rileybol commited on
Commit
dd49d97
1 Parent(s): 6d95d36

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - object-detection
6
+ - vision
7
+ widget:
8
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
9
+ example_title: Tiger
10
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
11
+ example_title: Teapot
12
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
13
+ example_title: Palace
14
+ ---
15
+
16
+ # Model Trained Using AutoTrain
17
+
18
+ - Problem type: Object Detection
19
+
20
+ ## Validation Metrics
21
+ loss: 0.8856489658355713
22
+
23
+ map: 0.1595
24
+
25
+ map_50: 0.2552
26
+
27
+ map_75: 0.1847
28
+
29
+ map_small: 0.0
30
+
31
+ map_medium: 0.0755
32
+
33
+ map_large: 0.1961
34
+
35
+ mar_1: 0.2338
36
+
37
+ mar_10: 0.5162
38
+
39
+ mar_100: 0.6897
40
+
41
+ mar_small: 0.0
42
+
43
+ mar_medium: 0.5297
44
+
45
+ mar_large: 0.7544
checkpoint-339/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/detr-resnet-101",
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": "resnet101",
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": "Face"
42
+ },
43
+ "init_std": 0.02,
44
+ "init_xavier_std": 1.0,
45
+ "is_encoder_decoder": true,
46
+ "label2id": {
47
+ "Face": 0
48
+ },
49
+ "mask_loss_coefficient": 1,
50
+ "max_position_embeddings": 1024,
51
+ "model_type": "detr",
52
+ "num_channels": 3,
53
+ "num_hidden_layers": 6,
54
+ "num_queries": 100,
55
+ "position_embedding_type": "sine",
56
+ "scale_embedding": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.41.0",
59
+ "use_pretrained_backbone": true,
60
+ "use_timm_backbone": true
61
+ }
checkpoint-339/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659494bcede8bf5d6bc7b89639fa453c833c85798404c46ee240c337cf6a4702
3
+ size 242704552
checkpoint-339/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebca2363dead62135a9a4907b791291fbc1e1a654e8ec726aa8125c0946f405b
3
+ size 482055300
checkpoint-339/preprocessor_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "annotations",
5
+ "return_segmentation_masks",
6
+ "masks_path",
7
+ "do_resize",
8
+ "size",
9
+ "resample",
10
+ "do_rescale",
11
+ "rescale_factor",
12
+ "do_normalize",
13
+ "do_convert_annotations",
14
+ "image_mean",
15
+ "image_std",
16
+ "do_pad",
17
+ "format",
18
+ "return_tensors",
19
+ "data_format",
20
+ "input_data_format"
21
+ ],
22
+ "do_convert_annotations": true,
23
+ "do_normalize": true,
24
+ "do_pad": false,
25
+ "do_rescale": true,
26
+ "do_resize": false,
27
+ "format": "coco_detection",
28
+ "image_mean": [
29
+ 0.485,
30
+ 0.456,
31
+ 0.406
32
+ ],
33
+ "image_processor_type": "DetrImageProcessor",
34
+ "image_std": [
35
+ 0.229,
36
+ 0.224,
37
+ 0.225
38
+ ],
39
+ "resample": 2,
40
+ "rescale_factor": 0.00392156862745098,
41
+ "size": {
42
+ "longest_edge": 600
43
+ }
44
+ }
checkpoint-339/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb8d84f201c4d310d01d391c8db647098d5210a2e526a0d0f5e426ce270412e
3
+ size 14244
checkpoint-339/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f5e05de16c989d52ed1d2926d42e3e6d436b7c6bfe0cc6c5ee82f8b2e2bda7
3
+ size 1064
checkpoint-339/trainer_state.json ADDED
@@ -0,0 +1,1291 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8856489658355713,
3
+ "best_model_checkpoint": "autotrain-1hkeo-o33ms/checkpoint-339",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 339,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017699115044247787,
13
+ "grad_norm": NaN,
14
+ "learning_rate": 0.0,
15
+ "loss": 2.8516,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.035398230088495575,
20
+ "grad_norm": 106.12066650390625,
21
+ "learning_rate": 1.4705882352941177e-06,
22
+ "loss": 2.7397,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.05309734513274336,
27
+ "grad_norm": 239.92628479003906,
28
+ "learning_rate": 2.9411764705882355e-06,
29
+ "loss": 2.5233,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.07079646017699115,
34
+ "grad_norm": 219.21218872070312,
35
+ "learning_rate": 5.882352941176471e-06,
36
+ "loss": 2.7366,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.08849557522123894,
41
+ "grad_norm": 214.71096801757812,
42
+ "learning_rate": 8.823529411764707e-06,
43
+ "loss": 2.6004,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.10619469026548672,
48
+ "grad_norm": Infinity,
49
+ "learning_rate": 8.823529411764707e-06,
50
+ "loss": 2.4951,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.12389380530973451,
55
+ "grad_norm": 320.1042785644531,
56
+ "learning_rate": 1.1764705882352942e-05,
57
+ "loss": 1.8943,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.1415929203539823,
62
+ "grad_norm": 1234.984619140625,
63
+ "learning_rate": 1.4705882352941177e-05,
64
+ "loss": 2.1298,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.1592920353982301,
69
+ "grad_norm": 85.23419189453125,
70
+ "learning_rate": 1.7647058823529414e-05,
71
+ "loss": 1.978,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.17699115044247787,
76
+ "grad_norm": 148.04153442382812,
77
+ "learning_rate": 2.058823529411765e-05,
78
+ "loss": 1.9334,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.19469026548672566,
83
+ "grad_norm": 70.3712387084961,
84
+ "learning_rate": 2.3529411764705884e-05,
85
+ "loss": 1.9477,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.21238938053097345,
90
+ "grad_norm": 279.7557678222656,
91
+ "learning_rate": 2.647058823529412e-05,
92
+ "loss": 1.8483,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.23008849557522124,
97
+ "grad_norm": 294.1581115722656,
98
+ "learning_rate": 2.9411764705882354e-05,
99
+ "loss": 1.5582,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.24778761061946902,
104
+ "grad_norm": 110.91650390625,
105
+ "learning_rate": 3.235294117647059e-05,
106
+ "loss": 1.5439,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.26548672566371684,
111
+ "grad_norm": 68.54044342041016,
112
+ "learning_rate": 3.529411764705883e-05,
113
+ "loss": 1.5531,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.2831858407079646,
118
+ "grad_norm": 67.14613342285156,
119
+ "learning_rate": 3.8235294117647055e-05,
120
+ "loss": 1.5641,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.3008849557522124,
125
+ "grad_norm": 73.9820785522461,
126
+ "learning_rate": 4.11764705882353e-05,
127
+ "loss": 1.687,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 0.3185840707964602,
132
+ "grad_norm": 38.29616928100586,
133
+ "learning_rate": 4.411764705882353e-05,
134
+ "loss": 1.4187,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 0.336283185840708,
139
+ "grad_norm": 84.34982299804688,
140
+ "learning_rate": 4.705882352941177e-05,
141
+ "loss": 1.3998,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 0.35398230088495575,
146
+ "grad_norm": 188.01791381835938,
147
+ "learning_rate": 5e-05,
148
+ "loss": 1.477,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 0.37168141592920356,
153
+ "grad_norm": 443.12078857421875,
154
+ "learning_rate": 4.967213114754098e-05,
155
+ "loss": 1.4343,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 0.3893805309734513,
160
+ "grad_norm": 70.84330749511719,
161
+ "learning_rate": 4.934426229508197e-05,
162
+ "loss": 1.4312,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 0.40707964601769914,
167
+ "grad_norm": 151.94332885742188,
168
+ "learning_rate": 4.9016393442622957e-05,
169
+ "loss": 1.5684,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 0.4247787610619469,
174
+ "grad_norm": 44.81299591064453,
175
+ "learning_rate": 4.868852459016394e-05,
176
+ "loss": 1.6841,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 0.4424778761061947,
181
+ "grad_norm": 212.30218505859375,
182
+ "learning_rate": 4.836065573770492e-05,
183
+ "loss": 1.3116,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 0.46017699115044247,
188
+ "grad_norm": 146.485595703125,
189
+ "learning_rate": 4.8032786885245904e-05,
190
+ "loss": 1.5651,
191
+ "step": 52
192
+ },
193
+ {
194
+ "epoch": 0.4778761061946903,
195
+ "grad_norm": 56.38231658935547,
196
+ "learning_rate": 4.770491803278689e-05,
197
+ "loss": 1.611,
198
+ "step": 54
199
+ },
200
+ {
201
+ "epoch": 0.49557522123893805,
202
+ "grad_norm": 168.2674102783203,
203
+ "learning_rate": 4.737704918032787e-05,
204
+ "loss": 1.5692,
205
+ "step": 56
206
+ },
207
+ {
208
+ "epoch": 0.5132743362831859,
209
+ "grad_norm": 62.2509765625,
210
+ "learning_rate": 4.704918032786885e-05,
211
+ "loss": 1.8457,
212
+ "step": 58
213
+ },
214
+ {
215
+ "epoch": 0.5309734513274337,
216
+ "grad_norm": 272.4936828613281,
217
+ "learning_rate": 4.672131147540984e-05,
218
+ "loss": 1.5168,
219
+ "step": 60
220
+ },
221
+ {
222
+ "epoch": 0.5486725663716814,
223
+ "grad_norm": 45.84150695800781,
224
+ "learning_rate": 4.6393442622950825e-05,
225
+ "loss": 1.3566,
226
+ "step": 62
227
+ },
228
+ {
229
+ "epoch": 0.5663716814159292,
230
+ "grad_norm": 78.61536407470703,
231
+ "learning_rate": 4.6065573770491805e-05,
232
+ "loss": 1.2089,
233
+ "step": 64
234
+ },
235
+ {
236
+ "epoch": 0.584070796460177,
237
+ "grad_norm": 65.8510513305664,
238
+ "learning_rate": 4.5737704918032786e-05,
239
+ "loss": 1.2913,
240
+ "step": 66
241
+ },
242
+ {
243
+ "epoch": 0.6017699115044248,
244
+ "grad_norm": 90.05781555175781,
245
+ "learning_rate": 4.540983606557377e-05,
246
+ "loss": 1.193,
247
+ "step": 68
248
+ },
249
+ {
250
+ "epoch": 0.6194690265486725,
251
+ "grad_norm": 87.59015655517578,
252
+ "learning_rate": 4.508196721311476e-05,
253
+ "loss": 1.3291,
254
+ "step": 70
255
+ },
256
+ {
257
+ "epoch": 0.6371681415929203,
258
+ "grad_norm": 52.730377197265625,
259
+ "learning_rate": 4.475409836065574e-05,
260
+ "loss": 1.2274,
261
+ "step": 72
262
+ },
263
+ {
264
+ "epoch": 0.6548672566371682,
265
+ "grad_norm": 39.25498962402344,
266
+ "learning_rate": 4.442622950819673e-05,
267
+ "loss": 1.2745,
268
+ "step": 74
269
+ },
270
+ {
271
+ "epoch": 0.672566371681416,
272
+ "grad_norm": 31.809101104736328,
273
+ "learning_rate": 4.409836065573771e-05,
274
+ "loss": 1.1752,
275
+ "step": 76
276
+ },
277
+ {
278
+ "epoch": 0.6902654867256637,
279
+ "grad_norm": 48.21644592285156,
280
+ "learning_rate": 4.377049180327869e-05,
281
+ "loss": 1.313,
282
+ "step": 78
283
+ },
284
+ {
285
+ "epoch": 0.7079646017699115,
286
+ "grad_norm": 37.171226501464844,
287
+ "learning_rate": 4.3442622950819674e-05,
288
+ "loss": 1.2738,
289
+ "step": 80
290
+ },
291
+ {
292
+ "epoch": 0.7256637168141593,
293
+ "grad_norm": 129.79141235351562,
294
+ "learning_rate": 4.311475409836066e-05,
295
+ "loss": 1.1686,
296
+ "step": 82
297
+ },
298
+ {
299
+ "epoch": 0.7433628318584071,
300
+ "grad_norm": 77.16220092773438,
301
+ "learning_rate": 4.278688524590164e-05,
302
+ "loss": 1.3718,
303
+ "step": 84
304
+ },
305
+ {
306
+ "epoch": 0.7610619469026548,
307
+ "grad_norm": 45.43793487548828,
308
+ "learning_rate": 4.245901639344262e-05,
309
+ "loss": 1.1993,
310
+ "step": 86
311
+ },
312
+ {
313
+ "epoch": 0.7787610619469026,
314
+ "grad_norm": 130.69161987304688,
315
+ "learning_rate": 4.213114754098361e-05,
316
+ "loss": 1.052,
317
+ "step": 88
318
+ },
319
+ {
320
+ "epoch": 0.7964601769911505,
321
+ "grad_norm": 42.368804931640625,
322
+ "learning_rate": 4.1803278688524595e-05,
323
+ "loss": 1.0408,
324
+ "step": 90
325
+ },
326
+ {
327
+ "epoch": 0.8141592920353983,
328
+ "grad_norm": 42.31563949584961,
329
+ "learning_rate": 4.1475409836065575e-05,
330
+ "loss": 1.3483,
331
+ "step": 92
332
+ },
333
+ {
334
+ "epoch": 0.831858407079646,
335
+ "grad_norm": 47.8664665222168,
336
+ "learning_rate": 4.1147540983606556e-05,
337
+ "loss": 1.2632,
338
+ "step": 94
339
+ },
340
+ {
341
+ "epoch": 0.8495575221238938,
342
+ "grad_norm": 64.5959243774414,
343
+ "learning_rate": 4.081967213114754e-05,
344
+ "loss": 1.1907,
345
+ "step": 96
346
+ },
347
+ {
348
+ "epoch": 0.8672566371681416,
349
+ "grad_norm": 260.2913513183594,
350
+ "learning_rate": 4.049180327868853e-05,
351
+ "loss": 1.1238,
352
+ "step": 98
353
+ },
354
+ {
355
+ "epoch": 0.8849557522123894,
356
+ "grad_norm": 42.65099334716797,
357
+ "learning_rate": 4.016393442622951e-05,
358
+ "loss": 1.3226,
359
+ "step": 100
360
+ },
361
+ {
362
+ "epoch": 0.9026548672566371,
363
+ "grad_norm": 42.4586181640625,
364
+ "learning_rate": 3.983606557377049e-05,
365
+ "loss": 1.2652,
366
+ "step": 102
367
+ },
368
+ {
369
+ "epoch": 0.9203539823008849,
370
+ "grad_norm": 50.917659759521484,
371
+ "learning_rate": 3.950819672131148e-05,
372
+ "loss": 1.1128,
373
+ "step": 104
374
+ },
375
+ {
376
+ "epoch": 0.9380530973451328,
377
+ "grad_norm": 90.57892608642578,
378
+ "learning_rate": 3.9180327868852464e-05,
379
+ "loss": 1.5618,
380
+ "step": 106
381
+ },
382
+ {
383
+ "epoch": 0.9557522123893806,
384
+ "grad_norm": 126.1560287475586,
385
+ "learning_rate": 3.8852459016393444e-05,
386
+ "loss": 1.5922,
387
+ "step": 108
388
+ },
389
+ {
390
+ "epoch": 0.9734513274336283,
391
+ "grad_norm": 45.01774978637695,
392
+ "learning_rate": 3.8524590163934424e-05,
393
+ "loss": 1.4205,
394
+ "step": 110
395
+ },
396
+ {
397
+ "epoch": 0.9911504424778761,
398
+ "grad_norm": 49.559791564941406,
399
+ "learning_rate": 3.819672131147541e-05,
400
+ "loss": 1.2759,
401
+ "step": 112
402
+ },
403
+ {
404
+ "epoch": 1.0,
405
+ "eval_loss": 1.0817503929138184,
406
+ "eval_map": 0.0905,
407
+ "eval_map_50": 0.1567,
408
+ "eval_map_75": 0.0974,
409
+ "eval_map_large": 0.1083,
410
+ "eval_map_medium": 0.0595,
411
+ "eval_map_per_class": 0.0905,
412
+ "eval_map_small": 0.0,
413
+ "eval_mar_1": 0.2077,
414
+ "eval_mar_10": 0.3979,
415
+ "eval_mar_100": 0.6491,
416
+ "eval_mar_100_per_class": 0.6491,
417
+ "eval_mar_large": 0.7243,
418
+ "eval_mar_medium": 0.4609,
419
+ "eval_mar_small": 0.0,
420
+ "eval_runtime": 6.9741,
421
+ "eval_samples_per_second": 14.339,
422
+ "eval_steps_per_second": 1.004,
423
+ "step": 113
424
+ },
425
+ {
426
+ "epoch": 1.008849557522124,
427
+ "grad_norm": 55.82676315307617,
428
+ "learning_rate": 3.78688524590164e-05,
429
+ "loss": 1.3204,
430
+ "step": 114
431
+ },
432
+ {
433
+ "epoch": 1.0265486725663717,
434
+ "grad_norm": 56.670345306396484,
435
+ "learning_rate": 3.754098360655738e-05,
436
+ "loss": 1.0837,
437
+ "step": 116
438
+ },
439
+ {
440
+ "epoch": 1.0442477876106195,
441
+ "grad_norm": 166.82949829101562,
442
+ "learning_rate": 3.721311475409836e-05,
443
+ "loss": 1.1722,
444
+ "step": 118
445
+ },
446
+ {
447
+ "epoch": 1.0619469026548674,
448
+ "grad_norm": 83.52169036865234,
449
+ "learning_rate": 3.6885245901639346e-05,
450
+ "loss": 1.2194,
451
+ "step": 120
452
+ },
453
+ {
454
+ "epoch": 1.079646017699115,
455
+ "grad_norm": 56.17623519897461,
456
+ "learning_rate": 3.655737704918033e-05,
457
+ "loss": 1.1828,
458
+ "step": 122
459
+ },
460
+ {
461
+ "epoch": 1.0973451327433628,
462
+ "grad_norm": 24.509546279907227,
463
+ "learning_rate": 3.622950819672131e-05,
464
+ "loss": 1.009,
465
+ "step": 124
466
+ },
467
+ {
468
+ "epoch": 1.1150442477876106,
469
+ "grad_norm": 80.25348663330078,
470
+ "learning_rate": 3.590163934426229e-05,
471
+ "loss": 1.1667,
472
+ "step": 126
473
+ },
474
+ {
475
+ "epoch": 1.1327433628318584,
476
+ "grad_norm": 98.71533966064453,
477
+ "learning_rate": 3.557377049180328e-05,
478
+ "loss": 1.1607,
479
+ "step": 128
480
+ },
481
+ {
482
+ "epoch": 1.1504424778761062,
483
+ "grad_norm": 42.726444244384766,
484
+ "learning_rate": 3.524590163934427e-05,
485
+ "loss": 1.0344,
486
+ "step": 130
487
+ },
488
+ {
489
+ "epoch": 1.168141592920354,
490
+ "grad_norm": 47.48421859741211,
491
+ "learning_rate": 3.491803278688525e-05,
492
+ "loss": 1.1513,
493
+ "step": 132
494
+ },
495
+ {
496
+ "epoch": 1.1858407079646018,
497
+ "grad_norm": 38.87162780761719,
498
+ "learning_rate": 3.459016393442623e-05,
499
+ "loss": 1.0672,
500
+ "step": 134
501
+ },
502
+ {
503
+ "epoch": 1.2035398230088497,
504
+ "grad_norm": 30.703020095825195,
505
+ "learning_rate": 3.4262295081967214e-05,
506
+ "loss": 1.2524,
507
+ "step": 136
508
+ },
509
+ {
510
+ "epoch": 1.2212389380530975,
511
+ "grad_norm": 62.74378967285156,
512
+ "learning_rate": 3.39344262295082e-05,
513
+ "loss": 1.0351,
514
+ "step": 138
515
+ },
516
+ {
517
+ "epoch": 1.238938053097345,
518
+ "grad_norm": 32.68797302246094,
519
+ "learning_rate": 3.360655737704918e-05,
520
+ "loss": 1.0135,
521
+ "step": 140
522
+ },
523
+ {
524
+ "epoch": 1.2566371681415929,
525
+ "grad_norm": 260.8392639160156,
526
+ "learning_rate": 3.327868852459017e-05,
527
+ "loss": 1.1592,
528
+ "step": 142
529
+ },
530
+ {
531
+ "epoch": 1.2743362831858407,
532
+ "grad_norm": 102.03837585449219,
533
+ "learning_rate": 3.295081967213115e-05,
534
+ "loss": 1.0648,
535
+ "step": 144
536
+ },
537
+ {
538
+ "epoch": 1.2920353982300885,
539
+ "grad_norm": 50.19871520996094,
540
+ "learning_rate": 3.2622950819672136e-05,
541
+ "loss": 1.0932,
542
+ "step": 146
543
+ },
544
+ {
545
+ "epoch": 1.3097345132743363,
546
+ "grad_norm": 108.73077392578125,
547
+ "learning_rate": 3.2295081967213116e-05,
548
+ "loss": 1.0388,
549
+ "step": 148
550
+ },
551
+ {
552
+ "epoch": 1.3274336283185841,
553
+ "grad_norm": 166.00540161132812,
554
+ "learning_rate": 3.19672131147541e-05,
555
+ "loss": 1.189,
556
+ "step": 150
557
+ },
558
+ {
559
+ "epoch": 1.3451327433628317,
560
+ "grad_norm": 29.591773986816406,
561
+ "learning_rate": 3.163934426229508e-05,
562
+ "loss": 0.9697,
563
+ "step": 152
564
+ },
565
+ {
566
+ "epoch": 1.3628318584070795,
567
+ "grad_norm": 96.86643981933594,
568
+ "learning_rate": 3.131147540983606e-05,
569
+ "loss": 1.1525,
570
+ "step": 154
571
+ },
572
+ {
573
+ "epoch": 1.3805309734513274,
574
+ "grad_norm": 52.641666412353516,
575
+ "learning_rate": 3.098360655737705e-05,
576
+ "loss": 1.1335,
577
+ "step": 156
578
+ },
579
+ {
580
+ "epoch": 1.3982300884955752,
581
+ "grad_norm": 34.866493225097656,
582
+ "learning_rate": 3.065573770491804e-05,
583
+ "loss": 1.285,
584
+ "step": 158
585
+ },
586
+ {
587
+ "epoch": 1.415929203539823,
588
+ "grad_norm": 23.98964500427246,
589
+ "learning_rate": 3.0327868852459017e-05,
590
+ "loss": 1.2042,
591
+ "step": 160
592
+ },
593
+ {
594
+ "epoch": 1.4336283185840708,
595
+ "grad_norm": 145.60592651367188,
596
+ "learning_rate": 3e-05,
597
+ "loss": 1.29,
598
+ "step": 162
599
+ },
600
+ {
601
+ "epoch": 1.4513274336283186,
602
+ "grad_norm": 53.379520416259766,
603
+ "learning_rate": 2.967213114754098e-05,
604
+ "loss": 1.1392,
605
+ "step": 164
606
+ },
607
+ {
608
+ "epoch": 1.4690265486725664,
609
+ "grad_norm": 60.14817428588867,
610
+ "learning_rate": 2.934426229508197e-05,
611
+ "loss": 1.2606,
612
+ "step": 166
613
+ },
614
+ {
615
+ "epoch": 1.4867256637168142,
616
+ "grad_norm": 31.738466262817383,
617
+ "learning_rate": 2.901639344262295e-05,
618
+ "loss": 1.1376,
619
+ "step": 168
620
+ },
621
+ {
622
+ "epoch": 1.504424778761062,
623
+ "grad_norm": 38.88958740234375,
624
+ "learning_rate": 2.8688524590163935e-05,
625
+ "loss": 1.1329,
626
+ "step": 170
627
+ },
628
+ {
629
+ "epoch": 1.5221238938053099,
630
+ "grad_norm": 61.10131072998047,
631
+ "learning_rate": 2.8360655737704922e-05,
632
+ "loss": 1.0537,
633
+ "step": 172
634
+ },
635
+ {
636
+ "epoch": 1.5398230088495575,
637
+ "grad_norm": 43.02183532714844,
638
+ "learning_rate": 2.8032786885245906e-05,
639
+ "loss": 1.1499,
640
+ "step": 174
641
+ },
642
+ {
643
+ "epoch": 1.5575221238938053,
644
+ "grad_norm": 37.601444244384766,
645
+ "learning_rate": 2.7704918032786886e-05,
646
+ "loss": 1.3708,
647
+ "step": 176
648
+ },
649
+ {
650
+ "epoch": 1.575221238938053,
651
+ "grad_norm": 29.7570743560791,
652
+ "learning_rate": 2.737704918032787e-05,
653
+ "loss": 1.138,
654
+ "step": 178
655
+ },
656
+ {
657
+ "epoch": 1.592920353982301,
658
+ "grad_norm": 94.0286865234375,
659
+ "learning_rate": 2.7049180327868856e-05,
660
+ "loss": 1.0933,
661
+ "step": 180
662
+ },
663
+ {
664
+ "epoch": 1.6106194690265485,
665
+ "grad_norm": 38.72492599487305,
666
+ "learning_rate": 2.6721311475409837e-05,
667
+ "loss": 0.9599,
668
+ "step": 182
669
+ },
670
+ {
671
+ "epoch": 1.6283185840707963,
672
+ "grad_norm": 30.70404624938965,
673
+ "learning_rate": 2.639344262295082e-05,
674
+ "loss": 1.0226,
675
+ "step": 184
676
+ },
677
+ {
678
+ "epoch": 1.6460176991150441,
679
+ "grad_norm": 57.246028900146484,
680
+ "learning_rate": 2.6065573770491804e-05,
681
+ "loss": 0.9137,
682
+ "step": 186
683
+ },
684
+ {
685
+ "epoch": 1.663716814159292,
686
+ "grad_norm": 30.864009857177734,
687
+ "learning_rate": 2.573770491803279e-05,
688
+ "loss": 1.0321,
689
+ "step": 188
690
+ },
691
+ {
692
+ "epoch": 1.6814159292035398,
693
+ "grad_norm": 21.78902816772461,
694
+ "learning_rate": 2.540983606557377e-05,
695
+ "loss": 1.1898,
696
+ "step": 190
697
+ },
698
+ {
699
+ "epoch": 1.6991150442477876,
700
+ "grad_norm": 50.869197845458984,
701
+ "learning_rate": 2.5081967213114754e-05,
702
+ "loss": 1.2291,
703
+ "step": 192
704
+ },
705
+ {
706
+ "epoch": 1.7168141592920354,
707
+ "grad_norm": 81.57111358642578,
708
+ "learning_rate": 2.4754098360655738e-05,
709
+ "loss": 1.1021,
710
+ "step": 194
711
+ },
712
+ {
713
+ "epoch": 1.7345132743362832,
714
+ "grad_norm": 28.92418098449707,
715
+ "learning_rate": 2.442622950819672e-05,
716
+ "loss": 0.9841,
717
+ "step": 196
718
+ },
719
+ {
720
+ "epoch": 1.752212389380531,
721
+ "grad_norm": 23.563941955566406,
722
+ "learning_rate": 2.4098360655737705e-05,
723
+ "loss": 1.4778,
724
+ "step": 198
725
+ },
726
+ {
727
+ "epoch": 1.7699115044247788,
728
+ "grad_norm": 39.69824981689453,
729
+ "learning_rate": 2.377049180327869e-05,
730
+ "loss": 1.0115,
731
+ "step": 200
732
+ },
733
+ {
734
+ "epoch": 1.7876106194690267,
735
+ "grad_norm": 503.5774841308594,
736
+ "learning_rate": 2.3442622950819672e-05,
737
+ "loss": 1.3526,
738
+ "step": 202
739
+ },
740
+ {
741
+ "epoch": 1.8053097345132745,
742
+ "grad_norm": 47.411170959472656,
743
+ "learning_rate": 2.311475409836066e-05,
744
+ "loss": 1.0035,
745
+ "step": 204
746
+ },
747
+ {
748
+ "epoch": 1.823008849557522,
749
+ "grad_norm": 60.6224479675293,
750
+ "learning_rate": 2.278688524590164e-05,
751
+ "loss": 1.2126,
752
+ "step": 206
753
+ },
754
+ {
755
+ "epoch": 1.8407079646017699,
756
+ "grad_norm": 51.3713264465332,
757
+ "learning_rate": 2.2459016393442626e-05,
758
+ "loss": 1.2112,
759
+ "step": 208
760
+ },
761
+ {
762
+ "epoch": 1.8584070796460177,
763
+ "grad_norm": 43.3449821472168,
764
+ "learning_rate": 2.2131147540983607e-05,
765
+ "loss": 1.1825,
766
+ "step": 210
767
+ },
768
+ {
769
+ "epoch": 1.8761061946902655,
770
+ "grad_norm": 51.22021484375,
771
+ "learning_rate": 2.1803278688524594e-05,
772
+ "loss": 1.0688,
773
+ "step": 212
774
+ },
775
+ {
776
+ "epoch": 1.893805309734513,
777
+ "grad_norm": 47.7821044921875,
778
+ "learning_rate": 2.1475409836065574e-05,
779
+ "loss": 1.1192,
780
+ "step": 214
781
+ },
782
+ {
783
+ "epoch": 1.911504424778761,
784
+ "grad_norm": 26.08221435546875,
785
+ "learning_rate": 2.114754098360656e-05,
786
+ "loss": 0.9688,
787
+ "step": 216
788
+ },
789
+ {
790
+ "epoch": 1.9292035398230087,
791
+ "grad_norm": 35.32424545288086,
792
+ "learning_rate": 2.081967213114754e-05,
793
+ "loss": 0.96,
794
+ "step": 218
795
+ },
796
+ {
797
+ "epoch": 1.9469026548672566,
798
+ "grad_norm": 33.47419357299805,
799
+ "learning_rate": 2.0491803278688525e-05,
800
+ "loss": 1.237,
801
+ "step": 220
802
+ },
803
+ {
804
+ "epoch": 1.9646017699115044,
805
+ "grad_norm": 54.51090621948242,
806
+ "learning_rate": 2.0163934426229508e-05,
807
+ "loss": 1.0218,
808
+ "step": 222
809
+ },
810
+ {
811
+ "epoch": 1.9823008849557522,
812
+ "grad_norm": 46.36600875854492,
813
+ "learning_rate": 1.9836065573770492e-05,
814
+ "loss": 1.0245,
815
+ "step": 224
816
+ },
817
+ {
818
+ "epoch": 2.0,
819
+ "grad_norm": 39.30439758300781,
820
+ "learning_rate": 1.9508196721311475e-05,
821
+ "loss": 1.0934,
822
+ "step": 226
823
+ },
824
+ {
825
+ "epoch": 2.0,
826
+ "eval_loss": 1.2027697563171387,
827
+ "eval_map": 0.186,
828
+ "eval_map_50": 0.3347,
829
+ "eval_map_75": 0.2021,
830
+ "eval_map_large": 0.2317,
831
+ "eval_map_medium": 0.1023,
832
+ "eval_map_per_class": 0.186,
833
+ "eval_map_small": 0.0,
834
+ "eval_mar_1": 0.2299,
835
+ "eval_mar_10": 0.4979,
836
+ "eval_mar_100": 0.5718,
837
+ "eval_mar_100_per_class": 0.5718,
838
+ "eval_mar_large": 0.6669,
839
+ "eval_mar_medium": 0.3297,
840
+ "eval_mar_small": 0.0,
841
+ "eval_runtime": 6.8411,
842
+ "eval_samples_per_second": 14.617,
843
+ "eval_steps_per_second": 1.023,
844
+ "step": 226
845
+ },
846
+ {
847
+ "epoch": 2.017699115044248,
848
+ "grad_norm": 64.81815338134766,
849
+ "learning_rate": 1.918032786885246e-05,
850
+ "loss": 0.9753,
851
+ "step": 228
852
+ },
853
+ {
854
+ "epoch": 2.0353982300884956,
855
+ "grad_norm": 33.4212532043457,
856
+ "learning_rate": 1.8852459016393442e-05,
857
+ "loss": 1.0836,
858
+ "step": 230
859
+ },
860
+ {
861
+ "epoch": 2.0530973451327434,
862
+ "grad_norm": 43.58014678955078,
863
+ "learning_rate": 1.8524590163934426e-05,
864
+ "loss": 0.9376,
865
+ "step": 232
866
+ },
867
+ {
868
+ "epoch": 2.0707964601769913,
869
+ "grad_norm": 49.71245574951172,
870
+ "learning_rate": 1.8196721311475413e-05,
871
+ "loss": 1.088,
872
+ "step": 234
873
+ },
874
+ {
875
+ "epoch": 2.088495575221239,
876
+ "grad_norm": 37.22849655151367,
877
+ "learning_rate": 1.7868852459016393e-05,
878
+ "loss": 1.1392,
879
+ "step": 236
880
+ },
881
+ {
882
+ "epoch": 2.106194690265487,
883
+ "grad_norm": 37.5290412902832,
884
+ "learning_rate": 1.754098360655738e-05,
885
+ "loss": 1.0028,
886
+ "step": 238
887
+ },
888
+ {
889
+ "epoch": 2.1238938053097347,
890
+ "grad_norm": 39.413692474365234,
891
+ "learning_rate": 1.721311475409836e-05,
892
+ "loss": 1.0709,
893
+ "step": 240
894
+ },
895
+ {
896
+ "epoch": 2.1415929203539825,
897
+ "grad_norm": 58.448463439941406,
898
+ "learning_rate": 1.6885245901639347e-05,
899
+ "loss": 1.1094,
900
+ "step": 242
901
+ },
902
+ {
903
+ "epoch": 2.15929203539823,
904
+ "grad_norm": 49.975345611572266,
905
+ "learning_rate": 1.6557377049180328e-05,
906
+ "loss": 1.0425,
907
+ "step": 244
908
+ },
909
+ {
910
+ "epoch": 2.1769911504424777,
911
+ "grad_norm": 40.28168487548828,
912
+ "learning_rate": 1.6229508196721314e-05,
913
+ "loss": 1.1666,
914
+ "step": 246
915
+ },
916
+ {
917
+ "epoch": 2.1946902654867255,
918
+ "grad_norm": 123.18711853027344,
919
+ "learning_rate": 1.5901639344262295e-05,
920
+ "loss": 0.9255,
921
+ "step": 248
922
+ },
923
+ {
924
+ "epoch": 2.2123893805309733,
925
+ "grad_norm": 35.56529998779297,
926
+ "learning_rate": 1.557377049180328e-05,
927
+ "loss": 0.9732,
928
+ "step": 250
929
+ },
930
+ {
931
+ "epoch": 2.230088495575221,
932
+ "grad_norm": 48.11013412475586,
933
+ "learning_rate": 1.5245901639344262e-05,
934
+ "loss": 0.9164,
935
+ "step": 252
936
+ },
937
+ {
938
+ "epoch": 2.247787610619469,
939
+ "grad_norm": 33.767940521240234,
940
+ "learning_rate": 1.4918032786885247e-05,
941
+ "loss": 0.9673,
942
+ "step": 254
943
+ },
944
+ {
945
+ "epoch": 2.265486725663717,
946
+ "grad_norm": 105.49449157714844,
947
+ "learning_rate": 1.4590163934426229e-05,
948
+ "loss": 0.9585,
949
+ "step": 256
950
+ },
951
+ {
952
+ "epoch": 2.2831858407079646,
953
+ "grad_norm": 77.859619140625,
954
+ "learning_rate": 1.4262295081967214e-05,
955
+ "loss": 0.9652,
956
+ "step": 258
957
+ },
958
+ {
959
+ "epoch": 2.3008849557522124,
960
+ "grad_norm": 30.470129013061523,
961
+ "learning_rate": 1.3934426229508196e-05,
962
+ "loss": 0.9409,
963
+ "step": 260
964
+ },
965
+ {
966
+ "epoch": 2.3185840707964602,
967
+ "grad_norm": 25.803863525390625,
968
+ "learning_rate": 1.3606557377049181e-05,
969
+ "loss": 0.8861,
970
+ "step": 262
971
+ },
972
+ {
973
+ "epoch": 2.336283185840708,
974
+ "grad_norm": 19.344310760498047,
975
+ "learning_rate": 1.3278688524590163e-05,
976
+ "loss": 1.0303,
977
+ "step": 264
978
+ },
979
+ {
980
+ "epoch": 2.353982300884956,
981
+ "grad_norm": 30.006305694580078,
982
+ "learning_rate": 1.2950819672131149e-05,
983
+ "loss": 1.0346,
984
+ "step": 266
985
+ },
986
+ {
987
+ "epoch": 2.3716814159292037,
988
+ "grad_norm": 53.978092193603516,
989
+ "learning_rate": 1.2622950819672132e-05,
990
+ "loss": 0.9385,
991
+ "step": 268
992
+ },
993
+ {
994
+ "epoch": 2.3893805309734515,
995
+ "grad_norm": 40.302066802978516,
996
+ "learning_rate": 1.2295081967213116e-05,
997
+ "loss": 0.9354,
998
+ "step": 270
999
+ },
1000
+ {
1001
+ "epoch": 2.4070796460176993,
1002
+ "grad_norm": 41.98043441772461,
1003
+ "learning_rate": 1.19672131147541e-05,
1004
+ "loss": 0.9648,
1005
+ "step": 272
1006
+ },
1007
+ {
1008
+ "epoch": 2.4247787610619467,
1009
+ "grad_norm": 18.923696517944336,
1010
+ "learning_rate": 1.1639344262295083e-05,
1011
+ "loss": 0.8274,
1012
+ "step": 274
1013
+ },
1014
+ {
1015
+ "epoch": 2.442477876106195,
1016
+ "grad_norm": 115.89277648925781,
1017
+ "learning_rate": 1.1311475409836065e-05,
1018
+ "loss": 0.905,
1019
+ "step": 276
1020
+ },
1021
+ {
1022
+ "epoch": 2.4601769911504423,
1023
+ "grad_norm": 45.129112243652344,
1024
+ "learning_rate": 1.0983606557377048e-05,
1025
+ "loss": 1.116,
1026
+ "step": 278
1027
+ },
1028
+ {
1029
+ "epoch": 2.47787610619469,
1030
+ "grad_norm": 40.201717376708984,
1031
+ "learning_rate": 1.0655737704918032e-05,
1032
+ "loss": 0.964,
1033
+ "step": 280
1034
+ },
1035
+ {
1036
+ "epoch": 2.495575221238938,
1037
+ "grad_norm": 53.22237777709961,
1038
+ "learning_rate": 1.0327868852459017e-05,
1039
+ "loss": 0.9607,
1040
+ "step": 282
1041
+ },
1042
+ {
1043
+ "epoch": 2.5132743362831858,
1044
+ "grad_norm": 49.16684341430664,
1045
+ "learning_rate": 1e-05,
1046
+ "loss": 1.0343,
1047
+ "step": 284
1048
+ },
1049
+ {
1050
+ "epoch": 2.5309734513274336,
1051
+ "grad_norm": 99.20750427246094,
1052
+ "learning_rate": 9.672131147540984e-06,
1053
+ "loss": 1.122,
1054
+ "step": 286
1055
+ },
1056
+ {
1057
+ "epoch": 2.5486725663716814,
1058
+ "grad_norm": 24.961946487426758,
1059
+ "learning_rate": 9.344262295081968e-06,
1060
+ "loss": 0.9803,
1061
+ "step": 288
1062
+ },
1063
+ {
1064
+ "epoch": 2.566371681415929,
1065
+ "grad_norm": 37.47533416748047,
1066
+ "learning_rate": 9.016393442622952e-06,
1067
+ "loss": 1.0125,
1068
+ "step": 290
1069
+ },
1070
+ {
1071
+ "epoch": 2.584070796460177,
1072
+ "grad_norm": 25.763242721557617,
1073
+ "learning_rate": 8.688524590163935e-06,
1074
+ "loss": 0.9614,
1075
+ "step": 292
1076
+ },
1077
+ {
1078
+ "epoch": 2.601769911504425,
1079
+ "grad_norm": 25.674652099609375,
1080
+ "learning_rate": 8.360655737704919e-06,
1081
+ "loss": 0.8985,
1082
+ "step": 294
1083
+ },
1084
+ {
1085
+ "epoch": 2.6194690265486726,
1086
+ "grad_norm": 26.32975196838379,
1087
+ "learning_rate": 8.032786885245902e-06,
1088
+ "loss": 0.9328,
1089
+ "step": 296
1090
+ },
1091
+ {
1092
+ "epoch": 2.6371681415929205,
1093
+ "grad_norm": 37.20893096923828,
1094
+ "learning_rate": 7.704918032786886e-06,
1095
+ "loss": 0.8681,
1096
+ "step": 298
1097
+ },
1098
+ {
1099
+ "epoch": 2.6548672566371683,
1100
+ "grad_norm": 21.895004272460938,
1101
+ "learning_rate": 7.3770491803278695e-06,
1102
+ "loss": 1.0877,
1103
+ "step": 300
1104
+ },
1105
+ {
1106
+ "epoch": 2.672566371681416,
1107
+ "grad_norm": 433.6007080078125,
1108
+ "learning_rate": 7.049180327868852e-06,
1109
+ "loss": 1.02,
1110
+ "step": 302
1111
+ },
1112
+ {
1113
+ "epoch": 2.6902654867256635,
1114
+ "grad_norm": 51.63364028930664,
1115
+ "learning_rate": 6.721311475409836e-06,
1116
+ "loss": 0.9108,
1117
+ "step": 304
1118
+ },
1119
+ {
1120
+ "epoch": 2.7079646017699117,
1121
+ "grad_norm": 31.832887649536133,
1122
+ "learning_rate": 6.393442622950819e-06,
1123
+ "loss": 1.2122,
1124
+ "step": 306
1125
+ },
1126
+ {
1127
+ "epoch": 2.725663716814159,
1128
+ "grad_norm": 52.633541107177734,
1129
+ "learning_rate": 6.065573770491804e-06,
1130
+ "loss": 1.0646,
1131
+ "step": 308
1132
+ },
1133
+ {
1134
+ "epoch": 2.7433628318584073,
1135
+ "grad_norm": 105.65243530273438,
1136
+ "learning_rate": 5.737704918032787e-06,
1137
+ "loss": 0.9322,
1138
+ "step": 310
1139
+ },
1140
+ {
1141
+ "epoch": 2.7610619469026547,
1142
+ "grad_norm": 23.349111557006836,
1143
+ "learning_rate": 5.409836065573771e-06,
1144
+ "loss": 1.0782,
1145
+ "step": 312
1146
+ },
1147
+ {
1148
+ "epoch": 2.7787610619469025,
1149
+ "grad_norm": 59.555641174316406,
1150
+ "learning_rate": 5.0819672131147545e-06,
1151
+ "loss": 0.8693,
1152
+ "step": 314
1153
+ },
1154
+ {
1155
+ "epoch": 2.7964601769911503,
1156
+ "grad_norm": 36.903785705566406,
1157
+ "learning_rate": 4.754098360655738e-06,
1158
+ "loss": 0.8108,
1159
+ "step": 316
1160
+ },
1161
+ {
1162
+ "epoch": 2.814159292035398,
1163
+ "grad_norm": 30.89893913269043,
1164
+ "learning_rate": 4.426229508196722e-06,
1165
+ "loss": 0.9355,
1166
+ "step": 318
1167
+ },
1168
+ {
1169
+ "epoch": 2.831858407079646,
1170
+ "grad_norm": 109.97364807128906,
1171
+ "learning_rate": 4.098360655737704e-06,
1172
+ "loss": 0.9326,
1173
+ "step": 320
1174
+ },
1175
+ {
1176
+ "epoch": 2.849557522123894,
1177
+ "grad_norm": 38.92977523803711,
1178
+ "learning_rate": 3.770491803278689e-06,
1179
+ "loss": 1.0016,
1180
+ "step": 322
1181
+ },
1182
+ {
1183
+ "epoch": 2.8672566371681416,
1184
+ "grad_norm": 28.991559982299805,
1185
+ "learning_rate": 3.4426229508196724e-06,
1186
+ "loss": 0.9364,
1187
+ "step": 324
1188
+ },
1189
+ {
1190
+ "epoch": 2.8849557522123894,
1191
+ "grad_norm": 49.69723892211914,
1192
+ "learning_rate": 3.114754098360656e-06,
1193
+ "loss": 1.056,
1194
+ "step": 326
1195
+ },
1196
+ {
1197
+ "epoch": 2.9026548672566372,
1198
+ "grad_norm": 50.34890365600586,
1199
+ "learning_rate": 2.7868852459016396e-06,
1200
+ "loss": 0.8493,
1201
+ "step": 328
1202
+ },
1203
+ {
1204
+ "epoch": 2.920353982300885,
1205
+ "grad_norm": 29.193132400512695,
1206
+ "learning_rate": 2.459016393442623e-06,
1207
+ "loss": 0.9151,
1208
+ "step": 330
1209
+ },
1210
+ {
1211
+ "epoch": 2.938053097345133,
1212
+ "grad_norm": 120.2429428100586,
1213
+ "learning_rate": 2.1311475409836067e-06,
1214
+ "loss": 0.8943,
1215
+ "step": 332
1216
+ },
1217
+ {
1218
+ "epoch": 2.9557522123893807,
1219
+ "grad_norm": 84.27303314208984,
1220
+ "learning_rate": 1.8032786885245903e-06,
1221
+ "loss": 0.9302,
1222
+ "step": 334
1223
+ },
1224
+ {
1225
+ "epoch": 2.9734513274336285,
1226
+ "grad_norm": 19.526248931884766,
1227
+ "learning_rate": 1.4754098360655739e-06,
1228
+ "loss": 0.8956,
1229
+ "step": 336
1230
+ },
1231
+ {
1232
+ "epoch": 2.991150442477876,
1233
+ "grad_norm": 51.6258430480957,
1234
+ "learning_rate": 1.1475409836065575e-06,
1235
+ "loss": 0.8992,
1236
+ "step": 338
1237
+ },
1238
+ {
1239
+ "epoch": 3.0,
1240
+ "eval_loss": 0.8856489658355713,
1241
+ "eval_map": 0.1595,
1242
+ "eval_map_50": 0.2552,
1243
+ "eval_map_75": 0.1847,
1244
+ "eval_map_large": 0.1961,
1245
+ "eval_map_medium": 0.0755,
1246
+ "eval_map_per_class": 0.1595,
1247
+ "eval_map_small": 0.0,
1248
+ "eval_mar_1": 0.2338,
1249
+ "eval_mar_10": 0.5162,
1250
+ "eval_mar_100": 0.6897,
1251
+ "eval_mar_100_per_class": 0.6897,
1252
+ "eval_mar_large": 0.7544,
1253
+ "eval_mar_medium": 0.5297,
1254
+ "eval_mar_small": 0.0,
1255
+ "eval_runtime": 6.7061,
1256
+ "eval_samples_per_second": 14.912,
1257
+ "eval_steps_per_second": 1.044,
1258
+ "step": 339
1259
+ }
1260
+ ],
1261
+ "logging_steps": 2,
1262
+ "max_steps": 339,
1263
+ "num_input_tokens_seen": 0,
1264
+ "num_train_epochs": 3,
1265
+ "save_steps": 500,
1266
+ "stateful_callbacks": {
1267
+ "EarlyStoppingCallback": {
1268
+ "args": {
1269
+ "early_stopping_patience": 5,
1270
+ "early_stopping_threshold": 0.01
1271
+ },
1272
+ "attributes": {
1273
+ "early_stopping_patience_counter": 0
1274
+ }
1275
+ },
1276
+ "TrainerControl": {
1277
+ "args": {
1278
+ "should_epoch_stop": false,
1279
+ "should_evaluate": false,
1280
+ "should_log": false,
1281
+ "should_save": true,
1282
+ "should_training_stop": true
1283
+ },
1284
+ "attributes": {}
1285
+ }
1286
+ },
1287
+ "total_flos": 1.05586283531952e+18,
1288
+ "train_batch_size": 8,
1289
+ "trial_name": null,
1290
+ "trial_params": null
1291
+ }
checkpoint-339/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cfe85f8088a851a046fa82abe8f86e125d3ad222308954b0b4b23b7e307e4c9
3
+ size 5176
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/detr-resnet-101",
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": "resnet101",
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": "Face"
42
+ },
43
+ "init_std": 0.02,
44
+ "init_xavier_std": 1.0,
45
+ "is_encoder_decoder": true,
46
+ "label2id": {
47
+ "Face": 0
48
+ },
49
+ "mask_loss_coefficient": 1,
50
+ "max_position_embeddings": 1024,
51
+ "model_type": "detr",
52
+ "num_channels": 3,
53
+ "num_hidden_layers": 6,
54
+ "num_queries": 100,
55
+ "position_embedding_type": "sine",
56
+ "scale_embedding": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.41.0",
59
+ "use_pretrained_backbone": true,
60
+ "use_timm_backbone": true
61
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659494bcede8bf5d6bc7b89639fa453c833c85798404c46ee240c337cf6a4702
3
+ size 242704552
preprocessor_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "annotations",
5
+ "return_segmentation_masks",
6
+ "masks_path",
7
+ "do_resize",
8
+ "size",
9
+ "resample",
10
+ "do_rescale",
11
+ "rescale_factor",
12
+ "do_normalize",
13
+ "do_convert_annotations",
14
+ "image_mean",
15
+ "image_std",
16
+ "do_pad",
17
+ "format",
18
+ "return_tensors",
19
+ "data_format",
20
+ "input_data_format"
21
+ ],
22
+ "do_convert_annotations": true,
23
+ "do_normalize": true,
24
+ "do_pad": false,
25
+ "do_rescale": true,
26
+ "do_resize": false,
27
+ "format": "coco_detection",
28
+ "image_mean": [
29
+ 0.485,
30
+ 0.456,
31
+ 0.406
32
+ ],
33
+ "image_processor_type": "DetrImageProcessor",
34
+ "image_std": [
35
+ 0.229,
36
+ 0.224,
37
+ 0.225
38
+ ],
39
+ "resample": 2,
40
+ "rescale_factor": 0.00392156862745098,
41
+ "size": {
42
+ "longest_edge": 600
43
+ }
44
+ }
runs/May24_15-26-14_r-rileybol-face-detection-v1-m1cjgjqo-4d503-pcn86/events.out.tfevents.1716564375.r-rileybol-face-detection-v1-m1cjgjqo-4d503-pcn86.158.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:650baf45efe46043cbfede027d50ba875b35a4c6521d7b8a97efb7c78ab7c0e6
3
- size 5547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa0287b79f9e132c0008e70765ad115f5b5931118867fdc8e15e33762477fe8
3
+ size 44307
runs/May24_15-26-14_r-rileybol-face-detection-v1-m1cjgjqo-4d503-pcn86/events.out.tfevents.1716564659.r-rileybol-face-detection-v1-m1cjgjqo-4d503-pcn86.158.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9baca0204ec61d808019137a46b5aa916bf1fd2bdb52a91fcc532c3287b682cd
3
+ size 1094
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cfe85f8088a851a046fa82abe8f86e125d3ad222308954b0b4b23b7e307e4c9
3
+ size 5176
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-1hkeo-o33ms/autotrain-data",
3
+ "model": "facebook/detr-resnet-101",
4
+ "username": "rileybol",
5
+ "lr": 5e-05,
6
+ "epochs": 3,
7
+ "batch_size": 8,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "logging_steps": -1,
18
+ "project_name": "autotrain-1hkeo-o33ms",
19
+ "auto_find_batch_size": false,
20
+ "mixed_precision": "fp16",
21
+ "save_total_limit": 1,
22
+ "push_to_hub": true,
23
+ "evaluation_strategy": "epoch",
24
+ "image_column": "autotrain_image",
25
+ "objects_column": "autotrain_objects",
26
+ "log": "tensorboard",
27
+ "image_square_size": 600,
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }