sam1120 commited on
Commit
34ca211
1 Parent(s): 0c59b9d

Training in progress, step 120

Browse files
checkpoint-120/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": "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": 6,
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:b4cee78cea20ab758b9daf848d73b7f47369a698e0374133e16adb6e3b69cc4e
3
+ size 29876485
checkpoint-120/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:038fba4f64c9f6ec3b43595b56d4c0c6a9fb20b5770e4abaa0deaeebe020f8c9
3
+ size 14951629
checkpoint-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04b46b261d14fecd73ba66387b3f4629081598b88c439e27184f26d8ce1edea
3
+ size 14575
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b327a48bc6952b63ba98db059a1f9072885b11acaf3c14f4ae0ef68dd6f7224
3
+ size 627
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3119274079799652,
3
+ "best_model_checkpoint": "/robodata/smodak/Projects/nspl/scripts/terrainseg/training/models/dropoff-utcustom-train-SF-RGBD-b0_5/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": 4.9999999999999996e-06,
13
+ "loss": 0.9932,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 9.999999999999999e-06,
19
+ "loss": 0.9915,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 1.5,
24
+ "learning_rate": 1.5e-05,
25
+ "loss": 0.9957,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "learning_rate": 1.9999999999999998e-05,
31
+ "loss": 0.9918,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 2.5,
36
+ "learning_rate": 2.5e-05,
37
+ "loss": 0.9772,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 3e-05,
43
+ "loss": 0.9703,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 3.5,
48
+ "learning_rate": 3.5000000000000004e-05,
49
+ "loss": 0.9584,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 3.9999999999999996e-05,
55
+ "loss": 0.9508,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 4.5,
60
+ "learning_rate": 4.5e-05,
61
+ "loss": 0.9357,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 5.0,
66
+ "learning_rate": 5e-05,
67
+ "loss": 0.9263,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "eval_accuracy_dropoff": 0.6617766462533544,
73
+ "eval_accuracy_undropoff": 0.7675487100699817,
74
+ "eval_accuracy_unlabeled": NaN,
75
+ "eval_iou_dropoff": 0.10419987677799743,
76
+ "eval_iou_undropoff": 0.7564535036864135,
77
+ "eval_iou_unlabeled": 0.0,
78
+ "eval_loss": 1.0369741916656494,
79
+ "eval_mean_accuracy": 0.7146626781616681,
80
+ "eval_mean_iou": 0.2868844601548037,
81
+ "eval_overall_accuracy": 0.7631507873535156,
82
+ "eval_runtime": 2.7168,
83
+ "eval_samples_per_second": 7.362,
84
+ "eval_steps_per_second": 0.736,
85
+ "step": 10
86
+ },
87
+ {
88
+ "epoch": 5.5,
89
+ "learning_rate": 5.5e-05,
90
+ "loss": 0.9136,
91
+ "step": 11
92
+ },
93
+ {
94
+ "epoch": 6.0,
95
+ "learning_rate": 6e-05,
96
+ "loss": 0.9077,
97
+ "step": 12
98
+ },
99
+ {
100
+ "epoch": 6.5,
101
+ "learning_rate": 5.973684210526316e-05,
102
+ "loss": 0.9036,
103
+ "step": 13
104
+ },
105
+ {
106
+ "epoch": 7.0,
107
+ "learning_rate": 5.9473684210526315e-05,
108
+ "loss": 0.8739,
109
+ "step": 14
110
+ },
111
+ {
112
+ "epoch": 7.5,
113
+ "learning_rate": 5.921052631578947e-05,
114
+ "loss": 0.8603,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 8.0,
119
+ "learning_rate": 5.894736842105263e-05,
120
+ "loss": 0.8455,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 8.5,
125
+ "learning_rate": 5.868421052631579e-05,
126
+ "loss": 0.8318,
127
+ "step": 17
128
+ },
129
+ {
130
+ "epoch": 9.0,
131
+ "learning_rate": 5.842105263157895e-05,
132
+ "loss": 0.824,
133
+ "step": 18
134
+ },
135
+ {
136
+ "epoch": 9.5,
137
+ "learning_rate": 5.815789473684211e-05,
138
+ "loss": 0.8011,
139
+ "step": 19
140
+ },
141
+ {
142
+ "epoch": 10.0,
143
+ "learning_rate": 5.789473684210527e-05,
144
+ "loss": 0.8069,
145
+ "step": 20
146
+ },
147
+ {
148
+ "epoch": 10.0,
149
+ "eval_accuracy_dropoff": 0.012454414092066332,
150
+ "eval_accuracy_undropoff": 0.9999438793126609,
151
+ "eval_accuracy_unlabeled": NaN,
152
+ "eval_iou_dropoff": 0.01243832378125043,
153
+ "eval_iou_undropoff": 0.9588635090688938,
154
+ "eval_iou_unlabeled": NaN,
155
+ "eval_loss": 0.8622230291366577,
156
+ "eval_mean_accuracy": 0.5061991467023637,
157
+ "eval_mean_iou": 0.48565091642507213,
158
+ "eval_overall_accuracy": 0.9588848114013672,
159
+ "eval_runtime": 2.8264,
160
+ "eval_samples_per_second": 7.076,
161
+ "eval_steps_per_second": 0.708,
162
+ "step": 20
163
+ },
164
+ {
165
+ "epoch": 10.5,
166
+ "learning_rate": 5.7631578947368423e-05,
167
+ "loss": 0.7927,
168
+ "step": 21
169
+ },
170
+ {
171
+ "epoch": 11.0,
172
+ "learning_rate": 5.736842105263158e-05,
173
+ "loss": 0.7775,
174
+ "step": 22
175
+ },
176
+ {
177
+ "epoch": 11.5,
178
+ "learning_rate": 5.7105263157894736e-05,
179
+ "loss": 0.7684,
180
+ "step": 23
181
+ },
182
+ {
183
+ "epoch": 12.0,
184
+ "learning_rate": 5.684210526315789e-05,
185
+ "loss": 0.7542,
186
+ "step": 24
187
+ },
188
+ {
189
+ "epoch": 12.5,
190
+ "learning_rate": 5.6578947368421056e-05,
191
+ "loss": 0.751,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 13.0,
196
+ "learning_rate": 5.631578947368421e-05,
197
+ "loss": 0.7325,
198
+ "step": 26
199
+ },
200
+ {
201
+ "epoch": 13.5,
202
+ "learning_rate": 5.605263157894737e-05,
203
+ "loss": 0.7199,
204
+ "step": 27
205
+ },
206
+ {
207
+ "epoch": 14.0,
208
+ "learning_rate": 5.5789473684210526e-05,
209
+ "loss": 0.7194,
210
+ "step": 28
211
+ },
212
+ {
213
+ "epoch": 14.5,
214
+ "learning_rate": 5.552631578947368e-05,
215
+ "loss": 0.7123,
216
+ "step": 29
217
+ },
218
+ {
219
+ "epoch": 15.0,
220
+ "learning_rate": 5.5263157894736845e-05,
221
+ "loss": 0.6851,
222
+ "step": 30
223
+ },
224
+ {
225
+ "epoch": 15.0,
226
+ "eval_accuracy_dropoff": 0.016743503291359894,
227
+ "eval_accuracy_undropoff": 0.9994596891272138,
228
+ "eval_accuracy_unlabeled": NaN,
229
+ "eval_iou_dropoff": 0.01653753794572063,
230
+ "eval_iou_undropoff": 0.9585702479181101,
231
+ "eval_iou_unlabeled": NaN,
232
+ "eval_loss": 0.649047315120697,
233
+ "eval_mean_accuracy": 0.5081015962092869,
234
+ "eval_mean_iou": 0.48755389293191537,
235
+ "eval_overall_accuracy": 0.9585990905761719,
236
+ "eval_runtime": 2.8111,
237
+ "eval_samples_per_second": 7.115,
238
+ "eval_steps_per_second": 0.711,
239
+ "step": 30
240
+ },
241
+ {
242
+ "epoch": 15.5,
243
+ "learning_rate": 5.5e-05,
244
+ "loss": 0.6899,
245
+ "step": 31
246
+ },
247
+ {
248
+ "epoch": 16.0,
249
+ "learning_rate": 5.473684210526316e-05,
250
+ "loss": 0.699,
251
+ "step": 32
252
+ },
253
+ {
254
+ "epoch": 16.5,
255
+ "learning_rate": 5.447368421052632e-05,
256
+ "loss": 0.6628,
257
+ "step": 33
258
+ },
259
+ {
260
+ "epoch": 17.0,
261
+ "learning_rate": 5.421052631578948e-05,
262
+ "loss": 0.6454,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 17.5,
267
+ "learning_rate": 5.3947368421052635e-05,
268
+ "loss": 0.6433,
269
+ "step": 35
270
+ },
271
+ {
272
+ "epoch": 18.0,
273
+ "learning_rate": 5.368421052631579e-05,
274
+ "loss": 0.6197,
275
+ "step": 36
276
+ },
277
+ {
278
+ "epoch": 18.5,
279
+ "learning_rate": 5.342105263157895e-05,
280
+ "loss": 0.5929,
281
+ "step": 37
282
+ },
283
+ {
284
+ "epoch": 19.0,
285
+ "learning_rate": 5.3157894736842104e-05,
286
+ "loss": 0.6429,
287
+ "step": 38
288
+ },
289
+ {
290
+ "epoch": 19.5,
291
+ "learning_rate": 5.289473684210526e-05,
292
+ "loss": 0.6129,
293
+ "step": 39
294
+ },
295
+ {
296
+ "epoch": 20.0,
297
+ "learning_rate": 5.263157894736842e-05,
298
+ "loss": 0.5882,
299
+ "step": 40
300
+ },
301
+ {
302
+ "epoch": 20.0,
303
+ "eval_accuracy_dropoff": 0.017670130048854333,
304
+ "eval_accuracy_undropoff": 0.9993924239062187,
305
+ "eval_accuracy_unlabeled": NaN,
306
+ "eval_iou_dropoff": 0.017427892772310823,
307
+ "eval_iou_undropoff": 0.9585426915068979,
308
+ "eval_iou_unlabeled": 0.0,
309
+ "eval_loss": 0.47389930486679077,
310
+ "eval_mean_accuracy": 0.5085312769775365,
311
+ "eval_mean_iou": 0.3253235280930696,
312
+ "eval_overall_accuracy": 0.9585731506347657,
313
+ "eval_runtime": 2.9413,
314
+ "eval_samples_per_second": 6.8,
315
+ "eval_steps_per_second": 0.68,
316
+ "step": 40
317
+ },
318
+ {
319
+ "epoch": 20.5,
320
+ "learning_rate": 5.236842105263158e-05,
321
+ "loss": 0.6071,
322
+ "step": 41
323
+ },
324
+ {
325
+ "epoch": 21.0,
326
+ "learning_rate": 5.210526315789474e-05,
327
+ "loss": 0.5821,
328
+ "step": 42
329
+ },
330
+ {
331
+ "epoch": 21.5,
332
+ "learning_rate": 5.18421052631579e-05,
333
+ "loss": 0.6139,
334
+ "step": 43
335
+ },
336
+ {
337
+ "epoch": 22.0,
338
+ "learning_rate": 5.157894736842106e-05,
339
+ "loss": 0.5813,
340
+ "step": 44
341
+ },
342
+ {
343
+ "epoch": 22.5,
344
+ "learning_rate": 5.131578947368421e-05,
345
+ "loss": 0.5747,
346
+ "step": 45
347
+ },
348
+ {
349
+ "epoch": 23.0,
350
+ "learning_rate": 5.105263157894737e-05,
351
+ "loss": 0.5474,
352
+ "step": 46
353
+ },
354
+ {
355
+ "epoch": 23.5,
356
+ "learning_rate": 5.0789473684210526e-05,
357
+ "loss": 0.5487,
358
+ "step": 47
359
+ },
360
+ {
361
+ "epoch": 24.0,
362
+ "learning_rate": 5.052631578947368e-05,
363
+ "loss": 0.5498,
364
+ "step": 48
365
+ },
366
+ {
367
+ "epoch": 24.5,
368
+ "learning_rate": 5.0263157894736846e-05,
369
+ "loss": 0.5379,
370
+ "step": 49
371
+ },
372
+ {
373
+ "epoch": 25.0,
374
+ "learning_rate": 5e-05,
375
+ "loss": 0.53,
376
+ "step": 50
377
+ },
378
+ {
379
+ "epoch": 25.0,
380
+ "eval_accuracy_dropoff": 0.057308653868207986,
381
+ "eval_accuracy_undropoff": 0.997473574022092,
382
+ "eval_accuracy_unlabeled": NaN,
383
+ "eval_iou_dropoff": 0.05417770704227795,
384
+ "eval_iou_undropoff": 0.9582828192254225,
385
+ "eval_iou_unlabeled": 0.0,
386
+ "eval_loss": 0.4153165817260742,
387
+ "eval_mean_accuracy": 0.52739111394515,
388
+ "eval_mean_iou": 0.33748684208923346,
389
+ "eval_overall_accuracy": 0.9583822250366211,
390
+ "eval_runtime": 2.8555,
391
+ "eval_samples_per_second": 7.004,
392
+ "eval_steps_per_second": 0.7,
393
+ "step": 50
394
+ },
395
+ {
396
+ "epoch": 25.5,
397
+ "learning_rate": 4.973684210526316e-05,
398
+ "loss": 0.5316,
399
+ "step": 51
400
+ },
401
+ {
402
+ "epoch": 26.0,
403
+ "learning_rate": 4.9473684210526315e-05,
404
+ "loss": 0.5182,
405
+ "step": 52
406
+ },
407
+ {
408
+ "epoch": 26.5,
409
+ "learning_rate": 4.921052631578947e-05,
410
+ "loss": 0.5111,
411
+ "step": 53
412
+ },
413
+ {
414
+ "epoch": 27.0,
415
+ "learning_rate": 4.8947368421052635e-05,
416
+ "loss": 0.5123,
417
+ "step": 54
418
+ },
419
+ {
420
+ "epoch": 27.5,
421
+ "learning_rate": 4.868421052631579e-05,
422
+ "loss": 0.503,
423
+ "step": 55
424
+ },
425
+ {
426
+ "epoch": 28.0,
427
+ "learning_rate": 4.842105263157895e-05,
428
+ "loss": 0.4843,
429
+ "step": 56
430
+ },
431
+ {
432
+ "epoch": 28.5,
433
+ "learning_rate": 4.815789473684211e-05,
434
+ "loss": 0.511,
435
+ "step": 57
436
+ },
437
+ {
438
+ "epoch": 29.0,
439
+ "learning_rate": 4.789473684210527e-05,
440
+ "loss": 0.5023,
441
+ "step": 58
442
+ },
443
+ {
444
+ "epoch": 29.5,
445
+ "learning_rate": 4.7631578947368424e-05,
446
+ "loss": 0.504,
447
+ "step": 59
448
+ },
449
+ {
450
+ "epoch": 30.0,
451
+ "learning_rate": 4.736842105263158e-05,
452
+ "loss": 0.5009,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 30.0,
457
+ "eval_accuracy_dropoff": 0.3230165829491502,
458
+ "eval_accuracy_undropoff": 0.9745914583119812,
459
+ "eval_accuracy_unlabeled": NaN,
460
+ "eval_iou_dropoff": 0.20371640094081706,
461
+ "eval_iou_undropoff": 0.946784743209426,
462
+ "eval_iou_unlabeled": 0.0,
463
+ "eval_loss": 0.4274832606315613,
464
+ "eval_mean_accuracy": 0.6488040206305657,
465
+ "eval_mean_iou": 0.38350038138341436,
466
+ "eval_overall_accuracy": 0.9474994659423828,
467
+ "eval_runtime": 2.8386,
468
+ "eval_samples_per_second": 7.046,
469
+ "eval_steps_per_second": 0.705,
470
+ "step": 60
471
+ },
472
+ {
473
+ "epoch": 30.5,
474
+ "learning_rate": 4.710526315789474e-05,
475
+ "loss": 0.4875,
476
+ "step": 61
477
+ },
478
+ {
479
+ "epoch": 31.0,
480
+ "learning_rate": 4.6842105263157894e-05,
481
+ "loss": 0.4752,
482
+ "step": 62
483
+ },
484
+ {
485
+ "epoch": 31.5,
486
+ "learning_rate": 4.657894736842105e-05,
487
+ "loss": 0.4921,
488
+ "step": 63
489
+ },
490
+ {
491
+ "epoch": 32.0,
492
+ "learning_rate": 4.631578947368421e-05,
493
+ "loss": 0.4734,
494
+ "step": 64
495
+ },
496
+ {
497
+ "epoch": 32.5,
498
+ "learning_rate": 4.605263157894737e-05,
499
+ "loss": 0.4495,
500
+ "step": 65
501
+ },
502
+ {
503
+ "epoch": 33.0,
504
+ "learning_rate": 4.5789473684210527e-05,
505
+ "loss": 0.4543,
506
+ "step": 66
507
+ },
508
+ {
509
+ "epoch": 33.5,
510
+ "learning_rate": 4.552631578947369e-05,
511
+ "loss": 0.4517,
512
+ "step": 67
513
+ },
514
+ {
515
+ "epoch": 34.0,
516
+ "learning_rate": 4.5263157894736846e-05,
517
+ "loss": 0.4487,
518
+ "step": 68
519
+ },
520
+ {
521
+ "epoch": 34.5,
522
+ "learning_rate": 4.5e-05,
523
+ "loss": 0.4513,
524
+ "step": 69
525
+ },
526
+ {
527
+ "epoch": 35.0,
528
+ "learning_rate": 4.473684210526316e-05,
529
+ "loss": 0.4699,
530
+ "step": 70
531
+ },
532
+ {
533
+ "epoch": 35.0,
534
+ "eval_accuracy_dropoff": 0.4157021950044726,
535
+ "eval_accuracy_undropoff": 0.9812761884102821,
536
+ "eval_accuracy_unlabeled": NaN,
537
+ "eval_iou_dropoff": 0.29037932824486185,
538
+ "eval_iou_undropoff": 0.9570171064769841,
539
+ "eval_iou_unlabeled": 0.0,
540
+ "eval_loss": 0.38186168670654297,
541
+ "eval_mean_accuracy": 0.6984891917073773,
542
+ "eval_mean_iou": 0.41579881157394866,
543
+ "eval_overall_accuracy": 0.9577600479125976,
544
+ "eval_runtime": 2.892,
545
+ "eval_samples_per_second": 6.916,
546
+ "eval_steps_per_second": 0.692,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 35.5,
551
+ "learning_rate": 4.4473684210526316e-05,
552
+ "loss": 0.4379,
553
+ "step": 71
554
+ },
555
+ {
556
+ "epoch": 36.0,
557
+ "learning_rate": 4.421052631578947e-05,
558
+ "loss": 0.4571,
559
+ "step": 72
560
+ },
561
+ {
562
+ "epoch": 36.5,
563
+ "learning_rate": 4.394736842105263e-05,
564
+ "loss": 0.4492,
565
+ "step": 73
566
+ },
567
+ {
568
+ "epoch": 37.0,
569
+ "learning_rate": 4.368421052631579e-05,
570
+ "loss": 0.4127,
571
+ "step": 74
572
+ },
573
+ {
574
+ "epoch": 37.5,
575
+ "learning_rate": 4.342105263157895e-05,
576
+ "loss": 0.4171,
577
+ "step": 75
578
+ },
579
+ {
580
+ "epoch": 38.0,
581
+ "learning_rate": 4.3157894736842105e-05,
582
+ "loss": 0.4115,
583
+ "step": 76
584
+ },
585
+ {
586
+ "epoch": 38.5,
587
+ "learning_rate": 4.289473684210526e-05,
588
+ "loss": 0.4204,
589
+ "step": 77
590
+ },
591
+ {
592
+ "epoch": 39.0,
593
+ "learning_rate": 4.2631578947368425e-05,
594
+ "loss": 0.4289,
595
+ "step": 78
596
+ },
597
+ {
598
+ "epoch": 39.5,
599
+ "learning_rate": 4.236842105263158e-05,
600
+ "loss": 0.4148,
601
+ "step": 79
602
+ },
603
+ {
604
+ "epoch": 40.0,
605
+ "learning_rate": 4.210526315789474e-05,
606
+ "loss": 0.3946,
607
+ "step": 80
608
+ },
609
+ {
610
+ "epoch": 40.0,
611
+ "eval_accuracy_dropoff": 0.3853758113718205,
612
+ "eval_accuracy_undropoff": 0.9833942468335096,
613
+ "eval_accuracy_unlabeled": NaN,
614
+ "eval_iou_dropoff": 0.27869836814989535,
615
+ "eval_iou_undropoff": 0.9578537547951392,
616
+ "eval_iou_unlabeled": NaN,
617
+ "eval_loss": 0.3562777638435364,
618
+ "eval_mean_accuracy": 0.6843850291026651,
619
+ "eval_mean_iou": 0.6182760614725173,
620
+ "eval_overall_accuracy": 0.9585290908813476,
621
+ "eval_runtime": 2.8829,
622
+ "eval_samples_per_second": 6.937,
623
+ "eval_steps_per_second": 0.694,
624
+ "step": 80
625
+ },
626
+ {
627
+ "epoch": 40.5,
628
+ "learning_rate": 4.1842105263157894e-05,
629
+ "loss": 0.4187,
630
+ "step": 81
631
+ },
632
+ {
633
+ "epoch": 41.0,
634
+ "learning_rate": 4.157894736842106e-05,
635
+ "loss": 0.3983,
636
+ "step": 82
637
+ },
638
+ {
639
+ "epoch": 41.5,
640
+ "learning_rate": 4.1315789473684214e-05,
641
+ "loss": 0.401,
642
+ "step": 83
643
+ },
644
+ {
645
+ "epoch": 42.0,
646
+ "learning_rate": 4.105263157894737e-05,
647
+ "loss": 0.3948,
648
+ "step": 84
649
+ },
650
+ {
651
+ "epoch": 42.5,
652
+ "learning_rate": 4.078947368421053e-05,
653
+ "loss": 0.3945,
654
+ "step": 85
655
+ },
656
+ {
657
+ "epoch": 43.0,
658
+ "learning_rate": 4.0526315789473684e-05,
659
+ "loss": 0.3759,
660
+ "step": 86
661
+ },
662
+ {
663
+ "epoch": 43.5,
664
+ "learning_rate": 4.026315789473684e-05,
665
+ "loss": 0.4164,
666
+ "step": 87
667
+ },
668
+ {
669
+ "epoch": 44.0,
670
+ "learning_rate": 3.9999999999999996e-05,
671
+ "loss": 0.3946,
672
+ "step": 88
673
+ },
674
+ {
675
+ "epoch": 44.5,
676
+ "learning_rate": 3.973684210526315e-05,
677
+ "loss": 0.4144,
678
+ "step": 89
679
+ },
680
+ {
681
+ "epoch": 45.0,
682
+ "learning_rate": 3.9473684210526316e-05,
683
+ "loss": 0.3788,
684
+ "step": 90
685
+ },
686
+ {
687
+ "epoch": 45.0,
688
+ "eval_accuracy_dropoff": 0.4196151287873575,
689
+ "eval_accuracy_undropoff": 0.9826666679933969,
690
+ "eval_accuracy_unlabeled": NaN,
691
+ "eval_iou_dropoff": 0.29982333255761356,
692
+ "eval_iou_undropoff": 0.9585319037171599,
693
+ "eval_iou_unlabeled": NaN,
694
+ "eval_loss": 0.3259146809577942,
695
+ "eval_mean_accuracy": 0.7011408983903772,
696
+ "eval_mean_iou": 0.6291776181373867,
697
+ "eval_overall_accuracy": 0.9592554092407226,
698
+ "eval_runtime": 2.8842,
699
+ "eval_samples_per_second": 6.934,
700
+ "eval_steps_per_second": 0.693,
701
+ "step": 90
702
+ },
703
+ {
704
+ "epoch": 45.5,
705
+ "learning_rate": 3.921052631578948e-05,
706
+ "loss": 0.3577,
707
+ "step": 91
708
+ },
709
+ {
710
+ "epoch": 46.0,
711
+ "learning_rate": 3.8947368421052636e-05,
712
+ "loss": 0.3748,
713
+ "step": 92
714
+ },
715
+ {
716
+ "epoch": 46.5,
717
+ "learning_rate": 3.868421052631579e-05,
718
+ "loss": 0.3641,
719
+ "step": 93
720
+ },
721
+ {
722
+ "epoch": 47.0,
723
+ "learning_rate": 3.842105263157895e-05,
724
+ "loss": 0.3444,
725
+ "step": 94
726
+ },
727
+ {
728
+ "epoch": 47.5,
729
+ "learning_rate": 3.8157894736842105e-05,
730
+ "loss": 0.3776,
731
+ "step": 95
732
+ },
733
+ {
734
+ "epoch": 48.0,
735
+ "learning_rate": 3.789473684210526e-05,
736
+ "loss": 0.3474,
737
+ "step": 96
738
+ },
739
+ {
740
+ "epoch": 48.5,
741
+ "learning_rate": 3.763157894736842e-05,
742
+ "loss": 0.3546,
743
+ "step": 97
744
+ },
745
+ {
746
+ "epoch": 49.0,
747
+ "learning_rate": 3.736842105263158e-05,
748
+ "loss": 0.3562,
749
+ "step": 98
750
+ },
751
+ {
752
+ "epoch": 49.5,
753
+ "learning_rate": 3.710526315789474e-05,
754
+ "loss": 0.3387,
755
+ "step": 99
756
+ },
757
+ {
758
+ "epoch": 50.0,
759
+ "learning_rate": 3.6842105263157895e-05,
760
+ "loss": 0.3412,
761
+ "step": 100
762
+ },
763
+ {
764
+ "epoch": 50.0,
765
+ "eval_accuracy_dropoff": 0.4065873070483268,
766
+ "eval_accuracy_undropoff": 0.9800554639558915,
767
+ "eval_accuracy_unlabeled": NaN,
768
+ "eval_iou_dropoff": 0.2785358280905303,
769
+ "eval_iou_undropoff": 0.9554580825207023,
770
+ "eval_iou_unlabeled": NaN,
771
+ "eval_loss": 0.3391803801059723,
772
+ "eval_mean_accuracy": 0.6933213855021092,
773
+ "eval_mean_iou": 0.6169969553056163,
774
+ "eval_overall_accuracy": 0.9562110900878906,
775
+ "eval_runtime": 2.9168,
776
+ "eval_samples_per_second": 6.857,
777
+ "eval_steps_per_second": 0.686,
778
+ "step": 100
779
+ },
780
+ {
781
+ "epoch": 50.5,
782
+ "learning_rate": 3.657894736842105e-05,
783
+ "loss": 0.3485,
784
+ "step": 101
785
+ },
786
+ {
787
+ "epoch": 51.0,
788
+ "learning_rate": 3.6315789473684214e-05,
789
+ "loss": 0.3646,
790
+ "step": 102
791
+ },
792
+ {
793
+ "epoch": 51.5,
794
+ "learning_rate": 3.605263157894737e-05,
795
+ "loss": 0.3234,
796
+ "step": 103
797
+ },
798
+ {
799
+ "epoch": 52.0,
800
+ "learning_rate": 3.578947368421053e-05,
801
+ "loss": 0.3435,
802
+ "step": 104
803
+ },
804
+ {
805
+ "epoch": 52.5,
806
+ "learning_rate": 3.5526315789473684e-05,
807
+ "loss": 0.3357,
808
+ "step": 105
809
+ },
810
+ {
811
+ "epoch": 53.0,
812
+ "learning_rate": 3.526315789473685e-05,
813
+ "loss": 0.3317,
814
+ "step": 106
815
+ },
816
+ {
817
+ "epoch": 53.5,
818
+ "learning_rate": 3.5000000000000004e-05,
819
+ "loss": 0.3166,
820
+ "step": 107
821
+ },
822
+ {
823
+ "epoch": 54.0,
824
+ "learning_rate": 3.473684210526316e-05,
825
+ "loss": 0.3606,
826
+ "step": 108
827
+ },
828
+ {
829
+ "epoch": 54.5,
830
+ "learning_rate": 3.447368421052632e-05,
831
+ "loss": 0.3257,
832
+ "step": 109
833
+ },
834
+ {
835
+ "epoch": 55.0,
836
+ "learning_rate": 3.421052631578947e-05,
837
+ "loss": 0.3326,
838
+ "step": 110
839
+ },
840
+ {
841
+ "epoch": 55.0,
842
+ "eval_accuracy_dropoff": 0.3976513222780339,
843
+ "eval_accuracy_undropoff": 0.9850716981582663,
844
+ "eval_accuracy_unlabeled": NaN,
845
+ "eval_iou_dropoff": 0.29584857751324195,
846
+ "eval_iou_undropoff": 0.9599856017830206,
847
+ "eval_iou_unlabeled": NaN,
848
+ "eval_loss": 0.32138317823410034,
849
+ "eval_mean_accuracy": 0.6913615102181501,
850
+ "eval_mean_iou": 0.6279170896481313,
851
+ "eval_overall_accuracy": 0.9606472015380859,
852
+ "eval_runtime": 2.8472,
853
+ "eval_samples_per_second": 7.024,
854
+ "eval_steps_per_second": 0.702,
855
+ "step": 110
856
+ },
857
+ {
858
+ "epoch": 55.5,
859
+ "learning_rate": 3.394736842105263e-05,
860
+ "loss": 0.3169,
861
+ "step": 111
862
+ },
863
+ {
864
+ "epoch": 56.0,
865
+ "learning_rate": 3.3684210526315786e-05,
866
+ "loss": 0.297,
867
+ "step": 112
868
+ },
869
+ {
870
+ "epoch": 56.5,
871
+ "learning_rate": 3.342105263157894e-05,
872
+ "loss": 0.3307,
873
+ "step": 113
874
+ },
875
+ {
876
+ "epoch": 57.0,
877
+ "learning_rate": 3.3157894736842106e-05,
878
+ "loss": 0.2873,
879
+ "step": 114
880
+ },
881
+ {
882
+ "epoch": 57.5,
883
+ "learning_rate": 3.289473684210527e-05,
884
+ "loss": 0.3111,
885
+ "step": 115
886
+ },
887
+ {
888
+ "epoch": 58.0,
889
+ "learning_rate": 3.2631578947368426e-05,
890
+ "loss": 0.3102,
891
+ "step": 116
892
+ },
893
+ {
894
+ "epoch": 58.5,
895
+ "learning_rate": 3.236842105263158e-05,
896
+ "loss": 0.3094,
897
+ "step": 117
898
+ },
899
+ {
900
+ "epoch": 59.0,
901
+ "learning_rate": 3.210526315789474e-05,
902
+ "loss": 0.3189,
903
+ "step": 118
904
+ },
905
+ {
906
+ "epoch": 59.5,
907
+ "learning_rate": 3.1842105263157895e-05,
908
+ "loss": 0.3024,
909
+ "step": 119
910
+ },
911
+ {
912
+ "epoch": 60.0,
913
+ "learning_rate": 3.157894736842105e-05,
914
+ "loss": 0.2954,
915
+ "step": 120
916
+ },
917
+ {
918
+ "epoch": 60.0,
919
+ "eval_accuracy_dropoff": 0.3830684190004358,
920
+ "eval_accuracy_undropoff": 0.9863793897770795,
921
+ "eval_accuracy_unlabeled": NaN,
922
+ "eval_iou_dropoff": 0.2915370570142824,
923
+ "eval_iou_undropoff": 0.9606677012885093,
924
+ "eval_iou_unlabeled": NaN,
925
+ "eval_loss": 0.3119274079799652,
926
+ "eval_mean_accuracy": 0.6847239043887576,
927
+ "eval_mean_iou": 0.6261023791513959,
928
+ "eval_overall_accuracy": 0.9612941741943359,
929
+ "eval_runtime": 2.8355,
930
+ "eval_samples_per_second": 7.053,
931
+ "eval_steps_per_second": 0.705,
932
+ "step": 120
933
+ }
934
+ ],
935
+ "max_steps": 240,
936
+ "num_train_epochs": 120,
937
+ "total_flos": 6.107874830843904e+16,
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 sha256:802d4edbb071ea5456776afdb74b9f178937fc6675946bfc71313e889f03f698
3
+ size 4219
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7ee570980bac7c3ba7538e3a72d3c66edd6b33e79b350d6271a49f0e469101e
3
  size 14951629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:038fba4f64c9f6ec3b43595b56d4c0c6a9fb20b5770e4abaa0deaeebe020f8c9
3
  size 14951629
runs/Feb12_06-52-50_robovision.csres.utexas.edu/events.out.tfevents.1707742376.robovision.csres.utexas.edu.2755643.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe4288a7ac521ed682a9d8e6f62fe66d9690bea06c1bfa17b73bb0ff76fbc212
3
- size 23332
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4301e350108a28be39d9166c855866b8561d05c37c7fe5dd0457723f794dd7e
3
+ size 32608