sam1120 commited on
Commit
9bcdc34
1 Parent(s): 49e020a

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 sha256:3b2cf1f8c39e08854fca9e66dae5d2893332eca71dcf9d121697a17054a9950c
3
+ size 677455167
checkpoint-120/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1841e3db49073c6d8e770a52cc7cb2e2fc9c5a6e8e922ec300795afa879fda
3
+ size 338796489
checkpoint-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf2268b500c70d62bb9560f818c5739f01ae09edc2e0c44ab3d6cc516280c7a
3
+ size 14575
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a5f6f45f9db261119d8e0dc0aa6eaf9386fd0481f42dface05ac30ba5d92df1
3
+ size 627
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3126855492591858,
3
+ "best_model_checkpoint": "/robodata/smodak/Projects/nspl/scripts/terrainseg/training/models/dropoff-utcustom-train-SF-RGB-b5_4/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": 5.833333333333333e-07,
13
+ "loss": 0.9908,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 1.1666666666666666e-06,
19
+ "loss": 0.9755,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 1.5,
24
+ "learning_rate": 1.75e-06,
25
+ "loss": 0.9832,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "learning_rate": 2.333333333333333e-06,
31
+ "loss": 0.9833,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 2.5,
36
+ "learning_rate": 2.9166666666666666e-06,
37
+ "loss": 0.9793,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 3.5e-06,
43
+ "loss": 0.975,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 3.5,
48
+ "learning_rate": 4.083333333333334e-06,
49
+ "loss": 0.9728,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 4.666666666666666e-06,
55
+ "loss": 0.9563,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 4.5,
60
+ "learning_rate": 5.25e-06,
61
+ "loss": 0.952,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 5.0,
66
+ "learning_rate": 5.833333333333333e-06,
67
+ "loss": 0.9465,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "eval_accuracy_dropoff": 0.30711254845294617,
73
+ "eval_accuracy_undropoff": 0.6931472063539763,
74
+ "eval_accuracy_unlabeled": NaN,
75
+ "eval_iou_dropoff": 0.12608002952896777,
76
+ "eval_iou_undropoff": 0.6824276188640029,
77
+ "eval_iou_unlabeled": 0.0,
78
+ "eval_loss": 0.9973907470703125,
79
+ "eval_mean_accuracy": 0.5001298774034613,
80
+ "eval_mean_iou": 0.26950254946432356,
81
+ "eval_overall_accuracy": 0.677096176147461,
82
+ "eval_runtime": 2.6009,
83
+ "eval_samples_per_second": 7.69,
84
+ "eval_steps_per_second": 0.769,
85
+ "step": 10
86
+ },
87
+ {
88
+ "epoch": 5.5,
89
+ "learning_rate": 6.4166666666666665e-06,
90
+ "loss": 0.9364,
91
+ "step": 11
92
+ },
93
+ {
94
+ "epoch": 6.0,
95
+ "learning_rate": 7e-06,
96
+ "loss": 0.9277,
97
+ "step": 12
98
+ },
99
+ {
100
+ "epoch": 6.5,
101
+ "learning_rate": 6.969298245614035e-06,
102
+ "loss": 0.9148,
103
+ "step": 13
104
+ },
105
+ {
106
+ "epoch": 7.0,
107
+ "learning_rate": 6.9385964912280696e-06,
108
+ "loss": 0.9038,
109
+ "step": 14
110
+ },
111
+ {
112
+ "epoch": 7.5,
113
+ "learning_rate": 6.907894736842105e-06,
114
+ "loss": 0.8925,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 8.0,
119
+ "learning_rate": 6.87719298245614e-06,
120
+ "loss": 0.8917,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 8.5,
125
+ "learning_rate": 6.846491228070175e-06,
126
+ "loss": 0.8802,
127
+ "step": 17
128
+ },
129
+ {
130
+ "epoch": 9.0,
131
+ "learning_rate": 6.815789473684211e-06,
132
+ "loss": 0.8682,
133
+ "step": 18
134
+ },
135
+ {
136
+ "epoch": 9.5,
137
+ "learning_rate": 6.785087719298246e-06,
138
+ "loss": 0.8584,
139
+ "step": 19
140
+ },
141
+ {
142
+ "epoch": 10.0,
143
+ "learning_rate": 6.75438596491228e-06,
144
+ "loss": 0.8558,
145
+ "step": 20
146
+ },
147
+ {
148
+ "epoch": 10.0,
149
+ "eval_accuracy_dropoff": 0.543416133397555,
150
+ "eval_accuracy_undropoff": 0.8804402488813177,
151
+ "eval_accuracy_unlabeled": NaN,
152
+ "eval_iou_dropoff": 0.2787406762512059,
153
+ "eval_iou_undropoff": 0.8677574035561078,
154
+ "eval_iou_unlabeled": 0.0,
155
+ "eval_loss": 0.8237255215644836,
156
+ "eval_mean_accuracy": 0.7119281911394364,
157
+ "eval_mean_iou": 0.38216602660243787,
158
+ "eval_overall_accuracy": 0.8664270401000976,
159
+ "eval_runtime": 2.0893,
160
+ "eval_samples_per_second": 9.573,
161
+ "eval_steps_per_second": 0.957,
162
+ "step": 20
163
+ },
164
+ {
165
+ "epoch": 10.5,
166
+ "learning_rate": 6.7236842105263156e-06,
167
+ "loss": 0.8292,
168
+ "step": 21
169
+ },
170
+ {
171
+ "epoch": 11.0,
172
+ "learning_rate": 6.692982456140351e-06,
173
+ "loss": 0.8484,
174
+ "step": 22
175
+ },
176
+ {
177
+ "epoch": 11.5,
178
+ "learning_rate": 6.662280701754385e-06,
179
+ "loss": 0.8316,
180
+ "step": 23
181
+ },
182
+ {
183
+ "epoch": 12.0,
184
+ "learning_rate": 6.6315789473684205e-06,
185
+ "loss": 0.8077,
186
+ "step": 24
187
+ },
188
+ {
189
+ "epoch": 12.5,
190
+ "learning_rate": 6.600877192982457e-06,
191
+ "loss": 0.8079,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 13.0,
196
+ "learning_rate": 6.570175438596491e-06,
197
+ "loss": 0.7915,
198
+ "step": 26
199
+ },
200
+ {
201
+ "epoch": 13.5,
202
+ "learning_rate": 6.539473684210526e-06,
203
+ "loss": 0.792,
204
+ "step": 27
205
+ },
206
+ {
207
+ "epoch": 14.0,
208
+ "learning_rate": 6.5087719298245616e-06,
209
+ "loss": 0.7818,
210
+ "step": 28
211
+ },
212
+ {
213
+ "epoch": 14.5,
214
+ "learning_rate": 6.478070175438596e-06,
215
+ "loss": 0.7716,
216
+ "step": 29
217
+ },
218
+ {
219
+ "epoch": 15.0,
220
+ "learning_rate": 6.447368421052631e-06,
221
+ "loss": 0.7585,
222
+ "step": 30
223
+ },
224
+ {
225
+ "epoch": 15.0,
226
+ "eval_accuracy_dropoff": 0.5624716163214752,
227
+ "eval_accuracy_undropoff": 0.9348810967813194,
228
+ "eval_accuracy_unlabeled": NaN,
229
+ "eval_iou_dropoff": 0.349393058642503,
230
+ "eval_iou_undropoff": 0.9201710251519329,
231
+ "eval_iou_unlabeled": 0.0,
232
+ "eval_loss": 0.680091917514801,
233
+ "eval_mean_accuracy": 0.7486763565513973,
234
+ "eval_mean_iou": 0.42318802793147864,
235
+ "eval_overall_accuracy": 0.9193965911865234,
236
+ "eval_runtime": 2.1213,
237
+ "eval_samples_per_second": 9.428,
238
+ "eval_steps_per_second": 0.943,
239
+ "step": 30
240
+ },
241
+ {
242
+ "epoch": 15.5,
243
+ "learning_rate": 6.4166666666666665e-06,
244
+ "loss": 0.7533,
245
+ "step": 31
246
+ },
247
+ {
248
+ "epoch": 16.0,
249
+ "learning_rate": 6.385964912280701e-06,
250
+ "loss": 0.7398,
251
+ "step": 32
252
+ },
253
+ {
254
+ "epoch": 16.5,
255
+ "learning_rate": 6.355263157894737e-06,
256
+ "loss": 0.7511,
257
+ "step": 33
258
+ },
259
+ {
260
+ "epoch": 17.0,
261
+ "learning_rate": 6.324561403508772e-06,
262
+ "loss": 0.7172,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 17.5,
267
+ "learning_rate": 6.293859649122807e-06,
268
+ "loss": 0.708,
269
+ "step": 35
270
+ },
271
+ {
272
+ "epoch": 18.0,
273
+ "learning_rate": 6.263157894736842e-06,
274
+ "loss": 0.7258,
275
+ "step": 36
276
+ },
277
+ {
278
+ "epoch": 18.5,
279
+ "learning_rate": 6.232456140350877e-06,
280
+ "loss": 0.7048,
281
+ "step": 37
282
+ },
283
+ {
284
+ "epoch": 19.0,
285
+ "learning_rate": 6.201754385964912e-06,
286
+ "loss": 0.6919,
287
+ "step": 38
288
+ },
289
+ {
290
+ "epoch": 19.5,
291
+ "learning_rate": 6.171052631578947e-06,
292
+ "loss": 0.6687,
293
+ "step": 39
294
+ },
295
+ {
296
+ "epoch": 20.0,
297
+ "learning_rate": 6.140350877192982e-06,
298
+ "loss": 0.715,
299
+ "step": 40
300
+ },
301
+ {
302
+ "epoch": 20.0,
303
+ "eval_accuracy_dropoff": 0.5952063120713778,
304
+ "eval_accuracy_undropoff": 0.9374720018468085,
305
+ "eval_accuracy_unlabeled": NaN,
306
+ "eval_iou_dropoff": 0.3660574736640166,
307
+ "eval_iou_undropoff": 0.9233451410139708,
308
+ "eval_iou_unlabeled": 0.0,
309
+ "eval_loss": 0.6076321601867676,
310
+ "eval_mean_accuracy": 0.7663391569590932,
311
+ "eval_mean_iou": 0.4298008715593291,
312
+ "eval_overall_accuracy": 0.923240852355957,
313
+ "eval_runtime": 2.0795,
314
+ "eval_samples_per_second": 9.618,
315
+ "eval_steps_per_second": 0.962,
316
+ "step": 40
317
+ },
318
+ {
319
+ "epoch": 20.5,
320
+ "learning_rate": 6.1096491228070174e-06,
321
+ "loss": 0.663,
322
+ "step": 41
323
+ },
324
+ {
325
+ "epoch": 21.0,
326
+ "learning_rate": 6.078947368421053e-06,
327
+ "loss": 0.6637,
328
+ "step": 42
329
+ },
330
+ {
331
+ "epoch": 21.5,
332
+ "learning_rate": 6.048245614035088e-06,
333
+ "loss": 0.64,
334
+ "step": 43
335
+ },
336
+ {
337
+ "epoch": 22.0,
338
+ "learning_rate": 6.017543859649122e-06,
339
+ "loss": 0.6611,
340
+ "step": 44
341
+ },
342
+ {
343
+ "epoch": 22.5,
344
+ "learning_rate": 5.986842105263158e-06,
345
+ "loss": 0.6221,
346
+ "step": 45
347
+ },
348
+ {
349
+ "epoch": 23.0,
350
+ "learning_rate": 5.956140350877193e-06,
351
+ "loss": 0.6652,
352
+ "step": 46
353
+ },
354
+ {
355
+ "epoch": 23.5,
356
+ "learning_rate": 5.925438596491228e-06,
357
+ "loss": 0.6329,
358
+ "step": 47
359
+ },
360
+ {
361
+ "epoch": 24.0,
362
+ "learning_rate": 5.894736842105263e-06,
363
+ "loss": 0.6025,
364
+ "step": 48
365
+ },
366
+ {
367
+ "epoch": 24.5,
368
+ "learning_rate": 5.864035087719299e-06,
369
+ "loss": 0.6005,
370
+ "step": 49
371
+ },
372
+ {
373
+ "epoch": 25.0,
374
+ "learning_rate": 5.833333333333333e-06,
375
+ "loss": 0.6145,
376
+ "step": 50
377
+ },
378
+ {
379
+ "epoch": 25.0,
380
+ "eval_accuracy_dropoff": 0.5993531961742242,
381
+ "eval_accuracy_undropoff": 0.95265662796263,
382
+ "eval_accuracy_unlabeled": NaN,
383
+ "eval_iou_dropoff": 0.38194797677722625,
384
+ "eval_iou_undropoff": 0.9374606493852639,
385
+ "eval_iou_unlabeled": 0.0,
386
+ "eval_loss": 0.5297996997833252,
387
+ "eval_mean_accuracy": 0.7760049120684271,
388
+ "eval_mean_iou": 0.4398028753874967,
389
+ "eval_overall_accuracy": 0.9379665374755859,
390
+ "eval_runtime": 5.0194,
391
+ "eval_samples_per_second": 3.985,
392
+ "eval_steps_per_second": 0.398,
393
+ "step": 50
394
+ },
395
+ {
396
+ "epoch": 25.5,
397
+ "learning_rate": 5.802631578947368e-06,
398
+ "loss": 0.5857,
399
+ "step": 51
400
+ },
401
+ {
402
+ "epoch": 26.0,
403
+ "learning_rate": 5.771929824561404e-06,
404
+ "loss": 0.5952,
405
+ "step": 52
406
+ },
407
+ {
408
+ "epoch": 26.5,
409
+ "learning_rate": 5.741228070175439e-06,
410
+ "loss": 0.5949,
411
+ "step": 53
412
+ },
413
+ {
414
+ "epoch": 27.0,
415
+ "learning_rate": 5.710526315789473e-06,
416
+ "loss": 0.5617,
417
+ "step": 54
418
+ },
419
+ {
420
+ "epoch": 27.5,
421
+ "learning_rate": 5.6798245614035086e-06,
422
+ "loss": 0.5524,
423
+ "step": 55
424
+ },
425
+ {
426
+ "epoch": 28.0,
427
+ "learning_rate": 5.649122807017544e-06,
428
+ "loss": 0.5645,
429
+ "step": 56
430
+ },
431
+ {
432
+ "epoch": 28.5,
433
+ "learning_rate": 5.618421052631579e-06,
434
+ "loss": 0.5292,
435
+ "step": 57
436
+ },
437
+ {
438
+ "epoch": 29.0,
439
+ "learning_rate": 5.587719298245614e-06,
440
+ "loss": 0.5744,
441
+ "step": 58
442
+ },
443
+ {
444
+ "epoch": 29.5,
445
+ "learning_rate": 5.55701754385965e-06,
446
+ "loss": 0.5422,
447
+ "step": 59
448
+ },
449
+ {
450
+ "epoch": 30.0,
451
+ "learning_rate": 5.526315789473684e-06,
452
+ "loss": 0.5355,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 30.0,
457
+ "eval_accuracy_dropoff": 0.5917658661895915,
458
+ "eval_accuracy_undropoff": 0.9580567515475479,
459
+ "eval_accuracy_unlabeled": NaN,
460
+ "eval_iou_dropoff": 0.3856504387079416,
461
+ "eval_iou_undropoff": 0.9421913855333733,
462
+ "eval_iou_unlabeled": 0.0,
463
+ "eval_loss": 0.4821084141731262,
464
+ "eval_mean_accuracy": 0.7749113088685697,
465
+ "eval_mean_iou": 0.4426139414137717,
466
+ "eval_overall_accuracy": 0.9428266525268555,
467
+ "eval_runtime": 2.0486,
468
+ "eval_samples_per_second": 9.763,
469
+ "eval_steps_per_second": 0.976,
470
+ "step": 60
471
+ },
472
+ {
473
+ "epoch": 30.5,
474
+ "learning_rate": 5.495614035087719e-06,
475
+ "loss": 0.5131,
476
+ "step": 61
477
+ },
478
+ {
479
+ "epoch": 31.0,
480
+ "learning_rate": 5.4649122807017546e-06,
481
+ "loss": 0.528,
482
+ "step": 62
483
+ },
484
+ {
485
+ "epoch": 31.5,
486
+ "learning_rate": 5.434210526315789e-06,
487
+ "loss": 0.5148,
488
+ "step": 63
489
+ },
490
+ {
491
+ "epoch": 32.0,
492
+ "learning_rate": 5.403508771929824e-06,
493
+ "loss": 0.497,
494
+ "step": 64
495
+ },
496
+ {
497
+ "epoch": 32.5,
498
+ "learning_rate": 5.37280701754386e-06,
499
+ "loss": 0.5018,
500
+ "step": 65
501
+ },
502
+ {
503
+ "epoch": 33.0,
504
+ "learning_rate": 5.342105263157895e-06,
505
+ "loss": 0.4883,
506
+ "step": 66
507
+ },
508
+ {
509
+ "epoch": 33.5,
510
+ "learning_rate": 5.31140350877193e-06,
511
+ "loss": 0.4913,
512
+ "step": 67
513
+ },
514
+ {
515
+ "epoch": 34.0,
516
+ "learning_rate": 5.280701754385965e-06,
517
+ "loss": 0.479,
518
+ "step": 68
519
+ },
520
+ {
521
+ "epoch": 34.5,
522
+ "learning_rate": 5.25e-06,
523
+ "loss": 0.4777,
524
+ "step": 69
525
+ },
526
+ {
527
+ "epoch": 35.0,
528
+ "learning_rate": 5.219298245614035e-06,
529
+ "loss": 0.4619,
530
+ "step": 70
531
+ },
532
+ {
533
+ "epoch": 35.0,
534
+ "eval_accuracy_dropoff": 0.57430675015482,
535
+ "eval_accuracy_undropoff": 0.9688024701062811,
536
+ "eval_accuracy_unlabeled": NaN,
537
+ "eval_iou_dropoff": 0.3961785898502891,
538
+ "eval_iou_undropoff": 0.9516637965632654,
539
+ "eval_iou_unlabeled": 0.0,
540
+ "eval_loss": 0.426582396030426,
541
+ "eval_mean_accuracy": 0.7715546101305506,
542
+ "eval_mean_iou": 0.4492807954711848,
543
+ "eval_overall_accuracy": 0.9523996353149414,
544
+ "eval_runtime": 2.1625,
545
+ "eval_samples_per_second": 9.248,
546
+ "eval_steps_per_second": 0.925,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 35.5,
551
+ "learning_rate": 5.18859649122807e-06,
552
+ "loss": 0.4508,
553
+ "step": 71
554
+ },
555
+ {
556
+ "epoch": 36.0,
557
+ "learning_rate": 5.157894736842105e-06,
558
+ "loss": 0.465,
559
+ "step": 72
560
+ },
561
+ {
562
+ "epoch": 36.5,
563
+ "learning_rate": 5.12719298245614e-06,
564
+ "loss": 0.4234,
565
+ "step": 73
566
+ },
567
+ {
568
+ "epoch": 37.0,
569
+ "learning_rate": 5.096491228070176e-06,
570
+ "loss": 0.5107,
571
+ "step": 74
572
+ },
573
+ {
574
+ "epoch": 37.5,
575
+ "learning_rate": 5.0657894736842104e-06,
576
+ "loss": 0.4482,
577
+ "step": 75
578
+ },
579
+ {
580
+ "epoch": 38.0,
581
+ "learning_rate": 5.035087719298246e-06,
582
+ "loss": 0.4299,
583
+ "step": 76
584
+ },
585
+ {
586
+ "epoch": 38.5,
587
+ "learning_rate": 5.004385964912281e-06,
588
+ "loss": 0.4463,
589
+ "step": 77
590
+ },
591
+ {
592
+ "epoch": 39.0,
593
+ "learning_rate": 4.973684210526315e-06,
594
+ "loss": 0.4152,
595
+ "step": 78
596
+ },
597
+ {
598
+ "epoch": 39.5,
599
+ "learning_rate": 4.942982456140351e-06,
600
+ "loss": 0.4062,
601
+ "step": 79
602
+ },
603
+ {
604
+ "epoch": 40.0,
605
+ "learning_rate": 4.912280701754386e-06,
606
+ "loss": 0.4367,
607
+ "step": 80
608
+ },
609
+ {
610
+ "epoch": 40.0,
611
+ "eval_accuracy_dropoff": 0.57421041767013,
612
+ "eval_accuracy_undropoff": 0.9734218793066906,
613
+ "eval_accuracy_unlabeled": NaN,
614
+ "eval_iou_dropoff": 0.39970303668933804,
615
+ "eval_iou_undropoff": 0.9559435963272845,
616
+ "eval_iou_unlabeled": 0.0,
617
+ "eval_loss": 0.3941105604171753,
618
+ "eval_mean_accuracy": 0.7738161484884103,
619
+ "eval_mean_iou": 0.4518822110055409,
620
+ "eval_overall_accuracy": 0.9568229675292969,
621
+ "eval_runtime": 2.0471,
622
+ "eval_samples_per_second": 9.77,
623
+ "eval_steps_per_second": 0.977,
624
+ "step": 80
625
+ },
626
+ {
627
+ "epoch": 40.5,
628
+ "learning_rate": 4.88157894736842e-06,
629
+ "loss": 0.3861,
630
+ "step": 81
631
+ },
632
+ {
633
+ "epoch": 41.0,
634
+ "learning_rate": 4.8508771929824564e-06,
635
+ "loss": 0.4259,
636
+ "step": 82
637
+ },
638
+ {
639
+ "epoch": 41.5,
640
+ "learning_rate": 4.820175438596492e-06,
641
+ "loss": 0.4131,
642
+ "step": 83
643
+ },
644
+ {
645
+ "epoch": 42.0,
646
+ "learning_rate": 4.789473684210526e-06,
647
+ "loss": 0.3905,
648
+ "step": 84
649
+ },
650
+ {
651
+ "epoch": 42.5,
652
+ "learning_rate": 4.758771929824561e-06,
653
+ "loss": 0.3853,
654
+ "step": 85
655
+ },
656
+ {
657
+ "epoch": 43.0,
658
+ "learning_rate": 4.728070175438597e-06,
659
+ "loss": 0.405,
660
+ "step": 86
661
+ },
662
+ {
663
+ "epoch": 43.5,
664
+ "learning_rate": 4.697368421052631e-06,
665
+ "loss": 0.3566,
666
+ "step": 87
667
+ },
668
+ {
669
+ "epoch": 44.0,
670
+ "learning_rate": 4.666666666666666e-06,
671
+ "loss": 0.4075,
672
+ "step": 88
673
+ },
674
+ {
675
+ "epoch": 44.5,
676
+ "learning_rate": 4.635964912280702e-06,
677
+ "loss": 0.3765,
678
+ "step": 89
679
+ },
680
+ {
681
+ "epoch": 45.0,
682
+ "learning_rate": 4.605263157894737e-06,
683
+ "loss": 0.3839,
684
+ "step": 90
685
+ },
686
+ {
687
+ "epoch": 45.0,
688
+ "eval_accuracy_dropoff": 0.5852886534094819,
689
+ "eval_accuracy_undropoff": 0.9738350230900806,
690
+ "eval_accuracy_unlabeled": NaN,
691
+ "eval_iou_dropoff": 0.40173932756916064,
692
+ "eval_iou_undropoff": 0.9567496536398221,
693
+ "eval_iou_unlabeled": 0.0,
694
+ "eval_loss": 0.3801003098487854,
695
+ "eval_mean_accuracy": 0.7795618382497813,
696
+ "eval_mean_iou": 0.45282966040299427,
697
+ "eval_overall_accuracy": 0.957679557800293,
698
+ "eval_runtime": 2.0345,
699
+ "eval_samples_per_second": 9.83,
700
+ "eval_steps_per_second": 0.983,
701
+ "step": 90
702
+ },
703
+ {
704
+ "epoch": 45.5,
705
+ "learning_rate": 4.574561403508772e-06,
706
+ "loss": 0.3629,
707
+ "step": 91
708
+ },
709
+ {
710
+ "epoch": 46.0,
711
+ "learning_rate": 4.543859649122807e-06,
712
+ "loss": 0.3631,
713
+ "step": 92
714
+ },
715
+ {
716
+ "epoch": 46.5,
717
+ "learning_rate": 4.513157894736842e-06,
718
+ "loss": 0.3893,
719
+ "step": 93
720
+ },
721
+ {
722
+ "epoch": 47.0,
723
+ "learning_rate": 4.482456140350877e-06,
724
+ "loss": 0.3262,
725
+ "step": 94
726
+ },
727
+ {
728
+ "epoch": 47.5,
729
+ "learning_rate": 4.451754385964912e-06,
730
+ "loss": 0.3453,
731
+ "step": 95
732
+ },
733
+ {
734
+ "epoch": 48.0,
735
+ "learning_rate": 4.421052631578947e-06,
736
+ "loss": 0.3552,
737
+ "step": 96
738
+ },
739
+ {
740
+ "epoch": 48.5,
741
+ "learning_rate": 4.390350877192982e-06,
742
+ "loss": 0.3294,
743
+ "step": 97
744
+ },
745
+ {
746
+ "epoch": 49.0,
747
+ "learning_rate": 4.359649122807018e-06,
748
+ "loss": 0.3545,
749
+ "step": 98
750
+ },
751
+ {
752
+ "epoch": 49.5,
753
+ "learning_rate": 4.3289473684210525e-06,
754
+ "loss": 0.3348,
755
+ "step": 99
756
+ },
757
+ {
758
+ "epoch": 50.0,
759
+ "learning_rate": 4.298245614035088e-06,
760
+ "loss": 0.3164,
761
+ "step": 100
762
+ },
763
+ {
764
+ "epoch": 50.0,
765
+ "eval_accuracy_dropoff": 0.579715131080988,
766
+ "eval_accuracy_undropoff": 0.9773475412870145,
767
+ "eval_accuracy_unlabeled": NaN,
768
+ "eval_iou_dropoff": 0.402982790123693,
769
+ "eval_iou_undropoff": 0.9598959470439332,
770
+ "eval_iou_unlabeled": 0.0,
771
+ "eval_loss": 0.35493195056915283,
772
+ "eval_mean_accuracy": 0.7785313361840013,
773
+ "eval_mean_iou": 0.45429291238920877,
774
+ "eval_overall_accuracy": 0.9608142852783204,
775
+ "eval_runtime": 4.9884,
776
+ "eval_samples_per_second": 4.009,
777
+ "eval_steps_per_second": 0.401,
778
+ "step": 100
779
+ },
780
+ {
781
+ "epoch": 50.5,
782
+ "learning_rate": 4.267543859649123e-06,
783
+ "loss": 0.3212,
784
+ "step": 101
785
+ },
786
+ {
787
+ "epoch": 51.0,
788
+ "learning_rate": 4.2368421052631575e-06,
789
+ "loss": 0.317,
790
+ "step": 102
791
+ },
792
+ {
793
+ "epoch": 51.5,
794
+ "learning_rate": 4.206140350877193e-06,
795
+ "loss": 0.3036,
796
+ "step": 103
797
+ },
798
+ {
799
+ "epoch": 52.0,
800
+ "learning_rate": 4.175438596491228e-06,
801
+ "loss": 0.3359,
802
+ "step": 104
803
+ },
804
+ {
805
+ "epoch": 52.5,
806
+ "learning_rate": 4.144736842105262e-06,
807
+ "loss": 0.3258,
808
+ "step": 105
809
+ },
810
+ {
811
+ "epoch": 53.0,
812
+ "learning_rate": 4.1140350877192985e-06,
813
+ "loss": 0.2865,
814
+ "step": 106
815
+ },
816
+ {
817
+ "epoch": 53.5,
818
+ "learning_rate": 4.083333333333334e-06,
819
+ "loss": 0.302,
820
+ "step": 107
821
+ },
822
+ {
823
+ "epoch": 54.0,
824
+ "learning_rate": 4.052631578947368e-06,
825
+ "loss": 0.2893,
826
+ "step": 108
827
+ },
828
+ {
829
+ "epoch": 54.5,
830
+ "learning_rate": 4.0219298245614034e-06,
831
+ "loss": 0.2898,
832
+ "step": 109
833
+ },
834
+ {
835
+ "epoch": 55.0,
836
+ "learning_rate": 3.991228070175439e-06,
837
+ "loss": 0.3018,
838
+ "step": 110
839
+ },
840
+ {
841
+ "epoch": 55.0,
842
+ "eval_accuracy_dropoff": 0.56500378449047,
843
+ "eval_accuracy_undropoff": 0.9812415607521366,
844
+ "eval_accuracy_unlabeled": NaN,
845
+ "eval_iou_dropoff": 0.40872075659532103,
846
+ "eval_iou_undropoff": 0.9631125878264742,
847
+ "eval_iou_unlabeled": 0.0,
848
+ "eval_loss": 0.3326951861381531,
849
+ "eval_mean_accuracy": 0.7731226726213033,
850
+ "eval_mean_iou": 0.4572777814739317,
851
+ "eval_overall_accuracy": 0.9639347076416016,
852
+ "eval_runtime": 2.119,
853
+ "eval_samples_per_second": 9.438,
854
+ "eval_steps_per_second": 0.944,
855
+ "step": 110
856
+ },
857
+ {
858
+ "epoch": 55.5,
859
+ "learning_rate": 3.960526315789473e-06,
860
+ "loss": 0.3035,
861
+ "step": 111
862
+ },
863
+ {
864
+ "epoch": 56.0,
865
+ "learning_rate": 3.929824561403508e-06,
866
+ "loss": 0.2833,
867
+ "step": 112
868
+ },
869
+ {
870
+ "epoch": 56.5,
871
+ "learning_rate": 3.899122807017544e-06,
872
+ "loss": 0.3054,
873
+ "step": 113
874
+ },
875
+ {
876
+ "epoch": 57.0,
877
+ "learning_rate": 3.868421052631579e-06,
878
+ "loss": 0.2554,
879
+ "step": 114
880
+ },
881
+ {
882
+ "epoch": 57.5,
883
+ "learning_rate": 3.837719298245614e-06,
884
+ "loss": 0.2572,
885
+ "step": 115
886
+ },
887
+ {
888
+ "epoch": 58.0,
889
+ "learning_rate": 3.8070175438596494e-06,
890
+ "loss": 0.3069,
891
+ "step": 116
892
+ },
893
+ {
894
+ "epoch": 58.5,
895
+ "learning_rate": 3.7763157894736843e-06,
896
+ "loss": 0.2838,
897
+ "step": 117
898
+ },
899
+ {
900
+ "epoch": 59.0,
901
+ "learning_rate": 3.745614035087719e-06,
902
+ "loss": 0.2495,
903
+ "step": 118
904
+ },
905
+ {
906
+ "epoch": 59.5,
907
+ "learning_rate": 3.7149122807017544e-06,
908
+ "loss": 0.2681,
909
+ "step": 119
910
+ },
911
+ {
912
+ "epoch": 60.0,
913
+ "learning_rate": 3.6842105263157892e-06,
914
+ "loss": 0.2646,
915
+ "step": 120
916
+ },
917
+ {
918
+ "epoch": 60.0,
919
+ "eval_accuracy_dropoff": 0.5570815844400101,
920
+ "eval_accuracy_undropoff": 0.9835134535417228,
921
+ "eval_accuracy_unlabeled": NaN,
922
+ "eval_iou_dropoff": 0.412100255185145,
923
+ "eval_iou_undropoff": 0.9650224323826128,
924
+ "eval_iou_unlabeled": 0.0,
925
+ "eval_loss": 0.3126855492591858,
926
+ "eval_mean_accuracy": 0.7702975189908665,
927
+ "eval_mean_iou": 0.4590408958559193,
928
+ "eval_overall_accuracy": 0.9657827377319336,
929
+ "eval_runtime": 2.0509,
930
+ "eval_samples_per_second": 9.752,
931
+ "eval_steps_per_second": 0.975,
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:d541eb9cd9b153de2e6b2fcae6c39a719cc274ef45c9af26ed96caf2dc871364
3
+ size 4155
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:512a293bb1e33f1cf5c703b8faedaa829a418a02878e8b85fce8233c38c8a9b5
3
  size 338796489
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1841e3db49073c6d8e770a52cc7cb2e2fc9c5a6e8e922ec300795afa879fda
3
  size 338796489
runs/Feb12_08-24-44_robolidar/events.out.tfevents.1707747891.robolidar.10260.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c175938aeeeb9539664effa3604aac906787234b1cecc3053d83bd475886330e
3
- size 23312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda8cde10771126122cd85428a5ef38c763f148da730c2b41607b4175bacf7bc
3
+ size 32588