103
+ "epoch": 0.84,
104
+ "grad_norm": 76.19355010986328,
105
+ "learning_rate": 9.999226242972445e-06,
106
+ "loss": 1.6913,
107
+ "step": 420
108
+ },
109
+ {
110
+ "epoch": 0.9,
111
+ "grad_norm": 3.1019766330718994,
112
+ "learning_rate": 9.999111761904046e-06,
113
+ "loss": 1.2515,
114
+ "step": 450
115
+ },
116
+ {
117
+ "epoch": 0.96,
118
+ "grad_norm": 81.1119384765625,
119
+ "learning_rate": 9.998989386555815e-06,
120
+ "loss": 1.2525,
121
+ "step": 480
122
+ },
123
+ {
124
+ "epoch": 1.0,
125
+ "eval_loss": 1.49143648147583,
126
+ "eval_map": 0.0431,
127
+ "eval_map_50": 0.0683,
128
+ "eval_map_75": 0.0461,
129
+ "eval_map_chicken": 0.0272,
130
+ "eval_map_duck": 0.0,
131
+ "eval_map_large": 0.0695,
132
+ "eval_map_medium": 0.0195,
133
+ "eval_map_plant": 0.1019,
134
+ "eval_map_small": 0.0038,
135
+ "eval_mar_1": 0.0492,
136
+ "eval_mar_10": 0.1277,
137
+ "eval_mar_100": 0.2728,
138
+ "eval_mar_100_chicken": 0.123,
139
+ "eval_mar_100_duck": 0.0,
140
+ "eval_mar_100_plant": 0.6955,
141
+ "eval_mar_large": 0.2835,
142
+ "eval_mar_medium": 0.2434,
143
+ "eval_mar_small": 0.1105,
144
+ "eval_runtime": 6.7968,
145
+ "eval_samples_per_second": 14.713,
146
+ "eval_steps_per_second": 1.913,
147
+ "step": 500
148
+ }
149
+ ],
150
+ "logging_steps": 30,
151
+ "max_steps": 75000,
152
+ "num_input_tokens_seen": 0,
153
+ "num_train_epochs": 150,
154
+ "save_steps": 10,
155
+ "stateful_callbacks": {
156
+ "TrainerControl": {
157
+ "args": {
158
+ "should_epoch_stop": false,
159
+ "should_evaluate": false,
160
+ "should_log": false,
161
+ "should_save": true,
162
+ "should_training_stop": false
163
+ },
164
+ "attributes": {}
165
+ }
166
+ },
167
+ "total_flos": 1.720115564544e+17,
168
+ "train_batch_size": 2,
169
+ "trial_name": null,
170
+ "trial_params": null
171
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5cc8c9158f582b16df1d0ef90cb224b4855f24c5c3adf7c1d9a7f0991018dab
3
+ size 5432