Upload Kromoss dual-T4 training log
Browse files- training_logs/kromoss_training_log.txt +73 -1356
training_logs/kromoss_training_log.txt
CHANGED
|
@@ -1,1356 +1,73 @@
|
|
| 1 |
-
2026-11-01 23:
|
| 2 |
-
2026-11-01 23:
|
| 3 |
-
2026-11-01 23:
|
| 4 |
-
2026-11-01 23:
|
| 5 |
-
2026-11-01 23:
|
| 6 |
-
2026-11-01 23:
|
| 7 |
-
2026-11-01 23:
|
| 8 |
-
2026-11-01 23:
|
| 9 |
-
2026-11-01 23:
|
| 10 |
-
2026-11-01 23:
|
| 11 |
-
2026-11-01 23:
|
| 12 |
-
2026-11-01 23:
|
| 13 |
-
2026-11-01 23:
|
| 14 |
-
2026-11-01 23:
|
| 15 |
-
2026-11-01 23:
|
| 16 |
-
2026-11-01 23:
|
| 17 |
-
2026-11-01 23:
|
| 18 |
-
2026-11-01 23:
|
| 19 |
-
2026-11-01 23:
|
| 20 |
-
2026-11-01 23:
|
| 21 |
-
2026-11-01 23:
|
| 22 |
-
2026-11-01 23:
|
| 23 |
-
2026-11-01 23:
|
| 24 |
-
2026-11-01 23:
|
| 25 |
-
2026-11-01 23:
|
| 26 |
-
2026-11-01 23:
|
| 27 |
-
2026-11-01 23:
|
| 28 |
-
2026-11-01 23:
|
| 29 |
-
2026-11-01 23:
|
| 30 |
-
2026-11-01 23:
|
| 31 |
-
2026-11-01 23:
|
| 32 |
-
2026-11-01 23:
|
| 33 |
-
2026-11-01 23:
|
| 34 |
-
2026-11-01 23:
|
| 35 |
-
2026-11-01 23:
|
| 36 |
-
2026-11-01 23:
|
| 37 |
-
2026-11-01 23:
|
| 38 |
-
2026-11-01 23:
|
| 39 |
-
2026-11-01 23:
|
| 40 |
-
2026-11-01 23:
|
| 41 |
-
2026-11-01 23:
|
| 42 |
-
2026-11-01 23:
|
| 43 |
-
2026-11-01 23:
|
| 44 |
-
2026-11-01 23:
|
| 45 |
-
2026-11-01 23:
|
| 46 |
-
2026-11-01 23:
|
| 47 |
-
2026-11-01 23:
|
| 48 |
-
2026-11-01 23:
|
| 49 |
-
2026-11-01 23:
|
| 50 |
-
2026-11-01 23:
|
| 51 |
-
2026-11-01 23:
|
| 52 |
-
2026-11-01 23:
|
| 53 |
-
2026-11-01 23:
|
| 54 |
-
2026-11-01 23:
|
| 55 |
-
2026-11-01 23:
|
| 56 |
-
2026-11-01 23:
|
| 57 |
-
2026-11-01 23:
|
| 58 |
-
2026-11-01 23:
|
| 59 |
-
2026-11-01 23:
|
| 60 |
-
2026-11-01 23:
|
| 61 |
-
2026-11-01 23:
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
2026-11-01 23:
|
| 73 |
-
2026-11-01 23:
|
| 74 |
-
2026-11-01 23:20:21 | INFO | ELAPSED TRAINING TIME: 15.46s
|
| 75 |
-
2026-11-01 23:20:21 | INFO | STEP 1 | GPU0 | allocated=5.070 GB | reserved=12.859 GB | peak=12.624 GB | free=1.565 GB
|
| 76 |
-
2026-11-01 23:20:21 | INFO | STEP 1 | GPU1 | allocated=4.984 GB | reserved=12.785 GB | peak=12.519 GB | free=1.639 GB
|
| 77 |
-
2026-11-01 23:20:37 | INFO | --------------------------------------------------------------------------------
|
| 78 |
-
2026-11-01 23:20:37 | INFO | STEP 2/70 | epoch=1/10 | position=2/7 | dataset_item=3
|
| 79 |
-
2026-11-01 23:20:37 | INFO | DATASET FILE: 00000003.pt
|
| 80 |
-
2026-11-01 23:20:37 | INFO | LOSS: 1.13788939
|
| 81 |
-
2026-11-01 23:20:37 | INFO | LR: 4.96376812e-05
|
| 82 |
-
2026-11-01 23:20:37 | INFO | TIMESTEP: 0.26634458
|
| 83 |
-
2026-11-01 23:20:37 | INFO | GLOBAL GRADIENT NORM: 0.09846493
|
| 84 |
-
2026-11-01 23:20:37 | INFO | MAX ABSOLUTE GRADIENT: 5.50842285e-03
|
| 85 |
-
2026-11-01 23:20:37 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 86 |
-
2026-11-01 23:20:37 | INFO | MISSING GRADIENT TENSORS: 0
|
| 87 |
-
2026-11-01 23:20:37 | INFO | GPU0 FORWARD: 2.041s
|
| 88 |
-
2026-11-01 23:20:37 | INFO | GPU1 FORWARD: 2.241s
|
| 89 |
-
2026-11-01 23:20:37 | INFO | GPU1 BACKWARD: 5.726s
|
| 90 |
-
2026-11-01 23:20:37 | INFO | GPU0 BACKWARD: 5.318s
|
| 91 |
-
2026-11-01 23:20:37 | INFO | UPDATE WALL TIME: 15.473s
|
| 92 |
-
2026-11-01 23:20:37 | INFO | ELAPSED TRAINING TIME: 30.94s
|
| 93 |
-
2026-11-01 23:20:37 | INFO | STEP 2 | GPU0 | allocated=5.070 GB | reserved=12.996 GB | peak=12.898 GB | free=1.429 GB
|
| 94 |
-
2026-11-01 23:20:37 | INFO | STEP 2 | GPU1 | allocated=4.984 GB | reserved=12.922 GB | peak=12.805 GB | free=1.503 GB
|
| 95 |
-
2026-11-01 23:20:53 | INFO | --------------------------------------------------------------------------------
|
| 96 |
-
2026-11-01 23:20:53 | INFO | STEP 3/70 | epoch=1/10 | position=3/7 | dataset_item=4
|
| 97 |
-
2026-11-01 23:20:53 | INFO | DATASET FILE: 00000004.pt
|
| 98 |
-
2026-11-01 23:20:53 | INFO | LOSS: 1.15446568
|
| 99 |
-
2026-11-01 23:20:53 | INFO | LR: 4.92753623e-05
|
| 100 |
-
2026-11-01 23:20:53 | INFO | TIMESTEP: 0.25900331
|
| 101 |
-
2026-11-01 23:20:53 | INFO | GLOBAL GRADIENT NORM: 0.08567047
|
| 102 |
-
2026-11-01 23:20:53 | INFO | MAX ABSOLUTE GRADIENT: 3.32260132e-03
|
| 103 |
-
2026-11-01 23:20:53 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 104 |
-
2026-11-01 23:20:53 | INFO | MISSING GRADIENT TENSORS: 0
|
| 105 |
-
2026-11-01 23:20:53 | INFO | GPU0 FORWARD: 2.051s
|
| 106 |
-
2026-11-01 23:20:53 | INFO | GPU1 FORWARD: 2.290s
|
| 107 |
-
2026-11-01 23:20:53 | INFO | GPU1 BACKWARD: 5.770s
|
| 108 |
-
2026-11-01 23:20:53 | INFO | GPU0 BACKWARD: 5.389s
|
| 109 |
-
2026-11-01 23:20:53 | INFO | UPDATE WALL TIME: 15.645s
|
| 110 |
-
2026-11-01 23:20:53 | INFO | ELAPSED TRAINING TIME: 46.60s
|
| 111 |
-
2026-11-01 23:20:53 | INFO | STEP 3 | GPU0 | allocated=5.070 GB | reserved=12.996 GB | peak=12.862 GB | free=1.429 GB
|
| 112 |
-
2026-11-01 23:20:53 | INFO | STEP 3 | GPU1 | allocated=4.984 GB | reserved=12.922 GB | peak=12.768 GB | free=1.503 GB
|
| 113 |
-
2026-11-01 23:21:08 | INFO | --------------------------------------------------------------------------------
|
| 114 |
-
2026-11-01 23:21:08 | INFO | STEP 4/70 | epoch=1/10 | position=4/7 | dataset_item=2
|
| 115 |
-
2026-11-01 23:21:08 | INFO | DATASET FILE: 00000002.pt
|
| 116 |
-
2026-11-01 23:21:08 | INFO | LOSS: 1.09719360
|
| 117 |
-
2026-11-01 23:21:08 | INFO | LR: 4.89130435e-05
|
| 118 |
-
2026-11-01 23:21:08 | INFO | TIMESTEP: 0.32806167
|
| 119 |
-
2026-11-01 23:21:08 | INFO | GLOBAL GRADIENT NORM: 0.09014856
|
| 120 |
-
2026-11-01 23:21:08 | INFO | MAX ABSOLUTE GRADIENT: 4.48989868e-03
|
| 121 |
-
2026-11-01 23:21:08 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 122 |
-
2026-11-01 23:21:08 | INFO | MISSING GRADIENT TENSORS: 0
|
| 123 |
-
2026-11-01 23:21:08 | INFO | GPU0 FORWARD: 2.097s
|
| 124 |
-
2026-11-01 23:21:08 | INFO | GPU1 FORWARD: 2.272s
|
| 125 |
-
2026-11-01 23:21:08 | INFO | GPU1 BACKWARD: 5.790s
|
| 126 |
-
2026-11-01 23:21:08 | INFO | GPU0 BACKWARD: 5.476s
|
| 127 |
-
2026-11-01 23:21:08 | INFO | UPDATE WALL TIME: 15.788s
|
| 128 |
-
2026-11-01 23:21:08 | INFO | ELAPSED TRAINING TIME: 62.40s
|
| 129 |
-
2026-11-01 23:21:08 | INFO | STEP 4 | GPU0 | allocated=5.070 GB | reserved=12.996 GB | peak=12.835 GB | free=1.429 GB
|
| 130 |
-
2026-11-01 23:21:08 | INFO | STEP 4 | GPU1 | allocated=4.984 GB | reserved=12.922 GB | peak=12.742 GB | free=1.503 GB
|
| 131 |
-
2026-11-01 23:21:24 | INFO | --------------------------------------------------------------------------------
|
| 132 |
-
2026-11-01 23:21:24 | INFO | STEP 5/70 | epoch=1/10 | position=5/7 | dataset_item=6
|
| 133 |
-
2026-11-01 23:21:24 | INFO | DATASET FILE: 00000006.pt
|
| 134 |
-
2026-11-01 23:21:24 | INFO | LOSS: 1.18125892
|
| 135 |
-
2026-11-01 23:21:24 | INFO | LR: 4.85507246e-05
|
| 136 |
-
2026-11-01 23:21:24 | INFO | TIMESTEP: 0.22171448
|
| 137 |
-
2026-11-01 23:21:24 | INFO | GLOBAL GRADIENT NORM: 0.11910705
|
| 138 |
-
2026-11-01 23:21:24 | INFO | MAX ABSOLUTE GRADIENT: 3.12423706e-03
|
| 139 |
-
2026-11-01 23:21:24 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 140 |
-
2026-11-01 23:21:24 | INFO | MISSING GRADIENT TENSORS: 0
|
| 141 |
-
2026-11-01 23:21:24 | INFO | GPU0 FORWARD: 2.169s
|
| 142 |
-
2026-11-01 23:21:24 | INFO | GPU1 FORWARD: 2.286s
|
| 143 |
-
2026-11-01 23:21:24 | INFO | GPU1 BACKWARD: 5.805s
|
| 144 |
-
2026-11-01 23:21:24 | INFO | GPU0 BACKWARD: 5.700s
|
| 145 |
-
2026-11-01 23:21:24 | INFO | UPDATE WALL TIME: 16.102s
|
| 146 |
-
2026-11-01 23:21:24 | INFO | ELAPSED TRAINING TIME: 78.51s
|
| 147 |
-
2026-11-01 23:21:24 | INFO | STEP 5 | GPU0 | allocated=5.070 GB | reserved=12.996 GB | peak=12.882 GB | free=1.429 GB
|
| 148 |
-
2026-11-01 23:21:24 | INFO | STEP 5 | GPU1 | allocated=4.984 GB | reserved=12.922 GB | peak=12.788 GB | free=1.503 GB
|
| 149 |
-
2026-11-01 23:21:41 | INFO | --------------------------------------------------------------------------------
|
| 150 |
-
2026-11-01 23:21:41 | INFO | STEP 6/70 | epoch=1/10 | position=6/7 | dataset_item=0
|
| 151 |
-
2026-11-01 23:21:41 | INFO | DATASET FILE: 00000000.pt
|
| 152 |
-
2026-11-01 23:21:41 | INFO | LOSS: 1.17807746
|
| 153 |
-
2026-11-01 23:21:41 | INFO | LR: 4.81884058e-05
|
| 154 |
-
2026-11-01 23:21:41 | INFO | TIMESTEP: 0.14347191
|
| 155 |
-
2026-11-01 23:21:41 | INFO | GLOBAL GRADIENT NORM: 0.09497192
|
| 156 |
-
2026-11-01 23:21:41 | INFO | MAX ABSOLUTE GRADIENT: 3.74603271e-03
|
| 157 |
-
2026-11-01 23:21:41 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 158 |
-
2026-11-01 23:21:41 | INFO | MISSING GRADIENT TENSORS: 0
|
| 159 |
-
2026-11-01 23:21:41 | INFO | GPU0 FORWARD: 2.218s
|
| 160 |
-
2026-11-01 23:21:41 | INFO | GPU1 FORWARD: 2.291s
|
| 161 |
-
2026-11-01 23:21:41 | INFO | GPU1 BACKWARD: 5.917s
|
| 162 |
-
2026-11-01 23:21:41 | INFO | GPU0 BACKWARD: 5.780s
|
| 163 |
-
2026-11-01 23:21:41 | INFO | UPDATE WALL TIME: 16.356s
|
| 164 |
-
2026-11-01 23:21:41 | INFO | ELAPSED TRAINING TIME: 94.88s
|
| 165 |
-
2026-11-01 23:21:41 | INFO | STEP 6 | GPU0 | allocated=5.070 GB | reserved=12.996 GB | peak=12.821 GB | free=1.429 GB
|
| 166 |
-
2026-11-01 23:21:41 | INFO | STEP 6 | GPU1 | allocated=4.984 GB | reserved=12.922 GB | peak=12.728 GB | free=1.503 GB
|
| 167 |
-
2026-11-01 23:21:58 | INFO | --------------------------------------------------------------------------------
|
| 168 |
-
2026-11-01 23:21:58 | INFO | STEP 7/70 | epoch=1/10 | position=7/7 | dataset_item=5
|
| 169 |
-
2026-11-01 23:21:58 | INFO | DATASET FILE: 00000005.pt
|
| 170 |
-
2026-11-01 23:21:58 | INFO | LOSS: 0.63784271
|
| 171 |
-
2026-11-01 23:21:58 | INFO | LR: 4.78260870e-05
|
| 172 |
-
2026-11-01 23:21:58 | INFO | TIMESTEP: 0.57760578
|
| 173 |
-
2026-11-01 23:21:58 | INFO | GLOBAL GRADIENT NORM: 0.09459939
|
| 174 |
-
2026-11-01 23:21:58 | INFO | MAX ABSOLUTE GRADIENT: 2.33268738e-03
|
| 175 |
-
2026-11-01 23:21:58 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 176 |
-
2026-11-01 23:21:58 | INFO | MISSING GRADIENT TENSORS: 0
|
| 177 |
-
2026-11-01 23:21:58 | INFO | GPU0 FORWARD: 2.358s
|
| 178 |
-
2026-11-01 23:21:58 | INFO | GPU1 FORWARD: 2.387s
|
| 179 |
-
2026-11-01 23:21:58 | INFO | GPU1 BACKWARD: 6.309s
|
| 180 |
-
2026-11-01 23:21:58 | INFO | GPU0 BACKWARD: 6.067s
|
| 181 |
-
2026-11-01 23:21:58 | INFO | UPDATE WALL TIME: 17.271s
|
| 182 |
-
2026-11-01 23:21:58 | INFO | ELAPSED TRAINING TIME: 112.16s
|
| 183 |
-
2026-11-01 23:21:58 | INFO | STEP 7 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 184 |
-
2026-11-01 23:21:58 | INFO | STEP 7 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 185 |
-
2026-11-01 23:22:16 | INFO | --------------------------------------------------------------------------------
|
| 186 |
-
2026-11-01 23:22:16 | INFO | STEP 8/70 | epoch=2/10 | position=1/7 | dataset_item=3
|
| 187 |
-
2026-11-01 23:22:16 | INFO | DATASET FILE: 00000003.pt
|
| 188 |
-
2026-11-01 23:22:16 | INFO | LOSS: 1.11418712
|
| 189 |
-
2026-11-01 23:22:16 | INFO | LR: 4.74637681e-05
|
| 190 |
-
2026-11-01 23:22:16 | INFO | TIMESTEP: 0.27784425
|
| 191 |
-
2026-11-01 23:22:16 | INFO | GLOBAL GRADIENT NORM: 0.08368929
|
| 192 |
-
2026-11-01 23:22:16 | INFO | MAX ABSOLUTE GRADIENT: 2.32315063e-03
|
| 193 |
-
2026-11-01 23:22:16 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 194 |
-
2026-11-01 23:22:16 | INFO | MISSING GRADIENT TENSORS: 0
|
| 195 |
-
2026-11-01 23:22:16 | INFO | GPU0 FORWARD: 2.423s
|
| 196 |
-
2026-11-01 23:22:16 | INFO | GPU1 FORWARD: 2.406s
|
| 197 |
-
2026-11-01 23:22:16 | INFO | GPU1 BACKWARD: 6.315s
|
| 198 |
-
2026-11-01 23:22:16 | INFO | GPU0 BACKWARD: 6.153s
|
| 199 |
-
2026-11-01 23:22:16 | INFO | UPDATE WALL TIME: 17.448s
|
| 200 |
-
2026-11-01 23:22:16 | INFO | ELAPSED TRAINING TIME: 129.62s
|
| 201 |
-
2026-11-01 23:22:16 | INFO | STEP 8 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.898 GB | free=1.389 GB
|
| 202 |
-
2026-11-01 23:22:16 | INFO | STEP 8 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.805 GB | free=1.464 GB
|
| 203 |
-
2026-11-01 23:22:33 | INFO | --------------------------------------------------------------------------------
|
| 204 |
-
2026-11-01 23:22:33 | INFO | STEP 9/70 | epoch=2/10 | position=2/7 | dataset_item=6
|
| 205 |
-
2026-11-01 23:22:33 | INFO | DATASET FILE: 00000006.pt
|
| 206 |
-
2026-11-01 23:22:33 | INFO | LOSS: 0.57072091
|
| 207 |
-
2026-11-01 23:22:33 | INFO | LR: 4.71014493e-05
|
| 208 |
-
2026-11-01 23:22:33 | INFO | TIMESTEP: 0.73534703
|
| 209 |
-
2026-11-01 23:22:33 | INFO | GLOBAL GRADIENT NORM: 0.08181708
|
| 210 |
-
2026-11-01 23:22:33 | INFO | MAX ABSOLUTE GRADIENT: 2.39753723e-03
|
| 211 |
-
2026-11-01 23:22:33 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 212 |
-
2026-11-01 23:22:33 | INFO | MISSING GRADIENT TENSORS: 0
|
| 213 |
-
2026-11-01 23:22:33 | INFO | GPU0 FORWARD: 2.459s
|
| 214 |
-
2026-11-01 23:22:33 | INFO | GPU1 FORWARD: 2.446s
|
| 215 |
-
2026-11-01 23:22:33 | INFO | GPU1 BACKWARD: 6.383s
|
| 216 |
-
2026-11-01 23:22:33 | INFO | GPU0 BACKWARD: 6.250s
|
| 217 |
-
2026-11-01 23:22:33 | INFO | UPDATE WALL TIME: 17.682s
|
| 218 |
-
2026-11-01 23:22:33 | INFO | ELAPSED TRAINING TIME: 147.32s
|
| 219 |
-
2026-11-01 23:22:33 | INFO | STEP 9 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.882 GB | free=1.389 GB
|
| 220 |
-
2026-11-01 23:22:33 | INFO | STEP 9 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.788 GB | free=1.464 GB
|
| 221 |
-
2026-11-01 23:22:51 | INFO | --------------------------------------------------------------------------------
|
| 222 |
-
2026-11-01 23:22:51 | INFO | STEP 10/70 | epoch=2/10 | position=3/7 | dataset_item=2
|
| 223 |
-
2026-11-01 23:22:51 | INFO | DATASET FILE: 00000002.pt
|
| 224 |
-
2026-11-01 23:22:51 | INFO | LOSS: 0.71565700
|
| 225 |
-
2026-11-01 23:22:51 | INFO | LR: 4.67391304e-05
|
| 226 |
-
2026-11-01 23:22:51 | INFO | TIMESTEP: 0.57242364
|
| 227 |
-
2026-11-01 23:22:51 | INFO | GLOBAL GRADIENT NORM: 0.06862144
|
| 228 |
-
2026-11-01 23:22:51 | INFO | MAX ABSOLUTE GRADIENT: 2.21061707e-03
|
| 229 |
-
2026-11-01 23:22:51 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 230 |
-
2026-11-01 23:22:51 | INFO | MISSING GRADIENT TENSORS: 0
|
| 231 |
-
2026-11-01 23:22:51 | INFO | GPU0 FORWARD: 2.503s
|
| 232 |
-
2026-11-01 23:22:51 | INFO | GPU1 FORWARD: 2.380s
|
| 233 |
-
2026-11-01 23:22:51 | INFO | GPU1 BACKWARD: 6.149s
|
| 234 |
-
2026-11-01 23:22:51 | INFO | GPU0 BACKWARD: 6.307s
|
| 235 |
-
2026-11-01 23:22:51 | INFO | UPDATE WALL TIME: 17.486s
|
| 236 |
-
2026-11-01 23:22:51 | INFO | ELAPSED TRAINING TIME: 164.81s
|
| 237 |
-
2026-11-01 23:22:51 | INFO | STEP 10 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.835 GB | free=1.389 GB
|
| 238 |
-
2026-11-01 23:22:51 | INFO | STEP 10 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.742 GB | free=1.464 GB
|
| 239 |
-
2026-11-01 23:23:08 | INFO | --------------------------------------------------------------------------------
|
| 240 |
-
2026-11-01 23:23:08 | INFO | STEP 11/70 | epoch=2/10 | position=4/7 | dataset_item=4
|
| 241 |
-
2026-11-01 23:23:08 | INFO | DATASET FILE: 00000004.pt
|
| 242 |
-
2026-11-01 23:23:08 | INFO | LOSS: 0.55634642
|
| 243 |
-
2026-11-01 23:23:08 | INFO | LR: 4.63768116e-05
|
| 244 |
-
2026-11-01 23:23:08 | INFO | TIMESTEP: 0.72895420
|
| 245 |
-
2026-11-01 23:23:08 | INFO | GLOBAL GRADIENT NORM: 0.08422560
|
| 246 |
-
2026-11-01 23:23:08 | INFO | MAX ABSOLUTE GRADIENT: 2.57110596e-03
|
| 247 |
-
2026-11-01 23:23:08 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 248 |
-
2026-11-01 23:23:08 | INFO | MISSING GRADIENT TENSORS: 0
|
| 249 |
-
2026-11-01 23:23:08 | INFO | GPU0 FORWARD: 2.535s
|
| 250 |
-
2026-11-01 23:23:08 | INFO | GPU1 FORWARD: 2.383s
|
| 251 |
-
2026-11-01 23:23:08 | INFO | GPU1 BACKWARD: 6.230s
|
| 252 |
-
2026-11-01 23:23:08 | INFO | GPU0 BACKWARD: 6.204s
|
| 253 |
-
2026-11-01 23:23:08 | INFO | UPDATE WALL TIME: 17.500s
|
| 254 |
-
2026-11-01 23:23:08 | INFO | ELAPSED TRAINING TIME: 182.33s
|
| 255 |
-
2026-11-01 23:23:08 | INFO | STEP 11 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.862 GB | free=1.389 GB
|
| 256 |
-
2026-11-01 23:23:08 | INFO | STEP 11 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.768 GB | free=1.464 GB
|
| 257 |
-
2026-11-01 23:23:26 | INFO | --------------------------------------------------------------------------------
|
| 258 |
-
2026-11-01 23:23:26 | INFO | STEP 12/70 | epoch=2/10 | position=5/7 | dataset_item=0
|
| 259 |
-
2026-11-01 23:23:26 | INFO | DATASET FILE: 00000000.pt
|
| 260 |
-
2026-11-01 23:23:26 | INFO | LOSS: 1.15281069
|
| 261 |
-
2026-11-01 23:23:26 | INFO | LR: 4.60144928e-05
|
| 262 |
-
2026-11-01 23:23:26 | INFO | TIMESTEP: 0.10170523
|
| 263 |
-
2026-11-01 23:23:26 | INFO | GLOBAL GRADIENT NORM: 0.09061066
|
| 264 |
-
2026-11-01 23:23:26 | INFO | MAX ABSOLUTE GRADIENT: 4.42504883e-03
|
| 265 |
-
2026-11-01 23:23:26 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 266 |
-
2026-11-01 23:23:26 | INFO | MISSING GRADIENT TENSORS: 0
|
| 267 |
-
2026-11-01 23:23:26 | INFO | GPU0 FORWARD: 2.471s
|
| 268 |
-
2026-11-01 23:23:26 | INFO | GPU1 FORWARD: 2.365s
|
| 269 |
-
2026-11-01 23:23:26 | INFO | GPU1 BACKWARD: 6.184s
|
| 270 |
-
2026-11-01 23:23:26 | INFO | GPU0 BACKWARD: 6.154s
|
| 271 |
-
2026-11-01 23:23:26 | INFO | UPDATE WALL TIME: 17.321s
|
| 272 |
-
2026-11-01 23:23:26 | INFO | ELAPSED TRAINING TIME: 199.66s
|
| 273 |
-
2026-11-01 23:23:26 | INFO | STEP 12 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.821 GB | free=1.389 GB
|
| 274 |
-
2026-11-01 23:23:26 | INFO | STEP 12 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.728 GB | free=1.464 GB
|
| 275 |
-
2026-11-01 23:23:43 | INFO | --------------------------------------------------------------------------------
|
| 276 |
-
2026-11-01 23:23:43 | INFO | STEP 13/70 | epoch=2/10 | position=6/7 | dataset_item=5
|
| 277 |
-
2026-11-01 23:23:43 | INFO | DATASET FILE: 00000005.pt
|
| 278 |
-
2026-11-01 23:23:43 | INFO | LOSS: 0.51763958
|
| 279 |
-
2026-11-01 23:23:43 | INFO | LR: 4.56521739e-05
|
| 280 |
-
2026-11-01 23:23:43 | INFO | TIMESTEP: 0.83249700
|
| 281 |
-
2026-11-01 23:23:43 | INFO | GLOBAL GRADIENT NORM: 0.15706175
|
| 282 |
-
2026-11-01 23:23:43 | INFO | MAX ABSOLUTE GRADIENT: 1.00936890e-02
|
| 283 |
-
2026-11-01 23:23:43 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 284 |
-
2026-11-01 23:23:43 | INFO | MISSING GRADIENT TENSORS: 0
|
| 285 |
-
2026-11-01 23:23:43 | INFO | GPU0 FORWARD: 2.444s
|
| 286 |
-
2026-11-01 23:23:43 | INFO | GPU1 FORWARD: 2.444s
|
| 287 |
-
2026-11-01 23:23:43 | INFO | GPU1 BACKWARD: 6.431s
|
| 288 |
-
2026-11-01 23:23:43 | INFO | GPU0 BACKWARD: 6.234s
|
| 289 |
-
2026-11-01 23:23:43 | INFO | UPDATE WALL TIME: 17.704s
|
| 290 |
-
2026-11-01 23:23:43 | INFO | ELAPSED TRAINING TIME: 217.37s
|
| 291 |
-
2026-11-01 23:23:43 | INFO | STEP 13 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 292 |
-
2026-11-01 23:23:43 | INFO | STEP 13 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 293 |
-
2026-11-01 23:24:01 | INFO | --------------------------------------------------------------------------------
|
| 294 |
-
2026-11-01 23:24:01 | INFO | STEP 14/70 | epoch=2/10 | position=7/7 | dataset_item=1
|
| 295 |
-
2026-11-01 23:24:01 | INFO | DATASET FILE: 00000001.pt
|
| 296 |
-
2026-11-01 23:24:01 | INFO | LOSS: 0.58677816
|
| 297 |
-
2026-11-01 23:24:01 | INFO | LR: 4.52898551e-05
|
| 298 |
-
2026-11-01 23:24:01 | INFO | TIMESTEP: 0.68447441
|
| 299 |
-
2026-11-01 23:24:01 | INFO | GLOBAL GRADIENT NORM: 0.07559282
|
| 300 |
-
2026-11-01 23:24:01 | INFO | MAX ABSOLUTE GRADIENT: 2.25257874e-03
|
| 301 |
-
2026-11-01 23:24:01 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 302 |
-
2026-11-01 23:24:01 | INFO | MISSING GRADIENT TENSORS: 0
|
| 303 |
-
2026-11-01 23:24:01 | INFO | GPU0 FORWARD: 2.439s
|
| 304 |
-
2026-11-01 23:24:01 | INFO | GPU1 FORWARD: 2.383s
|
| 305 |
-
2026-11-01 23:24:01 | INFO | GPU1 BACKWARD: 6.212s
|
| 306 |
-
2026-11-01 23:24:01 | INFO | GPU0 BACKWARD: 6.142s
|
| 307 |
-
2026-11-01 23:24:01 | INFO | UPDATE WALL TIME: 17.323s
|
| 308 |
-
2026-11-01 23:24:01 | INFO | ELAPSED TRAINING TIME: 234.71s
|
| 309 |
-
2026-11-01 23:24:01 | INFO | STEP 14 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.756 GB | free=1.389 GB
|
| 310 |
-
2026-11-01 23:24:01 | INFO | STEP 14 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.664 GB | free=1.464 GB
|
| 311 |
-
2026-11-01 23:24:01 | INFO | ================================================================================
|
| 312 |
-
2026-11-01 23:24:01 | INFO | CHECKPOINT TRIGGERED AT OPTIMIZER STEP 14
|
| 313 |
-
2026-11-01 23:24:05 | INFO | CHECKPOINT SUCCESS: kromoss_lora_step_000014.safetensors
|
| 314 |
-
2026-11-01 23:24:05 | INFO | CHECKPOINT SIZE: 70.93 MB
|
| 315 |
-
2026-11-01 23:24:05 | INFO | ================================================================================
|
| 316 |
-
2026-11-01 23:24:22 | INFO | --------------------------------------------------------------------------------
|
| 317 |
-
2026-11-01 23:24:22 | INFO | STEP 15/70 | epoch=3/10 | position=1/7 | dataset_item=3
|
| 318 |
-
2026-11-01 23:24:22 | INFO | DATASET FILE: 00000003.pt
|
| 319 |
-
2026-11-01 23:24:22 | INFO | LOSS: 1.12059379
|
| 320 |
-
2026-11-01 23:24:22 | INFO | LR: 4.49275362e-05
|
| 321 |
-
2026-11-01 23:24:22 | INFO | TIMESTEP: 0.27099666
|
| 322 |
-
2026-11-01 23:24:22 | INFO | GLOBAL GRADIENT NORM: 0.08447098
|
| 323 |
-
2026-11-01 23:24:22 | INFO | MAX ABSOLUTE GRADIENT: 3.82041931e-03
|
| 324 |
-
2026-11-01 23:24:22 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 325 |
-
2026-11-01 23:24:22 | INFO | MISSING GRADIENT TENSORS: 0
|
| 326 |
-
2026-11-01 23:24:22 | INFO | GPU0 FORWARD: 2.469s
|
| 327 |
-
2026-11-01 23:24:22 | INFO | GPU1 FORWARD: 2.370s
|
| 328 |
-
2026-11-01 23:24:22 | INFO | GPU1 BACKWARD: 6.226s
|
| 329 |
-
2026-11-01 23:24:22 | INFO | GPU0 BACKWARD: 6.292s
|
| 330 |
-
2026-11-01 23:24:22 | INFO | UPDATE WALL TIME: 17.502s
|
| 331 |
-
2026-11-01 23:24:22 | INFO | ELAPSED TRAINING TIME: 256.37s
|
| 332 |
-
2026-11-01 23:24:22 | INFO | STEP 15 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.898 GB | free=1.389 GB
|
| 333 |
-
2026-11-01 23:24:22 | INFO | STEP 15 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.805 GB | free=1.464 GB
|
| 334 |
-
2026-11-01 23:24:40 | INFO | --------------------------------------------------------------------------------
|
| 335 |
-
2026-11-01 23:24:40 | INFO | STEP 16/70 | epoch=3/10 | position=2/7 | dataset_item=2
|
| 336 |
-
2026-11-01 23:24:40 | INFO | DATASET FILE: 00000002.pt
|
| 337 |
-
2026-11-01 23:24:40 | INFO | LOSS: 1.07068217
|
| 338 |
-
2026-11-01 23:24:40 | INFO | LR: 4.45652174e-05
|
| 339 |
-
2026-11-01 23:24:40 | INFO | TIMESTEP: 0.34128180
|
| 340 |
-
2026-11-01 23:24:40 | INFO | GLOBAL GRADIENT NORM: 0.09242336
|
| 341 |
-
2026-11-01 23:24:40 | INFO | MAX ABSOLUTE GRADIENT: 4.89044189e-03
|
| 342 |
-
2026-11-01 23:24:40 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 343 |
-
2026-11-01 23:24:40 | INFO | MISSING GRADIENT TENSORS: 0
|
| 344 |
-
2026-11-01 23:24:40 | INFO | GPU0 FORWARD: 2.515s
|
| 345 |
-
2026-11-01 23:24:40 | INFO | GPU1 FORWARD: 2.413s
|
| 346 |
-
2026-11-01 23:24:40 | INFO | GPU1 BACKWARD: 6.276s
|
| 347 |
-
2026-11-01 23:24:40 | INFO | GPU0 BACKWARD: 6.269s
|
| 348 |
-
2026-11-01 23:24:40 | INFO | UPDATE WALL TIME: 17.625s
|
| 349 |
-
2026-11-01 23:24:40 | INFO | ELAPSED TRAINING TIME: 274.00s
|
| 350 |
-
2026-11-01 23:24:40 | INFO | STEP 16 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.835 GB | free=1.389 GB
|
| 351 |
-
2026-11-01 23:24:40 | INFO | STEP 16 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.742 GB | free=1.464 GB
|
| 352 |
-
2026-11-01 23:24:57 | INFO | --------------------------------------------------------------------------------
|
| 353 |
-
2026-11-01 23:24:57 | INFO | STEP 17/70 | epoch=3/10 | position=3/7 | dataset_item=4
|
| 354 |
-
2026-11-01 23:24:57 | INFO | DATASET FILE: 00000004.pt
|
| 355 |
-
2026-11-01 23:24:57 | INFO | LOSS: 1.04439282
|
| 356 |
-
2026-11-01 23:24:57 | INFO | LR: 4.42028986e-05
|
| 357 |
-
2026-11-01 23:24:57 | INFO | TIMESTEP: 0.00303028
|
| 358 |
-
2026-11-01 23:24:57 | INFO | GLOBAL GRADIENT NORM: 0.28457307
|
| 359 |
-
2026-11-01 23:24:57 | INFO | MAX ABSOLUTE GRADIENT: 1.71508789e-02
|
| 360 |
-
2026-11-01 23:24:57 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 361 |
-
2026-11-01 23:24:57 | INFO | MISSING GRADIENT TENSORS: 0
|
| 362 |
-
2026-11-01 23:24:57 | INFO | GPU0 FORWARD: 2.454s
|
| 363 |
-
2026-11-01 23:24:57 | INFO | GPU1 FORWARD: 2.417s
|
| 364 |
-
2026-11-01 23:24:57 | INFO | GPU1 BACKWARD: 6.183s
|
| 365 |
-
2026-11-01 23:24:57 | INFO | GPU0 BACKWARD: 6.217s
|
| 366 |
-
2026-11-01 23:24:57 | INFO | UPDATE WALL TIME: 17.418s
|
| 367 |
-
2026-11-01 23:24:57 | INFO | ELAPSED TRAINING TIME: 291.43s
|
| 368 |
-
2026-11-01 23:24:57 | INFO | STEP 17 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.862 GB | free=1.389 GB
|
| 369 |
-
2026-11-01 23:24:57 | INFO | STEP 17 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.768 GB | free=1.464 GB
|
| 370 |
-
2026-11-01 23:25:15 | INFO | --------------------------------------------------------------------------------
|
| 371 |
-
2026-11-01 23:25:15 | INFO | STEP 18/70 | epoch=3/10 | position=4/7 | dataset_item=1
|
| 372 |
-
2026-11-01 23:25:15 | INFO | DATASET FILE: 00000001.pt
|
| 373 |
-
2026-11-01 23:25:15 | INFO | LOSS: 0.74975574
|
| 374 |
-
2026-11-01 23:25:15 | INFO | LR: 4.38405797e-05
|
| 375 |
-
2026-11-01 23:25:15 | INFO | TIMESTEP: 0.98469913
|
| 376 |
-
2026-11-01 23:25:15 | INFO | GLOBAL GRADIENT NORM: 0.22894168
|
| 377 |
-
2026-11-01 23:25:15 | INFO | MAX ABSOLUTE GRADIENT: 2.11334229e-02
|
| 378 |
-
2026-11-01 23:25:15 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 379 |
-
2026-11-01 23:25:15 | INFO | MISSING GRADIENT TENSORS: 0
|
| 380 |
-
2026-11-01 23:25:15 | INFO | GPU0 FORWARD: 2.430s
|
| 381 |
-
2026-11-01 23:25:15 | INFO | GPU1 FORWARD: 2.377s
|
| 382 |
-
2026-11-01 23:25:15 | INFO | GPU1 BACKWARD: 6.254s
|
| 383 |
-
2026-11-01 23:25:15 | INFO | GPU0 BACKWARD: 6.152s
|
| 384 |
-
2026-11-01 23:25:15 | INFO | UPDATE WALL TIME: 17.361s
|
| 385 |
-
2026-11-01 23:25:15 | INFO | ELAPSED TRAINING TIME: 308.80s
|
| 386 |
-
2026-11-01 23:25:15 | INFO | STEP 18 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.756 GB | free=1.389 GB
|
| 387 |
-
2026-11-01 23:25:15 | INFO | STEP 18 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.664 GB | free=1.464 GB
|
| 388 |
-
2026-11-01 23:25:32 | INFO | --------------------------------------------------------------------------------
|
| 389 |
-
2026-11-01 23:25:32 | INFO | STEP 19/70 | epoch=3/10 | position=5/7 | dataset_item=5
|
| 390 |
-
2026-11-01 23:25:32 | INFO | DATASET FILE: 00000005.pt
|
| 391 |
-
2026-11-01 23:25:32 | INFO | LOSS: 0.60971481
|
| 392 |
-
2026-11-01 23:25:32 | INFO | LR: 4.34782609e-05
|
| 393 |
-
2026-11-01 23:25:32 | INFO | TIMESTEP: 0.60690606
|
| 394 |
-
2026-11-01 23:25:32 | INFO | GLOBAL GRADIENT NORM: 0.07898372
|
| 395 |
-
2026-11-01 23:25:32 | INFO | MAX ABSOLUTE GRADIENT: 3.92532349e-03
|
| 396 |
-
2026-11-01 23:25:32 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 397 |
-
2026-11-01 23:25:32 | INFO | MISSING GRADIENT TENSORS: 0
|
| 398 |
-
2026-11-01 23:25:32 | INFO | GPU0 FORWARD: 2.528s
|
| 399 |
-
2026-11-01 23:25:32 | INFO | GPU1 FORWARD: 2.436s
|
| 400 |
-
2026-11-01 23:25:32 | INFO | GPU1 BACKWARD: 6.354s
|
| 401 |
-
2026-11-01 23:25:32 | INFO | GPU0 BACKWARD: 6.257s
|
| 402 |
-
2026-11-01 23:25:32 | INFO | UPDATE WALL TIME: 17.720s
|
| 403 |
-
2026-11-01 23:25:32 | INFO | ELAPSED TRAINING TIME: 326.54s
|
| 404 |
-
2026-11-01 23:25:32 | INFO | STEP 19 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 405 |
-
2026-11-01 23:25:32 | INFO | STEP 19 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 406 |
-
2026-11-01 23:25:50 | INFO | --------------------------------------------------------------------------------
|
| 407 |
-
2026-11-01 23:25:50 | INFO | STEP 20/70 | epoch=3/10 | position=6/7 | dataset_item=6
|
| 408 |
-
2026-11-01 23:25:50 | INFO | DATASET FILE: 00000006.pt
|
| 409 |
-
2026-11-01 23:25:50 | INFO | LOSS: 0.68332738
|
| 410 |
-
2026-11-01 23:25:50 | INFO | LR: 4.31159420e-05
|
| 411 |
-
2026-11-01 23:25:50 | INFO | TIMESTEP: 0.59872955
|
| 412 |
-
2026-11-01 23:25:50 | INFO | GLOBAL GRADIENT NORM: 0.08477836
|
| 413 |
-
2026-11-01 23:25:50 | INFO | MAX ABSOLUTE GRADIENT: 2.14004517e-03
|
| 414 |
-
2026-11-01 23:25:50 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 415 |
-
2026-11-01 23:25:50 | INFO | MISSING GRADIENT TENSORS: 0
|
| 416 |
-
2026-11-01 23:25:50 | INFO | GPU0 FORWARD: 2.487s
|
| 417 |
-
2026-11-01 23:25:50 | INFO | GPU1 FORWARD: 2.406s
|
| 418 |
-
2026-11-01 23:25:50 | INFO | GPU1 BACKWARD: 6.320s
|
| 419 |
-
2026-11-01 23:25:50 | INFO | GPU0 BACKWARD: 6.288s
|
| 420 |
-
2026-11-01 23:25:50 | INFO | UPDATE WALL TIME: 17.649s
|
| 421 |
-
2026-11-01 23:25:50 | INFO | ELAPSED TRAINING TIME: 344.20s
|
| 422 |
-
2026-11-01 23:25:50 | INFO | STEP 20 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.882 GB | free=1.389 GB
|
| 423 |
-
2026-11-01 23:25:50 | INFO | STEP 20 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.788 GB | free=1.464 GB
|
| 424 |
-
2026-11-01 23:26:08 | INFO | --------------------------------------------------------------------------------
|
| 425 |
-
2026-11-01 23:26:08 | INFO | STEP 21/70 | epoch=3/10 | position=7/7 | dataset_item=0
|
| 426 |
-
2026-11-01 23:26:08 | INFO | DATASET FILE: 00000000.pt
|
| 427 |
-
2026-11-01 23:26:08 | INFO | LOSS: 1.02696204
|
| 428 |
-
2026-11-01 23:26:08 | INFO | LR: 4.27536232e-05
|
| 429 |
-
2026-11-01 23:26:08 | INFO | TIMESTEP: 0.32843283
|
| 430 |
-
2026-11-01 23:26:08 | INFO | GLOBAL GRADIENT NORM: 0.13469819
|
| 431 |
-
2026-11-01 23:26:08 | INFO | MAX ABSOLUTE GRADIENT: 5.49697876e-03
|
| 432 |
-
2026-11-01 23:26:08 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 433 |
-
2026-11-01 23:26:08 | INFO | MISSING GRADIENT TENSORS: 0
|
| 434 |
-
2026-11-01 23:26:08 | INFO | GPU0 FORWARD: 2.502s
|
| 435 |
-
2026-11-01 23:26:08 | INFO | GPU1 FORWARD: 2.368s
|
| 436 |
-
2026-11-01 23:26:08 | INFO | GPU1 BACKWARD: 6.205s
|
| 437 |
-
2026-11-01 23:26:08 | INFO | GPU0 BACKWARD: 6.243s
|
| 438 |
-
2026-11-01 23:26:08 | INFO | UPDATE WALL TIME: 17.487s
|
| 439 |
-
2026-11-01 23:26:08 | INFO | ELAPSED TRAINING TIME: 361.70s
|
| 440 |
-
2026-11-01 23:26:08 | INFO | STEP 21 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.821 GB | free=1.389 GB
|
| 441 |
-
2026-11-01 23:26:08 | INFO | STEP 21 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.728 GB | free=1.464 GB
|
| 442 |
-
2026-11-01 23:26:25 | INFO | --------------------------------------------------------------------------------
|
| 443 |
-
2026-11-01 23:26:25 | INFO | STEP 22/70 | epoch=4/10 | position=1/7 | dataset_item=2
|
| 444 |
-
2026-11-01 23:26:25 | INFO | DATASET FILE: 00000002.pt
|
| 445 |
-
2026-11-01 23:26:25 | INFO | LOSS: 0.73557556
|
| 446 |
-
2026-11-01 23:26:25 | INFO | LR: 4.23913043e-05
|
| 447 |
-
2026-11-01 23:26:25 | INFO | TIMESTEP: 0.55734289
|
| 448 |
-
2026-11-01 23:26:25 | INFO | GLOBAL GRADIENT NORM: 0.08130765
|
| 449 |
-
2026-11-01 23:26:25 | INFO | MAX ABSOLUTE GRADIENT: 2.48908997e-03
|
| 450 |
-
2026-11-01 23:26:25 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 451 |
-
2026-11-01 23:26:25 | INFO | MISSING GRADIENT TENSORS: 0
|
| 452 |
-
2026-11-01 23:26:25 | INFO | GPU0 FORWARD: 2.486s
|
| 453 |
-
2026-11-01 23:26:25 | INFO | GPU1 FORWARD: 2.420s
|
| 454 |
-
2026-11-01 23:26:25 | INFO | GPU1 BACKWARD: 6.312s
|
| 455 |
-
2026-11-01 23:26:25 | INFO | GPU0 BACKWARD: 6.133s
|
| 456 |
-
2026-11-01 23:26:25 | INFO | UPDATE WALL TIME: 17.497s
|
| 457 |
-
2026-11-01 23:26:25 | INFO | ELAPSED TRAINING TIME: 379.20s
|
| 458 |
-
2026-11-01 23:26:25 | INFO | STEP 22 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.835 GB | free=1.389 GB
|
| 459 |
-
2026-11-01 23:26:25 | INFO | STEP 22 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.742 GB | free=1.464 GB
|
| 460 |
-
2026-11-01 23:26:43 | INFO | --------------------------------------------------------------------------------
|
| 461 |
-
2026-11-01 23:26:43 | INFO | STEP 23/70 | epoch=4/10 | position=2/7 | dataset_item=5
|
| 462 |
-
2026-11-01 23:26:43 | INFO | DATASET FILE: 00000005.pt
|
| 463 |
-
2026-11-01 23:26:43 | INFO | LOSS: 0.55721855
|
| 464 |
-
2026-11-01 23:26:43 | INFO | LR: 4.20289855e-05
|
| 465 |
-
2026-11-01 23:26:43 | INFO | TIMESTEP: 0.67500418
|
| 466 |
-
2026-11-01 23:26:43 | INFO | GLOBAL GRADIENT NORM: 0.08756581
|
| 467 |
-
2026-11-01 23:26:43 | INFO | MAX ABSOLUTE GRADIENT: 1.85298920e-03
|
| 468 |
-
2026-11-01 23:26:43 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 469 |
-
2026-11-01 23:26:43 | INFO | MISSING GRADIENT TENSORS: 0
|
| 470 |
-
2026-11-01 23:26:43 | INFO | GPU0 FORWARD: 2.458s
|
| 471 |
-
2026-11-01 23:26:43 | INFO | GPU1 FORWARD: 2.421s
|
| 472 |
-
2026-11-01 23:26:43 | INFO | GPU1 BACKWARD: 6.387s
|
| 473 |
-
2026-11-01 23:26:43 | INFO | GPU0 BACKWARD: 6.245s
|
| 474 |
-
2026-11-01 23:26:43 | INFO | UPDATE WALL TIME: 17.661s
|
| 475 |
-
2026-11-01 23:26:43 | INFO | ELAPSED TRAINING TIME: 396.88s
|
| 476 |
-
2026-11-01 23:26:43 | INFO | STEP 23 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 477 |
-
2026-11-01 23:26:43 | INFO | STEP 23 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 478 |
-
2026-11-01 23:27:00 | INFO | --------------------------------------------------------------------------------
|
| 479 |
-
2026-11-01 23:27:00 | INFO | STEP 24/70 | epoch=4/10 | position=3/7 | dataset_item=0
|
| 480 |
-
2026-11-01 23:27:00 | INFO | DATASET FILE: 00000000.pt
|
| 481 |
-
2026-11-01 23:27:00 | INFO | LOSS: 0.55830789
|
| 482 |
-
2026-11-01 23:27:00 | INFO | LR: 4.16666667e-05
|
| 483 |
-
2026-11-01 23:27:00 | INFO | TIMESTEP: 0.67845470
|
| 484 |
-
2026-11-01 23:27:00 | INFO | GLOBAL GRADIENT NORM: 0.08147401
|
| 485 |
-
2026-11-01 23:27:00 | INFO | MAX ABSOLUTE GRADIENT: 6.52694702e-03
|
| 486 |
-
2026-11-01 23:27:00 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 487 |
-
2026-11-01 23:27:00 | INFO | MISSING GRADIENT TENSORS: 0
|
| 488 |
-
2026-11-01 23:27:00 | INFO | GPU0 FORWARD: 2.454s
|
| 489 |
-
2026-11-01 23:27:00 | INFO | GPU1 FORWARD: 2.386s
|
| 490 |
-
2026-11-01 23:27:00 | INFO | GPU1 BACKWARD: 6.216s
|
| 491 |
-
2026-11-01 23:27:00 | INFO | GPU0 BACKWARD: 6.232s
|
| 492 |
-
2026-11-01 23:27:00 | INFO | UPDATE WALL TIME: 17.432s
|
| 493 |
-
2026-11-01 23:27:00 | INFO | ELAPSED TRAINING TIME: 414.32s
|
| 494 |
-
2026-11-01 23:27:00 | INFO | STEP 24 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.821 GB | free=1.389 GB
|
| 495 |
-
2026-11-01 23:27:00 | INFO | STEP 24 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.728 GB | free=1.464 GB
|
| 496 |
-
2026-11-01 23:27:18 | INFO | --------------------------------------------------------------------------------
|
| 497 |
-
2026-11-01 23:27:18 | INFO | STEP 25/70 | epoch=4/10 | position=4/7 | dataset_item=3
|
| 498 |
-
2026-11-01 23:27:18 | INFO | DATASET FILE: 00000003.pt
|
| 499 |
-
2026-11-01 23:27:18 | INFO | LOSS: 0.53031009
|
| 500 |
-
2026-11-01 23:27:18 | INFO | LR: 4.13043478e-05
|
| 501 |
-
2026-11-01 23:27:18 | INFO | TIMESTEP: 0.74678826
|
| 502 |
-
2026-11-01 23:27:18 | INFO | GLOBAL GRADIENT NORM: 0.07190437
|
| 503 |
-
2026-11-01 23:27:18 | INFO | MAX ABSOLUTE GRADIENT: 4.97055054e-03
|
| 504 |
-
2026-11-01 23:27:18 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 505 |
-
2026-11-01 23:27:18 | INFO | MISSING GRADIENT TENSORS: 0
|
| 506 |
-
2026-11-01 23:27:18 | INFO | GPU0 FORWARD: 2.522s
|
| 507 |
-
2026-11-01 23:27:18 | INFO | GPU1 FORWARD: 2.390s
|
| 508 |
-
2026-11-01 23:27:18 | INFO | GPU1 BACKWARD: 6.218s
|
| 509 |
-
2026-11-01 23:27:18 | INFO | GPU0 BACKWARD: 6.223s
|
| 510 |
-
2026-11-01 23:27:18 | INFO | UPDATE WALL TIME: 17.495s
|
| 511 |
-
2026-11-01 23:27:18 | INFO | ELAPSED TRAINING TIME: 431.83s
|
| 512 |
-
2026-11-01 23:27:18 | INFO | STEP 25 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.898 GB | free=1.389 GB
|
| 513 |
-
2026-11-01 23:27:18 | INFO | STEP 25 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.805 GB | free=1.464 GB
|
| 514 |
-
2026-11-01 23:27:35 | INFO | --------------------------------------------------------------------------------
|
| 515 |
-
2026-11-01 23:27:35 | INFO | STEP 26/70 | epoch=4/10 | position=5/7 | dataset_item=6
|
| 516 |
-
2026-11-01 23:27:35 | INFO | DATASET FILE: 00000006.pt
|
| 517 |
-
2026-11-01 23:27:35 | INFO | LOSS: 1.11747813
|
| 518 |
-
2026-11-01 23:27:35 | INFO | LR: 4.09420290e-05
|
| 519 |
-
2026-11-01 23:27:35 | INFO | TIMESTEP: 0.05546549
|
| 520 |
-
2026-11-01 23:27:35 | INFO | GLOBAL GRADIENT NORM: 0.25360535
|
| 521 |
-
2026-11-01 23:27:35 | INFO | MAX ABSOLUTE GRADIENT: 1.23672485e-02
|
| 522 |
-
2026-11-01 23:27:35 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 523 |
-
2026-11-01 23:27:35 | INFO | MISSING GRADIENT TENSORS: 0
|
| 524 |
-
2026-11-01 23:27:35 | INFO | GPU0 FORWARD: 2.518s
|
| 525 |
-
2026-11-01 23:27:35 | INFO | GPU1 FORWARD: 2.429s
|
| 526 |
-
2026-11-01 23:27:35 | INFO | GPU1 BACKWARD: 6.286s
|
| 527 |
-
2026-11-01 23:27:35 | INFO | GPU0 BACKWARD: 6.234s
|
| 528 |
-
2026-11-01 23:27:35 | INFO | UPDATE WALL TIME: 17.618s
|
| 529 |
-
2026-11-01 23:27:35 | INFO | ELAPSED TRAINING TIME: 449.46s
|
| 530 |
-
2026-11-01 23:27:35 | INFO | STEP 26 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.882 GB | free=1.389 GB
|
| 531 |
-
2026-11-01 23:27:35 | INFO | STEP 26 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.788 GB | free=1.464 GB
|
| 532 |
-
2026-11-01 23:27:53 | INFO | --------------------------------------------------------------------------------
|
| 533 |
-
2026-11-01 23:27:53 | INFO | STEP 27/70 | epoch=4/10 | position=6/7 | dataset_item=1
|
| 534 |
-
2026-11-01 23:27:53 | INFO | DATASET FILE: 00000001.pt
|
| 535 |
-
2026-11-01 23:27:53 | INFO | LOSS: 0.76441371
|
| 536 |
-
2026-11-01 23:27:53 | INFO | LR: 4.05797101e-05
|
| 537 |
-
2026-11-01 23:27:53 | INFO | TIMESTEP: 0.99145281
|
| 538 |
-
2026-11-01 23:27:53 | INFO | GLOBAL GRADIENT NORM: 0.27154939
|
| 539 |
-
2026-11-01 23:27:53 | INFO | MAX ABSOLUTE GRADIENT: 3.07769775e-02
|
| 540 |
-
2026-11-01 23:27:53 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 541 |
-
2026-11-01 23:27:53 | INFO | MISSING GRADIENT TENSORS: 0
|
| 542 |
-
2026-11-01 23:27:53 | INFO | GPU0 FORWARD: 2.435s
|
| 543 |
-
2026-11-01 23:27:53 | INFO | GPU1 FORWARD: 2.364s
|
| 544 |
-
2026-11-01 23:27:53 | INFO | GPU1 BACKWARD: 6.230s
|
| 545 |
-
2026-11-01 23:27:53 | INFO | GPU0 BACKWARD: 6.115s
|
| 546 |
-
2026-11-01 23:27:53 | INFO | UPDATE WALL TIME: 17.290s
|
| 547 |
-
2026-11-01 23:27:53 | INFO | ELAPSED TRAINING TIME: 466.76s
|
| 548 |
-
2026-11-01 23:27:53 | INFO | STEP 27 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.756 GB | free=1.389 GB
|
| 549 |
-
2026-11-01 23:27:53 | INFO | STEP 27 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.664 GB | free=1.464 GB
|
| 550 |
-
2026-11-01 23:28:10 | INFO | --------------------------------------------------------------------------------
|
| 551 |
-
2026-11-01 23:28:10 | INFO | STEP 28/70 | epoch=4/10 | position=7/7 | dataset_item=4
|
| 552 |
-
2026-11-01 23:28:10 | INFO | DATASET FILE: 00000004.pt
|
| 553 |
-
2026-11-01 23:28:10 | INFO | LOSS: 0.89462411
|
| 554 |
-
2026-11-01 23:28:10 | INFO | LR: 4.02173913e-05
|
| 555 |
-
2026-11-01 23:28:10 | INFO | TIMESTEP: 0.44384053
|
| 556 |
-
2026-11-01 23:28:10 | INFO | GLOBAL GRADIENT NORM: 0.11380419
|
| 557 |
-
2026-11-01 23:28:10 | INFO | MAX ABSOLUTE GRADIENT: 4.21142578e-03
|
| 558 |
-
2026-11-01 23:28:10 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 559 |
-
2026-11-01 23:28:10 | INFO | MISSING GRADIENT TENSORS: 0
|
| 560 |
-
2026-11-01 23:28:10 | INFO | GPU0 FORWARD: 2.452s
|
| 561 |
-
2026-11-01 23:28:10 | INFO | GPU1 FORWARD: 2.425s
|
| 562 |
-
2026-11-01 23:28:10 | INFO | GPU1 BACKWARD: 6.343s
|
| 563 |
-
2026-11-01 23:28:10 | INFO | GPU0 BACKWARD: 6.241s
|
| 564 |
-
2026-11-01 23:28:10 | INFO | UPDATE WALL TIME: 17.607s
|
| 565 |
-
2026-11-01 23:28:10 | INFO | ELAPSED TRAINING TIME: 484.38s
|
| 566 |
-
2026-11-01 23:28:10 | INFO | STEP 28 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.862 GB | free=1.389 GB
|
| 567 |
-
2026-11-01 23:28:10 | INFO | STEP 28 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.768 GB | free=1.464 GB
|
| 568 |
-
2026-11-01 23:28:28 | INFO | --------------------------------------------------------------------------------
|
| 569 |
-
2026-11-01 23:28:28 | INFO | STEP 29/70 | epoch=5/10 | position=1/7 | dataset_item=6
|
| 570 |
-
2026-11-01 23:28:28 | INFO | DATASET FILE: 00000006.pt
|
| 571 |
-
2026-11-01 23:28:28 | INFO | LOSS: 1.18787646
|
| 572 |
-
2026-11-01 23:28:28 | INFO | LR: 3.98550725e-05
|
| 573 |
-
2026-11-01 23:28:28 | INFO | TIMESTEP: 0.19323446
|
| 574 |
-
2026-11-01 23:28:28 | INFO | GLOBAL GRADIENT NORM: 0.13397921
|
| 575 |
-
2026-11-01 23:28:28 | INFO | MAX ABSOLUTE GRADIENT: 5.12695312e-03
|
| 576 |
-
2026-11-01 23:28:28 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 577 |
-
2026-11-01 23:28:28 | INFO | MISSING GRADIENT TENSORS: 0
|
| 578 |
-
2026-11-01 23:28:28 | INFO | GPU0 FORWARD: 2.449s
|
| 579 |
-
2026-11-01 23:28:28 | INFO | GPU1 FORWARD: 2.399s
|
| 580 |
-
2026-11-01 23:28:28 | INFO | GPU1 BACKWARD: 6.248s
|
| 581 |
-
2026-11-01 23:28:28 | INFO | GPU0 BACKWARD: 6.220s
|
| 582 |
-
2026-11-01 23:28:28 | INFO | UPDATE WALL TIME: 17.461s
|
| 583 |
-
2026-11-01 23:28:28 | INFO | ELAPSED TRAINING TIME: 501.85s
|
| 584 |
-
2026-11-01 23:28:28 | INFO | STEP 29 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.882 GB | free=1.389 GB
|
| 585 |
-
2026-11-01 23:28:28 | INFO | STEP 29 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.788 GB | free=1.464 GB
|
| 586 |
-
2026-11-01 23:28:45 | INFO | --------------------------------------------------------------------------------
|
| 587 |
-
2026-11-01 23:28:45 | INFO | STEP 30/70 | epoch=5/10 | position=2/7 | dataset_item=3
|
| 588 |
-
2026-11-01 23:28:45 | INFO | DATASET FILE: 00000003.pt
|
| 589 |
-
2026-11-01 23:28:45 | INFO | LOSS: 0.53480107
|
| 590 |
-
2026-11-01 23:28:45 | INFO | LR: 3.94927536e-05
|
| 591 |
-
2026-11-01 23:28:45 | INFO | TIMESTEP: 0.94193894
|
| 592 |
-
2026-11-01 23:28:45 | INFO | GLOBAL GRADIENT NORM: 0.17610645
|
| 593 |
-
2026-11-01 23:28:45 | INFO | MAX ABSOLUTE GRADIENT: 1.18408203e-02
|
| 594 |
-
2026-11-01 23:28:45 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 595 |
-
2026-11-01 23:28:45 | INFO | MISSING GRADIENT TENSORS: 0
|
| 596 |
-
2026-11-01 23:28:45 | INFO | GPU0 FORWARD: 2.495s
|
| 597 |
-
2026-11-01 23:28:45 | INFO | GPU1 FORWARD: 2.423s
|
| 598 |
-
2026-11-01 23:28:45 | INFO | GPU1 BACKWARD: 6.340s
|
| 599 |
-
2026-11-01 23:28:45 | INFO | GPU0 BACKWARD: 6.265s
|
| 600 |
-
2026-11-01 23:28:45 | INFO | UPDATE WALL TIME: 17.674s
|
| 601 |
-
2026-11-01 23:28:45 | INFO | ELAPSED TRAINING TIME: 519.54s
|
| 602 |
-
2026-11-01 23:28:45 | INFO | STEP 30 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.898 GB | free=1.389 GB
|
| 603 |
-
2026-11-01 23:28:45 | INFO | STEP 30 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.805 GB | free=1.464 GB
|
| 604 |
-
2026-11-01 23:29:03 | INFO | --------------------------------------------------------------------------------
|
| 605 |
-
2026-11-01 23:29:03 | INFO | STEP 31/70 | epoch=5/10 | position=3/7 | dataset_item=5
|
| 606 |
-
2026-11-01 23:29:03 | INFO | DATASET FILE: 00000005.pt
|
| 607 |
-
2026-11-01 23:29:03 | INFO | LOSS: 1.11169529
|
| 608 |
-
2026-11-01 23:29:03 | INFO | LR: 3.91304348e-05
|
| 609 |
-
2026-11-01 23:29:03 | INFO | TIMESTEP: 0.22701375
|
| 610 |
-
2026-11-01 23:29:03 | INFO | GLOBAL GRADIENT NORM: 0.16362807
|
| 611 |
-
2026-11-01 23:29:03 | INFO | MAX ABSOLUTE GRADIENT: 1.30233765e-02
|
| 612 |
-
2026-11-01 23:29:03 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 613 |
-
2026-11-01 23:29:03 | INFO | MISSING GRADIENT TENSORS: 0
|
| 614 |
-
2026-11-01 23:29:03 | INFO | GPU0 FORWARD: 2.557s
|
| 615 |
-
2026-11-01 23:29:03 | INFO | GPU1 FORWARD: 2.429s
|
| 616 |
-
2026-11-01 23:29:03 | INFO | GPU1 BACKWARD: 6.369s
|
| 617 |
-
2026-11-01 23:29:03 | INFO | GPU0 BACKWARD: 6.334s
|
| 618 |
-
2026-11-01 23:29:03 | INFO | UPDATE WALL TIME: 17.838s
|
| 619 |
-
2026-11-01 23:29:03 | INFO | ELAPSED TRAINING TIME: 537.39s
|
| 620 |
-
2026-11-01 23:29:03 | INFO | STEP 31 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 621 |
-
2026-11-01 23:29:03 | INFO | STEP 31 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 622 |
-
2026-11-01 23:29:21 | INFO | --------------------------------------------------------------------------------
|
| 623 |
-
2026-11-01 23:29:21 | INFO | STEP 32/70 | epoch=5/10 | position=4/7 | dataset_item=1
|
| 624 |
-
2026-11-01 23:29:21 | INFO | DATASET FILE: 00000001.pt
|
| 625 |
-
2026-11-01 23:29:21 | INFO | LOSS: 1.12055850
|
| 626 |
-
2026-11-01 23:29:21 | INFO | LR: 3.87681159e-05
|
| 627 |
-
2026-11-01 23:29:21 | INFO | TIMESTEP: 0.05574556
|
| 628 |
-
2026-11-01 23:29:21 | INFO | GLOBAL GRADIENT NORM: 0.19391994
|
| 629 |
-
2026-11-01 23:29:21 | INFO | MAX ABSOLUTE GRADIENT: 1.56402588e-02
|
| 630 |
-
2026-11-01 23:29:21 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 631 |
-
2026-11-01 23:29:21 | INFO | MISSING GRADIENT TENSORS: 0
|
| 632 |
-
2026-11-01 23:29:21 | INFO | GPU0 FORWARD: 2.429s
|
| 633 |
-
2026-11-01 23:29:21 | INFO | GPU1 FORWARD: 2.391s
|
| 634 |
-
2026-11-01 23:29:21 | INFO | GPU1 BACKWARD: 6.190s
|
| 635 |
-
2026-11-01 23:29:21 | INFO | GPU0 BACKWARD: 6.234s
|
| 636 |
-
2026-11-01 23:29:21 | INFO | UPDATE WALL TIME: 17.395s
|
| 637 |
-
2026-11-01 23:29:21 | INFO | ELAPSED TRAINING TIME: 554.79s
|
| 638 |
-
2026-11-01 23:29:21 | INFO | STEP 32 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.756 GB | free=1.389 GB
|
| 639 |
-
2026-11-01 23:29:21 | INFO | STEP 32 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.664 GB | free=1.464 GB
|
| 640 |
-
2026-11-01 23:29:38 | INFO | --------------------------------------------------------------------------------
|
| 641 |
-
2026-11-01 23:29:38 | INFO | STEP 33/70 | epoch=5/10 | position=5/7 | dataset_item=0
|
| 642 |
-
2026-11-01 23:29:38 | INFO | DATASET FILE: 00000000.pt
|
| 643 |
-
2026-11-01 23:29:38 | INFO | LOSS: 1.08607912
|
| 644 |
-
2026-11-01 23:29:38 | INFO | LR: 3.84057971e-05
|
| 645 |
-
2026-11-01 23:29:38 | INFO | TIMESTEP: 0.03580014
|
| 646 |
-
2026-11-01 23:29:38 | INFO | GLOBAL GRADIENT NORM: 0.19619415
|
| 647 |
-
2026-11-01 23:29:38 | INFO | MAX ABSOLUTE GRADIENT: 1.38320923e-02
|
| 648 |
-
2026-11-01 23:29:38 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 649 |
-
2026-11-01 23:29:38 | INFO | MISSING GRADIENT TENSORS: 0
|
| 650 |
-
2026-11-01 23:29:38 | INFO | GPU0 FORWARD: 2.467s
|
| 651 |
-
2026-11-01 23:29:38 | INFO | GPU1 FORWARD: 2.357s
|
| 652 |
-
2026-11-01 23:29:38 | INFO | GPU1 BACKWARD: 6.107s
|
| 653 |
-
2026-11-01 23:29:38 | INFO | GPU0 BACKWARD: 6.194s
|
| 654 |
-
2026-11-01 23:29:38 | INFO | UPDATE WALL TIME: 17.279s
|
| 655 |
-
2026-11-01 23:29:38 | INFO | ELAPSED TRAINING TIME: 572.08s
|
| 656 |
-
2026-11-01 23:29:38 | INFO | STEP 33 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.821 GB | free=1.389 GB
|
| 657 |
-
2026-11-01 23:29:38 | INFO | STEP 33 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.728 GB | free=1.464 GB
|
| 658 |
-
2026-11-01 23:29:55 | INFO | --------------------------------------------------------------------------------
|
| 659 |
-
2026-11-01 23:29:55 | INFO | STEP 34/70 | epoch=5/10 | position=6/7 | dataset_item=2
|
| 660 |
-
2026-11-01 23:29:55 | INFO | DATASET FILE: 00000002.pt
|
| 661 |
-
2026-11-01 23:29:55 | INFO | LOSS: 0.75155067
|
| 662 |
-
2026-11-01 23:29:55 | INFO | LR: 3.80434783e-05
|
| 663 |
-
2026-11-01 23:29:55 | INFO | TIMESTEP: 0.54746217
|
| 664 |
-
2026-11-01 23:29:55 | INFO | GLOBAL GRADIENT NORM: 0.08184964
|
| 665 |
-
2026-11-01 23:29:55 | INFO | MAX ABSOLUTE GRADIENT: 5.22613525e-03
|
| 666 |
-
2026-11-01 23:29:55 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 667 |
-
2026-11-01 23:29:55 | INFO | MISSING GRADIENT TENSORS: 0
|
| 668 |
-
2026-11-01 23:29:55 | INFO | GPU0 FORWARD: 2.450s
|
| 669 |
-
2026-11-01 23:29:55 | INFO | GPU1 FORWARD: 2.401s
|
| 670 |
-
2026-11-01 23:29:55 | INFO | GPU1 BACKWARD: 6.268s
|
| 671 |
-
2026-11-01 23:29:55 | INFO | GPU0 BACKWARD: 6.187s
|
| 672 |
-
2026-11-01 23:29:55 | INFO | UPDATE WALL TIME: 17.457s
|
| 673 |
-
2026-11-01 23:29:55 | INFO | ELAPSED TRAINING TIME: 589.55s
|
| 674 |
-
2026-11-01 23:29:55 | INFO | STEP 34 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.835 GB | free=1.389 GB
|
| 675 |
-
2026-11-01 23:29:55 | INFO | STEP 34 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.742 GB | free=1.464 GB
|
| 676 |
-
2026-11-01 23:30:13 | INFO | --------------------------------------------------------------------------------
|
| 677 |
-
2026-11-01 23:30:13 | INFO | STEP 35/70 | epoch=5/10 | position=7/7 | dataset_item=4
|
| 678 |
-
2026-11-01 23:30:13 | INFO | DATASET FILE: 00000004.pt
|
| 679 |
-
2026-11-01 23:30:13 | INFO | LOSS: 0.72215509
|
| 680 |
-
2026-11-01 23:30:13 | INFO | LR: 3.76811594e-05
|
| 681 |
-
2026-11-01 23:30:13 | INFO | TIMESTEP: 0.56448138
|
| 682 |
-
2026-11-01 23:30:13 | INFO | GLOBAL GRADIENT NORM: 0.07382349
|
| 683 |
-
2026-11-01 23:30:13 | INFO | MAX ABSOLUTE GRADIENT: 5.40924072e-03
|
| 684 |
-
2026-11-01 23:30:13 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 685 |
-
2026-11-01 23:30:13 | INFO | MISSING GRADIENT TENSORS: 0
|
| 686 |
-
2026-11-01 23:30:13 | INFO | GPU0 FORWARD: 2.469s
|
| 687 |
-
2026-11-01 23:30:13 | INFO | GPU1 FORWARD: 2.401s
|
| 688 |
-
2026-11-01 23:30:13 | INFO | GPU1 BACKWARD: 6.229s
|
| 689 |
-
2026-11-01 23:30:13 | INFO | GPU0 BACKWARD: 6.201s
|
| 690 |
-
2026-11-01 23:30:13 | INFO | UPDATE WALL TIME: 17.448s
|
| 691 |
-
2026-11-01 23:30:13 | INFO | ELAPSED TRAINING TIME: 607.01s
|
| 692 |
-
2026-11-01 23:30:13 | INFO | STEP 35 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.862 GB | free=1.389 GB
|
| 693 |
-
2026-11-01 23:30:13 | INFO | STEP 35 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.768 GB | free=1.464 GB
|
| 694 |
-
2026-11-01 23:30:13 | INFO | ================================================================================
|
| 695 |
-
2026-11-01 23:30:13 | INFO | CHECKPOINT TRIGGERED AT OPTIMIZER STEP 35
|
| 696 |
-
2026-11-01 23:30:17 | INFO | CHECKPOINT SUCCESS: kromoss_lora_step_000035.safetensors
|
| 697 |
-
2026-11-01 23:30:17 | INFO | CHECKPOINT SIZE: 70.93 MB
|
| 698 |
-
2026-11-01 23:30:17 | INFO | ================================================================================
|
| 699 |
-
2026-11-01 23:30:34 | INFO | --------------------------------------------------------------------------------
|
| 700 |
-
2026-11-01 23:30:34 | INFO | STEP 36/70 | epoch=6/10 | position=1/7 | dataset_item=5
|
| 701 |
-
2026-11-01 23:30:34 | INFO | DATASET FILE: 00000005.pt
|
| 702 |
-
2026-11-01 23:30:34 | INFO | LOSS: 1.09069192
|
| 703 |
-
2026-11-01 23:30:34 | INFO | LR: 3.73188406e-05
|
| 704 |
-
2026-11-01 23:30:34 | INFO | TIMESTEP: 0.03447602
|
| 705 |
-
2026-11-01 23:30:34 | INFO | GLOBAL GRADIENT NORM: 0.24189210
|
| 706 |
-
2026-11-01 23:30:34 | INFO | MAX ABSOLUTE GRADIENT: 1.19171143e-02
|
| 707 |
-
2026-11-01 23:30:34 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 708 |
-
2026-11-01 23:30:34 | INFO | MISSING GRADIENT TENSORS: 0
|
| 709 |
-
2026-11-01 23:30:34 | INFO | GPU0 FORWARD: 2.529s
|
| 710 |
-
2026-11-01 23:30:34 | INFO | GPU1 FORWARD: 2.428s
|
| 711 |
-
2026-11-01 23:30:34 | INFO | GPU1 BACKWARD: 6.350s
|
| 712 |
-
2026-11-01 23:30:34 | INFO | GPU0 BACKWARD: 6.344s
|
| 713 |
-
2026-11-01 23:30:34 | INFO | UPDATE WALL TIME: 17.801s
|
| 714 |
-
2026-11-01 23:30:34 | INFO | ELAPSED TRAINING TIME: 628.56s
|
| 715 |
-
2026-11-01 23:30:34 | INFO | STEP 36 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 716 |
-
2026-11-01 23:30:34 | INFO | STEP 36 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 717 |
-
2026-11-01 23:30:52 | INFO | --------------------------------------------------------------------------------
|
| 718 |
-
2026-11-01 23:30:52 | INFO | STEP 37/70 | epoch=6/10 | position=2/7 | dataset_item=0
|
| 719 |
-
2026-11-01 23:30:52 | INFO | DATASET FILE: 00000000.pt
|
| 720 |
-
2026-11-01 23:30:52 | INFO | LOSS: 0.48794767
|
| 721 |
-
2026-11-01 23:30:52 | INFO | LR: 3.69565217e-05
|
| 722 |
-
2026-11-01 23:30:52 | INFO | TIMESTEP: 0.84535515
|
| 723 |
-
2026-11-01 23:30:52 | INFO | GLOBAL GRADIENT NORM: 0.11927136
|
| 724 |
-
2026-11-01 23:30:52 | INFO | MAX ABSOLUTE GRADIENT: 7.75909424e-03
|
| 725 |
-
2026-11-01 23:30:52 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 726 |
-
2026-11-01 23:30:52 | INFO | MISSING GRADIENT TENSORS: 0
|
| 727 |
-
2026-11-01 23:30:52 | INFO | GPU0 FORWARD: 2.465s
|
| 728 |
-
2026-11-01 23:30:52 | INFO | GPU1 FORWARD: 2.395s
|
| 729 |
-
2026-11-01 23:30:52 | INFO | GPU1 BACKWARD: 6.345s
|
| 730 |
-
2026-11-01 23:30:52 | INFO | GPU0 BACKWARD: 6.203s
|
| 731 |
-
2026-11-01 23:30:52 | INFO | UPDATE WALL TIME: 17.553s
|
| 732 |
-
2026-11-01 23:30:52 | INFO | ELAPSED TRAINING TIME: 646.12s
|
| 733 |
-
2026-11-01 23:30:52 | INFO | STEP 37 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.821 GB | free=1.389 GB
|
| 734 |
-
2026-11-01 23:30:52 | INFO | STEP 37 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.728 GB | free=1.464 GB
|
| 735 |
-
2026-11-01 23:31:10 | INFO | --------------------------------------------------------------------------------
|
| 736 |
-
2026-11-01 23:31:10 | INFO | STEP 38/70 | epoch=6/10 | position=3/7 | dataset_item=3
|
| 737 |
-
2026-11-01 23:31:10 | INFO | DATASET FILE: 00000003.pt
|
| 738 |
-
2026-11-01 23:31:10 | INFO | LOSS: 0.96387875
|
| 739 |
-
2026-11-01 23:31:10 | INFO | LR: 3.65942029e-05
|
| 740 |
-
2026-11-01 23:31:10 | INFO | TIMESTEP: 0.39176139
|
| 741 |
-
2026-11-01 23:31:10 | INFO | GLOBAL GRADIENT NORM: 0.10431517
|
| 742 |
-
2026-11-01 23:31:10 | INFO | MAX ABSOLUTE GRADIENT: 3.28636169e-03
|
| 743 |
-
2026-11-01 23:31:10 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 744 |
-
2026-11-01 23:31:10 | INFO | MISSING GRADIENT TENSORS: 0
|
| 745 |
-
2026-11-01 23:31:10 | INFO | GPU0 FORWARD: 2.502s
|
| 746 |
-
2026-11-01 23:31:10 | INFO | GPU1 FORWARD: 2.404s
|
| 747 |
-
2026-11-01 23:31:10 | INFO | GPU1 BACKWARD: 6.275s
|
| 748 |
-
2026-11-01 23:31:10 | INFO | GPU0 BACKWARD: 6.248s
|
| 749 |
-
2026-11-01 23:31:10 | INFO | UPDATE WALL TIME: 17.579s
|
| 750 |
-
2026-11-01 23:31:10 | INFO | ELAPSED TRAINING TIME: 663.72s
|
| 751 |
-
2026-11-01 23:31:10 | INFO | STEP 38 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.898 GB | free=1.389 GB
|
| 752 |
-
2026-11-01 23:31:10 | INFO | STEP 38 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.805 GB | free=1.464 GB
|
| 753 |
-
2026-11-01 23:31:27 | INFO | --------------------------------------------------------------------------------
|
| 754 |
-
2026-11-01 23:31:27 | INFO | STEP 39/70 | epoch=6/10 | position=4/7 | dataset_item=4
|
| 755 |
-
2026-11-01 23:31:27 | INFO | DATASET FILE: 00000004.pt
|
| 756 |
-
2026-11-01 23:31:27 | INFO | LOSS: 0.82819331
|
| 757 |
-
2026-11-01 23:31:27 | INFO | LR: 3.62318841e-05
|
| 758 |
-
2026-11-01 23:31:27 | INFO | TIMESTEP: 0.48779073
|
| 759 |
-
2026-11-01 23:31:27 | INFO | GLOBAL GRADIENT NORM: 0.08383896
|
| 760 |
-
2026-11-01 23:31:27 | INFO | MAX ABSOLUTE GRADIENT: 3.06701660e-03
|
| 761 |
-
2026-11-01 23:31:27 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 762 |
-
2026-11-01 23:31:27 | INFO | MISSING GRADIENT TENSORS: 0
|
| 763 |
-
2026-11-01 23:31:27 | INFO | GPU0 FORWARD: 2.474s
|
| 764 |
-
2026-11-01 23:31:27 | INFO | GPU1 FORWARD: 2.404s
|
| 765 |
-
2026-11-01 23:31:27 | INFO | GPU1 BACKWARD: 6.283s
|
| 766 |
-
2026-11-01 23:31:27 | INFO | GPU0 BACKWARD: 6.236s
|
| 767 |
-
2026-11-01 23:31:27 | INFO | UPDATE WALL TIME: 17.549s
|
| 768 |
-
2026-11-01 23:31:27 | INFO | ELAPSED TRAINING TIME: 681.28s
|
| 769 |
-
2026-11-01 23:31:27 | INFO | STEP 39 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.862 GB | free=1.389 GB
|
| 770 |
-
2026-11-01 23:31:27 | INFO | STEP 39 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.768 GB | free=1.464 GB
|
| 771 |
-
2026-11-01 23:31:44 | INFO | --------------------------------------------------------------------------------
|
| 772 |
-
2026-11-01 23:31:44 | INFO | STEP 40/70 | epoch=6/10 | position=5/7 | dataset_item=1
|
| 773 |
-
2026-11-01 23:31:44 | INFO | DATASET FILE: 00000001.pt
|
| 774 |
-
2026-11-01 23:31:44 | INFO | LOSS: 0.56365967
|
| 775 |
-
2026-11-01 23:31:44 | INFO | LR: 3.58695652e-05
|
| 776 |
-
2026-11-01 23:31:44 | INFO | TIMESTEP: 0.72132856
|
| 777 |
-
2026-11-01 23:31:44 | INFO | GLOBAL GRADIENT NORM: 0.08286749
|
| 778 |
-
2026-11-01 23:31:44 | INFO | MAX ABSOLUTE GRADIENT: 4.44030762e-03
|
| 779 |
-
2026-11-01 23:31:44 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 780 |
-
2026-11-01 23:31:44 | INFO | MISSING GRADIENT TENSORS: 0
|
| 781 |
-
2026-11-01 23:31:44 | INFO | GPU0 FORWARD: 2.438s
|
| 782 |
-
2026-11-01 23:31:44 | INFO | GPU1 FORWARD: 2.358s
|
| 783 |
-
2026-11-01 23:31:44 | INFO | GPU1 BACKWARD: 6.180s
|
| 784 |
-
2026-11-01 23:31:44 | INFO | GPU0 BACKWARD: 6.156s
|
| 785 |
-
2026-11-01 23:31:44 | INFO | UPDATE WALL TIME: 17.279s
|
| 786 |
-
2026-11-01 23:31:44 | INFO | ELAPSED TRAINING TIME: 698.57s
|
| 787 |
-
2026-11-01 23:31:44 | INFO | STEP 40 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.756 GB | free=1.389 GB
|
| 788 |
-
2026-11-01 23:31:44 | INFO | STEP 40 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.664 GB | free=1.464 GB
|
| 789 |
-
2026-11-01 23:32:02 | INFO | --------------------------------------------------------------------------------
|
| 790 |
-
2026-11-01 23:32:02 | INFO | STEP 41/70 | epoch=6/10 | position=6/7 | dataset_item=6
|
| 791 |
-
2026-11-01 23:32:02 | INFO | DATASET FILE: 00000006.pt
|
| 792 |
-
2026-11-01 23:32:02 | INFO | LOSS: 1.13808560
|
| 793 |
-
2026-11-01 23:32:02 | INFO | LR: 3.55072464e-05
|
| 794 |
-
2026-11-01 23:32:02 | INFO | TIMESTEP: 0.06130258
|
| 795 |
-
2026-11-01 23:32:02 | INFO | GLOBAL GRADIENT NORM: 0.29548634
|
| 796 |
-
2026-11-01 23:32:02 | INFO | MAX ABSOLUTE GRADIENT: 1.49993896e-02
|
| 797 |
-
2026-11-01 23:32:02 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 798 |
-
2026-11-01 23:32:02 | INFO | MISSING GRADIENT TENSORS: 0
|
| 799 |
-
2026-11-01 23:32:02 | INFO | GPU0 FORWARD: 2.493s
|
| 800 |
-
2026-11-01 23:32:02 | INFO | GPU1 FORWARD: 2.401s
|
| 801 |
-
2026-11-01 23:32:02 | INFO | GPU1 BACKWARD: 6.259s
|
| 802 |
-
2026-11-01 23:32:02 | INFO | GPU0 BACKWARD: 6.314s
|
| 803 |
-
2026-11-01 23:32:02 | INFO | UPDATE WALL TIME: 17.613s
|
| 804 |
-
2026-11-01 23:32:02 | INFO | ELAPSED TRAINING TIME: 716.19s
|
| 805 |
-
2026-11-01 23:32:02 | INFO | STEP 41 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.882 GB | free=1.389 GB
|
| 806 |
-
2026-11-01 23:32:02 | INFO | STEP 41 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.788 GB | free=1.464 GB
|
| 807 |
-
2026-11-01 23:32:20 | INFO | --------------------------------------------------------------------------------
|
| 808 |
-
2026-11-01 23:32:20 | INFO | STEP 42/70 | epoch=6/10 | position=7/7 | dataset_item=2
|
| 809 |
-
2026-11-01 23:32:20 | INFO | DATASET FILE: 00000002.pt
|
| 810 |
-
2026-11-01 23:32:20 | INFO | LOSS: 1.17065358
|
| 811 |
-
2026-11-01 23:32:20 | INFO | LR: 3.51449275e-05
|
| 812 |
-
2026-11-01 23:32:20 | INFO | TIMESTEP: 0.26449913
|
| 813 |
-
2026-11-01 23:32:20 | INFO | GLOBAL GRADIENT NORM: 0.14144331
|
| 814 |
-
2026-11-01 23:32:20 | INFO | MAX ABSOLUTE GRADIENT: 4.80651855e-03
|
| 815 |
-
2026-11-01 23:32:20 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 816 |
-
2026-11-01 23:32:20 | INFO | MISSING GRADIENT TENSORS: 0
|
| 817 |
-
2026-11-01 23:32:20 | INFO | GPU0 FORWARD: 2.432s
|
| 818 |
-
2026-11-01 23:32:20 | INFO | GPU1 FORWARD: 2.415s
|
| 819 |
-
2026-11-01 23:32:20 | INFO | GPU1 BACKWARD: 6.246s
|
| 820 |
-
2026-11-01 23:32:20 | INFO | GPU0 BACKWARD: 6.173s
|
| 821 |
-
2026-11-01 23:32:20 | INFO | UPDATE WALL TIME: 17.410s
|
| 822 |
-
2026-11-01 23:32:20 | INFO | ELAPSED TRAINING TIME: 733.61s
|
| 823 |
-
2026-11-01 23:32:20 | INFO | STEP 42 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.835 GB | free=1.389 GB
|
| 824 |
-
2026-11-01 23:32:20 | INFO | STEP 42 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.742 GB | free=1.464 GB
|
| 825 |
-
2026-11-01 23:32:37 | INFO | --------------------------------------------------------------------------------
|
| 826 |
-
2026-11-01 23:32:37 | INFO | STEP 43/70 | epoch=7/10 | position=1/7 | dataset_item=4
|
| 827 |
-
2026-11-01 23:32:37 | INFO | DATASET FILE: 00000004.pt
|
| 828 |
-
2026-11-01 23:32:37 | INFO | LOSS: 1.11446595
|
| 829 |
-
2026-11-01 23:32:37 | INFO | LR: 3.47826087e-05
|
| 830 |
-
2026-11-01 23:32:37 | INFO | TIMESTEP: 0.29757562
|
| 831 |
-
2026-11-01 23:32:37 | INFO | GLOBAL GRADIENT NORM: 0.10815306
|
| 832 |
-
2026-11-01 23:32:37 | INFO | MAX ABSOLUTE GRADIENT: 5.15747070e-03
|
| 833 |
-
2026-11-01 23:32:37 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 834 |
-
2026-11-01 23:32:37 | INFO | MISSING GRADIENT TENSORS: 0
|
| 835 |
-
2026-11-01 23:32:37 | INFO | GPU0 FORWARD: 2.473s
|
| 836 |
-
2026-11-01 23:32:37 | INFO | GPU1 FORWARD: 2.380s
|
| 837 |
-
2026-11-01 23:32:37 | INFO | GPU1 BACKWARD: 6.260s
|
| 838 |
-
2026-11-01 23:32:37 | INFO | GPU0 BACKWARD: 6.292s
|
| 839 |
-
2026-11-01 23:32:37 | INFO | UPDATE WALL TIME: 17.552s
|
| 840 |
-
2026-11-01 23:32:37 | INFO | ELAPSED TRAINING TIME: 751.17s
|
| 841 |
-
2026-11-01 23:32:37 | INFO | STEP 43 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.862 GB | free=1.389 GB
|
| 842 |
-
2026-11-01 23:32:37 | INFO | STEP 43 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.768 GB | free=1.464 GB
|
| 843 |
-
2026-11-01 23:32:55 | INFO | --------------------------------------------------------------------------------
|
| 844 |
-
2026-11-01 23:32:55 | INFO | STEP 44/70 | epoch=7/10 | position=2/7 | dataset_item=5
|
| 845 |
-
2026-11-01 23:32:55 | INFO | DATASET FILE: 00000005.pt
|
| 846 |
-
2026-11-01 23:32:55 | INFO | LOSS: 0.60464799
|
| 847 |
-
2026-11-01 23:32:55 | INFO | LR: 3.44202899e-05
|
| 848 |
-
2026-11-01 23:32:55 | INFO | TIMESTEP: 0.61395168
|
| 849 |
-
2026-11-01 23:32:55 | INFO | GLOBAL GRADIENT NORM: 0.21718825
|
| 850 |
-
2026-11-01 23:32:55 | INFO | MAX ABSOLUTE GRADIENT: 1.10473633e-02
|
| 851 |
-
2026-11-01 23:32:55 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 852 |
-
2026-11-01 23:32:55 | INFO | MISSING GRADIENT TENSORS: 0
|
| 853 |
-
2026-11-01 23:32:55 | INFO | GPU0 FORWARD: 2.543s
|
| 854 |
-
2026-11-01 23:32:55 | INFO | GPU1 FORWARD: 2.445s
|
| 855 |
-
2026-11-01 23:32:55 | INFO | GPU1 BACKWARD: 6.391s
|
| 856 |
-
2026-11-01 23:32:55 | INFO | GPU0 BACKWARD: 6.278s
|
| 857 |
-
2026-11-01 23:32:55 | INFO | UPDATE WALL TIME: 17.806s
|
| 858 |
-
2026-11-01 23:32:55 | INFO | ELAPSED TRAINING TIME: 768.99s
|
| 859 |
-
2026-11-01 23:32:55 | INFO | STEP 44 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 860 |
-
2026-11-01 23:32:55 | INFO | STEP 44 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 861 |
-
2026-11-01 23:33:12 | INFO | --------------------------------------------------------------------------------
|
| 862 |
-
2026-11-01 23:33:12 | INFO | STEP 45/70 | epoch=7/10 | position=3/7 | dataset_item=1
|
| 863 |
-
2026-11-01 23:33:12 | INFO | DATASET FILE: 00000001.pt
|
| 864 |
-
2026-11-01 23:33:12 | INFO | LOSS: 0.59427971
|
| 865 |
-
2026-11-01 23:33:12 | INFO | LR: 3.40579710e-05
|
| 866 |
-
2026-11-01 23:33:12 | INFO | TIMESTEP: 0.67698693
|
| 867 |
-
2026-11-01 23:33:12 | INFO | GLOBAL GRADIENT NORM: 0.06830193
|
| 868 |
-
2026-11-01 23:33:12 | INFO | MAX ABSOLUTE GRADIENT: 3.22151184e-03
|
| 869 |
-
2026-11-01 23:33:12 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 870 |
-
2026-11-01 23:33:12 | INFO | MISSING GRADIENT TENSORS: 0
|
| 871 |
-
2026-11-01 23:33:12 | INFO | GPU0 FORWARD: 2.446s
|
| 872 |
-
2026-11-01 23:33:12 | INFO | GPU1 FORWARD: 2.363s
|
| 873 |
-
2026-11-01 23:33:12 | INFO | GPU1 BACKWARD: 6.226s
|
| 874 |
-
2026-11-01 23:33:12 | INFO | GPU0 BACKWARD: 6.185s
|
| 875 |
-
2026-11-01 23:33:12 | INFO | UPDATE WALL TIME: 17.365s
|
| 876 |
-
2026-11-01 23:33:12 | INFO | ELAPSED TRAINING TIME: 786.37s
|
| 877 |
-
2026-11-01 23:33:12 | INFO | STEP 45 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.756 GB | free=1.389 GB
|
| 878 |
-
2026-11-01 23:33:12 | INFO | STEP 45 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.664 GB | free=1.464 GB
|
| 879 |
-
2026-11-01 23:33:30 | INFO | --------------------------------------------------------------------------------
|
| 880 |
-
2026-11-01 23:33:30 | INFO | STEP 46/70 | epoch=7/10 | position=4/7 | dataset_item=2
|
| 881 |
-
2026-11-01 23:33:30 | INFO | DATASET FILE: 00000002.pt
|
| 882 |
-
2026-11-01 23:33:30 | INFO | LOSS: 1.10766661
|
| 883 |
-
2026-11-01 23:33:30 | INFO | LR: 3.36956522e-05
|
| 884 |
-
2026-11-01 23:33:30 | INFO | TIMESTEP: 0.03403377
|
| 885 |
-
2026-11-01 23:33:30 | INFO | GLOBAL GRADIENT NORM: 0.26566451
|
| 886 |
-
2026-11-01 23:33:30 | INFO | MAX ABSOLUTE GRADIENT: 2.34985352e-02
|
| 887 |
-
2026-11-01 23:33:30 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 888 |
-
2026-11-01 23:33:30 | INFO | MISSING GRADIENT TENSORS: 0
|
| 889 |
-
2026-11-01 23:33:30 | INFO | GPU0 FORWARD: 2.515s
|
| 890 |
-
2026-11-01 23:33:30 | INFO | GPU1 FORWARD: 2.375s
|
| 891 |
-
2026-11-01 23:33:30 | INFO | GPU1 BACKWARD: 6.185s
|
| 892 |
-
2026-11-01 23:33:30 | INFO | GPU0 BACKWARD: 6.256s
|
| 893 |
-
2026-11-01 23:33:30 | INFO | UPDATE WALL TIME: 17.481s
|
| 894 |
-
2026-11-01 23:33:30 | INFO | ELAPSED TRAINING TIME: 803.86s
|
| 895 |
-
2026-11-01 23:33:30 | INFO | STEP 46 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.835 GB | free=1.389 GB
|
| 896 |
-
2026-11-01 23:33:30 | INFO | STEP 46 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.742 GB | free=1.464 GB
|
| 897 |
-
2026-11-01 23:33:47 | INFO | --------------------------------------------------------------------------------
|
| 898 |
-
2026-11-01 23:33:47 | INFO | STEP 47/70 | epoch=7/10 | position=5/7 | dataset_item=6
|
| 899 |
-
2026-11-01 23:33:47 | INFO | DATASET FILE: 00000006.pt
|
| 900 |
-
2026-11-01 23:33:47 | INFO | LOSS: 0.55366147
|
| 901 |
-
2026-11-01 23:33:47 | INFO | LR: 3.33333333e-05
|
| 902 |
-
2026-11-01 23:33:47 | INFO | TIMESTEP: 0.76543015
|
| 903 |
-
2026-11-01 23:33:47 | INFO | GLOBAL GRADIENT NORM: 0.09578727
|
| 904 |
-
2026-11-01 23:33:47 | INFO | MAX ABSOLUTE GRADIENT: 8.12530518e-03
|
| 905 |
-
2026-11-01 23:33:47 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 906 |
-
2026-11-01 23:33:47 | INFO | MISSING GRADIENT TENSORS: 0
|
| 907 |
-
2026-11-01 23:33:47 | INFO | GPU0 FORWARD: 2.505s
|
| 908 |
-
2026-11-01 23:33:47 | INFO | GPU1 FORWARD: 2.433s
|
| 909 |
-
2026-11-01 23:33:47 | INFO | GPU1 BACKWARD: 6.334s
|
| 910 |
-
2026-11-01 23:33:47 | INFO | GPU0 BACKWARD: 6.230s
|
| 911 |
-
2026-11-01 23:33:47 | INFO | UPDATE WALL TIME: 17.664s
|
| 912 |
-
2026-11-01 23:33:47 | INFO | ELAPSED TRAINING TIME: 821.54s
|
| 913 |
-
2026-11-01 23:33:47 | INFO | STEP 47 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.882 GB | free=1.389 GB
|
| 914 |
-
2026-11-01 23:33:47 | INFO | STEP 47 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.788 GB | free=1.464 GB
|
| 915 |
-
2026-11-01 23:34:05 | INFO | --------------------------------------------------------------------------------
|
| 916 |
-
2026-11-01 23:34:05 | INFO | STEP 48/70 | epoch=7/10 | position=6/7 | dataset_item=3
|
| 917 |
-
2026-11-01 23:34:05 | INFO | DATASET FILE: 00000003.pt
|
| 918 |
-
2026-11-01 23:34:05 | INFO | LOSS: 0.49302477
|
| 919 |
-
2026-11-01 23:34:05 | INFO | LR: 3.29710145e-05
|
| 920 |
-
2026-11-01 23:34:05 | INFO | TIMESTEP: 0.83247983
|
| 921 |
-
2026-11-01 23:34:05 | INFO | GLOBAL GRADIENT NORM: 0.10111229
|
| 922 |
-
2026-11-01 23:34:05 | INFO | MAX ABSOLUTE GRADIENT: 4.60815430e-03
|
| 923 |
-
2026-11-01 23:34:05 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 924 |
-
2026-11-01 23:34:05 | INFO | MISSING GRADIENT TENSORS: 0
|
| 925 |
-
2026-11-01 23:34:05 | INFO | GPU0 FORWARD: 2.461s
|
| 926 |
-
2026-11-01 23:34:05 | INFO | GPU1 FORWARD: 2.403s
|
| 927 |
-
2026-11-01 23:34:05 | INFO | GPU1 BACKWARD: 6.299s
|
| 928 |
-
2026-11-01 23:34:05 | INFO | GPU0 BACKWARD: 6.173s
|
| 929 |
-
2026-11-01 23:34:05 | INFO | UPDATE WALL TIME: 17.480s
|
| 930 |
-
2026-11-01 23:34:05 | INFO | ELAPSED TRAINING TIME: 839.03s
|
| 931 |
-
2026-11-01 23:34:05 | INFO | STEP 48 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.898 GB | free=1.389 GB
|
| 932 |
-
2026-11-01 23:34:05 | INFO | STEP 48 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.805 GB | free=1.464 GB
|
| 933 |
-
2026-11-01 23:34:22 | INFO | --------------------------------------------------------------------------------
|
| 934 |
-
2026-11-01 23:34:22 | INFO | STEP 49/70 | epoch=7/10 | position=7/7 | dataset_item=0
|
| 935 |
-
2026-11-01 23:34:22 | INFO | DATASET FILE: 00000000.pt
|
| 936 |
-
2026-11-01 23:34:22 | INFO | LOSS: 1.19202948
|
| 937 |
-
2026-11-01 23:34:22 | INFO | LR: 3.26086957e-05
|
| 938 |
-
2026-11-01 23:34:22 | INFO | TIMESTEP: 0.11672945
|
| 939 |
-
2026-11-01 23:34:22 | INFO | GLOBAL GRADIENT NORM: 0.22136453
|
| 940 |
-
2026-11-01 23:34:22 | INFO | MAX ABSOLUTE GRADIENT: 1.06353760e-02
|
| 941 |
-
2026-11-01 23:34:22 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 942 |
-
2026-11-01 23:34:22 | INFO | MISSING GRADIENT TENSORS: 0
|
| 943 |
-
2026-11-01 23:34:22 | INFO | GPU0 FORWARD: 2.447s
|
| 944 |
-
2026-11-01 23:34:22 | INFO | GPU1 FORWARD: 2.405s
|
| 945 |
-
2026-11-01 23:34:22 | INFO | GPU1 BACKWARD: 6.186s
|
| 946 |
-
2026-11-01 23:34:22 | INFO | GPU0 BACKWARD: 6.269s
|
| 947 |
-
2026-11-01 23:34:22 | INFO | UPDATE WALL TIME: 17.453s
|
| 948 |
-
2026-11-01 23:34:22 | INFO | ELAPSED TRAINING TIME: 856.50s
|
| 949 |
-
2026-11-01 23:34:22 | INFO | STEP 49 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.821 GB | free=1.389 GB
|
| 950 |
-
2026-11-01 23:34:22 | INFO | STEP 49 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.728 GB | free=1.464 GB
|
| 951 |
-
2026-11-01 23:34:40 | INFO | --------------------------------------------------------------------------------
|
| 952 |
-
2026-11-01 23:34:40 | INFO | STEP 50/70 | epoch=8/10 | position=1/7 | dataset_item=2
|
| 953 |
-
2026-11-01 23:34:40 | INFO | DATASET FILE: 00000002.pt
|
| 954 |
-
2026-11-01 23:34:40 | INFO | LOSS: 1.08855247
|
| 955 |
-
2026-11-01 23:34:40 | INFO | LR: 3.22463768e-05
|
| 956 |
-
2026-11-01 23:34:40 | INFO | TIMESTEP: 0.33134848
|
| 957 |
-
2026-11-01 23:34:40 | INFO | GLOBAL GRADIENT NORM: 0.09441752
|
| 958 |
-
2026-11-01 23:34:40 | INFO | MAX ABSOLUTE GRADIENT: 7.21359253e-03
|
| 959 |
-
2026-11-01 23:34:40 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 960 |
-
2026-11-01 23:34:40 | INFO | MISSING GRADIENT TENSORS: 0
|
| 961 |
-
2026-11-01 23:34:40 | INFO | GPU0 FORWARD: 2.470s
|
| 962 |
-
2026-11-01 23:34:40 | INFO | GPU1 FORWARD: 2.372s
|
| 963 |
-
2026-11-01 23:34:40 | INFO | GPU1 BACKWARD: 6.200s
|
| 964 |
-
2026-11-01 23:34:40 | INFO | GPU0 BACKWARD: 6.261s
|
| 965 |
-
2026-11-01 23:34:40 | INFO | UPDATE WALL TIME: 17.456s
|
| 966 |
-
2026-11-01 23:34:40 | INFO | ELAPSED TRAINING TIME: 873.96s
|
| 967 |
-
2026-11-01 23:34:40 | INFO | STEP 50 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.835 GB | free=1.389 GB
|
| 968 |
-
2026-11-01 23:34:40 | INFO | STEP 50 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.742 GB | free=1.464 GB
|
| 969 |
-
2026-11-01 23:34:57 | INFO | --------------------------------------------------------------------------------
|
| 970 |
-
2026-11-01 23:34:57 | INFO | STEP 51/70 | epoch=8/10 | position=2/7 | dataset_item=4
|
| 971 |
-
2026-11-01 23:34:57 | INFO | DATASET FILE: 00000004.pt
|
| 972 |
-
2026-11-01 23:34:57 | INFO | LOSS: 0.54909748
|
| 973 |
-
2026-11-01 23:34:57 | INFO | LR: 3.18840580e-05
|
| 974 |
-
2026-11-01 23:34:57 | INFO | TIMESTEP: 0.73580515
|
| 975 |
-
2026-11-01 23:34:57 | INFO | GLOBAL GRADIENT NORM: 0.07353024
|
| 976 |
-
2026-11-01 23:34:57 | INFO | MAX ABSOLUTE GRADIENT: 4.26483154e-03
|
| 977 |
-
2026-11-01 23:34:57 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 978 |
-
2026-11-01 23:34:57 | INFO | MISSING GRADIENT TENSORS: 0
|
| 979 |
-
2026-11-01 23:34:57 | INFO | GPU0 FORWARD: 2.498s
|
| 980 |
-
2026-11-01 23:34:57 | INFO | GPU1 FORWARD: 2.380s
|
| 981 |
-
2026-11-01 23:34:57 | INFO | GPU1 BACKWARD: 6.299s
|
| 982 |
-
2026-11-01 23:34:57 | INFO | GPU0 BACKWARD: 6.186s
|
| 983 |
-
2026-11-01 23:34:57 | INFO | UPDATE WALL TIME: 17.508s
|
| 984 |
-
2026-11-01 23:34:57 | INFO | ELAPSED TRAINING TIME: 891.48s
|
| 985 |
-
2026-11-01 23:34:57 | INFO | STEP 51 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.862 GB | free=1.389 GB
|
| 986 |
-
2026-11-01 23:34:57 | INFO | STEP 51 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.768 GB | free=1.464 GB
|
| 987 |
-
2026-11-01 23:35:15 | INFO | --------------------------------------------------------------------------------
|
| 988 |
-
2026-11-01 23:35:15 | INFO | STEP 52/70 | epoch=8/10 | position=3/7 | dataset_item=1
|
| 989 |
-
2026-11-01 23:35:15 | INFO | DATASET FILE: 00000001.pt
|
| 990 |
-
2026-11-01 23:35:15 | INFO | LOSS: 0.60545063
|
| 991 |
-
2026-11-01 23:35:15 | INFO | LR: 3.15217391e-05
|
| 992 |
-
2026-11-01 23:35:15 | INFO | TIMESTEP: 0.65707183
|
| 993 |
-
2026-11-01 23:35:15 | INFO | GLOBAL GRADIENT NORM: 0.07113345
|
| 994 |
-
2026-11-01 23:35:15 | INFO | MAX ABSOLUTE GRADIENT: 2.50625610e-03
|
| 995 |
-
2026-11-01 23:35:15 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 996 |
-
2026-11-01 23:35:15 | INFO | MISSING GRADIENT TENSORS: 0
|
| 997 |
-
2026-11-01 23:35:15 | INFO | GPU0 FORWARD: 2.433s
|
| 998 |
-
2026-11-01 23:35:15 | INFO | GPU1 FORWARD: 2.370s
|
| 999 |
-
2026-11-01 23:35:15 | INFO | GPU1 BACKWARD: 6.190s
|
| 1000 |
-
2026-11-01 23:35:15 | INFO | GPU0 BACKWARD: 6.235s
|
| 1001 |
-
2026-11-01 23:35:15 | INFO | UPDATE WALL TIME: 17.378s
|
| 1002 |
-
2026-11-01 23:35:15 | INFO | ELAPSED TRAINING TIME: 908.87s
|
| 1003 |
-
2026-11-01 23:35:15 | INFO | STEP 52 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.756 GB | free=1.389 GB
|
| 1004 |
-
2026-11-01 23:35:15 | INFO | STEP 52 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.664 GB | free=1.464 GB
|
| 1005 |
-
2026-11-01 23:35:33 | INFO | --------------------------------------------------------------------------------
|
| 1006 |
-
2026-11-01 23:35:33 | INFO | STEP 53/70 | epoch=8/10 | position=4/7 | dataset_item=5
|
| 1007 |
-
2026-11-01 23:35:33 | INFO | DATASET FILE: 00000005.pt
|
| 1008 |
-
2026-11-01 23:35:33 | INFO | LOSS: 1.14804661
|
| 1009 |
-
2026-11-01 23:35:33 | INFO | LR: 3.11594203e-05
|
| 1010 |
-
2026-11-01 23:35:33 | INFO | TIMESTEP: 0.03221190
|
| 1011 |
-
2026-11-01 23:35:33 | INFO | GLOBAL GRADIENT NORM: 0.99011529
|
| 1012 |
-
2026-11-01 23:35:33 | INFO | MAX ABSOLUTE GRADIENT: 7.36083984e-02
|
| 1013 |
-
2026-11-01 23:35:33 | INFO | GRADIENT CLIP COEFFICIENT: 0.50499119
|
| 1014 |
-
2026-11-01 23:35:33 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1015 |
-
2026-11-01 23:35:33 | INFO | GPU0 FORWARD: 2.556s
|
| 1016 |
-
2026-11-01 23:35:33 | INFO | GPU1 FORWARD: 2.444s
|
| 1017 |
-
2026-11-01 23:35:33 | INFO | GPU1 BACKWARD: 6.351s
|
| 1018 |
-
2026-11-01 23:35:33 | INFO | GPU0 BACKWARD: 6.392s
|
| 1019 |
-
2026-11-01 23:35:33 | INFO | UPDATE WALL TIME: 17.899s
|
| 1020 |
-
2026-11-01 23:35:33 | INFO | ELAPSED TRAINING TIME: 926.78s
|
| 1021 |
-
2026-11-01 23:35:33 | INFO | STEP 53 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 1022 |
-
2026-11-01 23:35:33 | INFO | STEP 53 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 1023 |
-
2026-11-01 23:35:50 | INFO | --------------------------------------------------------------------------------
|
| 1024 |
-
2026-11-01 23:35:50 | INFO | STEP 54/70 | epoch=8/10 | position=5/7 | dataset_item=3
|
| 1025 |
-
2026-11-01 23:35:50 | INFO | DATASET FILE: 00000003.pt
|
| 1026 |
-
2026-11-01 23:35:50 | INFO | LOSS: 1.17867565
|
| 1027 |
-
2026-11-01 23:35:50 | INFO | LR: 3.07971014e-05
|
| 1028 |
-
2026-11-01 23:35:50 | INFO | TIMESTEP: 0.06505132
|
| 1029 |
-
2026-11-01 23:35:50 | INFO | GLOBAL GRADIENT NORM: 0.63161639
|
| 1030 |
-
2026-11-01 23:35:50 | INFO | MAX ABSOLUTE GRADIENT: 5.27038574e-02
|
| 1031 |
-
2026-11-01 23:35:50 | INFO | GRADIENT CLIP COEFFICIENT: 0.79161848
|
| 1032 |
-
2026-11-01 23:35:50 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1033 |
-
2026-11-01 23:35:50 | INFO | GPU0 FORWARD: 2.469s
|
| 1034 |
-
2026-11-01 23:35:50 | INFO | GPU1 FORWARD: 2.417s
|
| 1035 |
-
2026-11-01 23:35:50 | INFO | GPU1 BACKWARD: 6.321s
|
| 1036 |
-
2026-11-01 23:35:50 | INFO | GPU0 BACKWARD: 6.343s
|
| 1037 |
-
2026-11-01 23:35:50 | INFO | UPDATE WALL TIME: 17.706s
|
| 1038 |
-
2026-11-01 23:35:50 | INFO | ELAPSED TRAINING TIME: 944.50s
|
| 1039 |
-
2026-11-01 23:35:50 | INFO | STEP 54 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.898 GB | free=1.389 GB
|
| 1040 |
-
2026-11-01 23:35:50 | INFO | STEP 54 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.805 GB | free=1.464 GB
|
| 1041 |
-
2026-11-01 23:36:08 | INFO | --------------------------------------------------------------------------------
|
| 1042 |
-
2026-11-01 23:36:08 | INFO | STEP 55/70 | epoch=8/10 | position=6/7 | dataset_item=0
|
| 1043 |
-
2026-11-01 23:36:08 | INFO | DATASET FILE: 00000000.pt
|
| 1044 |
-
2026-11-01 23:36:08 | INFO | LOSS: 0.51088017
|
| 1045 |
-
2026-11-01 23:36:08 | INFO | LR: 3.04347826e-05
|
| 1046 |
-
2026-11-01 23:36:08 | INFO | TIMESTEP: 0.75211012
|
| 1047 |
-
2026-11-01 23:36:08 | INFO | GLOBAL GRADIENT NORM: 0.10390844
|
| 1048 |
-
2026-11-01 23:36:08 | INFO | MAX ABSOLUTE GRADIENT: 9.74273682e-03
|
| 1049 |
-
2026-11-01 23:36:08 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1050 |
-
2026-11-01 23:36:08 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1051 |
-
2026-11-01 23:36:08 | INFO | GPU0 FORWARD: 2.481s
|
| 1052 |
-
2026-11-01 23:36:08 | INFO | GPU1 FORWARD: 2.380s
|
| 1053 |
-
2026-11-01 23:36:08 | INFO | GPU1 BACKWARD: 6.208s
|
| 1054 |
-
2026-11-01 23:36:08 | INFO | GPU0 BACKWARD: 6.127s
|
| 1055 |
-
2026-11-01 23:36:08 | INFO | UPDATE WALL TIME: 17.345s
|
| 1056 |
-
2026-11-01 23:36:08 | INFO | ELAPSED TRAINING TIME: 961.86s
|
| 1057 |
-
2026-11-01 23:36:08 | INFO | STEP 55 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.821 GB | free=1.389 GB
|
| 1058 |
-
2026-11-01 23:36:08 | INFO | STEP 55 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.728 GB | free=1.464 GB
|
| 1059 |
-
2026-11-01 23:36:25 | INFO | --------------------------------------------------------------------------------
|
| 1060 |
-
2026-11-01 23:36:25 | INFO | STEP 56/70 | epoch=8/10 | position=7/7 | dataset_item=6
|
| 1061 |
-
2026-11-01 23:36:25 | INFO | DATASET FILE: 00000006.pt
|
| 1062 |
-
2026-11-01 23:36:25 | INFO | LOSS: 0.55729181
|
| 1063 |
-
2026-11-01 23:36:25 | INFO | LR: 3.00724638e-05
|
| 1064 |
-
2026-11-01 23:36:25 | INFO | TIMESTEP: 0.75565380
|
| 1065 |
-
2026-11-01 23:36:25 | INFO | GLOBAL GRADIENT NORM: 0.09028654
|
| 1066 |
-
2026-11-01 23:36:25 | INFO | MAX ABSOLUTE GRADIENT: 6.85501099e-03
|
| 1067 |
-
2026-11-01 23:36:25 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1068 |
-
2026-11-01 23:36:25 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1069 |
-
2026-11-01 23:36:25 | INFO | GPU0 FORWARD: 2.476s
|
| 1070 |
-
2026-11-01 23:36:25 | INFO | GPU1 FORWARD: 2.403s
|
| 1071 |
-
2026-11-01 23:36:25 | INFO | GPU1 BACKWARD: 6.321s
|
| 1072 |
-
2026-11-01 23:36:25 | INFO | GPU0 BACKWARD: 6.275s
|
| 1073 |
-
2026-11-01 23:36:25 | INFO | UPDATE WALL TIME: 17.623s
|
| 1074 |
-
2026-11-01 23:36:25 | INFO | ELAPSED TRAINING TIME: 979.49s
|
| 1075 |
-
2026-11-01 23:36:25 | INFO | STEP 56 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.882 GB | free=1.389 GB
|
| 1076 |
-
2026-11-01 23:36:25 | INFO | STEP 56 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.788 GB | free=1.464 GB
|
| 1077 |
-
2026-11-01 23:36:43 | INFO | --------------------------------------------------------------------------------
|
| 1078 |
-
2026-11-01 23:36:43 | INFO | STEP 57/70 | epoch=9/10 | position=1/7 | dataset_item=1
|
| 1079 |
-
2026-11-01 23:36:43 | INFO | DATASET FILE: 00000001.pt
|
| 1080 |
-
2026-11-01 23:36:43 | INFO | LOSS: 1.22109509
|
| 1081 |
-
2026-11-01 23:36:43 | INFO | LR: 2.97101449e-05
|
| 1082 |
-
2026-11-01 23:36:43 | INFO | TIMESTEP: 0.06928300
|
| 1083 |
-
2026-11-01 23:36:43 | INFO | GLOBAL GRADIENT NORM: 0.95304904
|
| 1084 |
-
2026-11-01 23:36:43 | INFO | MAX ABSOLUTE GRADIENT: 6.16760254e-02
|
| 1085 |
-
2026-11-01 23:36:43 | INFO | GRADIENT CLIP COEFFICIENT: 0.52463143
|
| 1086 |
-
2026-11-01 23:36:43 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1087 |
-
2026-11-01 23:36:43 | INFO | GPU0 FORWARD: 2.480s
|
| 1088 |
-
2026-11-01 23:36:43 | INFO | GPU1 FORWARD: 2.339s
|
| 1089 |
-
2026-11-01 23:36:43 | INFO | GPU1 BACKWARD: 6.129s
|
| 1090 |
-
2026-11-01 23:36:43 | INFO | GPU0 BACKWARD: 6.204s
|
| 1091 |
-
2026-11-01 23:36:43 | INFO | UPDATE WALL TIME: 17.301s
|
| 1092 |
-
2026-11-01 23:36:43 | INFO | ELAPSED TRAINING TIME: 996.80s
|
| 1093 |
-
2026-11-01 23:36:43 | INFO | STEP 57 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.756 GB | free=1.389 GB
|
| 1094 |
-
2026-11-01 23:36:43 | INFO | STEP 57 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.664 GB | free=1.464 GB
|
| 1095 |
-
2026-11-01 23:37:00 | INFO | --------------------------------------------------------------------------------
|
| 1096 |
-
2026-11-01 23:37:00 | INFO | STEP 58/70 | epoch=9/10 | position=2/7 | dataset_item=0
|
| 1097 |
-
2026-11-01 23:37:00 | INFO | DATASET FILE: 00000000.pt
|
| 1098 |
-
2026-11-01 23:37:00 | INFO | LOSS: 0.51689565
|
| 1099 |
-
2026-11-01 23:37:00 | INFO | LR: 2.93478261e-05
|
| 1100 |
-
2026-11-01 23:37:00 | INFO | TIMESTEP: 0.74342495
|
| 1101 |
-
2026-11-01 23:37:00 | INFO | GLOBAL GRADIENT NORM: 0.11001887
|
| 1102 |
-
2026-11-01 23:37:00 | INFO | MAX ABSOLUTE GRADIENT: 6.96945190e-03
|
| 1103 |
-
2026-11-01 23:37:00 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1104 |
-
2026-11-01 23:37:00 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1105 |
-
2026-11-01 23:37:00 | INFO | GPU0 FORWARD: 2.440s
|
| 1106 |
-
2026-11-01 23:37:00 | INFO | GPU1 FORWARD: 2.393s
|
| 1107 |
-
2026-11-01 23:37:00 | INFO | GPU1 BACKWARD: 6.307s
|
| 1108 |
-
2026-11-01 23:37:00 | INFO | GPU0 BACKWARD: 6.185s
|
| 1109 |
-
2026-11-01 23:37:00 | INFO | UPDATE WALL TIME: 17.472s
|
| 1110 |
-
2026-11-01 23:37:00 | INFO | ELAPSED TRAINING TIME: 1014.29s
|
| 1111 |
-
2026-11-01 23:37:00 | INFO | STEP 58 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.821 GB | free=1.389 GB
|
| 1112 |
-
2026-11-01 23:37:00 | INFO | STEP 58 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.728 GB | free=1.464 GB
|
| 1113 |
-
2026-11-01 23:37:18 | INFO | --------------------------------------------------------------------------------
|
| 1114 |
-
2026-11-01 23:37:18 | INFO | STEP 59/70 | epoch=9/10 | position=3/7 | dataset_item=3
|
| 1115 |
-
2026-11-01 23:37:18 | INFO | DATASET FILE: 00000003.pt
|
| 1116 |
-
2026-11-01 23:37:18 | INFO | LOSS: 1.21733952
|
| 1117 |
-
2026-11-01 23:37:18 | INFO | LR: 2.89855072e-05
|
| 1118 |
-
2026-11-01 23:37:18 | INFO | TIMESTEP: 0.03509389
|
| 1119 |
-
2026-11-01 23:37:18 | INFO | GLOBAL GRADIENT NORM: 1.21723954
|
| 1120 |
-
2026-11-01 23:37:18 | INFO | MAX ABSOLUTE GRADIENT: 1.07666016e-01
|
| 1121 |
-
2026-11-01 23:37:18 | INFO | GRADIENT CLIP COEFFICIENT: 0.41076515
|
| 1122 |
-
2026-11-01 23:37:18 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1123 |
-
2026-11-01 23:37:18 | INFO | GPU0 FORWARD: 2.491s
|
| 1124 |
-
2026-11-01 23:37:18 | INFO | GPU1 FORWARD: 2.375s
|
| 1125 |
-
2026-11-01 23:37:18 | INFO | GPU1 BACKWARD: 6.226s
|
| 1126 |
-
2026-11-01 23:37:18 | INFO | GPU0 BACKWARD: 6.308s
|
| 1127 |
-
2026-11-01 23:37:18 | INFO | UPDATE WALL TIME: 17.550s
|
| 1128 |
-
2026-11-01 23:37:18 | INFO | ELAPSED TRAINING TIME: 1031.85s
|
| 1129 |
-
2026-11-01 23:37:18 | INFO | STEP 59 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.898 GB | free=1.389 GB
|
| 1130 |
-
2026-11-01 23:37:18 | INFO | STEP 59 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.805 GB | free=1.464 GB
|
| 1131 |
-
2026-11-01 23:37:36 | INFO | --------------------------------------------------------------------------------
|
| 1132 |
-
2026-11-01 23:37:36 | INFO | STEP 60/70 | epoch=9/10 | position=4/7 | dataset_item=5
|
| 1133 |
-
2026-11-01 23:37:36 | INFO | DATASET FILE: 00000005.pt
|
| 1134 |
-
2026-11-01 23:37:36 | INFO | LOSS: 0.92453688
|
| 1135 |
-
2026-11-01 23:37:36 | INFO | LR: 2.86231884e-05
|
| 1136 |
-
2026-11-01 23:37:36 | INFO | TIMESTEP: 0.39239028
|
| 1137 |
-
2026-11-01 23:37:36 | INFO | GLOBAL GRADIENT NORM: 0.24530688
|
| 1138 |
-
2026-11-01 23:37:36 | INFO | MAX ABSOLUTE GRADIENT: 8.63647461e-03
|
| 1139 |
-
2026-11-01 23:37:36 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1140 |
-
2026-11-01 23:37:36 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1141 |
-
2026-11-01 23:37:36 | INFO | GPU0 FORWARD: 2.542s
|
| 1142 |
-
2026-11-01 23:37:36 | INFO | GPU1 FORWARD: 2.431s
|
| 1143 |
-
2026-11-01 23:37:36 | INFO | GPU1 BACKWARD: 6.382s
|
| 1144 |
-
2026-11-01 23:37:36 | INFO | GPU0 BACKWARD: 6.512s
|
| 1145 |
-
2026-11-01 23:37:36 | INFO | UPDATE WALL TIME: 18.008s
|
| 1146 |
-
2026-11-01 23:37:36 | INFO | ELAPSED TRAINING TIME: 1049.87s
|
| 1147 |
-
2026-11-01 23:37:36 | INFO | STEP 60 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 1148 |
-
2026-11-01 23:37:36 | INFO | STEP 60 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 1149 |
-
2026-11-01 23:37:53 | INFO | --------------------------------------------------------------------------------
|
| 1150 |
-
2026-11-01 23:37:53 | INFO | STEP 61/70 | epoch=9/10 | position=5/7 | dataset_item=6
|
| 1151 |
-
2026-11-01 23:37:53 | INFO | DATASET FILE: 00000006.pt
|
| 1152 |
-
2026-11-01 23:37:53 | INFO | LOSS: 1.15974355
|
| 1153 |
-
2026-11-01 23:37:53 | INFO | LR: 2.82608696e-05
|
| 1154 |
-
2026-11-01 23:37:53 | INFO | TIMESTEP: 0.31237870
|
| 1155 |
-
2026-11-01 23:37:53 | INFO | GLOBAL GRADIENT NORM: 0.34283411
|
| 1156 |
-
2026-11-01 23:37:53 | INFO | MAX ABSOLUTE GRADIENT: 1.44805908e-02
|
| 1157 |
-
2026-11-01 23:37:53 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1158 |
-
2026-11-01 23:37:53 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1159 |
-
2026-11-01 23:37:53 | INFO | GPU0 FORWARD: 2.524s
|
| 1160 |
-
2026-11-01 23:37:53 | INFO | GPU1 FORWARD: 2.403s
|
| 1161 |
-
2026-11-01 23:37:53 | INFO | GPU1 BACKWARD: 6.212s
|
| 1162 |
-
2026-11-01 23:37:53 | INFO | GPU0 BACKWARD: 6.232s
|
| 1163 |
-
2026-11-01 23:37:53 | INFO | UPDATE WALL TIME: 17.519s
|
| 1164 |
-
2026-11-01 23:37:53 | INFO | ELAPSED TRAINING TIME: 1067.40s
|
| 1165 |
-
2026-11-01 23:37:53 | INFO | STEP 61 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.882 GB | free=1.389 GB
|
| 1166 |
-
2026-11-01 23:37:53 | INFO | STEP 61 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.788 GB | free=1.464 GB
|
| 1167 |
-
2026-11-01 23:38:11 | INFO | --------------------------------------------------------------------------------
|
| 1168 |
-
2026-11-01 23:38:11 | INFO | STEP 62/70 | epoch=9/10 | position=6/7 | dataset_item=2
|
| 1169 |
-
2026-11-01 23:38:11 | INFO | DATASET FILE: 00000002.pt
|
| 1170 |
-
2026-11-01 23:38:11 | INFO | LOSS: 1.24041653
|
| 1171 |
-
2026-11-01 23:38:11 | INFO | LR: 2.78985507e-05
|
| 1172 |
-
2026-11-01 23:38:11 | INFO | TIMESTEP: 0.24778335
|
| 1173 |
-
2026-11-01 23:38:11 | INFO | GLOBAL GRADIENT NORM: 0.31334188
|
| 1174 |
-
2026-11-01 23:38:11 | INFO | MAX ABSOLUTE GRADIENT: 1.16882324e-02
|
| 1175 |
-
2026-11-01 23:38:11 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1176 |
-
2026-11-01 23:38:11 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1177 |
-
2026-11-01 23:38:11 | INFO | GPU0 FORWARD: 2.425s
|
| 1178 |
-
2026-11-01 23:38:11 | INFO | GPU1 FORWARD: 2.392s
|
| 1179 |
-
2026-11-01 23:38:11 | INFO | GPU1 BACKWARD: 6.243s
|
| 1180 |
-
2026-11-01 23:38:11 | INFO | GPU0 BACKWARD: 6.219s
|
| 1181 |
-
2026-11-01 23:38:11 | INFO | UPDATE WALL TIME: 17.430s
|
| 1182 |
-
2026-11-01 23:38:11 | INFO | ELAPSED TRAINING TIME: 1084.84s
|
| 1183 |
-
2026-11-01 23:38:11 | INFO | STEP 62 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.835 GB | free=1.389 GB
|
| 1184 |
-
2026-11-01 23:38:11 | INFO | STEP 62 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.742 GB | free=1.464 GB
|
| 1185 |
-
2026-11-01 23:38:28 | INFO | --------------------------------------------------------------------------------
|
| 1186 |
-
2026-11-01 23:38:28 | INFO | STEP 63/70 | epoch=9/10 | position=7/7 | dataset_item=4
|
| 1187 |
-
2026-11-01 23:38:28 | INFO | DATASET FILE: 00000004.pt
|
| 1188 |
-
2026-11-01 23:38:28 | INFO | LOSS: 0.93932259
|
| 1189 |
-
2026-11-01 23:38:28 | INFO | LR: 2.75362319e-05
|
| 1190 |
-
2026-11-01 23:38:28 | INFO | TIMESTEP: 0.43518484
|
| 1191 |
-
2026-11-01 23:38:28 | INFO | GLOBAL GRADIENT NORM: 0.16493047
|
| 1192 |
-
2026-11-01 23:38:28 | INFO | MAX ABSOLUTE GRADIENT: 1.10321045e-02
|
| 1193 |
-
2026-11-01 23:38:28 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1194 |
-
2026-11-01 23:38:28 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1195 |
-
2026-11-01 23:38:28 | INFO | GPU0 FORWARD: 2.460s
|
| 1196 |
-
2026-11-01 23:38:28 | INFO | GPU1 FORWARD: 2.407s
|
| 1197 |
-
2026-11-01 23:38:28 | INFO | GPU1 BACKWARD: 6.250s
|
| 1198 |
-
2026-11-01 23:38:28 | INFO | GPU0 BACKWARD: 6.262s
|
| 1199 |
-
2026-11-01 23:38:28 | INFO | UPDATE WALL TIME: 17.526s
|
| 1200 |
-
2026-11-01 23:38:28 | INFO | ELAPSED TRAINING TIME: 1102.38s
|
| 1201 |
-
2026-11-01 23:38:28 | INFO | STEP 63 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.862 GB | free=1.389 GB
|
| 1202 |
-
2026-11-01 23:38:28 | INFO | STEP 63 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.768 GB | free=1.464 GB
|
| 1203 |
-
2026-11-01 23:38:46 | INFO | --------------------------------------------------------------------------------
|
| 1204 |
-
2026-11-01 23:38:46 | INFO | STEP 64/70 | epoch=10/10 | position=1/7 | dataset_item=2
|
| 1205 |
-
2026-11-01 23:38:46 | INFO | DATASET FILE: 00000002.pt
|
| 1206 |
-
2026-11-01 23:38:46 | INFO | LOSS: 0.76127219
|
| 1207 |
-
2026-11-01 23:38:46 | INFO | LR: 2.71739130e-05
|
| 1208 |
-
2026-11-01 23:38:46 | INFO | TIMESTEP: 0.54496264
|
| 1209 |
-
2026-11-01 23:38:46 | INFO | GLOBAL GRADIENT NORM: 0.11708542
|
| 1210 |
-
2026-11-01 23:38:46 | INFO | MAX ABSOLUTE GRADIENT: 7.44628906e-03
|
| 1211 |
-
2026-11-01 23:38:46 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1212 |
-
2026-11-01 23:38:46 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1213 |
-
2026-11-01 23:38:46 | INFO | GPU0 FORWARD: 2.503s
|
| 1214 |
-
2026-11-01 23:38:46 | INFO | GPU1 FORWARD: 2.408s
|
| 1215 |
-
2026-11-01 23:38:46 | INFO | GPU1 BACKWARD: 6.299s
|
| 1216 |
-
2026-11-01 23:38:46 | INFO | GPU0 BACKWARD: 6.249s
|
| 1217 |
-
2026-11-01 23:38:46 | INFO | UPDATE WALL TIME: 17.607s
|
| 1218 |
-
2026-11-01 23:38:46 | INFO | ELAPSED TRAINING TIME: 1120.00s
|
| 1219 |
-
2026-11-01 23:38:46 | INFO | STEP 64 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.835 GB | free=1.389 GB
|
| 1220 |
-
2026-11-01 23:38:46 | INFO | STEP 64 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.742 GB | free=1.464 GB
|
| 1221 |
-
2026-11-01 23:39:03 | INFO | --------------------------------------------------------------------------------
|
| 1222 |
-
2026-11-01 23:39:03 | INFO | STEP 65/70 | epoch=10/10 | position=2/7 | dataset_item=4
|
| 1223 |
-
2026-11-01 23:39:03 | INFO | DATASET FILE: 00000004.pt
|
| 1224 |
-
2026-11-01 23:39:03 | INFO | LOSS: 1.15107083
|
| 1225 |
-
2026-11-01 23:39:03 | INFO | LR: 2.68115942e-05
|
| 1226 |
-
2026-11-01 23:39:03 | INFO | TIMESTEP: 0.33064201
|
| 1227 |
-
2026-11-01 23:39:03 | INFO | GLOBAL GRADIENT NORM: 0.26678461
|
| 1228 |
-
2026-11-01 23:39:03 | INFO | MAX ABSOLUTE GRADIENT: 1.66015625e-02
|
| 1229 |
-
2026-11-01 23:39:03 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1230 |
-
2026-11-01 23:39:03 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1231 |
-
2026-11-01 23:39:03 | INFO | GPU0 FORWARD: 2.488s
|
| 1232 |
-
2026-11-01 23:39:03 | INFO | GPU1 FORWARD: 2.366s
|
| 1233 |
-
2026-11-01 23:39:03 | INFO | GPU1 BACKWARD: 6.240s
|
| 1234 |
-
2026-11-01 23:39:03 | INFO | GPU0 BACKWARD: 6.281s
|
| 1235 |
-
2026-11-01 23:39:03 | INFO | UPDATE WALL TIME: 17.521s
|
| 1236 |
-
2026-11-01 23:39:03 | INFO | ELAPSED TRAINING TIME: 1137.53s
|
| 1237 |
-
2026-11-01 23:39:03 | INFO | STEP 65 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.862 GB | free=1.389 GB
|
| 1238 |
-
2026-11-01 23:39:03 | INFO | STEP 65 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.768 GB | free=1.464 GB
|
| 1239 |
-
2026-11-01 23:39:21 | INFO | --------------------------------------------------------------------------------
|
| 1240 |
-
2026-11-01 23:39:21 | INFO | STEP 66/70 | epoch=10/10 | position=3/7 | dataset_item=3
|
| 1241 |
-
2026-11-01 23:39:21 | INFO | DATASET FILE: 00000003.pt
|
| 1242 |
-
2026-11-01 23:39:21 | INFO | LOSS: 0.86686647
|
| 1243 |
-
2026-11-01 23:39:21 | INFO | LR: 2.64492754e-05
|
| 1244 |
-
2026-11-01 23:39:21 | INFO | TIMESTEP: 0.46732426
|
| 1245 |
-
2026-11-01 23:39:21 | INFO | GLOBAL GRADIENT NORM: 0.14438007
|
| 1246 |
-
2026-11-01 23:39:21 | INFO | MAX ABSOLUTE GRADIENT: 9.64355469e-03
|
| 1247 |
-
2026-11-01 23:39:21 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1248 |
-
2026-11-01 23:39:21 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1249 |
-
2026-11-01 23:39:21 | INFO | GPU0 FORWARD: 2.477s
|
| 1250 |
-
2026-11-01 23:39:21 | INFO | GPU1 FORWARD: 2.391s
|
| 1251 |
-
2026-11-01 23:39:21 | INFO | GPU1 BACKWARD: 6.313s
|
| 1252 |
-
2026-11-01 23:39:21 | INFO | GPU0 BACKWARD: 6.230s
|
| 1253 |
-
2026-11-01 23:39:21 | INFO | UPDATE WALL TIME: 17.562s
|
| 1254 |
-
2026-11-01 23:39:21 | INFO | ELAPSED TRAINING TIME: 1155.10s
|
| 1255 |
-
2026-11-01 23:39:21 | INFO | STEP 66 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.898 GB | free=1.389 GB
|
| 1256 |
-
2026-11-01 23:39:21 | INFO | STEP 66 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.805 GB | free=1.464 GB
|
| 1257 |
-
2026-11-01 23:39:38 | INFO | --------------------------------------------------------------------------------
|
| 1258 |
-
2026-11-01 23:39:38 | INFO | STEP 67/70 | epoch=10/10 | position=4/7 | dataset_item=1
|
| 1259 |
-
2026-11-01 23:39:38 | INFO | DATASET FILE: 00000001.pt
|
| 1260 |
-
2026-11-01 23:39:38 | INFO | LOSS: 0.68726248
|
| 1261 |
-
2026-11-01 23:39:38 | INFO | LR: 2.60869565e-05
|
| 1262 |
-
2026-11-01 23:39:38 | INFO | TIMESTEP: 0.58846909
|
| 1263 |
-
2026-11-01 23:39:38 | INFO | GLOBAL GRADIENT NORM: 0.10802477
|
| 1264 |
-
2026-11-01 23:39:38 | INFO | MAX ABSOLUTE GRADIENT: 7.20596313e-03
|
| 1265 |
-
2026-11-01 23:39:38 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1266 |
-
2026-11-01 23:39:38 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1267 |
-
2026-11-01 23:39:38 | INFO | GPU0 FORWARD: 2.420s
|
| 1268 |
-
2026-11-01 23:39:38 | INFO | GPU1 FORWARD: 2.345s
|
| 1269 |
-
2026-11-01 23:39:38 | INFO | GPU1 BACKWARD: 6.145s
|
| 1270 |
-
2026-11-01 23:39:38 | INFO | GPU0 BACKWARD: 6.197s
|
| 1271 |
-
2026-11-01 23:39:38 | INFO | UPDATE WALL TIME: 17.252s
|
| 1272 |
-
2026-11-01 23:39:38 | INFO | ELAPSED TRAINING TIME: 1172.37s
|
| 1273 |
-
2026-11-01 23:39:38 | INFO | STEP 67 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.756 GB | free=1.389 GB
|
| 1274 |
-
2026-11-01 23:39:38 | INFO | STEP 67 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.664 GB | free=1.464 GB
|
| 1275 |
-
2026-11-01 23:39:56 | INFO | --------------------------------------------------------------------------------
|
| 1276 |
-
2026-11-01 23:39:56 | INFO | STEP 68/70 | epoch=10/10 | position=5/7 | dataset_item=6
|
| 1277 |
-
2026-11-01 23:39:56 | INFO | DATASET FILE: 00000006.pt
|
| 1278 |
-
2026-11-01 23:39:56 | INFO | LOSS: 1.29654109
|
| 1279 |
-
2026-11-01 23:39:56 | INFO | LR: 2.57246377e-05
|
| 1280 |
-
2026-11-01 23:39:56 | INFO | TIMESTEP: 0.24980362
|
| 1281 |
-
2026-11-01 23:39:56 | INFO | GLOBAL GRADIENT NORM: 0.76038267
|
| 1282 |
-
2026-11-01 23:39:56 | INFO | MAX ABSOLUTE GRADIENT: 2.78167725e-02
|
| 1283 |
-
2026-11-01 23:39:56 | INFO | GRADIENT CLIP COEFFICIENT: 0.65756278
|
| 1284 |
-
2026-11-01 23:39:56 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1285 |
-
2026-11-01 23:39:56 | INFO | GPU0 FORWARD: 2.514s
|
| 1286 |
-
2026-11-01 23:39:56 | INFO | GPU1 FORWARD: 2.400s
|
| 1287 |
-
2026-11-01 23:39:56 | INFO | GPU1 BACKWARD: 6.262s
|
| 1288 |
-
2026-11-01 23:39:56 | INFO | GPU0 BACKWARD: 6.344s
|
| 1289 |
-
2026-11-01 23:39:56 | INFO | UPDATE WALL TIME: 17.666s
|
| 1290 |
-
2026-11-01 23:39:56 | INFO | ELAPSED TRAINING TIME: 1190.04s
|
| 1291 |
-
2026-11-01 23:39:56 | INFO | STEP 68 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.882 GB | free=1.389 GB
|
| 1292 |
-
2026-11-01 23:39:56 | INFO | STEP 68 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.788 GB | free=1.464 GB
|
| 1293 |
-
2026-11-01 23:40:13 | INFO | --------------------------------------------------------------------------------
|
| 1294 |
-
2026-11-01 23:40:13 | INFO | STEP 69/70 | epoch=10/10 | position=6/7 | dataset_item=0
|
| 1295 |
-
2026-11-01 23:40:13 | INFO | DATASET FILE: 00000000.pt
|
| 1296 |
-
2026-11-01 23:40:13 | INFO | LOSS: 0.49238670
|
| 1297 |
-
2026-11-01 23:40:13 | INFO | LR: 2.53623188e-05
|
| 1298 |
-
2026-11-01 23:40:13 | INFO | TIMESTEP: 0.81050289
|
| 1299 |
-
2026-11-01 23:40:13 | INFO | GLOBAL GRADIENT NORM: 0.12303477
|
| 1300 |
-
2026-11-01 23:40:13 | INFO | MAX ABSOLUTE GRADIENT: 3.88908386e-03
|
| 1301 |
-
2026-11-01 23:40:13 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1302 |
-
2026-11-01 23:40:13 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1303 |
-
2026-11-01 23:40:13 | INFO | GPU0 FORWARD: 2.473s
|
| 1304 |
-
2026-11-01 23:40:13 | INFO | GPU1 FORWARD: 2.399s
|
| 1305 |
-
2026-11-01 23:40:13 | INFO | GPU1 BACKWARD: 6.264s
|
| 1306 |
-
2026-11-01 23:40:13 | INFO | GPU0 BACKWARD: 6.199s
|
| 1307 |
-
2026-11-01 23:40:13 | INFO | UPDATE WALL TIME: 17.481s
|
| 1308 |
-
2026-11-01 23:40:13 | INFO | ELAPSED TRAINING TIME: 1207.54s
|
| 1309 |
-
2026-11-01 23:40:13 | INFO | STEP 69 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.821 GB | free=1.389 GB
|
| 1310 |
-
2026-11-01 23:40:13 | INFO | STEP 69 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.728 GB | free=1.464 GB
|
| 1311 |
-
2026-11-01 23:40:31 | INFO | --------------------------------------------------------------------------------
|
| 1312 |
-
2026-11-01 23:40:31 | INFO | STEP 70/70 | epoch=10/10 | position=7/7 | dataset_item=5
|
| 1313 |
-
2026-11-01 23:40:31 | INFO | DATASET FILE: 00000005.pt
|
| 1314 |
-
2026-11-01 23:40:31 | INFO | LOSS: 0.66494811
|
| 1315 |
-
2026-11-01 23:40:31 | INFO | LR: 2.50000000e-05
|
| 1316 |
-
2026-11-01 23:40:31 | INFO | TIMESTEP: 0.57378495
|
| 1317 |
-
2026-11-01 23:40:31 | INFO | GLOBAL GRADIENT NORM: 0.16218607
|
| 1318 |
-
2026-11-01 23:40:31 | INFO | MAX ABSOLUTE GRADIENT: 6.96182251e-03
|
| 1319 |
-
2026-11-01 23:40:31 | INFO | GRADIENT CLIP COEFFICIENT: 1.00000000
|
| 1320 |
-
2026-11-01 23:40:31 | INFO | MISSING GRADIENT TENSORS: 0
|
| 1321 |
-
2026-11-01 23:40:31 | INFO | GPU0 FORWARD: 2.531s
|
| 1322 |
-
2026-11-01 23:40:31 | INFO | GPU1 FORWARD: 2.469s
|
| 1323 |
-
2026-11-01 23:40:31 | INFO | GPU1 BACKWARD: 6.403s
|
| 1324 |
-
2026-11-01 23:40:31 | INFO | GPU0 BACKWARD: 6.281s
|
| 1325 |
-
2026-11-01 23:40:31 | INFO | UPDATE WALL TIME: 17.826s
|
| 1326 |
-
2026-11-01 23:40:31 | INFO | ELAPSED TRAINING TIME: 1225.37s
|
| 1327 |
-
2026-11-01 23:40:31 | INFO | STEP 70 | GPU0 | allocated=5.070 GB | reserved=13.035 GB | peak=12.935 GB | free=1.389 GB
|
| 1328 |
-
2026-11-01 23:40:31 | INFO | STEP 70 | GPU1 | allocated=4.984 GB | reserved=12.961 GB | peak=12.842 GB | free=1.464 GB
|
| 1329 |
-
2026-11-01 23:40:31 | INFO | ================================================================================
|
| 1330 |
-
2026-11-01 23:40:31 | INFO | CHECKPOINT TRIGGERED AT OPTIMIZER STEP 70
|
| 1331 |
-
2026-11-01 23:40:35 | INFO | CHECKPOINT SUCCESS: kromoss_lora_step_000070.safetensors
|
| 1332 |
-
2026-11-01 23:40:35 | INFO | CHECKPOINT SIZE: 70.93 MB
|
| 1333 |
-
2026-11-01 23:40:35 | INFO | ================================================================================
|
| 1334 |
-
2026-11-01 23:40:35 | INFO | ================================================================================
|
| 1335 |
-
2026-11-01 23:40:35 | INFO | ALL 70 OPTIMIZER UPDATES COMPLETED SUCCESSFULLY
|
| 1336 |
-
2026-11-01 23:40:35 | INFO | ================================================================================
|
| 1337 |
-
2026-11-01 23:40:35 | INFO | UPDATING CONTINUATION LORA
|
| 1338 |
-
2026-11-01 23:40:36 | INFO | CONTINUATION LORA UPDATED: codeShare/kromoss-lora-exports/continue.safetensors
|
| 1339 |
-
2026-11-01 23:40:36 | INFO | CONTINUATION URL: https://huggingface.co/codeShare/kromoss-lora-exports/commit/6a73ffbe4417a5fcdeafd972bf800b5225ba38cf
|
| 1340 |
-
2026-11-01 23:40:36 | INFO | ================================================================================
|
| 1341 |
-
2026-11-01 23:40:36 | INFO | TRAINING FINISHED SUCCESSFULLY
|
| 1342 |
-
2026-11-01 23:40:36 | INFO | ================================================================================
|
| 1343 |
-
2026-11-01 23:40:36 | INFO | Optimizer updates: 70
|
| 1344 |
-
2026-11-01 23:40:36 | INFO | Dataset items: 7
|
| 1345 |
-
2026-11-01 23:40:36 | INFO | Presentations per item: 10
|
| 1346 |
-
2026-11-01 23:40:36 | INFO | Checkpoint steps: [14, 35, 70]
|
| 1347 |
-
2026-11-01 23:40:36 | INFO | Initial global learning rate: 5.00000000e-05
|
| 1348 |
-
2026-11-01 23:40:36 | INFO | Final global learning rate: 2.50000000e-05
|
| 1349 |
-
2026-11-01 23:40:36 | INFO | AdamW state persisted across all seven dataset items.
|
| 1350 |
-
2026-11-01 23:40:36 | INFO | Learning rate was smoothly scheduled across all 70 steps.
|
| 1351 |
-
2026-11-01 23:40:36 | INFO | Dataset presentation order was deterministically shuffled.
|
| 1352 |
-
2026-11-01 23:40:36 | INFO | Final export: /kaggle/working/kromoss_lora_out/comfyui/kromoss_lora_step_000070.safetensors
|
| 1353 |
-
2026-11-01 23:40:36 | INFO | Continuation file: continue.safetensors
|
| 1354 |
-
2026-11-01 23:40:36 | INFO | HF repository: codeShare/kromoss-lora-exports
|
| 1355 |
-
2026-11-01 23:40:36 | INFO | Total elapsed time: 1230.10s
|
| 1356 |
-
2026-11-01 23:40:36 | INFO | ================================================================================
|
|
|
|
| 1 |
+
2026-11-01 23:41:22 | INFO | ================================================================================
|
| 2 |
+
2026-11-01 23:41:22 | INFO | KROMOSS DUAL-T4 TWO-STAGE TRAINING
|
| 3 |
+
2026-11-01 23:41:22 | INFO | ================================================================================
|
| 4 |
+
2026-11-01 23:41:22 | INFO | PyTorch version: 2.11.0+cu128
|
| 5 |
+
2026-11-01 23:41:22 | INFO | CUDA version: 12.8
|
| 6 |
+
2026-11-01 23:41:22 | INFO | Dataset size: 7
|
| 7 |
+
2026-11-01 23:41:22 | INFO | Presentations per image: 10
|
| 8 |
+
2026-11-01 23:41:22 | INFO | Total optimizer updates: 70
|
| 9 |
+
2026-11-01 23:41:22 | INFO | Checkpoint steps: [14, 35, 70]
|
| 10 |
+
2026-11-01 23:41:22 | INFO | Initial global learning rate: 5.00000000e-05
|
| 11 |
+
2026-11-01 23:41:22 | INFO | Final global learning rate: 2.50000000e-05
|
| 12 |
+
2026-11-01 23:41:22 | INFO | Weight decay: 0.01
|
| 13 |
+
2026-11-01 23:41:22 | INFO | Gradient clipping: 0.5
|
| 14 |
+
2026-11-01 23:41:22 | INFO | Loss scale: 128.0
|
| 15 |
+
2026-11-01 23:41:22 | INFO | LoRA rank: 16
|
| 16 |
+
2026-11-01 23:41:22 | INFO | LoRA alpha: 16
|
| 17 |
+
2026-11-01 23:41:22 | INFO | Trainable parameters: 37,158,912
|
| 18 |
+
2026-11-01 23:41:22 | INFO | GPU0 LoRA parameters: 17,694,720
|
| 19 |
+
2026-11-01 23:41:22 | INFO | GPU1 LoRA parameters: 19,464,192
|
| 20 |
+
2026-11-01 23:41:22 | INFO | Continuation loaded: True
|
| 21 |
+
2026-11-01 23:41:22 | INFO | Continuation loading enabled: True
|
| 22 |
+
2026-11-01 23:41:22 | INFO | HF repository: codeShare/kromoss-lora-exports
|
| 23 |
+
2026-11-01 23:41:22 | INFO | HF log destination: training_logs/kromoss_training_log.txt
|
| 24 |
+
2026-11-01 23:41:22 | INFO | GPU0: Tesla T4 | 14.562 GB
|
| 25 |
+
2026-11-01 23:41:22 | INFO | GPU1: Tesla T4 | 14.562 GB
|
| 26 |
+
2026-11-01 23:41:22 | INFO | DATASET ITEM 0: 00000000.pt | presentations=10
|
| 27 |
+
2026-11-01 23:41:22 | INFO | DATASET ITEM 1: 00000001.pt | presentations=10
|
| 28 |
+
2026-11-01 23:41:22 | INFO | DATASET ITEM 2: 00000002.pt | presentations=10
|
| 29 |
+
2026-11-01 23:41:22 | INFO | DATASET ITEM 3: 00000003.pt | presentations=10
|
| 30 |
+
2026-11-01 23:41:22 | INFO | DATASET ITEM 4: 00000004.pt | presentations=10
|
| 31 |
+
2026-11-01 23:41:22 | INFO | DATASET ITEM 5: 00000005.pt | presentations=10
|
| 32 |
+
2026-11-01 23:41:22 | INFO | DATASET ITEM 6: 00000006.pt | presentations=10
|
| 33 |
+
2026-11-01 23:41:22 | INFO | --------------------------------------------------------------------------------
|
| 34 |
+
2026-11-01 23:41:22 | INFO | DETERMINISTIC SHUFFLED SAMPLE PLAN
|
| 35 |
+
2026-11-01 23:41:22 | INFO | EPOCH 01: 1 3 4 2 6 0 5
|
| 36 |
+
2026-11-01 23:41:22 | INFO | EPOCH 02: 3 6 2 4 0 5 1
|
| 37 |
+
2026-11-01 23:41:22 | INFO | EPOCH 03: 3 2 4 1 5 6 0
|
| 38 |
+
2026-11-01 23:41:22 | INFO | EPOCH 04: 2 5 0 3 6 1 4
|
| 39 |
+
2026-11-01 23:41:22 | INFO | EPOCH 05: 6 3 5 1 0 2 4
|
| 40 |
+
2026-11-01 23:41:22 | INFO | EPOCH 06: 5 0 3 4 1 6 2
|
| 41 |
+
2026-11-01 23:41:22 | INFO | EPOCH 07: 4 5 1 2 6 3 0
|
| 42 |
+
2026-11-01 23:41:22 | INFO | EPOCH 08: 2 4 1 5 3 0 6
|
| 43 |
+
2026-11-01 23:41:22 | INFO | EPOCH 09: 1 0 3 5 6 2 4
|
| 44 |
+
2026-11-01 23:41:22 | INFO | EPOCH 10: 2 4 3 1 6 0 5
|
| 45 |
+
2026-11-01 23:41:22 | INFO | INITIAL MODEL STATE | GPU0 | allocated=4.856 GB | reserved=4.873 GB | peak=4.857 GB | free=9.587 GB
|
| 46 |
+
2026-11-01 23:41:22 | INFO | INITIAL MODEL STATE | GPU1 | allocated=4.749 GB | reserved=4.764 GB | peak=4.750 GB | free=9.696 GB
|
| 47 |
+
2026-11-01 23:41:22 | INFO | ================================================================================
|
| 48 |
+
2026-11-01 23:41:22 | INFO | STARTING TRAINING
|
| 49 |
+
2026-11-01 23:41:22 | INFO | ================================================================================
|
| 50 |
+
2026-11-01 23:41:22 | INFO | Schedule: ten shuffled seven-image epochs, one optimizer update per image presentation.
|
| 51 |
+
2026-11-01 23:41:22 | INFO | Global LR schedule: 5.00000000e-05 -> 2.50000000e-05 across all 70 optimizer steps.
|
| 52 |
+
2026-11-01 23:41:22 | INFO | AdamW optimizer state is retained across all 70 updates.
|
| 53 |
+
2026-11-01 23:41:22 | INFO | Learning rate does NOT reset when the dataset image changes.
|
| 54 |
+
2026-11-01 23:41:22 | INFO | Gradient clipping threshold: 0.5
|
| 55 |
+
2026-11-01 23:41:22 | INFO | Noise is generated in FP32 and cast to FP16.
|
| 56 |
+
2026-11-01 23:41:22 | INFO | Timestep is logged for every optimizer update.
|
| 57 |
+
2026-11-01 23:41:22 | INFO | Continuation loading enabled: True
|
| 58 |
+
2026-11-01 23:41:22 | INFO | Continuation actually loaded: True
|
| 59 |
+
2026-11-01 23:41:22 | ERROR | ================================================================================
|
| 60 |
+
2026-11-01 23:41:22 | ERROR | TRAINING FAILED
|
| 61 |
+
2026-11-01 23:41:22 | ERROR | Traceback (most recent call last):
|
| 62 |
+
File "/tmp/ipykernel_841/4050970492.py", line 1153, in <cell line: 0>
|
| 63 |
+
result = train_one_image(
|
| 64 |
+
dataset_index=dataset_index,
|
| 65 |
+
step=step
|
| 66 |
+
)
|
| 67 |
+
File "/tmp/ipykernel_841/4050970492.py", line 809, in train_one_image
|
| 68 |
+
for group in optimizer.param_groups:
|
| 69 |
+
^^^^^^^^^
|
| 70 |
+
NameError: name 'optimizer' is not defined. Did you mean: 'optimizer0'?
|
| 71 |
+
|
| 72 |
+
2026-11-01 23:41:22 | INFO | ERROR STATE | GPU0 | allocated=4.856 GB | reserved=4.873 GB | peak=4.856 GB | free=9.587 GB
|
| 73 |
+
2026-11-01 23:41:22 | INFO | ERROR STATE | GPU1 | allocated=4.749 GB | reserved=4.764 GB | peak=4.749 GB | free=9.696 GB
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|