sam1120 commited on
Commit
0973ef9
1 Parent(s): ff0855c

Training in progress, step 200

Browse files
checkpoint-200/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nvidia/mit-b0",
3
+ "architectures": [
4
+ "SegformerForSemanticSegmentation"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout_prob": 0.1,
8
+ "decoder_hidden_size": 256,
9
+ "depths": [
10
+ 2,
11
+ 2,
12
+ 2,
13
+ 2
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
+ 32,
26
+ 64,
27
+ 160,
28
+ 256
29
+ ],
30
+ "id2label": {
31
+ "0": "unlabeled",
32
+ "1": "safe",
33
+ "2": "unsafe"
34
+ },
35
+ "image_size": 224,
36
+ "initializer_range": 0.02,
37
+ "label2id": {
38
+ "safe": 1,
39
+ "unlabeled": 0,
40
+ "unsafe": 2
41
+ },
42
+ "layer_norm_eps": 1e-06,
43
+ "mlp_ratios": [
44
+ 4,
45
+ 4,
46
+ 4,
47
+ 4
48
+ ],
49
+ "model_type": "segformer",
50
+ "num_attention_heads": [
51
+ 1,
52
+ 2,
53
+ 5,
54
+ 8
55
+ ],
56
+ "num_channels": 3,
57
+ "num_encoder_blocks": 4,
58
+ "patch_sizes": [
59
+ 7,
60
+ 3,
61
+ 3,
62
+ 3
63
+ ],
64
+ "reshape_last_stage": true,
65
+ "semantic_loss_ignore_index": 255,
66
+ "sr_ratios": [
67
+ 8,
68
+ 4,
69
+ 2,
70
+ 1
71
+ ],
72
+ "strides": [
73
+ 4,
74
+ 2,
75
+ 2,
76
+ 2
77
+ ],
78
+ "torch_dtype": "float32",
79
+ "transformers_version": "4.30.2"
80
+ }
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80104f9520347616bd14d75e363912645e12eb8065edf76367209ee91dcaf73f
3
+ size 29838853
checkpoint-200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59582f6e1b5e6baee90f035b3a76f3f040eb6460e794744b1ea3d93a2712ee2
3
+ size 14932813
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f22d22cb8935577b30011ec0e471351c5410dcd5625009ca150f3cf9873b425
3
+ size 14575
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809d6d0e1716982495dc370004559ed694149a6679e27266f39e5121a6e51032
3
+ size 627
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,1556 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7494363188743591,
3
+ "best_model_checkpoint": "/robodata/smodak/Projects/nspl/scripts/terrainseg/training/models/safety-utcustom-train-SF30-RGB-b0/checkpoint-200",
4
+ "epoch": 100.0,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.5,
12
+ "learning_rate": 7.5e-07,
13
+ "loss": 1.1677,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 1.5e-06,
19
+ "loss": 1.1594,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 1.5,
24
+ "learning_rate": 2.25e-06,
25
+ "loss": 1.1676,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "learning_rate": 3e-06,
31
+ "loss": 1.1627,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 2.5,
36
+ "learning_rate": 3.75e-06,
37
+ "loss": 1.1604,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 4.5e-06,
43
+ "loss": 1.1658,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 3.5,
48
+ "learning_rate": 5.2500000000000006e-06,
49
+ "loss": 1.1583,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6e-06,
55
+ "loss": 1.1687,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 4.5,
60
+ "learning_rate": 6.75e-06,
61
+ "loss": 1.1569,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 5.0,
66
+ "learning_rate": 7.5e-06,
67
+ "loss": 1.1527,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "eval_accuracy_safe": 0.7703764811759412,
73
+ "eval_accuracy_unlabeled": NaN,
74
+ "eval_accuracy_unsafe": 0.14652629277186402,
75
+ "eval_iou_safe": 0.030663997549793695,
76
+ "eval_iou_unlabeled": 0.0,
77
+ "eval_iou_unsafe": 0.14642944151194123,
78
+ "eval_loss": 1.1084816455841064,
79
+ "eval_mean_accuracy": 0.4584513869739026,
80
+ "eval_mean_iou": 0.059031146353911636,
81
+ "eval_overall_accuracy": 0.16635894775390625,
82
+ "eval_runtime": 1.4751,
83
+ "eval_samples_per_second": 5.423,
84
+ "eval_steps_per_second": 0.678,
85
+ "step": 10
86
+ },
87
+ {
88
+ "epoch": 5.5,
89
+ "learning_rate": 8.25e-06,
90
+ "loss": 1.1521,
91
+ "step": 11
92
+ },
93
+ {
94
+ "epoch": 6.0,
95
+ "learning_rate": 9e-06,
96
+ "loss": 1.1492,
97
+ "step": 12
98
+ },
99
+ {
100
+ "epoch": 6.5,
101
+ "learning_rate": 8.960526315789474e-06,
102
+ "loss": 1.1456,
103
+ "step": 13
104
+ },
105
+ {
106
+ "epoch": 7.0,
107
+ "learning_rate": 8.921052631578947e-06,
108
+ "loss": 1.1433,
109
+ "step": 14
110
+ },
111
+ {
112
+ "epoch": 7.5,
113
+ "learning_rate": 8.881578947368421e-06,
114
+ "loss": 1.1379,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 8.0,
119
+ "learning_rate": 8.842105263157895e-06,
120
+ "loss": 1.1431,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 8.5,
125
+ "learning_rate": 8.80263157894737e-06,
126
+ "loss": 1.1302,
127
+ "step": 17
128
+ },
129
+ {
130
+ "epoch": 9.0,
131
+ "learning_rate": 8.763157894736842e-06,
132
+ "loss": 1.1379,
133
+ "step": 18
134
+ },
135
+ {
136
+ "epoch": 9.5,
137
+ "learning_rate": 8.723684210526316e-06,
138
+ "loss": 1.1259,
139
+ "step": 19
140
+ },
141
+ {
142
+ "epoch": 10.0,
143
+ "learning_rate": 8.68421052631579e-06,
144
+ "loss": 1.1326,
145
+ "step": 20
146
+ },
147
+ {
148
+ "epoch": 10.0,
149
+ "eval_accuracy_safe": 0.9694915254237289,
150
+ "eval_accuracy_unlabeled": NaN,
151
+ "eval_accuracy_unsafe": 0.24695220149698446,
152
+ "eval_iou_safe": 0.04189444073553146,
153
+ "eval_iou_unlabeled": 0.0,
154
+ "eval_iou_unsafe": 0.24695195825231817,
155
+ "eval_loss": 1.1090760231018066,
156
+ "eval_mean_accuracy": 0.6082218634603567,
157
+ "eval_mean_iou": 0.09628213299594988,
158
+ "eval_overall_accuracy": 0.26992225646972656,
159
+ "eval_runtime": 1.192,
160
+ "eval_samples_per_second": 6.711,
161
+ "eval_steps_per_second": 0.839,
162
+ "step": 20
163
+ },
164
+ {
165
+ "epoch": 10.5,
166
+ "learning_rate": 8.644736842105263e-06,
167
+ "loss": 1.1296,
168
+ "step": 21
169
+ },
170
+ {
171
+ "epoch": 11.0,
172
+ "learning_rate": 8.605263157894737e-06,
173
+ "loss": 1.1125,
174
+ "step": 22
175
+ },
176
+ {
177
+ "epoch": 11.5,
178
+ "learning_rate": 8.56578947368421e-06,
179
+ "loss": 1.1224,
180
+ "step": 23
181
+ },
182
+ {
183
+ "epoch": 12.0,
184
+ "learning_rate": 8.526315789473683e-06,
185
+ "loss": 1.1105,
186
+ "step": 24
187
+ },
188
+ {
189
+ "epoch": 12.5,
190
+ "learning_rate": 8.486842105263159e-06,
191
+ "loss": 1.108,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 13.0,
196
+ "learning_rate": 8.447368421052632e-06,
197
+ "loss": 1.1265,
198
+ "step": 26
199
+ },
200
+ {
201
+ "epoch": 13.5,
202
+ "learning_rate": 8.407894736842106e-06,
203
+ "loss": 1.1047,
204
+ "step": 27
205
+ },
206
+ {
207
+ "epoch": 14.0,
208
+ "learning_rate": 8.36842105263158e-06,
209
+ "loss": 1.115,
210
+ "step": 28
211
+ },
212
+ {
213
+ "epoch": 14.5,
214
+ "learning_rate": 8.328947368421052e-06,
215
+ "loss": 1.092,
216
+ "step": 29
217
+ },
218
+ {
219
+ "epoch": 15.0,
220
+ "learning_rate": 8.289473684210526e-06,
221
+ "loss": 1.0981,
222
+ "step": 30
223
+ },
224
+ {
225
+ "epoch": 15.0,
226
+ "eval_accuracy_safe": 0.992200389980501,
227
+ "eval_accuracy_unlabeled": NaN,
228
+ "eval_accuracy_unsafe": 0.40550470282425555,
229
+ "eval_iou_safe": 0.053544543556037626,
230
+ "eval_iou_unlabeled": 0.0,
231
+ "eval_iou_unsafe": 0.40550470282425555,
232
+ "eval_loss": 1.0979702472686768,
233
+ "eval_mean_accuracy": 0.6988525464023783,
234
+ "eval_mean_iou": 0.15301641546009773,
235
+ "eval_overall_accuracy": 0.42415618896484375,
236
+ "eval_runtime": 1.213,
237
+ "eval_samples_per_second": 6.595,
238
+ "eval_steps_per_second": 0.824,
239
+ "step": 30
240
+ },
241
+ {
242
+ "epoch": 15.5,
243
+ "learning_rate": 8.25e-06,
244
+ "loss": 1.0895,
245
+ "step": 31
246
+ },
247
+ {
248
+ "epoch": 16.0,
249
+ "learning_rate": 8.210526315789473e-06,
250
+ "loss": 1.0659,
251
+ "step": 32
252
+ },
253
+ {
254
+ "epoch": 16.5,
255
+ "learning_rate": 8.171052631578947e-06,
256
+ "loss": 1.0868,
257
+ "step": 33
258
+ },
259
+ {
260
+ "epoch": 17.0,
261
+ "learning_rate": 8.131578947368421e-06,
262
+ "loss": 1.079,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 17.5,
267
+ "learning_rate": 8.092105263157896e-06,
268
+ "loss": 1.0884,
269
+ "step": 35
270
+ },
271
+ {
272
+ "epoch": 18.0,
273
+ "learning_rate": 8.052631578947368e-06,
274
+ "loss": 1.0499,
275
+ "step": 36
276
+ },
277
+ {
278
+ "epoch": 18.5,
279
+ "learning_rate": 8.013157894736842e-06,
280
+ "loss": 1.0726,
281
+ "step": 37
282
+ },
283
+ {
284
+ "epoch": 19.0,
285
+ "learning_rate": 7.973684210526316e-06,
286
+ "loss": 1.0718,
287
+ "step": 38
288
+ },
289
+ {
290
+ "epoch": 19.5,
291
+ "learning_rate": 7.934210526315789e-06,
292
+ "loss": 1.0653,
293
+ "step": 39
294
+ },
295
+ {
296
+ "epoch": 20.0,
297
+ "learning_rate": 7.894736842105263e-06,
298
+ "loss": 1.086,
299
+ "step": 40
300
+ },
301
+ {
302
+ "epoch": 20.0,
303
+ "eval_accuracy_safe": 0.9926503674816259,
304
+ "eval_accuracy_unlabeled": NaN,
305
+ "eval_accuracy_unsafe": 0.5103054348671892,
306
+ "eval_iou_safe": 0.06444250128047581,
307
+ "eval_iou_unlabeled": 0.0,
308
+ "eval_iou_unsafe": 0.5103054348671892,
309
+ "eval_loss": 1.0822405815124512,
310
+ "eval_mean_accuracy": 0.7514779011744075,
311
+ "eval_mean_iou": 0.19158264538255498,
312
+ "eval_overall_accuracy": 0.525639533996582,
313
+ "eval_runtime": 1.1977,
314
+ "eval_samples_per_second": 6.679,
315
+ "eval_steps_per_second": 0.835,
316
+ "step": 40
317
+ },
318
+ {
319
+ "epoch": 20.5,
320
+ "learning_rate": 7.855263157894737e-06,
321
+ "loss": 1.0638,
322
+ "step": 41
323
+ },
324
+ {
325
+ "epoch": 21.0,
326
+ "learning_rate": 7.815789473684211e-06,
327
+ "loss": 1.0491,
328
+ "step": 42
329
+ },
330
+ {
331
+ "epoch": 21.5,
332
+ "learning_rate": 7.776315789473685e-06,
333
+ "loss": 1.058,
334
+ "step": 43
335
+ },
336
+ {
337
+ "epoch": 22.0,
338
+ "learning_rate": 7.736842105263158e-06,
339
+ "loss": 1.0102,
340
+ "step": 44
341
+ },
342
+ {
343
+ "epoch": 22.5,
344
+ "learning_rate": 7.697368421052632e-06,
345
+ "loss": 1.0523,
346
+ "step": 45
347
+ },
348
+ {
349
+ "epoch": 23.0,
350
+ "learning_rate": 7.657894736842106e-06,
351
+ "loss": 1.0807,
352
+ "step": 46
353
+ },
354
+ {
355
+ "epoch": 23.5,
356
+ "learning_rate": 7.618421052631579e-06,
357
+ "loss": 1.0437,
358
+ "step": 47
359
+ },
360
+ {
361
+ "epoch": 24.0,
362
+ "learning_rate": 7.578947368421053e-06,
363
+ "loss": 1.0586,
364
+ "step": 48
365
+ },
366
+ {
367
+ "epoch": 24.5,
368
+ "learning_rate": 7.539473684210527e-06,
369
+ "loss": 1.036,
370
+ "step": 49
371
+ },
372
+ {
373
+ "epoch": 25.0,
374
+ "learning_rate": 7.5e-06,
375
+ "loss": 1.0466,
376
+ "step": 50
377
+ },
378
+ {
379
+ "epoch": 25.0,
380
+ "eval_accuracy_safe": 0.9901604919754012,
381
+ "eval_accuracy_unlabeled": NaN,
382
+ "eval_accuracy_unsafe": 0.5916703521626885,
383
+ "eval_iou_safe": 0.0760597426269381,
384
+ "eval_iou_unlabeled": 0.0,
385
+ "eval_iou_unsafe": 0.5916525776602614,
386
+ "eval_loss": 1.0541445016860962,
387
+ "eval_mean_accuracy": 0.7909154220690449,
388
+ "eval_mean_iou": 0.2225707734290665,
389
+ "eval_overall_accuracy": 0.6043386459350586,
390
+ "eval_runtime": 1.2115,
391
+ "eval_samples_per_second": 6.603,
392
+ "eval_steps_per_second": 0.825,
393
+ "step": 50
394
+ },
395
+ {
396
+ "epoch": 25.5,
397
+ "learning_rate": 7.460526315789474e-06,
398
+ "loss": 1.0143,
399
+ "step": 51
400
+ },
401
+ {
402
+ "epoch": 26.0,
403
+ "learning_rate": 7.421052631578948e-06,
404
+ "loss": 1.0743,
405
+ "step": 52
406
+ },
407
+ {
408
+ "epoch": 26.5,
409
+ "learning_rate": 7.381578947368421e-06,
410
+ "loss": 1.0126,
411
+ "step": 53
412
+ },
413
+ {
414
+ "epoch": 27.0,
415
+ "learning_rate": 7.342105263157895e-06,
416
+ "loss": 1.0943,
417
+ "step": 54
418
+ },
419
+ {
420
+ "epoch": 27.5,
421
+ "learning_rate": 7.302631578947368e-06,
422
+ "loss": 1.0216,
423
+ "step": 55
424
+ },
425
+ {
426
+ "epoch": 28.0,
427
+ "learning_rate": 7.263157894736842e-06,
428
+ "loss": 1.0104,
429
+ "step": 56
430
+ },
431
+ {
432
+ "epoch": 28.5,
433
+ "learning_rate": 7.223684210526317e-06,
434
+ "loss": 1.0259,
435
+ "step": 57
436
+ },
437
+ {
438
+ "epoch": 29.0,
439
+ "learning_rate": 7.18421052631579e-06,
440
+ "loss": 1.0378,
441
+ "step": 58
442
+ },
443
+ {
444
+ "epoch": 29.5,
445
+ "learning_rate": 7.144736842105263e-06,
446
+ "loss": 1.001,
447
+ "step": 59
448
+ },
449
+ {
450
+ "epoch": 30.0,
451
+ "learning_rate": 7.1052631578947375e-06,
452
+ "loss": 1.0533,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 30.0,
457
+ "eval_accuracy_safe": 0.9862906854657267,
458
+ "eval_accuracy_unlabeled": NaN,
459
+ "eval_accuracy_unsafe": 0.6471891895618873,
460
+ "eval_iou_safe": 0.08607076662094097,
461
+ "eval_iou_unlabeled": 0.0,
462
+ "eval_iou_unsafe": 0.6470951758858802,
463
+ "eval_loss": 1.024947166442871,
464
+ "eval_mean_accuracy": 0.816739937513807,
465
+ "eval_mean_iou": 0.2443886475022737,
466
+ "eval_overall_accuracy": 0.6579694747924805,
467
+ "eval_runtime": 1.2639,
468
+ "eval_samples_per_second": 6.33,
469
+ "eval_steps_per_second": 0.791,
470
+ "step": 60
471
+ },
472
+ {
473
+ "epoch": 30.5,
474
+ "learning_rate": 7.065789473684211e-06,
475
+ "loss": 1.0201,
476
+ "step": 61
477
+ },
478
+ {
479
+ "epoch": 31.0,
480
+ "learning_rate": 7.026315789473684e-06,
481
+ "loss": 0.9958,
482
+ "step": 62
483
+ },
484
+ {
485
+ "epoch": 31.5,
486
+ "learning_rate": 6.986842105263158e-06,
487
+ "loss": 1.0084,
488
+ "step": 63
489
+ },
490
+ {
491
+ "epoch": 32.0,
492
+ "learning_rate": 6.9473684210526315e-06,
493
+ "loss": 1.0021,
494
+ "step": 64
495
+ },
496
+ {
497
+ "epoch": 32.5,
498
+ "learning_rate": 6.907894736842106e-06,
499
+ "loss": 0.9748,
500
+ "step": 65
501
+ },
502
+ {
503
+ "epoch": 33.0,
504
+ "learning_rate": 6.86842105263158e-06,
505
+ "loss": 1.0624,
506
+ "step": 66
507
+ },
508
+ {
509
+ "epoch": 33.5,
510
+ "learning_rate": 6.828947368421053e-06,
511
+ "loss": 0.9931,
512
+ "step": 67
513
+ },
514
+ {
515
+ "epoch": 34.0,
516
+ "learning_rate": 6.7894736842105264e-06,
517
+ "loss": 1.0179,
518
+ "step": 68
519
+ },
520
+ {
521
+ "epoch": 34.5,
522
+ "learning_rate": 6.75e-06,
523
+ "loss": 1.0053,
524
+ "step": 69
525
+ },
526
+ {
527
+ "epoch": 35.0,
528
+ "learning_rate": 6.710526315789474e-06,
529
+ "loss": 0.9779,
530
+ "step": 70
531
+ },
532
+ {
533
+ "epoch": 35.0,
534
+ "eval_accuracy_safe": 0.9770661466926653,
535
+ "eval_accuracy_unlabeled": NaN,
536
+ "eval_accuracy_unsafe": 0.687357977071454,
537
+ "eval_iou_safe": 0.09514260217010605,
538
+ "eval_iou_unlabeled": 0.0,
539
+ "eval_iou_unsafe": 0.6870926801315042,
540
+ "eval_loss": 1.0009846687316895,
541
+ "eval_mean_accuracy": 0.8322120618820597,
542
+ "eval_mean_iou": 0.26074509410053676,
543
+ "eval_overall_accuracy": 0.6965680122375488,
544
+ "eval_runtime": 1.3535,
545
+ "eval_samples_per_second": 5.91,
546
+ "eval_steps_per_second": 0.739,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 35.5,
551
+ "learning_rate": 6.671052631578947e-06,
552
+ "loss": 1.0052,
553
+ "step": 71
554
+ },
555
+ {
556
+ "epoch": 36.0,
557
+ "learning_rate": 6.6315789473684205e-06,
558
+ "loss": 0.9521,
559
+ "step": 72
560
+ },
561
+ {
562
+ "epoch": 36.5,
563
+ "learning_rate": 6.592105263157895e-06,
564
+ "loss": 0.9952,
565
+ "step": 73
566
+ },
567
+ {
568
+ "epoch": 37.0,
569
+ "learning_rate": 6.552631578947369e-06,
570
+ "loss": 1.0184,
571
+ "step": 74
572
+ },
573
+ {
574
+ "epoch": 37.5,
575
+ "learning_rate": 6.513157894736842e-06,
576
+ "loss": 0.9709,
577
+ "step": 75
578
+ },
579
+ {
580
+ "epoch": 38.0,
581
+ "learning_rate": 6.473684210526316e-06,
582
+ "loss": 0.959,
583
+ "step": 76
584
+ },
585
+ {
586
+ "epoch": 38.5,
587
+ "learning_rate": 6.4342105263157896e-06,
588
+ "loss": 0.9497,
589
+ "step": 77
590
+ },
591
+ {
592
+ "epoch": 39.0,
593
+ "learning_rate": 6.394736842105263e-06,
594
+ "loss": 1.0239,
595
+ "step": 78
596
+ },
597
+ {
598
+ "epoch": 39.5,
599
+ "learning_rate": 6.355263157894737e-06,
600
+ "loss": 0.9677,
601
+ "step": 79
602
+ },
603
+ {
604
+ "epoch": 40.0,
605
+ "learning_rate": 6.31578947368421e-06,
606
+ "loss": 0.9161,
607
+ "step": 80
608
+ },
609
+ {
610
+ "epoch": 40.0,
611
+ "eval_accuracy_safe": 0.9634618269086546,
612
+ "eval_accuracy_unlabeled": NaN,
613
+ "eval_accuracy_unsafe": 0.7338942182201074,
614
+ "eval_iou_safe": 0.10909770285762813,
615
+ "eval_iou_unlabeled": 0.0,
616
+ "eval_iou_unsafe": 0.7333943281692789,
617
+ "eval_loss": 0.9695309400558472,
618
+ "eval_mean_accuracy": 0.848678022564381,
619
+ "eval_mean_iou": 0.28083067700896897,
620
+ "eval_overall_accuracy": 0.7411923408508301,
621
+ "eval_runtime": 1.2732,
622
+ "eval_samples_per_second": 6.284,
623
+ "eval_steps_per_second": 0.785,
624
+ "step": 80
625
+ },
626
+ {
627
+ "epoch": 40.5,
628
+ "learning_rate": 6.276315789473684e-06,
629
+ "loss": 0.9493,
630
+ "step": 81
631
+ },
632
+ {
633
+ "epoch": 41.0,
634
+ "learning_rate": 6.236842105263159e-06,
635
+ "loss": 0.9665,
636
+ "step": 82
637
+ },
638
+ {
639
+ "epoch": 41.5,
640
+ "learning_rate": 6.197368421052632e-06,
641
+ "loss": 0.9623,
642
+ "step": 83
643
+ },
644
+ {
645
+ "epoch": 42.0,
646
+ "learning_rate": 6.157894736842105e-06,
647
+ "loss": 0.9901,
648
+ "step": 84
649
+ },
650
+ {
651
+ "epoch": 42.5,
652
+ "learning_rate": 6.118421052631579e-06,
653
+ "loss": 0.9523,
654
+ "step": 85
655
+ },
656
+ {
657
+ "epoch": 43.0,
658
+ "learning_rate": 6.078947368421053e-06,
659
+ "loss": 0.9034,
660
+ "step": 86
661
+ },
662
+ {
663
+ "epoch": 43.5,
664
+ "learning_rate": 6.039473684210526e-06,
665
+ "loss": 0.9353,
666
+ "step": 87
667
+ },
668
+ {
669
+ "epoch": 44.0,
670
+ "learning_rate": 6e-06,
671
+ "loss": 1.0231,
672
+ "step": 88
673
+ },
674
+ {
675
+ "epoch": 44.5,
676
+ "learning_rate": 5.9605263157894735e-06,
677
+ "loss": 0.9537,
678
+ "step": 89
679
+ },
680
+ {
681
+ "epoch": 45.0,
682
+ "learning_rate": 5.921052631578948e-06,
683
+ "loss": 0.9843,
684
+ "step": 90
685
+ },
686
+ {
687
+ "epoch": 45.0,
688
+ "eval_accuracy_safe": 0.9493925303734814,
689
+ "eval_accuracy_unlabeled": NaN,
690
+ "eval_accuracy_unsafe": 0.7768244190295703,
691
+ "eval_iou_safe": 0.1253679077487413,
692
+ "eval_iou_unlabeled": 0.0,
693
+ "eval_iou_unsafe": 0.7759008194701261,
694
+ "eval_loss": 0.940314531326294,
695
+ "eval_mean_accuracy": 0.8631084747015259,
696
+ "eval_mean_iou": 0.3004229090729558,
697
+ "eval_overall_accuracy": 0.7823104858398438,
698
+ "eval_runtime": 1.3253,
699
+ "eval_samples_per_second": 6.036,
700
+ "eval_steps_per_second": 0.755,
701
+ "step": 90
702
+ },
703
+ {
704
+ "epoch": 45.5,
705
+ "learning_rate": 5.881578947368422e-06,
706
+ "loss": 0.9646,
707
+ "step": 91
708
+ },
709
+ {
710
+ "epoch": 46.0,
711
+ "learning_rate": 5.842105263157895e-06,
712
+ "loss": 0.9498,
713
+ "step": 92
714
+ },
715
+ {
716
+ "epoch": 46.5,
717
+ "learning_rate": 5.802631578947368e-06,
718
+ "loss": 0.9407,
719
+ "step": 93
720
+ },
721
+ {
722
+ "epoch": 47.0,
723
+ "learning_rate": 5.7631578947368425e-06,
724
+ "loss": 0.9684,
725
+ "step": 94
726
+ },
727
+ {
728
+ "epoch": 47.5,
729
+ "learning_rate": 5.723684210526316e-06,
730
+ "loss": 0.8967,
731
+ "step": 95
732
+ },
733
+ {
734
+ "epoch": 48.0,
735
+ "learning_rate": 5.684210526315789e-06,
736
+ "loss": 1.0137,
737
+ "step": 96
738
+ },
739
+ {
740
+ "epoch": 48.5,
741
+ "learning_rate": 5.644736842105263e-06,
742
+ "loss": 0.9542,
743
+ "step": 97
744
+ },
745
+ {
746
+ "epoch": 49.0,
747
+ "learning_rate": 5.6052631578947374e-06,
748
+ "loss": 0.8673,
749
+ "step": 98
750
+ },
751
+ {
752
+ "epoch": 49.5,
753
+ "learning_rate": 5.565789473684211e-06,
754
+ "loss": 0.9138,
755
+ "step": 99
756
+ },
757
+ {
758
+ "epoch": 50.0,
759
+ "learning_rate": 5.526315789473685e-06,
760
+ "loss": 0.9568,
761
+ "step": 100
762
+ },
763
+ {
764
+ "epoch": 50.0,
765
+ "eval_accuracy_safe": 0.9190940452977351,
766
+ "eval_accuracy_unlabeled": NaN,
767
+ "eval_accuracy_unsafe": 0.8135083196994605,
768
+ "eval_iou_safe": 0.14123580174066971,
769
+ "eval_iou_unlabeled": 0.0,
770
+ "eval_iou_unsafe": 0.8116862567811934,
771
+ "eval_loss": 0.9070925116539001,
772
+ "eval_mean_accuracy": 0.8663011824985978,
773
+ "eval_mean_iou": 0.3176406861739544,
774
+ "eval_overall_accuracy": 0.8168649673461914,
775
+ "eval_runtime": 1.2557,
776
+ "eval_samples_per_second": 6.371,
777
+ "eval_steps_per_second": 0.796,
778
+ "step": 100
779
+ },
780
+ {
781
+ "epoch": 50.5,
782
+ "learning_rate": 5.486842105263158e-06,
783
+ "loss": 0.9128,
784
+ "step": 101
785
+ },
786
+ {
787
+ "epoch": 51.0,
788
+ "learning_rate": 5.4473684210526315e-06,
789
+ "loss": 0.8691,
790
+ "step": 102
791
+ },
792
+ {
793
+ "epoch": 51.5,
794
+ "learning_rate": 5.407894736842106e-06,
795
+ "loss": 0.9109,
796
+ "step": 103
797
+ },
798
+ {
799
+ "epoch": 52.0,
800
+ "learning_rate": 5.368421052631579e-06,
801
+ "loss": 0.8425,
802
+ "step": 104
803
+ },
804
+ {
805
+ "epoch": 52.5,
806
+ "learning_rate": 5.328947368421052e-06,
807
+ "loss": 0.895,
808
+ "step": 105
809
+ },
810
+ {
811
+ "epoch": 53.0,
812
+ "learning_rate": 5.289473684210527e-06,
813
+ "loss": 0.9433,
814
+ "step": 106
815
+ },
816
+ {
817
+ "epoch": 53.5,
818
+ "learning_rate": 5.2500000000000006e-06,
819
+ "loss": 0.9005,
820
+ "step": 107
821
+ },
822
+ {
823
+ "epoch": 54.0,
824
+ "learning_rate": 5.210526315789474e-06,
825
+ "loss": 0.8744,
826
+ "step": 108
827
+ },
828
+ {
829
+ "epoch": 54.5,
830
+ "learning_rate": 5.171052631578947e-06,
831
+ "loss": 0.8999,
832
+ "step": 109
833
+ },
834
+ {
835
+ "epoch": 55.0,
836
+ "learning_rate": 5.131578947368421e-06,
837
+ "loss": 0.8443,
838
+ "step": 110
839
+ },
840
+ {
841
+ "epoch": 55.0,
842
+ "eval_accuracy_safe": 0.8742462876856157,
843
+ "eval_accuracy_unlabeled": NaN,
844
+ "eval_accuracy_unsafe": 0.8570024260249537,
845
+ "eval_iou_safe": 0.1671743332931789,
846
+ "eval_iou_unlabeled": 0.0,
847
+ "eval_iou_unsafe": 0.8537115815119297,
848
+ "eval_loss": 0.8626915812492371,
849
+ "eval_mean_accuracy": 0.8656243568552847,
850
+ "eval_mean_iou": 0.3402953049350362,
851
+ "eval_overall_accuracy": 0.8575506210327148,
852
+ "eval_runtime": 1.4008,
853
+ "eval_samples_per_second": 5.711,
854
+ "eval_steps_per_second": 0.714,
855
+ "step": 110
856
+ },
857
+ {
858
+ "epoch": 55.5,
859
+ "learning_rate": 5.092105263157895e-06,
860
+ "loss": 0.93,
861
+ "step": 111
862
+ },
863
+ {
864
+ "epoch": 56.0,
865
+ "learning_rate": 5.052631578947368e-06,
866
+ "loss": 0.8241,
867
+ "step": 112
868
+ },
869
+ {
870
+ "epoch": 56.5,
871
+ "learning_rate": 5.013157894736842e-06,
872
+ "loss": 0.919,
873
+ "step": 113
874
+ },
875
+ {
876
+ "epoch": 57.0,
877
+ "learning_rate": 4.973684210526316e-06,
878
+ "loss": 0.8839,
879
+ "step": 114
880
+ },
881
+ {
882
+ "epoch": 57.5,
883
+ "learning_rate": 4.9342105263157895e-06,
884
+ "loss": 0.8664,
885
+ "step": 115
886
+ },
887
+ {
888
+ "epoch": 58.0,
889
+ "learning_rate": 4.894736842105264e-06,
890
+ "loss": 0.8774,
891
+ "step": 116
892
+ },
893
+ {
894
+ "epoch": 58.5,
895
+ "learning_rate": 4.855263157894737e-06,
896
+ "loss": 0.8846,
897
+ "step": 117
898
+ },
899
+ {
900
+ "epoch": 59.0,
901
+ "learning_rate": 4.81578947368421e-06,
902
+ "loss": 0.931,
903
+ "step": 118
904
+ },
905
+ {
906
+ "epoch": 59.5,
907
+ "learning_rate": 4.7763157894736844e-06,
908
+ "loss": 0.8527,
909
+ "step": 119
910
+ },
911
+ {
912
+ "epoch": 60.0,
913
+ "learning_rate": 4.736842105263158e-06,
914
+ "loss": 0.8765,
915
+ "step": 120
916
+ },
917
+ {
918
+ "epoch": 60.0,
919
+ "eval_accuracy_safe": 0.8591420428978551,
920
+ "eval_accuracy_unlabeled": NaN,
921
+ "eval_accuracy_unsafe": 0.8658727336661936,
922
+ "eval_iou_safe": 0.17292191207636712,
923
+ "eval_iou_unlabeled": 0.0,
924
+ "eval_iou_unsafe": 0.8619790415433206,
925
+ "eval_loss": 0.8488205671310425,
926
+ "eval_mean_accuracy": 0.8625073882820243,
927
+ "eval_mean_iou": 0.34496698453989594,
928
+ "eval_overall_accuracy": 0.8656587600708008,
929
+ "eval_runtime": 1.4312,
930
+ "eval_samples_per_second": 5.59,
931
+ "eval_steps_per_second": 0.699,
932
+ "step": 120
933
+ },
934
+ {
935
+ "epoch": 60.5,
936
+ "learning_rate": 4.697368421052631e-06,
937
+ "loss": 0.8832,
938
+ "step": 121
939
+ },
940
+ {
941
+ "epoch": 61.0,
942
+ "learning_rate": 4.657894736842106e-06,
943
+ "loss": 0.9832,
944
+ "step": 122
945
+ },
946
+ {
947
+ "epoch": 61.5,
948
+ "learning_rate": 4.618421052631579e-06,
949
+ "loss": 0.8575,
950
+ "step": 123
951
+ },
952
+ {
953
+ "epoch": 62.0,
954
+ "learning_rate": 4.578947368421053e-06,
955
+ "loss": 0.8165,
956
+ "step": 124
957
+ },
958
+ {
959
+ "epoch": 62.5,
960
+ "learning_rate": 4.539473684210527e-06,
961
+ "loss": 0.8491,
962
+ "step": 125
963
+ },
964
+ {
965
+ "epoch": 63.0,
966
+ "learning_rate": 4.5e-06,
967
+ "loss": 0.9346,
968
+ "step": 126
969
+ },
970
+ {
971
+ "epoch": 63.5,
972
+ "learning_rate": 4.460526315789473e-06,
973
+ "loss": 0.8498,
974
+ "step": 127
975
+ },
976
+ {
977
+ "epoch": 64.0,
978
+ "learning_rate": 4.4210526315789476e-06,
979
+ "loss": 0.8806,
980
+ "step": 128
981
+ },
982
+ {
983
+ "epoch": 64.5,
984
+ "learning_rate": 4.381578947368421e-06,
985
+ "loss": 0.8288,
986
+ "step": 129
987
+ },
988
+ {
989
+ "epoch": 65.0,
990
+ "learning_rate": 4.342105263157895e-06,
991
+ "loss": 0.899,
992
+ "step": 130
993
+ },
994
+ {
995
+ "epoch": 65.0,
996
+ "eval_accuracy_safe": 0.8547922603869806,
997
+ "eval_accuracy_unlabeled": NaN,
998
+ "eval_accuracy_unsafe": 0.8710409646576527,
999
+ "eval_iou_safe": 0.17724703986962054,
1000
+ "eval_iou_unlabeled": 0.0,
1001
+ "eval_iou_unsafe": 0.8669472125956462,
1002
+ "eval_loss": 0.842871367931366,
1003
+ "eval_mean_accuracy": 0.8629166125223167,
1004
+ "eval_mean_iou": 0.3480647508217556,
1005
+ "eval_overall_accuracy": 0.8705244064331055,
1006
+ "eval_runtime": 1.237,
1007
+ "eval_samples_per_second": 6.467,
1008
+ "eval_steps_per_second": 0.808,
1009
+ "step": 130
1010
+ },
1011
+ {
1012
+ "epoch": 65.5,
1013
+ "learning_rate": 4.302631578947368e-06,
1014
+ "loss": 0.8852,
1015
+ "step": 131
1016
+ },
1017
+ {
1018
+ "epoch": 66.0,
1019
+ "learning_rate": 4.263157894736842e-06,
1020
+ "loss": 0.8237,
1021
+ "step": 132
1022
+ },
1023
+ {
1024
+ "epoch": 66.5,
1025
+ "learning_rate": 4.223684210526316e-06,
1026
+ "loss": 0.8323,
1027
+ "step": 133
1028
+ },
1029
+ {
1030
+ "epoch": 67.0,
1031
+ "learning_rate": 4.18421052631579e-06,
1032
+ "loss": 0.8761,
1033
+ "step": 134
1034
+ },
1035
+ {
1036
+ "epoch": 67.5,
1037
+ "learning_rate": 4.144736842105263e-06,
1038
+ "loss": 0.8837,
1039
+ "step": 135
1040
+ },
1041
+ {
1042
+ "epoch": 68.0,
1043
+ "learning_rate": 4.1052631578947365e-06,
1044
+ "loss": 0.8374,
1045
+ "step": 136
1046
+ },
1047
+ {
1048
+ "epoch": 68.5,
1049
+ "learning_rate": 4.065789473684211e-06,
1050
+ "loss": 0.8146,
1051
+ "step": 137
1052
+ },
1053
+ {
1054
+ "epoch": 69.0,
1055
+ "learning_rate": 4.026315789473684e-06,
1056
+ "loss": 0.9205,
1057
+ "step": 138
1058
+ },
1059
+ {
1060
+ "epoch": 69.5,
1061
+ "learning_rate": 3.986842105263158e-06,
1062
+ "loss": 0.8839,
1063
+ "step": 139
1064
+ },
1065
+ {
1066
+ "epoch": 70.0,
1067
+ "learning_rate": 3.9473684210526315e-06,
1068
+ "loss": 0.7713,
1069
+ "step": 140
1070
+ },
1071
+ {
1072
+ "epoch": 70.0,
1073
+ "eval_accuracy_safe": 0.8025648717564122,
1074
+ "eval_accuracy_unlabeled": NaN,
1075
+ "eval_accuracy_unsafe": 0.8968998493953653,
1076
+ "eval_iou_safe": 0.19830627825958047,
1077
+ "eval_iou_unlabeled": 0.0,
1078
+ "eval_iou_unsafe": 0.8911652674661912,
1079
+ "eval_loss": 0.8084838390350342,
1080
+ "eval_mean_accuracy": 0.8497323605758887,
1081
+ "eval_mean_iou": 0.3631571819085906,
1082
+ "eval_overall_accuracy": 0.8939008712768555,
1083
+ "eval_runtime": 1.2344,
1084
+ "eval_samples_per_second": 6.481,
1085
+ "eval_steps_per_second": 0.81,
1086
+ "step": 140
1087
+ },
1088
+ {
1089
+ "epoch": 70.5,
1090
+ "learning_rate": 3.907894736842106e-06,
1091
+ "loss": 0.7833,
1092
+ "step": 141
1093
+ },
1094
+ {
1095
+ "epoch": 71.0,
1096
+ "learning_rate": 3.868421052631579e-06,
1097
+ "loss": 0.9608,
1098
+ "step": 142
1099
+ },
1100
+ {
1101
+ "epoch": 71.5,
1102
+ "learning_rate": 3.828947368421053e-06,
1103
+ "loss": 0.8081,
1104
+ "step": 143
1105
+ },
1106
+ {
1107
+ "epoch": 72.0,
1108
+ "learning_rate": 3.7894736842105264e-06,
1109
+ "loss": 0.822,
1110
+ "step": 144
1111
+ },
1112
+ {
1113
+ "epoch": 72.5,
1114
+ "learning_rate": 3.75e-06,
1115
+ "loss": 0.8508,
1116
+ "step": 145
1117
+ },
1118
+ {
1119
+ "epoch": 73.0,
1120
+ "learning_rate": 3.710526315789474e-06,
1121
+ "loss": 0.8297,
1122
+ "step": 146
1123
+ },
1124
+ {
1125
+ "epoch": 73.5,
1126
+ "learning_rate": 3.6710526315789476e-06,
1127
+ "loss": 0.7963,
1128
+ "step": 147
1129
+ },
1130
+ {
1131
+ "epoch": 74.0,
1132
+ "learning_rate": 3.631578947368421e-06,
1133
+ "loss": 0.9092,
1134
+ "step": 148
1135
+ },
1136
+ {
1137
+ "epoch": 74.5,
1138
+ "learning_rate": 3.592105263157895e-06,
1139
+ "loss": 0.765,
1140
+ "step": 149
1141
+ },
1142
+ {
1143
+ "epoch": 75.0,
1144
+ "learning_rate": 3.5526315789473687e-06,
1145
+ "loss": 0.8505,
1146
+ "step": 150
1147
+ },
1148
+ {
1149
+ "epoch": 75.0,
1150
+ "eval_accuracy_safe": 0.7785660716964152,
1151
+ "eval_accuracy_unlabeled": NaN,
1152
+ "eval_accuracy_unsafe": 0.9144912390260047,
1153
+ "eval_iou_safe": 0.2207962907822536,
1154
+ "eval_iou_unlabeled": 0.0,
1155
+ "eval_iou_unsafe": 0.9079488517260416,
1156
+ "eval_loss": 0.7821168303489685,
1157
+ "eval_mean_accuracy": 0.8465286553612099,
1158
+ "eval_mean_iou": 0.3762483808360984,
1159
+ "eval_overall_accuracy": 0.9101700782775879,
1160
+ "eval_runtime": 1.2538,
1161
+ "eval_samples_per_second": 6.38,
1162
+ "eval_steps_per_second": 0.798,
1163
+ "step": 150
1164
+ },
1165
+ {
1166
+ "epoch": 75.5,
1167
+ "learning_rate": 3.513157894736842e-06,
1168
+ "loss": 0.8494,
1169
+ "step": 151
1170
+ },
1171
+ {
1172
+ "epoch": 76.0,
1173
+ "learning_rate": 3.4736842105263158e-06,
1174
+ "loss": 0.8188,
1175
+ "step": 152
1176
+ },
1177
+ {
1178
+ "epoch": 76.5,
1179
+ "learning_rate": 3.43421052631579e-06,
1180
+ "loss": 0.81,
1181
+ "step": 153
1182
+ },
1183
+ {
1184
+ "epoch": 77.0,
1185
+ "learning_rate": 3.3947368421052632e-06,
1186
+ "loss": 0.9673,
1187
+ "step": 154
1188
+ },
1189
+ {
1190
+ "epoch": 77.5,
1191
+ "learning_rate": 3.355263157894737e-06,
1192
+ "loss": 0.8161,
1193
+ "step": 155
1194
+ },
1195
+ {
1196
+ "epoch": 78.0,
1197
+ "learning_rate": 3.3157894736842103e-06,
1198
+ "loss": 0.8539,
1199
+ "step": 156
1200
+ },
1201
+ {
1202
+ "epoch": 78.5,
1203
+ "learning_rate": 3.2763157894736844e-06,
1204
+ "loss": 0.7757,
1205
+ "step": 157
1206
+ },
1207
+ {
1208
+ "epoch": 79.0,
1209
+ "learning_rate": 3.236842105263158e-06,
1210
+ "loss": 0.8716,
1211
+ "step": 158
1212
+ },
1213
+ {
1214
+ "epoch": 79.5,
1215
+ "learning_rate": 3.1973684210526314e-06,
1216
+ "loss": 0.8154,
1217
+ "step": 159
1218
+ },
1219
+ {
1220
+ "epoch": 80.0,
1221
+ "learning_rate": 3.157894736842105e-06,
1222
+ "loss": 0.7352,
1223
+ "step": 160
1224
+ },
1225
+ {
1226
+ "epoch": 80.0,
1227
+ "eval_accuracy_safe": 0.755677216139193,
1228
+ "eval_accuracy_unlabeled": NaN,
1229
+ "eval_accuracy_unsafe": 0.9226257607799527,
1230
+ "eval_iou_safe": 0.23039002730053915,
1231
+ "eval_iou_unlabeled": 0.0,
1232
+ "eval_iou_unsafe": 0.9153475450094228,
1233
+ "eval_loss": 0.7840872406959534,
1234
+ "eval_mean_accuracy": 0.8391514884595729,
1235
+ "eval_mean_iou": 0.3819125241033207,
1236
+ "eval_overall_accuracy": 0.9173183441162109,
1237
+ "eval_runtime": 1.4699,
1238
+ "eval_samples_per_second": 5.443,
1239
+ "eval_steps_per_second": 0.68,
1240
+ "step": 160
1241
+ },
1242
+ {
1243
+ "epoch": 80.5,
1244
+ "learning_rate": 3.1184210526315793e-06,
1245
+ "loss": 0.7745,
1246
+ "step": 161
1247
+ },
1248
+ {
1249
+ "epoch": 81.0,
1250
+ "learning_rate": 3.0789473684210526e-06,
1251
+ "loss": 0.885,
1252
+ "step": 162
1253
+ },
1254
+ {
1255
+ "epoch": 81.5,
1256
+ "learning_rate": 3.0394736842105263e-06,
1257
+ "loss": 0.827,
1258
+ "step": 163
1259
+ },
1260
+ {
1261
+ "epoch": 82.0,
1262
+ "learning_rate": 3e-06,
1263
+ "loss": 0.8288,
1264
+ "step": 164
1265
+ },
1266
+ {
1267
+ "epoch": 82.5,
1268
+ "learning_rate": 2.960526315789474e-06,
1269
+ "loss": 0.8158,
1270
+ "step": 165
1271
+ },
1272
+ {
1273
+ "epoch": 83.0,
1274
+ "learning_rate": 2.9210526315789475e-06,
1275
+ "loss": 0.8501,
1276
+ "step": 166
1277
+ },
1278
+ {
1279
+ "epoch": 83.5,
1280
+ "learning_rate": 2.8815789473684213e-06,
1281
+ "loss": 0.7772,
1282
+ "step": 167
1283
+ },
1284
+ {
1285
+ "epoch": 84.0,
1286
+ "learning_rate": 2.8421052631578946e-06,
1287
+ "loss": 0.8556,
1288
+ "step": 168
1289
+ },
1290
+ {
1291
+ "epoch": 84.5,
1292
+ "learning_rate": 2.8026315789473687e-06,
1293
+ "loss": 0.7853,
1294
+ "step": 169
1295
+ },
1296
+ {
1297
+ "epoch": 85.0,
1298
+ "learning_rate": 2.7631578947368424e-06,
1299
+ "loss": 0.7205,
1300
+ "step": 170
1301
+ },
1302
+ {
1303
+ "epoch": 85.0,
1304
+ "eval_accuracy_safe": 0.7412929353532324,
1305
+ "eval_accuracy_unlabeled": NaN,
1306
+ "eval_accuracy_unsafe": 0.9387982754833581,
1307
+ "eval_iou_safe": 0.2613219967957361,
1308
+ "eval_iou_unlabeled": 0.0,
1309
+ "eval_iou_unsafe": 0.930946709988782,
1310
+ "eval_loss": 0.7502496838569641,
1311
+ "eval_mean_accuracy": 0.8400456054182952,
1312
+ "eval_mean_iou": 0.39742290226150606,
1313
+ "eval_overall_accuracy": 0.9325194358825684,
1314
+ "eval_runtime": 1.338,
1315
+ "eval_samples_per_second": 5.979,
1316
+ "eval_steps_per_second": 0.747,
1317
+ "step": 170
1318
+ },
1319
+ {
1320
+ "epoch": 85.5,
1321
+ "learning_rate": 2.7236842105263157e-06,
1322
+ "loss": 0.818,
1323
+ "step": 171
1324
+ },
1325
+ {
1326
+ "epoch": 86.0,
1327
+ "learning_rate": 2.6842105263157895e-06,
1328
+ "loss": 0.8021,
1329
+ "step": 172
1330
+ },
1331
+ {
1332
+ "epoch": 86.5,
1333
+ "learning_rate": 2.6447368421052636e-06,
1334
+ "loss": 0.7861,
1335
+ "step": 173
1336
+ },
1337
+ {
1338
+ "epoch": 87.0,
1339
+ "learning_rate": 2.605263157894737e-06,
1340
+ "loss": 0.8586,
1341
+ "step": 174
1342
+ },
1343
+ {
1344
+ "epoch": 87.5,
1345
+ "learning_rate": 2.5657894736842107e-06,
1346
+ "loss": 0.8099,
1347
+ "step": 175
1348
+ },
1349
+ {
1350
+ "epoch": 88.0,
1351
+ "learning_rate": 2.526315789473684e-06,
1352
+ "loss": 0.923,
1353
+ "step": 176
1354
+ },
1355
+ {
1356
+ "epoch": 88.5,
1357
+ "learning_rate": 2.486842105263158e-06,
1358
+ "loss": 0.7752,
1359
+ "step": 177
1360
+ },
1361
+ {
1362
+ "epoch": 89.0,
1363
+ "learning_rate": 2.447368421052632e-06,
1364
+ "loss": 0.8386,
1365
+ "step": 178
1366
+ },
1367
+ {
1368
+ "epoch": 89.5,
1369
+ "learning_rate": 2.407894736842105e-06,
1370
+ "loss": 0.8237,
1371
+ "step": 179
1372
+ },
1373
+ {
1374
+ "epoch": 90.0,
1375
+ "learning_rate": 2.368421052631579e-06,
1376
+ "loss": 0.711,
1377
+ "step": 180
1378
+ },
1379
+ {
1380
+ "epoch": 90.0,
1381
+ "eval_accuracy_safe": 0.7483725813709314,
1382
+ "eval_accuracy_unlabeled": NaN,
1383
+ "eval_accuracy_unsafe": 0.9372695744163209,
1384
+ "eval_iou_safe": 0.2590913575631059,
1385
+ "eval_iou_unlabeled": 0.0,
1386
+ "eval_iou_unsafe": 0.9296319200611187,
1387
+ "eval_loss": 0.7416911125183105,
1388
+ "eval_mean_accuracy": 0.8428210778936261,
1389
+ "eval_mean_iou": 0.3962410925414082,
1390
+ "eval_overall_accuracy": 0.9312644004821777,
1391
+ "eval_runtime": 1.3549,
1392
+ "eval_samples_per_second": 5.905,
1393
+ "eval_steps_per_second": 0.738,
1394
+ "step": 180
1395
+ },
1396
+ {
1397
+ "epoch": 90.5,
1398
+ "learning_rate": 2.328947368421053e-06,
1399
+ "loss": 0.7583,
1400
+ "step": 181
1401
+ },
1402
+ {
1403
+ "epoch": 91.0,
1404
+ "learning_rate": 2.2894736842105263e-06,
1405
+ "loss": 0.761,
1406
+ "step": 182
1407
+ },
1408
+ {
1409
+ "epoch": 91.5,
1410
+ "learning_rate": 2.25e-06,
1411
+ "loss": 0.7724,
1412
+ "step": 183
1413
+ },
1414
+ {
1415
+ "epoch": 92.0,
1416
+ "learning_rate": 2.2105263157894738e-06,
1417
+ "loss": 0.8581,
1418
+ "step": 184
1419
+ },
1420
+ {
1421
+ "epoch": 92.5,
1422
+ "learning_rate": 2.1710526315789475e-06,
1423
+ "loss": 0.7619,
1424
+ "step": 185
1425
+ },
1426
+ {
1427
+ "epoch": 93.0,
1428
+ "learning_rate": 2.131578947368421e-06,
1429
+ "loss": 0.8492,
1430
+ "step": 186
1431
+ },
1432
+ {
1433
+ "epoch": 93.5,
1434
+ "learning_rate": 2.092105263157895e-06,
1435
+ "loss": 0.7315,
1436
+ "step": 187
1437
+ },
1438
+ {
1439
+ "epoch": 94.0,
1440
+ "learning_rate": 2.0526315789473683e-06,
1441
+ "loss": 0.8353,
1442
+ "step": 188
1443
+ },
1444
+ {
1445
+ "epoch": 94.5,
1446
+ "learning_rate": 2.013157894736842e-06,
1447
+ "loss": 0.7742,
1448
+ "step": 189
1449
+ },
1450
+ {
1451
+ "epoch": 95.0,
1452
+ "learning_rate": 1.9736842105263157e-06,
1453
+ "loss": 0.7855,
1454
+ "step": 190
1455
+ },
1456
+ {
1457
+ "epoch": 95.0,
1458
+ "eval_accuracy_safe": 0.7473226338683066,
1459
+ "eval_accuracy_unlabeled": NaN,
1460
+ "eval_accuracy_unsafe": 0.940405283080569,
1461
+ "eval_iou_safe": 0.26829938127009256,
1462
+ "eval_iou_unlabeled": 0.0,
1463
+ "eval_iou_unsafe": 0.9327183843815211,
1464
+ "eval_loss": 0.728053867816925,
1465
+ "eval_mean_accuracy": 0.8438639584744378,
1466
+ "eval_mean_iou": 0.40033925521720454,
1467
+ "eval_overall_accuracy": 0.9342670440673828,
1468
+ "eval_runtime": 1.3581,
1469
+ "eval_samples_per_second": 5.89,
1470
+ "eval_steps_per_second": 0.736,
1471
+ "step": 190
1472
+ },
1473
+ {
1474
+ "epoch": 95.5,
1475
+ "learning_rate": 1.9342105263157895e-06,
1476
+ "loss": 0.7316,
1477
+ "step": 191
1478
+ },
1479
+ {
1480
+ "epoch": 96.0,
1481
+ "learning_rate": 1.8947368421052632e-06,
1482
+ "loss": 0.8882,
1483
+ "step": 192
1484
+ },
1485
+ {
1486
+ "epoch": 96.5,
1487
+ "learning_rate": 1.855263157894737e-06,
1488
+ "loss": 0.7755,
1489
+ "step": 193
1490
+ },
1491
+ {
1492
+ "epoch": 97.0,
1493
+ "learning_rate": 1.8157894736842104e-06,
1494
+ "loss": 0.8066,
1495
+ "step": 194
1496
+ },
1497
+ {
1498
+ "epoch": 97.5,
1499
+ "learning_rate": 1.7763157894736844e-06,
1500
+ "loss": 0.8156,
1501
+ "step": 195
1502
+ },
1503
+ {
1504
+ "epoch": 98.0,
1505
+ "learning_rate": 1.7368421052631579e-06,
1506
+ "loss": 0.6941,
1507
+ "step": 196
1508
+ },
1509
+ {
1510
+ "epoch": 98.5,
1511
+ "learning_rate": 1.6973684210526316e-06,
1512
+ "loss": 0.8103,
1513
+ "step": 197
1514
+ },
1515
+ {
1516
+ "epoch": 99.0,
1517
+ "learning_rate": 1.6578947368421051e-06,
1518
+ "loss": 0.8466,
1519
+ "step": 198
1520
+ },
1521
+ {
1522
+ "epoch": 99.5,
1523
+ "learning_rate": 1.618421052631579e-06,
1524
+ "loss": 0.813,
1525
+ "step": 199
1526
+ },
1527
+ {
1528
+ "epoch": 100.0,
1529
+ "learning_rate": 1.5789473684210526e-06,
1530
+ "loss": 0.7632,
1531
+ "step": 200
1532
+ },
1533
+ {
1534
+ "epoch": 100.0,
1535
+ "eval_accuracy_safe": 0.7544922753862306,
1536
+ "eval_accuracy_unlabeled": NaN,
1537
+ "eval_accuracy_unsafe": 0.9292813233508103,
1538
+ "eval_iou_safe": 0.24304709997874027,
1539
+ "eval_iou_unlabeled": 0.0,
1540
+ "eval_iou_unsafe": 0.9218938484516696,
1541
+ "eval_loss": 0.7494363188743591,
1542
+ "eval_mean_accuracy": 0.8418867993685204,
1543
+ "eval_mean_iou": 0.3883136494768033,
1544
+ "eval_overall_accuracy": 0.9237246513366699,
1545
+ "eval_runtime": 1.5595,
1546
+ "eval_samples_per_second": 5.13,
1547
+ "eval_steps_per_second": 0.641,
1548
+ "step": 200
1549
+ }
1550
+ ],
1551
+ "max_steps": 240,
1552
+ "num_train_epochs": 120,
1553
+ "total_flos": 3.505833639936e+16,
1554
+ "trial_name": null,
1555
+ "trial_params": null
1556
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f65edb6c65320e63e4eca7bc9cd2cef41c49f7f9090402a3505eb4c323d13d
3
+ size 4155
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7242e168fe44bb25a2989377f760c2db980e849e156de98b8fe495f20e60b78d
3
  size 14932813
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59582f6e1b5e6baee90f035b3a76f3f040eb6460e794744b1ea3d93a2712ee2
3
  size 14932813
runs/Feb08_22-23-21_robovision.csres.utexas.edu/events.out.tfevents.1707452607.robovision.csres.utexas.edu.1751974.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3503afbba5b6cb7145f8839114ad01ac78d3641c3901788c9967f92870cefc34
3
- size 41825
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cab425bb97d4d30e9384d57e2ee50053c7ea072aff8f3572e4b7125e5f458a2
3
+ size 51229