sam1120 commited on
Commit
86599e6
·
1 Parent(s): d64fdcd

Training in progress, step 120

Browse files
checkpoint-120/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nvidia/mit-b5",
3
+ "architectures": [
4
+ "SegformerForSemanticSegmentation"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout_prob": 0.1,
8
+ "decoder_hidden_size": 768,
9
+ "depths": [
10
+ 3,
11
+ 6,
12
+ 40,
13
+ 3
14
+ ],
15
+ "downsampling_rates": [
16
+ 1,
17
+ 4,
18
+ 8,
19
+ 16
20
+ ],
21
+ "drop_path_rate": 0.1,
22
+ "hidden_act": "gelu",
23
+ "hidden_dropout_prob": 0.0,
24
+ "hidden_sizes": [
25
+ 64,
26
+ 128,
27
+ 320,
28
+ 512
29
+ ],
30
+ "id2label": {
31
+ "0": "unlabeled",
32
+ "1": "dropoff",
33
+ "2": "undropoff"
34
+ },
35
+ "image_size": 224,
36
+ "initializer_range": 0.02,
37
+ "label2id": {
38
+ "dropoff": 1,
39
+ "undropoff": 2,
40
+ "unlabeled": 0
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-120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac6c840f5f19fb07b573ec5b0a6af2573bb93f09ce7020a01e55bcbe698ff297
3
+ size 677455103
checkpoint-120/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd674207f8a506d763da21af79a71a811294cf6832ccedadac708ee579fb06a
3
+ size 338796489
checkpoint-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cbff776d551b234ad2de0430f403f7483134cc581f46f3137826495450c29fd
3
+ size 14575
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c31e4e64ded13fc7d73db84a65ec153d2726c56000b4f92a8af92c0e1712a7
3
+ size 627
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5971364974975586,
3
+ "best_model_checkpoint": "/robodata/smodak/Projects/nspl/scripts/terrainseg/training/models/dropoff-utcustom-train-SF-RGB-b5_3/checkpoint-120",
4
+ "epoch": 60.0,
5
+ "global_step": 120,
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": 4.1666666666666667e-07,
13
+ "loss": 1.3484,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 8.333333333333333e-07,
19
+ "loss": 1.3481,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 1.5,
24
+ "learning_rate": 1.25e-06,
25
+ "loss": 1.3531,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "learning_rate": 1.6666666666666667e-06,
31
+ "loss": 1.3399,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 2.5,
36
+ "learning_rate": 2.0833333333333334e-06,
37
+ "loss": 1.3398,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 2.5e-06,
43
+ "loss": 1.3386,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 3.5,
48
+ "learning_rate": 2.916666666666667e-06,
49
+ "loss": 1.3376,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 3.3333333333333333e-06,
55
+ "loss": 1.3249,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 4.5,
60
+ "learning_rate": 3.7500000000000005e-06,
61
+ "loss": 1.3205,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 5.0,
66
+ "learning_rate": 4.166666666666667e-06,
67
+ "loss": 1.3135,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "eval_accuracy_dropoff": 0.4068717172412211,
73
+ "eval_accuracy_undropoff": 0.11034322178517518,
74
+ "eval_accuracy_unlabeled": NaN,
75
+ "eval_iou_dropoff": 0.053473330857492875,
76
+ "eval_iou_undropoff": 0.1102453041626867,
77
+ "eval_iou_unlabeled": 0.0,
78
+ "eval_loss": 1.2007640600204468,
79
+ "eval_mean_accuracy": 0.25860746951319813,
80
+ "eval_mean_iou": 0.05457287834005986,
81
+ "eval_overall_accuracy": 0.12267265319824219,
82
+ "eval_runtime": 2.5511,
83
+ "eval_samples_per_second": 7.84,
84
+ "eval_steps_per_second": 0.784,
85
+ "step": 10
86
+ },
87
+ {
88
+ "epoch": 5.5,
89
+ "learning_rate": 4.583333333333333e-06,
90
+ "loss": 1.3089,
91
+ "step": 11
92
+ },
93
+ {
94
+ "epoch": 6.0,
95
+ "learning_rate": 5e-06,
96
+ "loss": 1.3043,
97
+ "step": 12
98
+ },
99
+ {
100
+ "epoch": 6.5,
101
+ "learning_rate": 4.978070175438597e-06,
102
+ "loss": 1.2871,
103
+ "step": 13
104
+ },
105
+ {
106
+ "epoch": 7.0,
107
+ "learning_rate": 4.956140350877193e-06,
108
+ "loss": 1.2832,
109
+ "step": 14
110
+ },
111
+ {
112
+ "epoch": 7.5,
113
+ "learning_rate": 4.9342105263157895e-06,
114
+ "loss": 1.2709,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 8.0,
119
+ "learning_rate": 4.912280701754386e-06,
120
+ "loss": 1.2634,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 8.5,
125
+ "learning_rate": 4.890350877192983e-06,
126
+ "loss": 1.257,
127
+ "step": 17
128
+ },
129
+ {
130
+ "epoch": 9.0,
131
+ "learning_rate": 4.8684210526315795e-06,
132
+ "loss": 1.2403,
133
+ "step": 18
134
+ },
135
+ {
136
+ "epoch": 9.5,
137
+ "learning_rate": 4.846491228070176e-06,
138
+ "loss": 1.2398,
139
+ "step": 19
140
+ },
141
+ {
142
+ "epoch": 10.0,
143
+ "learning_rate": 4.824561403508772e-06,
144
+ "loss": 1.2309,
145
+ "step": 20
146
+ },
147
+ {
148
+ "epoch": 10.0,
149
+ "eval_accuracy_dropoff": 0.43877153145714354,
150
+ "eval_accuracy_undropoff": 0.24072332003617994,
151
+ "eval_accuracy_unlabeled": NaN,
152
+ "eval_iou_dropoff": 0.11288106949650205,
153
+ "eval_iou_undropoff": 0.24004849364289937,
154
+ "eval_iou_unlabeled": 0.0,
155
+ "eval_loss": 1.1293678283691406,
156
+ "eval_mean_accuracy": 0.3397474257466617,
157
+ "eval_mean_iou": 0.11764318771313381,
158
+ "eval_overall_accuracy": 0.24895801544189453,
159
+ "eval_runtime": 2.6298,
160
+ "eval_samples_per_second": 7.605,
161
+ "eval_steps_per_second": 0.761,
162
+ "step": 20
163
+ },
164
+ {
165
+ "epoch": 10.5,
166
+ "learning_rate": 4.802631578947369e-06,
167
+ "loss": 1.2159,
168
+ "step": 21
169
+ },
170
+ {
171
+ "epoch": 11.0,
172
+ "learning_rate": 4.780701754385965e-06,
173
+ "loss": 1.2243,
174
+ "step": 22
175
+ },
176
+ {
177
+ "epoch": 11.5,
178
+ "learning_rate": 4.758771929824561e-06,
179
+ "loss": 1.2094,
180
+ "step": 23
181
+ },
182
+ {
183
+ "epoch": 12.0,
184
+ "learning_rate": 4.736842105263158e-06,
185
+ "loss": 1.1904,
186
+ "step": 24
187
+ },
188
+ {
189
+ "epoch": 12.5,
190
+ "learning_rate": 4.714912280701755e-06,
191
+ "loss": 1.1865,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 13.0,
196
+ "learning_rate": 4.692982456140351e-06,
197
+ "loss": 1.1715,
198
+ "step": 26
199
+ },
200
+ {
201
+ "epoch": 13.5,
202
+ "learning_rate": 4.671052631578948e-06,
203
+ "loss": 1.1722,
204
+ "step": 27
205
+ },
206
+ {
207
+ "epoch": 14.0,
208
+ "learning_rate": 4.649122807017544e-06,
209
+ "loss": 1.1511,
210
+ "step": 28
211
+ },
212
+ {
213
+ "epoch": 14.5,
214
+ "learning_rate": 4.6271929824561405e-06,
215
+ "loss": 1.1512,
216
+ "step": 29
217
+ },
218
+ {
219
+ "epoch": 15.0,
220
+ "learning_rate": 4.605263157894737e-06,
221
+ "loss": 1.1346,
222
+ "step": 30
223
+ },
224
+ {
225
+ "epoch": 15.0,
226
+ "eval_accuracy_dropoff": 0.46940067432739285,
227
+ "eval_accuracy_undropoff": 0.5035900324087019,
228
+ "eval_accuracy_unlabeled": NaN,
229
+ "eval_iou_dropoff": 0.15243042262584855,
230
+ "eval_iou_undropoff": 0.4989255427443525,
231
+ "eval_iou_unlabeled": 0.0,
232
+ "eval_loss": 1.039512276649475,
233
+ "eval_mean_accuracy": 0.4864953533680474,
234
+ "eval_mean_iou": 0.21711865512340034,
235
+ "eval_overall_accuracy": 0.5021684646606446,
236
+ "eval_runtime": 2.9463,
237
+ "eval_samples_per_second": 6.788,
238
+ "eval_steps_per_second": 0.679,
239
+ "step": 30
240
+ },
241
+ {
242
+ "epoch": 15.5,
243
+ "learning_rate": 4.583333333333333e-06,
244
+ "loss": 1.1343,
245
+ "step": 31
246
+ },
247
+ {
248
+ "epoch": 16.0,
249
+ "learning_rate": 4.56140350877193e-06,
250
+ "loss": 1.1182,
251
+ "step": 32
252
+ },
253
+ {
254
+ "epoch": 16.5,
255
+ "learning_rate": 4.539473684210527e-06,
256
+ "loss": 1.132,
257
+ "step": 33
258
+ },
259
+ {
260
+ "epoch": 17.0,
261
+ "learning_rate": 4.517543859649123e-06,
262
+ "loss": 1.0986,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 17.5,
267
+ "learning_rate": 4.4956140350877196e-06,
268
+ "loss": 1.0887,
269
+ "step": 35
270
+ },
271
+ {
272
+ "epoch": 18.0,
273
+ "learning_rate": 4.473684210526316e-06,
274
+ "loss": 1.1214,
275
+ "step": 36
276
+ },
277
+ {
278
+ "epoch": 18.5,
279
+ "learning_rate": 4.451754385964912e-06,
280
+ "loss": 1.0945,
281
+ "step": 37
282
+ },
283
+ {
284
+ "epoch": 19.0,
285
+ "learning_rate": 4.429824561403509e-06,
286
+ "loss": 1.076,
287
+ "step": 38
288
+ },
289
+ {
290
+ "epoch": 19.5,
291
+ "learning_rate": 4.407894736842105e-06,
292
+ "loss": 1.0444,
293
+ "step": 39
294
+ },
295
+ {
296
+ "epoch": 20.0,
297
+ "learning_rate": 4.385964912280702e-06,
298
+ "loss": 1.1088,
299
+ "step": 40
300
+ },
301
+ {
302
+ "epoch": 20.0,
303
+ "eval_accuracy_dropoff": 0.48076332025963897,
304
+ "eval_accuracy_undropoff": 0.6235115828521449,
305
+ "eval_accuracy_unlabeled": NaN,
306
+ "eval_iou_dropoff": 0.1660792839847365,
307
+ "eval_iou_undropoff": 0.616259059512146,
308
+ "eval_iou_unlabeled": 0.0,
309
+ "eval_loss": 0.9755474328994751,
310
+ "eval_mean_accuracy": 0.5521374515558919,
311
+ "eval_mean_iou": 0.2607794478322942,
312
+ "eval_overall_accuracy": 0.6175762176513672,
313
+ "eval_runtime": 3.0937,
314
+ "eval_samples_per_second": 6.465,
315
+ "eval_steps_per_second": 0.646,
316
+ "step": 40
317
+ },
318
+ {
319
+ "epoch": 20.5,
320
+ "learning_rate": 4.364035087719299e-06,
321
+ "loss": 1.0507,
322
+ "step": 41
323
+ },
324
+ {
325
+ "epoch": 21.0,
326
+ "learning_rate": 4.342105263157895e-06,
327
+ "loss": 1.0644,
328
+ "step": 42
329
+ },
330
+ {
331
+ "epoch": 21.5,
332
+ "learning_rate": 4.320175438596491e-06,
333
+ "loss": 1.0289,
334
+ "step": 43
335
+ },
336
+ {
337
+ "epoch": 22.0,
338
+ "learning_rate": 4.298245614035088e-06,
339
+ "loss": 1.0551,
340
+ "step": 44
341
+ },
342
+ {
343
+ "epoch": 22.5,
344
+ "learning_rate": 4.276315789473684e-06,
345
+ "loss": 1.0025,
346
+ "step": 45
347
+ },
348
+ {
349
+ "epoch": 23.0,
350
+ "learning_rate": 4.254385964912281e-06,
351
+ "loss": 1.0486,
352
+ "step": 46
353
+ },
354
+ {
355
+ "epoch": 23.5,
356
+ "learning_rate": 4.232456140350878e-06,
357
+ "loss": 1.019,
358
+ "step": 47
359
+ },
360
+ {
361
+ "epoch": 24.0,
362
+ "learning_rate": 4.210526315789474e-06,
363
+ "loss": 0.9953,
364
+ "step": 48
365
+ },
366
+ {
367
+ "epoch": 24.5,
368
+ "learning_rate": 4.1885964912280705e-06,
369
+ "loss": 0.9797,
370
+ "step": 49
371
+ },
372
+ {
373
+ "epoch": 25.0,
374
+ "learning_rate": 4.166666666666667e-06,
375
+ "loss": 1.007,
376
+ "step": 50
377
+ },
378
+ {
379
+ "epoch": 25.0,
380
+ "eval_accuracy_dropoff": 0.506777678387119,
381
+ "eval_accuracy_undropoff": 0.6849468196784603,
382
+ "eval_accuracy_unlabeled": NaN,
383
+ "eval_iou_dropoff": 0.19228861306779316,
384
+ "eval_iou_undropoff": 0.6762847927344823,
385
+ "eval_iou_unlabeled": 0.0,
386
+ "eval_loss": 0.9196955561637878,
387
+ "eval_mean_accuracy": 0.5958622490327896,
388
+ "eval_mean_iou": 0.2895244686007585,
389
+ "eval_overall_accuracy": 0.6775386810302735,
390
+ "eval_runtime": 2.8681,
391
+ "eval_samples_per_second": 6.973,
392
+ "eval_steps_per_second": 0.697,
393
+ "step": 50
394
+ },
395
+ {
396
+ "epoch": 25.5,
397
+ "learning_rate": 4.144736842105263e-06,
398
+ "loss": 0.9886,
399
+ "step": 51
400
+ },
401
+ {
402
+ "epoch": 26.0,
403
+ "learning_rate": 4.12280701754386e-06,
404
+ "loss": 0.9687,
405
+ "step": 52
406
+ },
407
+ {
408
+ "epoch": 26.5,
409
+ "learning_rate": 4.100877192982457e-06,
410
+ "loss": 0.9731,
411
+ "step": 53
412
+ },
413
+ {
414
+ "epoch": 27.0,
415
+ "learning_rate": 4.078947368421053e-06,
416
+ "loss": 0.9503,
417
+ "step": 54
418
+ },
419
+ {
420
+ "epoch": 27.5,
421
+ "learning_rate": 4.05701754385965e-06,
422
+ "loss": 0.9563,
423
+ "step": 55
424
+ },
425
+ {
426
+ "epoch": 28.0,
427
+ "learning_rate": 4.035087719298246e-06,
428
+ "loss": 0.9525,
429
+ "step": 56
430
+ },
431
+ {
432
+ "epoch": 28.5,
433
+ "learning_rate": 4.013157894736842e-06,
434
+ "loss": 0.911,
435
+ "step": 57
436
+ },
437
+ {
438
+ "epoch": 29.0,
439
+ "learning_rate": 3.991228070175439e-06,
440
+ "loss": 0.9646,
441
+ "step": 58
442
+ },
443
+ {
444
+ "epoch": 29.5,
445
+ "learning_rate": 3.969298245614036e-06,
446
+ "loss": 0.9424,
447
+ "step": 59
448
+ },
449
+ {
450
+ "epoch": 30.0,
451
+ "learning_rate": 3.947368421052632e-06,
452
+ "loss": 0.9145,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 30.0,
457
+ "eval_accuracy_dropoff": 0.5167962567948806,
458
+ "eval_accuracy_undropoff": 0.7429246639475331,
459
+ "eval_accuracy_unlabeled": NaN,
460
+ "eval_iou_dropoff": 0.21555466691667607,
461
+ "eval_iou_undropoff": 0.7329009745349515,
462
+ "eval_iou_unlabeled": 0.0,
463
+ "eval_loss": 0.8634790182113647,
464
+ "eval_mean_accuracy": 0.6298604603712068,
465
+ "eval_mean_iou": 0.3161518804838759,
466
+ "eval_overall_accuracy": 0.7335224151611328,
467
+ "eval_runtime": 2.85,
468
+ "eval_samples_per_second": 7.018,
469
+ "eval_steps_per_second": 0.702,
470
+ "step": 60
471
+ },
472
+ {
473
+ "epoch": 30.5,
474
+ "learning_rate": 3.925438596491229e-06,
475
+ "loss": 0.9084,
476
+ "step": 61
477
+ },
478
+ {
479
+ "epoch": 31.0,
480
+ "learning_rate": 3.903508771929825e-06,
481
+ "loss": 0.9234,
482
+ "step": 62
483
+ },
484
+ {
485
+ "epoch": 31.5,
486
+ "learning_rate": 3.8815789473684214e-06,
487
+ "loss": 0.9259,
488
+ "step": 63
489
+ },
490
+ {
491
+ "epoch": 32.0,
492
+ "learning_rate": 3.859649122807018e-06,
493
+ "loss": 0.8798,
494
+ "step": 64
495
+ },
496
+ {
497
+ "epoch": 32.5,
498
+ "learning_rate": 3.837719298245615e-06,
499
+ "loss": 0.8789,
500
+ "step": 65
501
+ },
502
+ {
503
+ "epoch": 33.0,
504
+ "learning_rate": 3.815789473684211e-06,
505
+ "loss": 0.8941,
506
+ "step": 66
507
+ },
508
+ {
509
+ "epoch": 33.5,
510
+ "learning_rate": 3.7938596491228073e-06,
511
+ "loss": 0.8674,
512
+ "step": 67
513
+ },
514
+ {
515
+ "epoch": 34.0,
516
+ "learning_rate": 3.7719298245614037e-06,
517
+ "loss": 0.8831,
518
+ "step": 68
519
+ },
520
+ {
521
+ "epoch": 34.5,
522
+ "learning_rate": 3.7500000000000005e-06,
523
+ "loss": 0.8512,
524
+ "step": 69
525
+ },
526
+ {
527
+ "epoch": 35.0,
528
+ "learning_rate": 3.728070175438597e-06,
529
+ "loss": 0.8745,
530
+ "step": 70
531
+ },
532
+ {
533
+ "epoch": 35.0,
534
+ "eval_accuracy_dropoff": 0.5666827220807816,
535
+ "eval_accuracy_undropoff": 0.7900781808936921,
536
+ "eval_accuracy_unlabeled": NaN,
537
+ "eval_iou_dropoff": 0.2404217803052419,
538
+ "eval_iou_undropoff": 0.7790981497740644,
539
+ "eval_iou_unlabeled": 0.0,
540
+ "eval_loss": 0.8070214986801147,
541
+ "eval_mean_accuracy": 0.6783804514872369,
542
+ "eval_mean_iou": 0.3398399766931021,
543
+ "eval_overall_accuracy": 0.780789566040039,
544
+ "eval_runtime": 2.9903,
545
+ "eval_samples_per_second": 6.688,
546
+ "eval_steps_per_second": 0.669,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 35.5,
551
+ "learning_rate": 3.7061403508771933e-06,
552
+ "loss": 0.8354,
553
+ "step": 71
554
+ },
555
+ {
556
+ "epoch": 36.0,
557
+ "learning_rate": 3.6842105263157896e-06,
558
+ "loss": 0.8436,
559
+ "step": 72
560
+ },
561
+ {
562
+ "epoch": 36.5,
563
+ "learning_rate": 3.662280701754386e-06,
564
+ "loss": 0.8022,
565
+ "step": 73
566
+ },
567
+ {
568
+ "epoch": 37.0,
569
+ "learning_rate": 3.640350877192983e-06,
570
+ "loss": 0.8872,
571
+ "step": 74
572
+ },
573
+ {
574
+ "epoch": 37.5,
575
+ "learning_rate": 3.618421052631579e-06,
576
+ "loss": 0.8419,
577
+ "step": 75
578
+ },
579
+ {
580
+ "epoch": 38.0,
581
+ "learning_rate": 3.596491228070176e-06,
582
+ "loss": 0.8014,
583
+ "step": 76
584
+ },
585
+ {
586
+ "epoch": 38.5,
587
+ "learning_rate": 3.5745614035087724e-06,
588
+ "loss": 0.8142,
589
+ "step": 77
590
+ },
591
+ {
592
+ "epoch": 39.0,
593
+ "learning_rate": 3.5526315789473687e-06,
594
+ "loss": 0.7952,
595
+ "step": 78
596
+ },
597
+ {
598
+ "epoch": 39.5,
599
+ "learning_rate": 3.530701754385965e-06,
600
+ "loss": 0.7875,
601
+ "step": 79
602
+ },
603
+ {
604
+ "epoch": 40.0,
605
+ "learning_rate": 3.5087719298245615e-06,
606
+ "loss": 0.8088,
607
+ "step": 80
608
+ },
609
+ {
610
+ "epoch": 40.0,
611
+ "eval_accuracy_dropoff": 0.5992797999954127,
612
+ "eval_accuracy_undropoff": 0.8389431797941644,
613
+ "eval_accuracy_unlabeled": NaN,
614
+ "eval_iou_dropoff": 0.27303754266211605,
615
+ "eval_iou_undropoff": 0.8271554915987344,
616
+ "eval_iou_unlabeled": 0.0,
617
+ "eval_loss": 0.7441512942314148,
618
+ "eval_mean_accuracy": 0.7191114898947886,
619
+ "eval_mean_iou": 0.36673101142028347,
620
+ "eval_overall_accuracy": 0.828978157043457,
621
+ "eval_runtime": 2.8979,
622
+ "eval_samples_per_second": 6.902,
623
+ "eval_steps_per_second": 0.69,
624
+ "step": 80
625
+ },
626
+ {
627
+ "epoch": 40.5,
628
+ "learning_rate": 3.486842105263158e-06,
629
+ "loss": 0.7679,
630
+ "step": 81
631
+ },
632
+ {
633
+ "epoch": 41.0,
634
+ "learning_rate": 3.464912280701755e-06,
635
+ "loss": 0.8128,
636
+ "step": 82
637
+ },
638
+ {
639
+ "epoch": 41.5,
640
+ "learning_rate": 3.4429824561403515e-06,
641
+ "loss": 0.805,
642
+ "step": 83
643
+ },
644
+ {
645
+ "epoch": 42.0,
646
+ "learning_rate": 3.421052631578948e-06,
647
+ "loss": 0.7599,
648
+ "step": 84
649
+ },
650
+ {
651
+ "epoch": 42.5,
652
+ "learning_rate": 3.399122807017544e-06,
653
+ "loss": 0.7712,
654
+ "step": 85
655
+ },
656
+ {
657
+ "epoch": 43.0,
658
+ "learning_rate": 3.3771929824561406e-06,
659
+ "loss": 0.7746,
660
+ "step": 86
661
+ },
662
+ {
663
+ "epoch": 43.5,
664
+ "learning_rate": 3.355263157894737e-06,
665
+ "loss": 0.7474,
666
+ "step": 87
667
+ },
668
+ {
669
+ "epoch": 44.0,
670
+ "learning_rate": 3.3333333333333333e-06,
671
+ "loss": 0.7928,
672
+ "step": 88
673
+ },
674
+ {
675
+ "epoch": 44.5,
676
+ "learning_rate": 3.3114035087719297e-06,
677
+ "loss": 0.7545,
678
+ "step": 89
679
+ },
680
+ {
681
+ "epoch": 45.0,
682
+ "learning_rate": 3.289473684210527e-06,
683
+ "loss": 0.7184,
684
+ "step": 90
685
+ },
686
+ {
687
+ "epoch": 45.0,
688
+ "eval_accuracy_dropoff": 0.6322713823711553,
689
+ "eval_accuracy_undropoff": 0.8702378263383143,
690
+ "eval_accuracy_unlabeled": NaN,
691
+ "eval_iou_dropoff": 0.2914895506858354,
692
+ "eval_iou_undropoff": 0.8580097549336819,
693
+ "eval_iou_unlabeled": 0.0,
694
+ "eval_loss": 0.6956223249435425,
695
+ "eval_mean_accuracy": 0.7512546043547348,
696
+ "eval_mean_iou": 0.3831664352065058,
697
+ "eval_overall_accuracy": 0.8603433609008789,
698
+ "eval_runtime": 2.9361,
699
+ "eval_samples_per_second": 6.812,
700
+ "eval_steps_per_second": 0.681,
701
+ "step": 90
702
+ },
703
+ {
704
+ "epoch": 45.5,
705
+ "learning_rate": 3.2675438596491233e-06,
706
+ "loss": 0.7254,
707
+ "step": 91
708
+ },
709
+ {
710
+ "epoch": 46.0,
711
+ "learning_rate": 3.2456140350877197e-06,
712
+ "loss": 0.7387,
713
+ "step": 92
714
+ },
715
+ {
716
+ "epoch": 46.5,
717
+ "learning_rate": 3.223684210526316e-06,
718
+ "loss": 0.7656,
719
+ "step": 93
720
+ },
721
+ {
722
+ "epoch": 47.0,
723
+ "learning_rate": 3.2017543859649124e-06,
724
+ "loss": 0.6769,
725
+ "step": 94
726
+ },
727
+ {
728
+ "epoch": 47.5,
729
+ "learning_rate": 3.179824561403509e-06,
730
+ "loss": 0.7103,
731
+ "step": 95
732
+ },
733
+ {
734
+ "epoch": 48.0,
735
+ "learning_rate": 3.157894736842105e-06,
736
+ "loss": 0.7061,
737
+ "step": 96
738
+ },
739
+ {
740
+ "epoch": 48.5,
741
+ "learning_rate": 3.135964912280702e-06,
742
+ "loss": 0.6942,
743
+ "step": 97
744
+ },
745
+ {
746
+ "epoch": 49.0,
747
+ "learning_rate": 3.1140350877192988e-06,
748
+ "loss": 0.6753,
749
+ "step": 98
750
+ },
751
+ {
752
+ "epoch": 49.5,
753
+ "learning_rate": 3.092105263157895e-06,
754
+ "loss": 0.6628,
755
+ "step": 99
756
+ },
757
+ {
758
+ "epoch": 50.0,
759
+ "learning_rate": 3.0701754385964915e-06,
760
+ "loss": 0.6908,
761
+ "step": 100
762
+ },
763
+ {
764
+ "epoch": 50.0,
765
+ "eval_accuracy_dropoff": 0.6332025963898255,
766
+ "eval_accuracy_undropoff": 0.8852680210591884,
767
+ "eval_accuracy_unlabeled": NaN,
768
+ "eval_iou_dropoff": 0.3066633490254799,
769
+ "eval_iou_undropoff": 0.872782516292678,
770
+ "eval_iou_unlabeled": 0.0,
771
+ "eval_loss": 0.6750925779342651,
772
+ "eval_mean_accuracy": 0.759235308724507,
773
+ "eval_mean_iou": 0.3931486217727193,
774
+ "eval_overall_accuracy": 0.8747873306274414,
775
+ "eval_runtime": 2.9141,
776
+ "eval_samples_per_second": 6.863,
777
+ "eval_steps_per_second": 0.686,
778
+ "step": 100
779
+ },
780
+ {
781
+ "epoch": 50.5,
782
+ "learning_rate": 3.048245614035088e-06,
783
+ "loss": 0.674,
784
+ "step": 101
785
+ },
786
+ {
787
+ "epoch": 51.0,
788
+ "learning_rate": 3.0263157894736843e-06,
789
+ "loss": 0.7057,
790
+ "step": 102
791
+ },
792
+ {
793
+ "epoch": 51.5,
794
+ "learning_rate": 3.004385964912281e-06,
795
+ "loss": 0.6581,
796
+ "step": 103
797
+ },
798
+ {
799
+ "epoch": 52.0,
800
+ "learning_rate": 2.9824561403508774e-06,
801
+ "loss": 0.6645,
802
+ "step": 104
803
+ },
804
+ {
805
+ "epoch": 52.5,
806
+ "learning_rate": 2.960526315789474e-06,
807
+ "loss": 0.711,
808
+ "step": 105
809
+ },
810
+ {
811
+ "epoch": 53.0,
812
+ "learning_rate": 2.9385964912280706e-06,
813
+ "loss": 0.6255,
814
+ "step": 106
815
+ },
816
+ {
817
+ "epoch": 53.5,
818
+ "learning_rate": 2.916666666666667e-06,
819
+ "loss": 0.6572,
820
+ "step": 107
821
+ },
822
+ {
823
+ "epoch": 54.0,
824
+ "learning_rate": 2.8947368421052634e-06,
825
+ "loss": 0.6244,
826
+ "step": 108
827
+ },
828
+ {
829
+ "epoch": 54.5,
830
+ "learning_rate": 2.8728070175438597e-06,
831
+ "loss": 0.6323,
832
+ "step": 109
833
+ },
834
+ {
835
+ "epoch": 55.0,
836
+ "learning_rate": 2.8508771929824565e-06,
837
+ "loss": 0.643,
838
+ "step": 110
839
+ },
840
+ {
841
+ "epoch": 55.0,
842
+ "eval_accuracy_dropoff": 0.6194224638179775,
843
+ "eval_accuracy_undropoff": 0.923405212258589,
844
+ "eval_accuracy_unlabeled": NaN,
845
+ "eval_iou_dropoff": 0.3308480506497834,
846
+ "eval_iou_undropoff": 0.9093924657307382,
847
+ "eval_iou_unlabeled": 0.0,
848
+ "eval_loss": 0.6101020574569702,
849
+ "eval_mean_accuracy": 0.7714138380382832,
850
+ "eval_mean_iou": 0.4134135054601738,
851
+ "eval_overall_accuracy": 0.9107658386230468,
852
+ "eval_runtime": 2.8349,
853
+ "eval_samples_per_second": 7.055,
854
+ "eval_steps_per_second": 0.705,
855
+ "step": 110
856
+ },
857
+ {
858
+ "epoch": 55.5,
859
+ "learning_rate": 2.828947368421053e-06,
860
+ "loss": 0.6638,
861
+ "step": 111
862
+ },
863
+ {
864
+ "epoch": 56.0,
865
+ "learning_rate": 2.8070175438596493e-06,
866
+ "loss": 0.5887,
867
+ "step": 112
868
+ },
869
+ {
870
+ "epoch": 56.5,
871
+ "learning_rate": 2.7850877192982456e-06,
872
+ "loss": 0.648,
873
+ "step": 113
874
+ },
875
+ {
876
+ "epoch": 57.0,
877
+ "learning_rate": 2.7631578947368424e-06,
878
+ "loss": 0.578,
879
+ "step": 114
880
+ },
881
+ {
882
+ "epoch": 57.5,
883
+ "learning_rate": 2.741228070175439e-06,
884
+ "loss": 0.6064,
885
+ "step": 115
886
+ },
887
+ {
888
+ "epoch": 58.0,
889
+ "learning_rate": 2.7192982456140356e-06,
890
+ "loss": 0.6784,
891
+ "step": 116
892
+ },
893
+ {
894
+ "epoch": 58.5,
895
+ "learning_rate": 2.697368421052632e-06,
896
+ "loss": 0.624,
897
+ "step": 117
898
+ },
899
+ {
900
+ "epoch": 59.0,
901
+ "learning_rate": 2.6754385964912284e-06,
902
+ "loss": 0.6188,
903
+ "step": 118
904
+ },
905
+ {
906
+ "epoch": 59.5,
907
+ "learning_rate": 2.6535087719298247e-06,
908
+ "loss": 0.607,
909
+ "step": 119
910
+ },
911
+ {
912
+ "epoch": 60.0,
913
+ "learning_rate": 2.631578947368421e-06,
914
+ "loss": 0.6014,
915
+ "step": 120
916
+ },
917
+ {
918
+ "epoch": 60.0,
919
+ "eval_accuracy_dropoff": 0.6338585747379527,
920
+ "eval_accuracy_undropoff": 0.9313126569065759,
921
+ "eval_accuracy_unlabeled": NaN,
922
+ "eval_iou_dropoff": 0.3323511938406625,
923
+ "eval_iou_undropoff": 0.9174802078875154,
924
+ "eval_iou_unlabeled": 0.0,
925
+ "eval_loss": 0.5971364974975586,
926
+ "eval_mean_accuracy": 0.7825856158222644,
927
+ "eval_mean_iou": 0.41661046724272593,
928
+ "eval_overall_accuracy": 0.9189447402954102,
929
+ "eval_runtime": 3.1128,
930
+ "eval_samples_per_second": 6.425,
931
+ "eval_steps_per_second": 0.643,
932
+ "step": 120
933
+ }
934
+ ],
935
+ "max_steps": 240,
936
+ "num_train_epochs": 120,
937
+ "total_flos": 6.945599099555021e+17,
938
+ "trial_name": null,
939
+ "trial_params": null
940
+ }
checkpoint-120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19dbb8838bbc178e3d0786cc91c0faed98fee5c083914189844b76cc687b2276
3
+ size 4155
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e665fd54ef91e119801a4b95dfe3cf2dc2d09fb672da609e6edde26a72220dd
3
  size 338796489
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd674207f8a506d763da21af79a71a811294cf6832ccedadac708ee579fb06a
3
  size 338796489
runs/Feb12_08-24-49_robovision.csres.utexas.edu/events.out.tfevents.1707747895.robovision.csres.utexas.edu.2833461.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f37eb30c8bc2018428790d4e6ec5f0cf50898697cc49a0f548e236c708744b5
3
- size 23328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df132efa3bbd80871bf945c7ca2d97f3ff392dfead953014c781becbd00eef7c
3
+ size 32604