diff --git "a/jy/log.txt" "b/jy/log.txt" --- "a/jy/log.txt" +++ "b/jy/log.txt" @@ -343,4 +343,21 @@ Unloading assistant lora Generating Images: 100%|##########| 3/3 [00:22<00:00, 7.51s/it] Generating Images: 100%|##########| 3/3 [00:22<00:00, 7.51s/it] Loading assistant lora - jy: 75%|#######5 | 2250/3000 [1:05:12<20:19, 1.63s/it, lr: 1.0e-04 loss: 1.705e-01] jy: 75%|#######5 | 2250/3000 [1:05:12<20:19, 1.63s/it, lr: 1.0e-04 loss: 1.705e-01] jy: 75%|#######5 | 2251/3000 [1:05:12<16:00, 1.28s/it, lr: 1.0e-04 loss: 1.705e-01] jy: 75%|#######5 | 2251/3000 [1:05:12<16:00, 1.28s/it, lr: 1.0e-04 loss: 1.705e-01] jy: 75%|#######5 | 2251/3000 [1:05:14<16:00, 1.28s/it, lr: 1.0e-04 loss: 5.153e-01] jy: 75%|#######5 | 2251/3000 [1:05:14<16:00, 1.28s/it, lr: 1.0e-04 loss: 5.153e-01] jy: 75%|#######5 | 2252/3000 [1:05:14<20:06, 1.61s/it, lr: 1.0e-04 loss: 5.153e-01] jy: 75%|#######5 | 2252/3000 [1:05:14<20:06, 1.61s/it, lr: 1.0e-04 loss: 5.153e-01] jy: 75%|#######5 | 2252/3000 [1:05:15<20:06, 1.61s/it, lr: 1.0e-04 loss: 2.807e-01] jy: 75%|#######5 | 2252/3000 [1:05:15<20:06, 1.61s/it, lr: 1.0e-04 loss: 2.807e-01] jy: 75%|#######5 | 2253/3000 [1:05:15<17:37, 1.42s/it, lr: 1.0e-04 loss: 2.807e-01] jy: 75%|#######5 | 2253/3000 [1:05:15<17:37, 1.42s/it, lr: 1.0e-04 loss: 2.807e-01] jy: 75%|#######5 | 2253/3000 [1:05:17<17:37, 1.42s/it, lr: 1.0e-04 loss: 1.068e-01] jy: 75%|#######5 | 2253/3000 [1:05:17<17:37, 1.42s/it, lr: 1.0e-04 loss: 1.068e-01] jy: 75%|#######5 | 2254/3000 [1:05:17<18:18, 1.47s/it, lr: 1.0e-04 loss: 1.068e-01] jy: 75%|#######5 | 2254/3000 [1:05:17<18:18, 1.47s/it, lr: 1.0e-04 loss: 1.068e-01] jy: 75%|#######5 | 2254/3000 [1:05:20<18:18, 1.47s/it, lr: 1.0e-04 loss: 6.404e-02] jy: 75%|#######5 | 2254/3000 [1:05:20<18:18, 1.47s/it, lr: 1.0e-04 loss: 6.404e-02] jy: 75%|#######5 | 2255/3000 [1:05:20<22:17, 1.80s/it, lr: 1.0e-04 loss: 6.404e-02] jy: 75%|#######5 | 2255/3000 [1:05:20<22:17, 1.80s/it, lr: 1.0e-04 loss: 6.404e-02] jy: 75%|#######5 | 2255/3000 [1:05:21<22:17, 1.80s/it, lr: 1.0e-04 loss: 2.320e-01] jy: 75%|#######5 | 2255/3000 [1:05:21<22:17, 1.80s/it, lr: 1.0e-04 loss: 2.320e-01] jy: 75%|#######5 | 2256/3000 [1:05:21<21:39, 1.75s/it, lr: 1.0e-04 loss: 2.320e-01] jy: 75%|#######5 | 2256/3000 [1:05:21<21:39, 1.75s/it, lr: 1.0e-04 loss: 2.320e-01] jy: 75%|#######5 | 2256/3000 [1:05:24<21:39, 1.75s/it, lr: 1.0e-04 loss: 4.885e-01] jy: 75%|#######5 | 2256/3000 [1:05:24<21:39, 1.75s/it, lr: 1.0e-04 loss: 4.885e-01] jy: 75%|#######5 | 2257/3000 [1:05:24<24:46, 2.00s/it, lr: 1.0e-04 loss: 4.885e-01] jy: 75%|#######5 | 2257/3000 [1:05:24<24:46, 2.00s/it, lr: 1.0e-04 loss: 4.885e-01] jy: 75%|#######5 | 2257/3000 [1:05:26<24:46, 2.00s/it, lr: 1.0e-04 loss: 2.842e-02] jy: 75%|#######5 | 2257/3000 [1:05:26<24:46, 2.00s/it, lr: 1.0e-04 loss: 2.842e-02] jy: 75%|#######5 | 2258/3000 [1:05:26<27:01, 2.19s/it, lr: 1.0e-04 loss: 2.842e-02] jy: 75%|#######5 | 2258/3000 [1:05:26<27:01, 2.19s/it, lr: 1.0e-04 loss: 2.842e-02] jy: 75%|#######5 | 2258/3000 [1:05:29<27:01, 2.19s/it, lr: 1.0e-04 loss: 2.209e-01] jy: 75%|#######5 | 2258/3000 [1:05:29<27:01, 2.19s/it, lr: 1.0e-04 loss: 2.209e-01] jy: 75%|#######5 | 2259/3000 [1:05:29<28:36, 2.32s/it, lr: 1.0e-04 loss: 2.209e-01] jy: 75%|#######5 | 2259/3000 [1:05:29<28:36, 2.32s/it, lr: 1.0e-04 loss: 2.209e-01] jy: 75%|#######5 | 2259/3000 [1:05:31<28:36, 2.32s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 75%|#######5 | 2259/3000 [1:05:31<28:36, 2.32s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 75%|#######5 | 2260/3000 [1:05:31<28:34, 2.32s/it, lr: 1.0e-04 loss: 4.859e-01] jy: 75%|#######5 | 2260/3000 [1:05:31<28:34, 2.32s/it, lr: 1.0e-04 loss: 4.859e-01] jy: 75%|#######5 | 2261/3000 [1:05:31<17:47, 1.44s/it, lr: 1.0e-04 loss: 4.859e-01] jy: 75%|#######5 | 2261/3000 [1:05:31<17:47, 1.44s/it, lr: 1.0e-04 loss: 4.859e-01] jy: 75%|#######5 | 2261/3000 [1:05:33<17:47, 1.44s/it, lr: 1.0e-04 loss: 4.190e-01] jy: 75%|#######5 | 2261/3000 [1:05:33<17:47, 1.44s/it, lr: 1.0e-04 loss: 4.190e-01] jy: 75%|#######5 | 2262/3000 [1:05:33<18:18, 1.49s/it, lr: 1.0e-04 loss: 4.190e-01] jy: 75%|#######5 | 2262/3000 [1:05:33<18:18, 1.49s/it, lr: 1.0e-04 loss: 4.190e-01] jy: 75%|#######5 | 2262/3000 [1:05:34<18:18, 1.49s/it, lr: 1.0e-04 loss: 3.349e-01] jy: 75%|#######5 | 2262/3000 [1:05:34<18:18, 1.49s/it, lr: 1.0e-04 loss: 3.349e-01] jy: 75%|#######5 | 2263/3000 [1:05:34<17:00, 1.38s/it, lr: 1.0e-04 loss: 3.349e-01] jy: 75%|#######5 | 2263/3000 [1:05:34<17:00, 1.38s/it, lr: 1.0e-04 loss: 3.349e-01] jy: 75%|#######5 | 2263/3000 [1:05:37<17:00, 1.38s/it, lr: 1.0e-04 loss: 5.037e-01] jy: 75%|#######5 | 2263/3000 [1:05:37<17:00, 1.38s/it, lr: 1.0e-04 loss: 5.037e-01] jy: 75%|#######5 | 2264/3000 [1:05:37<21:07, 1.72s/it, lr: 1.0e-04 loss: 5.037e-01] jy: 75%|#######5 | 2264/3000 [1:05:37<21:07, 1.72s/it, lr: 1.0e-04 loss: 5.037e-01] jy: 75%|#######5 | 2264/3000 [1:05:39<21:07, 1.72s/it, lr: 1.0e-04 loss: 3.929e-01] jy: 75%|#######5 | 2264/3000 [1:05:39<21:07, 1.72s/it, lr: 1.0e-04 loss: 3.929e-01] jy: 76%|#######5 | 2265/3000 [1:05:39<24:11, 1.98s/it, lr: 1.0e-04 loss: 3.929e-01] jy: 76%|#######5 | 2265/3000 [1:05:39<24:11, 1.98s/it, lr: 1.0e-04 loss: 3.929e-01] jy: 76%|#######5 | 2265/3000 [1:05:41<24:11, 1.98s/it, lr: 1.0e-04 loss: 3.969e-01] jy: 76%|#######5 | 2265/3000 [1:05:41<24:11, 1.98s/it, lr: 1.0e-04 loss: 3.969e-01] jy: 76%|#######5 | 2266/3000 [1:05:41<22:50, 1.87s/it, lr: 1.0e-04 loss: 3.969e-01] jy: 76%|#######5 | 2266/3000 [1:05:41<22:50, 1.87s/it, lr: 1.0e-04 loss: 3.969e-01] jy: 76%|#######5 | 2266/3000 [1:05:42<22:50, 1.87s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 76%|#######5 | 2266/3000 [1:05:42<22:50, 1.87s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 76%|#######5 | 2267/3000 [1:05:42<19:17, 1.58s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 76%|#######5 | 2267/3000 [1:05:42<19:17, 1.58s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 76%|#######5 | 2267/3000 [1:05:43<19:17, 1.58s/it, lr: 1.0e-04 loss: 2.980e-01] jy: 76%|#######5 | 2267/3000 [1:05:43<19:17, 1.58s/it, lr: 1.0e-04 loss: 2.980e-01] jy: 76%|#######5 | 2268/3000 [1:05:43<16:47, 1.38s/it, lr: 1.0e-04 loss: 2.980e-01] jy: 76%|#######5 | 2268/3000 [1:05:43<16:47, 1.38s/it, lr: 1.0e-04 loss: 2.980e-01] jy: 76%|#######5 | 2268/3000 [1:05:44<16:47, 1.38s/it, lr: 1.0e-04 loss: 5.504e-01] jy: 76%|#######5 | 2268/3000 [1:05:44<16:47, 1.38s/it, lr: 1.0e-04 loss: 5.504e-01] jy: 76%|#######5 | 2269/3000 [1:05:44<17:48, 1.46s/it, lr: 1.0e-04 loss: 5.504e-01] jy: 76%|#######5 | 2269/3000 [1:05:44<17:48, 1.46s/it, lr: 1.0e-04 loss: 5.504e-01] jy: 76%|#######5 | 2269/3000 [1:05:45<17:48, 1.46s/it, lr: 1.0e-04 loss: 4.291e-02] jy: 76%|#######5 | 2269/3000 [1:05:45<17:48, 1.46s/it, lr: 1.0e-04 loss: 4.291e-02] jy: 76%|#######5 | 2270/3000 [1:05:46<17:46, 1.46s/it, lr: 1.0e-04 loss: 9.681e-02] jy: 76%|#######5 | 2270/3000 [1:05:46<17:46, 1.46s/it, lr: 1.0e-04 loss: 9.681e-02] jy: 76%|#######5 | 2271/3000 [1:05:46<12:01, 1.01it/s, lr: 1.0e-04 loss: 9.681e-02] jy: 76%|#######5 | 2271/3000 [1:05:46<12:01, 1.01it/s, lr: 1.0e-04 loss: 9.681e-02] jy: 76%|#######5 | 2271/3000 [1:05:48<12:01, 1.01it/s, lr: 1.0e-04 loss: 3.683e-01] jy: 76%|#######5 | 2271/3000 [1:05:48<12:01, 1.01it/s, lr: 1.0e-04 loss: 3.683e-01] jy: 76%|#######5 | 2272/3000 [1:05:48<13:30, 1.11s/it, lr: 1.0e-04 loss: 3.683e-01] jy: 76%|#######5 | 2272/3000 [1:05:48<13:30, 1.11s/it, lr: 1.0e-04 loss: 3.683e-01] jy: 76%|#######5 | 2272/3000 [1:05:49<13:30, 1.11s/it, lr: 1.0e-04 loss: 9.999e-02] jy: 76%|#######5 | 2272/3000 [1:05:49<13:30, 1.11s/it, lr: 1.0e-04 loss: 9.999e-02] jy: 76%|#######5 | 2273/3000 [1:05:49<12:41, 1.05s/it, lr: 1.0e-04 loss: 9.999e-02] jy: 76%|#######5 | 2273/3000 [1:05:49<12:41, 1.05s/it, lr: 1.0e-04 loss: 9.999e-02] jy: 76%|#######5 | 2273/3000 [1:05:49<12:41, 1.05s/it, lr: 1.0e-04 loss: 2.190e-01] jy: 76%|#######5 | 2273/3000 [1:05:49<12:41, 1.05s/it, lr: 1.0e-04 loss: 2.190e-01] jy: 76%|#######5 | 2274/3000 [1:05:49<12:02, 1.01it/s, lr: 1.0e-04 loss: 2.190e-01] jy: 76%|#######5 | 2274/3000 [1:05:49<12:02, 1.01it/s, lr: 1.0e-04 loss: 2.190e-01] jy: 76%|#######5 | 2274/3000 [1:05:51<12:02, 1.01it/s, lr: 1.0e-04 loss: 3.513e-01] jy: 76%|#######5 | 2274/3000 [1:05:51<12:02, 1.01it/s, lr: 1.0e-04 loss: 3.513e-01] jy: 76%|#######5 | 2275/3000 [1:05:51<14:09, 1.17s/it, lr: 1.0e-04 loss: 3.513e-01] jy: 76%|#######5 | 2275/3000 [1:05:51<14:09, 1.17s/it, lr: 1.0e-04 loss: 3.513e-01] jy: 76%|#######5 | 2275/3000 [1:05:52<14:09, 1.17s/it, lr: 1.0e-04 loss: 3.321e-01] jy: 76%|#######5 | 2275/3000 [1:05:52<14:09, 1.17s/it, lr: 1.0e-04 loss: 3.321e-01] jy: 76%|#######5 | 2276/3000 [1:05:52<13:05, 1.09s/it, lr: 1.0e-04 loss: 3.321e-01] jy: 76%|#######5 | 2276/3000 [1:05:52<13:05, 1.09s/it, lr: 1.0e-04 loss: 3.321e-01] jy: 76%|#######5 | 2276/3000 [1:05:53<13:05, 1.09s/it, lr: 1.0e-04 loss: 6.727e-01] jy: 76%|#######5 | 2276/3000 [1:05:53<13:05, 1.09s/it, lr: 1.0e-04 loss: 6.727e-01] jy: 76%|#######5 | 2277/3000 [1:05:53<12:24, 1.03s/it, lr: 1.0e-04 loss: 6.727e-01] jy: 76%|#######5 | 2277/3000 [1:05:53<12:24, 1.03s/it, lr: 1.0e-04 loss: 6.727e-01] jy: 76%|#######5 | 2277/3000 [1:05:55<12:24, 1.03s/it, lr: 1.0e-04 loss: 3.293e-01] jy: 76%|#######5 | 2277/3000 [1:05:55<12:24, 1.03s/it, lr: 1.0e-04 loss: 3.293e-01] jy: 76%|#######5 | 2278/3000 [1:05:55<15:18, 1.27s/it, lr: 1.0e-04 loss: 3.293e-01] jy: 76%|#######5 | 2278/3000 [1:05:55<15:18, 1.27s/it, lr: 1.0e-04 loss: 3.293e-01] jy: 76%|#######5 | 2278/3000 [1:05:58<15:18, 1.27s/it, lr: 1.0e-04 loss: 3.790e-01] jy: 76%|#######5 | 2278/3000 [1:05:58<15:18, 1.27s/it, lr: 1.0e-04 loss: 3.790e-01] jy: 76%|#######5 | 2279/3000 [1:05:58<20:04, 1.67s/it, lr: 1.0e-04 loss: 3.790e-01] jy: 76%|#######5 | 2279/3000 [1:05:58<20:04, 1.67s/it, lr: 1.0e-04 loss: 3.790e-01] jy: 76%|#######5 | 2279/3000 [1:06:00<20:04, 1.67s/it, lr: 1.0e-04 loss: 4.740e-01] jy: 76%|#######5 | 2279/3000 [1:06:00<20:04, 1.67s/it, lr: 1.0e-04 loss: 4.740e-01] jy: 76%|#######6 | 2280/3000 [1:06:01<20:03, 1.67s/it, lr: 1.0e-04 loss: 3.486e-01] jy: 76%|#######6 | 2280/3000 [1:06:01<20:03, 1.67s/it, lr: 1.0e-04 loss: 3.486e-01] jy: 76%|#######6 | 2281/3000 [1:06:01<13:14, 1.11s/it, lr: 1.0e-04 loss: 3.486e-01] jy: 76%|#######6 | 2281/3000 [1:06:01<13:14, 1.11s/it, lr: 1.0e-04 loss: 3.486e-01] jy: 76%|#######6 | 2281/3000 [1:06:04<13:14, 1.11s/it, lr: 1.0e-04 loss: 1.271e-01] jy: 76%|#######6 | 2281/3000 [1:06:04<13:14, 1.11s/it, lr: 1.0e-04 loss: 1.271e-01] jy: 76%|#######6 | 2282/3000 [1:06:04<18:15, 1.53s/it, lr: 1.0e-04 loss: 1.271e-01] jy: 76%|#######6 | 2282/3000 [1:06:04<18:15, 1.53s/it, lr: 1.0e-04 loss: 1.271e-01] jy: 76%|#######6 | 2282/3000 [1:06:05<18:15, 1.53s/it, lr: 1.0e-04 loss: 2.238e-01] jy: 76%|#######6 | 2282/3000 [1:06:05<18:15, 1.53s/it, lr: 1.0e-04 loss: 2.238e-01] jy: 76%|#######6 | 2283/3000 [1:06:05<16:10, 1.35s/it, lr: 1.0e-04 loss: 2.238e-01] jy: 76%|#######6 | 2283/3000 [1:06:05<16:10, 1.35s/it, lr: 1.0e-04 loss: 2.238e-01] jy: 76%|#######6 | 2283/3000 [1:06:06<16:10, 1.35s/it, lr: 1.0e-04 loss: 4.430e-01] jy: 76%|#######6 | 2283/3000 [1:06:06<16:10, 1.35s/it, lr: 1.0e-04 loss: 4.430e-01] jy: 76%|#######6 | 2284/3000 [1:06:06<14:34, 1.22s/it, lr: 1.0e-04 loss: 4.430e-01] jy: 76%|#######6 | 2284/3000 [1:06:06<14:34, 1.22s/it, lr: 1.0e-04 loss: 4.430e-01] jy: 76%|#######6 | 2284/3000 [1:06:07<14:34, 1.22s/it, lr: 1.0e-04 loss: 2.886e-02] jy: 76%|#######6 | 2284/3000 [1:06:07<14:34, 1.22s/it, lr: 1.0e-04 loss: 2.886e-02] jy: 76%|#######6 | 2285/3000 [1:06:07<15:34, 1.31s/it, lr: 1.0e-04 loss: 2.886e-02] jy: 76%|#######6 | 2285/3000 [1:06:07<15:34, 1.31s/it, lr: 1.0e-04 loss: 2.886e-02] jy: 76%|#######6 | 2285/3000 [1:06:08<15:34, 1.31s/it, lr: 1.0e-04 loss: 1.931e-01] jy: 76%|#######6 | 2285/3000 [1:06:08<15:34, 1.31s/it, lr: 1.0e-04 loss: 1.931e-01] jy: 76%|#######6 | 2286/3000 [1:06:08<14:05, 1.18s/it, lr: 1.0e-04 loss: 1.931e-01] jy: 76%|#######6 | 2286/3000 [1:06:08<14:05, 1.18s/it, lr: 1.0e-04 loss: 1.931e-01] jy: 76%|#######6 | 2286/3000 [1:06:11<14:05, 1.18s/it, lr: 1.0e-04 loss: 6.574e-02] jy: 76%|#######6 | 2286/3000 [1:06:11<14:05, 1.18s/it, lr: 1.0e-04 loss: 6.574e-02] jy: 76%|#######6 | 2287/3000 [1:06:11<19:39, 1.65s/it, lr: 1.0e-04 loss: 6.574e-02] jy: 76%|#######6 | 2287/3000 [1:06:11<19:39, 1.65s/it, lr: 1.0e-04 loss: 6.574e-02] jy: 76%|#######6 | 2287/3000 [1:06:12<19:39, 1.65s/it, lr: 1.0e-04 loss: 2.645e-02] jy: 76%|#######6 | 2287/3000 [1:06:12<19:39, 1.65s/it, lr: 1.0e-04 loss: 2.645e-02] jy: 76%|#######6 | 2288/3000 [1:06:12<16:56, 1.43s/it, lr: 1.0e-04 loss: 2.645e-02] jy: 76%|#######6 | 2288/3000 [1:06:12<16:56, 1.43s/it, lr: 1.0e-04 loss: 2.645e-02] jy: 76%|#######6 | 2288/3000 [1:06:13<16:56, 1.43s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 76%|#######6 | 2288/3000 [1:06:13<16:56, 1.43s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 76%|#######6 | 2289/3000 [1:06:13<14:56, 1.26s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 76%|#######6 | 2289/3000 [1:06:13<14:56, 1.26s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 76%|#######6 | 2289/3000 [1:06:14<14:56, 1.26s/it, lr: 1.0e-04 loss: 6.294e-01] jy: 76%|#######6 | 2289/3000 [1:06:14<14:56, 1.26s/it, lr: 1.0e-04 loss: 6.294e-01] jy: 76%|#######6 | 2290/3000 [1:06:15<14:55, 1.26s/it, lr: 1.0e-04 loss: 0.000e+00] jy: 76%|#######6 | 2290/3000 [1:06:15<14:55, 1.26s/it, lr: 1.0e-04 loss: 0.000e+00] jy: 76%|#######6 | 2291/3000 [1:06:15<12:27, 1.05s/it, lr: 1.0e-04 loss: 0.000e+00] jy: 76%|#######6 | 2291/3000 [1:06:15<12:27, 1.05s/it, lr: 1.0e-04 loss: 0.000e+00] jy: 76%|#######6 | 2291/3000 [1:06:17<12:27, 1.05s/it, lr: 1.0e-04 loss: 1.386e-01] jy: 76%|#######6 | 2291/3000 [1:06:17<12:27, 1.05s/it, lr: 1.0e-04 loss: 1.386e-01] jy: 76%|#######6 | 2292/3000 [1:06:17<14:42, 1.25s/it, lr: 1.0e-04 loss: 1.386e-01] jy: 76%|#######6 | 2292/3000 [1:06:17<14:42, 1.25s/it, lr: 1.0e-04 loss: 1.386e-01] jy: 76%|#######6 | 2292/3000 [1:06:20<14:42, 1.25s/it, lr: 1.0e-04 loss: 1.679e-01] jy: 76%|#######6 | 2292/3000 [1:06:20<14:42, 1.25s/it, lr: 1.0e-04 loss: 1.679e-01] jy: 76%|#######6 | 2293/3000 [1:06:20<18:54, 1.61s/it, lr: 1.0e-04 loss: 1.679e-01] jy: 76%|#######6 | 2293/3000 [1:06:20<18:54, 1.61s/it, lr: 1.0e-04 loss: 1.679e-01] jy: 76%|#######6 | 2293/3000 [1:06:21<18:54, 1.61s/it, lr: 1.0e-04 loss: 4.141e-01] jy: 76%|#######6 | 2293/3000 [1:06:21<18:54, 1.61s/it, lr: 1.0e-04 loss: 4.141e-01] jy: 76%|#######6 | 2294/3000 [1:06:21<16:29, 1.40s/it, lr: 1.0e-04 loss: 4.141e-01] jy: 76%|#######6 | 2294/3000 [1:06:21<16:29, 1.40s/it, lr: 1.0e-04 loss: 4.141e-01] jy: 76%|#######6 | 2294/3000 [1:06:21<16:29, 1.40s/it, lr: 1.0e-04 loss: 1.065e-01] jy: 76%|#######6 | 2294/3000 [1:06:21<16:29, 1.40s/it, lr: 1.0e-04 loss: 1.065e-01] jy: 76%|#######6 | 2295/3000 [1:06:21<14:41, 1.25s/it, lr: 1.0e-04 loss: 1.065e-01] jy: 76%|#######6 | 2295/3000 [1:06:21<14:41, 1.25s/it, lr: 1.0e-04 loss: 1.065e-01] jy: 76%|#######6 | 2295/3000 [1:06:23<14:41, 1.25s/it, lr: 1.0e-04 loss: 2.995e-01] jy: 76%|#######6 | 2295/3000 [1:06:23<14:41, 1.25s/it, lr: 1.0e-04 loss: 2.995e-01] jy: 77%|#######6 | 2296/3000 [1:06:23<15:55, 1.36s/it, lr: 1.0e-04 loss: 2.995e-01] jy: 77%|#######6 | 2296/3000 [1:06:23<15:55, 1.36s/it, lr: 1.0e-04 loss: 2.995e-01] jy: 77%|#######6 | 2296/3000 [1:06:26<15:55, 1.36s/it, lr: 1.0e-04 loss: 4.474e-01] jy: 77%|#######6 | 2296/3000 [1:06:26<15:55, 1.36s/it, lr: 1.0e-04 loss: 4.474e-01] jy: 77%|#######6 | 2297/3000 [1:06:26<20:12, 1.72s/it, lr: 1.0e-04 loss: 4.474e-01] jy: 77%|#######6 | 2297/3000 [1:06:26<20:12, 1.72s/it, lr: 1.0e-04 loss: 4.474e-01] jy: 77%|#######6 | 2297/3000 [1:06:27<20:12, 1.72s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 77%|#######6 | 2297/3000 [1:06:27<20:12, 1.72s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 77%|#######6 | 2298/3000 [1:06:27<19:50, 1.70s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 77%|#######6 | 2298/3000 [1:06:27<19:50, 1.70s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 77%|#######6 | 2298/3000 [1:06:30<19:50, 1.70s/it, lr: 1.0e-04 loss: 4.578e-01] jy: 77%|#######6 | 2298/3000 [1:06:30<19:50, 1.70s/it, lr: 1.0e-04 loss: 4.578e-01] jy: 77%|#######6 | 2299/3000 [1:06:30<23:02, 1.97s/it, lr: 1.0e-04 loss: 4.578e-01] jy: 77%|#######6 | 2299/3000 [1:06:30<23:02, 1.97s/it, lr: 1.0e-04 loss: 4.578e-01] jy: 77%|#######6 | 2299/3000 [1:06:33<23:02, 1.97s/it, lr: 1.0e-04 loss: 4.425e-01] jy: 77%|#######6 | 2299/3000 [1:06:33<23:02, 1.97s/it, lr: 1.0e-04 loss: 4.425e-01] jy: 77%|#######6 | 2300/3000 [1:06:34<23:00, 1.97s/it, lr: 1.0e-04 loss: 4.776e-01] jy: 77%|#######6 | 2300/3000 [1:06:34<23:00, 1.97s/it, lr: 1.0e-04 loss: 4.776e-01] jy: 77%|#######6 | 2301/3000 [1:06:34<16:48, 1.44s/it, lr: 1.0e-04 loss: 4.776e-01] jy: 77%|#######6 | 2301/3000 [1:06:34<16:48, 1.44s/it, lr: 1.0e-04 loss: 4.776e-01] jy: 77%|#######6 | 2301/3000 [1:06:35<16:48, 1.44s/it, lr: 1.0e-04 loss: 5.443e-01] jy: 77%|#######6 | 2301/3000 [1:06:35<16:48, 1.44s/it, lr: 1.0e-04 loss: 5.443e-01] jy: 77%|#######6 | 2302/3000 [1:06:35<15:05, 1.30s/it, lr: 1.0e-04 loss: 5.443e-01] jy: 77%|#######6 | 2302/3000 [1:06:35<15:05, 1.30s/it, lr: 1.0e-04 loss: 5.443e-01] jy: 77%|#######6 | 2302/3000 [1:06:37<15:05, 1.30s/it, lr: 1.0e-04 loss: 1.244e-01] jy: 77%|#######6 | 2302/3000 [1:06:37<15:05, 1.30s/it, lr: 1.0e-04 loss: 1.244e-01] jy: 77%|#######6 | 2303/3000 [1:06:37<16:04, 1.38s/it, lr: 1.0e-04 loss: 1.244e-01] jy: 77%|#######6 | 2303/3000 [1:06:37<16:04, 1.38s/it, lr: 1.0e-04 loss: 1.244e-01] jy: 77%|#######6 | 2303/3000 [1:06:38<16:04, 1.38s/it, lr: 1.0e-04 loss: 5.456e-01] jy: 77%|#######6 | 2303/3000 [1:06:38<16:04, 1.38s/it, lr: 1.0e-04 loss: 5.456e-01] jy: 77%|#######6 | 2304/3000 [1:06:38<16:24, 1.41s/it, lr: 1.0e-04 loss: 5.456e-01] jy: 77%|#######6 | 2304/3000 [1:06:38<16:24, 1.41s/it, lr: 1.0e-04 loss: 5.456e-01] jy: 77%|#######6 | 2304/3000 [1:06:40<16:24, 1.41s/it, lr: 1.0e-04 loss: 4.360e-01] jy: 77%|#######6 | 2304/3000 [1:06:40<16:24, 1.41s/it, lr: 1.0e-04 loss: 4.360e-01] jy: 77%|#######6 | 2305/3000 [1:06:40<17:53, 1.54s/it, lr: 1.0e-04 loss: 4.360e-01] jy: 77%|#######6 | 2305/3000 [1:06:40<17:53, 1.54s/it, lr: 1.0e-04 loss: 4.360e-01] jy: 77%|#######6 | 2305/3000 [1:06:43<17:53, 1.54s/it, lr: 1.0e-04 loss: 3.303e-01] jy: 77%|#######6 | 2305/3000 [1:06:43<17:53, 1.54s/it, lr: 1.0e-04 loss: 3.303e-01] jy: 77%|#######6 | 2306/3000 [1:06:43<21:26, 1.85s/it, lr: 1.0e-04 loss: 3.303e-01] jy: 77%|#######6 | 2306/3000 [1:06:43<21:26, 1.85s/it, lr: 1.0e-04 loss: 3.303e-01] jy: 77%|#######6 | 2306/3000 [1:06:45<21:26, 1.85s/it, lr: 1.0e-04 loss: 1.863e-01] jy: 77%|#######6 | 2306/3000 [1:06:45<21:26, 1.85s/it, lr: 1.0e-04 loss: 1.863e-01] jy: 77%|#######6 | 2307/3000 [1:06:45<24:00, 2.08s/it, lr: 1.0e-04 loss: 1.863e-01] jy: 77%|#######6 | 2307/3000 [1:06:45<24:00, 2.08s/it, lr: 1.0e-04 loss: 1.863e-01] jy: 77%|#######6 | 2307/3000 [1:06:47<24:00, 2.08s/it, lr: 1.0e-04 loss: 3.780e-01] jy: 77%|#######6 | 2307/3000 [1:06:47<24:00, 2.08s/it, lr: 1.0e-04 loss: 3.780e-01] jy: 77%|#######6 | 2308/3000 [1:06:47<22:26, 1.95s/it, lr: 1.0e-04 loss: 3.780e-01] jy: 77%|#######6 | 2308/3000 [1:06:47<22:26, 1.95s/it, lr: 1.0e-04 loss: 3.780e-01] jy: 77%|#######6 | 2308/3000 [1:06:49<22:26, 1.95s/it, lr: 1.0e-04 loss: 2.993e-01] jy: 77%|#######6 | 2308/3000 [1:06:49<22:26, 1.95s/it, lr: 1.0e-04 loss: 2.993e-01] jy: 77%|#######6 | 2309/3000 [1:06:49<20:58, 1.82s/it, lr: 1.0e-04 loss: 2.993e-01] jy: 77%|#######6 | 2309/3000 [1:06:49<20:58, 1.82s/it, lr: 1.0e-04 loss: 2.993e-01] jy: 77%|#######6 | 2309/3000 [1:06:50<20:58, 1.82s/it, lr: 1.0e-04 loss: 2.558e-01] jy: 77%|#######6 | 2309/3000 [1:06:50<20:58, 1.82s/it, lr: 1.0e-04 loss: 2.558e-01] jy: 77%|#######7 | 2310/3000 [1:06:51<20:56, 1.82s/it, lr: 1.0e-04 loss: 3.508e-01] jy: 77%|#######7 | 2310/3000 [1:06:51<20:56, 1.82s/it, lr: 1.0e-04 loss: 3.508e-01] jy: 77%|#######7 | 2311/3000 [1:06:51<13:36, 1.18s/it, lr: 1.0e-04 loss: 3.508e-01] jy: 77%|#######7 | 2311/3000 [1:06:51<13:36, 1.18s/it, lr: 1.0e-04 loss: 3.508e-01] jy: 77%|#######7 | 2311/3000 [1:06:54<13:36, 1.18s/it, lr: 1.0e-04 loss: 4.603e-01] jy: 77%|#######7 | 2311/3000 [1:06:54<13:36, 1.18s/it, lr: 1.0e-04 loss: 4.603e-01] jy: 77%|#######7 | 2312/3000 [1:06:54<17:38, 1.54s/it, lr: 1.0e-04 loss: 4.603e-01] jy: 77%|#######7 | 2312/3000 [1:06:54<17:38, 1.54s/it, lr: 1.0e-04 loss: 4.603e-01] jy: 77%|#######7 | 2312/3000 [1:06:57<17:38, 1.54s/it, lr: 1.0e-04 loss: 4.475e-01] jy: 77%|#######7 | 2312/3000 [1:06:57<17:38, 1.54s/it, lr: 1.0e-04 loss: 4.475e-01] jy: 77%|#######7 | 2313/3000 [1:06:57<21:23, 1.87s/it, lr: 1.0e-04 loss: 4.475e-01] jy: 77%|#######7 | 2313/3000 [1:06:57<21:23, 1.87s/it, lr: 1.0e-04 loss: 4.475e-01] jy: 77%|#######7 | 2313/3000 [1:06:58<21:23, 1.87s/it, lr: 1.0e-04 loss: 6.922e-01] jy: 77%|#######7 | 2313/3000 [1:06:58<21:23, 1.87s/it, lr: 1.0e-04 loss: 6.922e-01] jy: 77%|#######7 | 2314/3000 [1:06:58<20:36, 1.80s/it, lr: 1.0e-04 loss: 6.922e-01] jy: 77%|#######7 | 2314/3000 [1:06:58<20:36, 1.80s/it, lr: 1.0e-04 loss: 6.922e-01] jy: 77%|#######7 | 2314/3000 [1:06:59<20:36, 1.80s/it, lr: 1.0e-04 loss: 5.251e-01] jy: 77%|#######7 | 2314/3000 [1:06:59<20:36, 1.80s/it, lr: 1.0e-04 loss: 5.251e-01] jy: 77%|#######7 | 2315/3000 [1:06:59<17:33, 1.54s/it, lr: 1.0e-04 loss: 5.251e-01] jy: 77%|#######7 | 2315/3000 [1:06:59<17:33, 1.54s/it, lr: 1.0e-04 loss: 5.251e-01] jy: 77%|#######7 | 2315/3000 [1:07:00<17:33, 1.54s/it, lr: 1.0e-04 loss: 4.309e-01] jy: 77%|#######7 | 2315/3000 [1:07:00<17:33, 1.54s/it, lr: 1.0e-04 loss: 4.309e-01] jy: 77%|#######7 | 2316/3000 [1:07:00<15:19, 1.34s/it, lr: 1.0e-04 loss: 4.309e-01] jy: 77%|#######7 | 2316/3000 [1:07:00<15:19, 1.34s/it, lr: 1.0e-04 loss: 4.309e-01] jy: 77%|#######7 | 2316/3000 [1:07:03<15:19, 1.34s/it, lr: 1.0e-04 loss: 1.328e-01] jy: 77%|#######7 | 2316/3000 [1:07:03<15:19, 1.34s/it, lr: 1.0e-04 loss: 1.328e-01] jy: 77%|#######7 | 2317/3000 [1:07:03<20:10, 1.77s/it, lr: 1.0e-04 loss: 1.328e-01] jy: 77%|#######7 | 2317/3000 [1:07:03<20:10, 1.77s/it, lr: 1.0e-04 loss: 1.328e-01] jy: 77%|#######7 | 2317/3000 [1:07:04<20:10, 1.77s/it, lr: 1.0e-04 loss: 8.238e-02] jy: 77%|#######7 | 2317/3000 [1:07:04<20:10, 1.77s/it, lr: 1.0e-04 loss: 8.238e-02] jy: 77%|#######7 | 2318/3000 [1:07:04<18:22, 1.62s/it, lr: 1.0e-04 loss: 8.238e-02] jy: 77%|#######7 | 2318/3000 [1:07:04<18:22, 1.62s/it, lr: 1.0e-04 loss: 8.238e-02] jy: 77%|#######7 | 2318/3000 [1:07:05<18:22, 1.62s/it, lr: 1.0e-04 loss: 3.402e-01] jy: 77%|#######7 | 2318/3000 [1:07:05<18:22, 1.62s/it, lr: 1.0e-04 loss: 3.402e-01] jy: 77%|#######7 | 2319/3000 [1:07:05<15:56, 1.41s/it, lr: 1.0e-04 loss: 3.402e-01] jy: 77%|#######7 | 2319/3000 [1:07:05<15:56, 1.41s/it, lr: 1.0e-04 loss: 3.402e-01] jy: 77%|#######7 | 2319/3000 [1:07:06<15:56, 1.41s/it, lr: 1.0e-04 loss: 5.240e-01] jy: 77%|#######7 | 2319/3000 [1:07:06<15:56, 1.41s/it, lr: 1.0e-04 loss: 5.240e-01] jy: 77%|#######7 | 2320/3000 [1:07:07<15:55, 1.41s/it, lr: 1.0e-04 loss: 5.502e-01] jy: 77%|#######7 | 2320/3000 [1:07:07<15:55, 1.41s/it, lr: 1.0e-04 loss: 5.502e-01] jy: 77%|#######7 | 2321/3000 [1:07:07<10:53, 1.04it/s, lr: 1.0e-04 loss: 5.502e-01] jy: 77%|#######7 | 2321/3000 [1:07:07<10:53, 1.04it/s, lr: 1.0e-04 loss: 5.502e-01] jy: 77%|#######7 | 2321/3000 [1:07:10<10:53, 1.04it/s, lr: 1.0e-04 loss: 3.549e-01] jy: 77%|#######7 | 2321/3000 [1:07:10<10:53, 1.04it/s, lr: 1.0e-04 loss: 3.549e-01] jy: 77%|#######7 | 2322/3000 [1:07:10<15:31, 1.37s/it, lr: 1.0e-04 loss: 3.549e-01] jy: 77%|#######7 | 2322/3000 [1:07:10<15:31, 1.37s/it, lr: 1.0e-04 loss: 3.549e-01] jy: 77%|#######7 | 2322/3000 [1:07:12<15:31, 1.37s/it, lr: 1.0e-04 loss: 4.201e-01] jy: 77%|#######7 | 2322/3000 [1:07:12<15:31, 1.37s/it, lr: 1.0e-04 loss: 4.201e-01] jy: 77%|#######7 | 2323/3000 [1:07:12<16:14, 1.44s/it, lr: 1.0e-04 loss: 4.201e-01] jy: 77%|#######7 | 2323/3000 [1:07:12<16:14, 1.44s/it, lr: 1.0e-04 loss: 4.201e-01] jy: 77%|#######7 | 2323/3000 [1:07:12<16:14, 1.44s/it, lr: 1.0e-04 loss: 5.171e-01] jy: 77%|#######7 | 2323/3000 [1:07:12<16:14, 1.44s/it, lr: 1.0e-04 loss: 5.171e-01] jy: 77%|#######7 | 2324/3000 [1:07:12<14:26, 1.28s/it, lr: 1.0e-04 loss: 5.171e-01] jy: 77%|#######7 | 2324/3000 [1:07:12<14:26, 1.28s/it, lr: 1.0e-04 loss: 5.171e-01] jy: 77%|#######7 | 2324/3000 [1:07:15<14:26, 1.28s/it, lr: 1.0e-04 loss: 1.431e-01] jy: 77%|#######7 | 2324/3000 [1:07:15<14:26, 1.28s/it, lr: 1.0e-04 loss: 1.431e-01] jy: 78%|#######7 | 2325/3000 [1:07:15<19:13, 1.71s/it, lr: 1.0e-04 loss: 1.431e-01] jy: 78%|#######7 | 2325/3000 [1:07:15<19:13, 1.71s/it, lr: 1.0e-04 loss: 1.431e-01] jy: 78%|#######7 | 2325/3000 [1:07:18<19:13, 1.71s/it, lr: 1.0e-04 loss: 2.330e-01] jy: 78%|#######7 | 2325/3000 [1:07:18<19:13, 1.71s/it, lr: 1.0e-04 loss: 2.330e-01] jy: 78%|#######7 | 2326/3000 [1:07:18<22:39, 2.02s/it, lr: 1.0e-04 loss: 2.330e-01] jy: 78%|#######7 | 2326/3000 [1:07:18<22:39, 2.02s/it, lr: 1.0e-04 loss: 2.330e-01] jy: 78%|#######7 | 2326/3000 [1:07:21<22:39, 2.02s/it, lr: 1.0e-04 loss: 4.824e-01] jy: 78%|#######7 | 2326/3000 [1:07:21<22:39, 2.02s/it, lr: 1.0e-04 loss: 4.824e-01] jy: 78%|#######7 | 2327/3000 [1:07:21<24:37, 2.19s/it, lr: 1.0e-04 loss: 4.824e-01] jy: 78%|#######7 | 2327/3000 [1:07:21<24:37, 2.19s/it, lr: 1.0e-04 loss: 4.824e-01] jy: 78%|#######7 | 2327/3000 [1:07:23<24:37, 2.19s/it, lr: 1.0e-04 loss: 4.821e-02] jy: 78%|#######7 | 2327/3000 [1:07:23<24:37, 2.19s/it, lr: 1.0e-04 loss: 4.821e-02] jy: 78%|#######7 | 2328/3000 [1:07:23<26:01, 2.32s/it, lr: 1.0e-04 loss: 4.821e-02] jy: 78%|#######7 | 2328/3000 [1:07:23<26:01, 2.32s/it, lr: 1.0e-04 loss: 4.821e-02] jy: 78%|#######7 | 2328/3000 [1:07:24<26:01, 2.32s/it, lr: 1.0e-04 loss: 3.708e-02] jy: 78%|#######7 | 2328/3000 [1:07:24<26:01, 2.32s/it, lr: 1.0e-04 loss: 3.708e-02] jy: 78%|#######7 | 2329/3000 [1:07:24<21:09, 1.89s/it, lr: 1.0e-04 loss: 3.708e-02] jy: 78%|#######7 | 2329/3000 [1:07:24<21:09, 1.89s/it, lr: 1.0e-04 loss: 3.708e-02] jy: 78%|#######7 | 2329/3000 [1:07:27<21:09, 1.89s/it, lr: 1.0e-04 loss: 4.997e-01] jy: 78%|#######7 | 2329/3000 [1:07:27<21:09, 1.89s/it, lr: 1.0e-04 loss: 4.997e-01] jy: 78%|#######7 | 2330/3000 [1:07:28<21:07, 1.89s/it, lr: 1.0e-04 loss: 2.512e-01] jy: 78%|#######7 | 2330/3000 [1:07:28<21:07, 1.89s/it, lr: 1.0e-04 loss: 2.512e-01] jy: 78%|#######7 | 2331/3000 [1:07:28<15:16, 1.37s/it, lr: 1.0e-04 loss: 2.512e-01] jy: 78%|#######7 | 2331/3000 [1:07:28<15:16, 1.37s/it, lr: 1.0e-04 loss: 2.512e-01] jy: 78%|#######7 | 2331/3000 [1:07:30<15:16, 1.37s/it, lr: 1.0e-04 loss: 6.639e-01] jy: 78%|#######7 | 2331/3000 [1:07:30<15:16, 1.37s/it, lr: 1.0e-04 loss: 6.639e-01] jy: 78%|#######7 | 2332/3000 [1:07:30<15:57, 1.43s/it, lr: 1.0e-04 loss: 6.639e-01] jy: 78%|#######7 | 2332/3000 [1:07:30<15:57, 1.43s/it, lr: 1.0e-04 loss: 6.639e-01] jy: 78%|#######7 | 2332/3000 [1:07:31<15:57, 1.43s/it, lr: 1.0e-04 loss: 4.117e-01] jy: 78%|#######7 | 2332/3000 [1:07:31<15:57, 1.43s/it, lr: 1.0e-04 loss: 4.117e-01] jy: 78%|#######7 | 2333/3000 [1:07:31<14:57, 1.35s/it, lr: 1.0e-04 loss: 4.117e-01] jy: 78%|#######7 | 2333/3000 [1:07:31<14:57, 1.35s/it, lr: 1.0e-04 loss: 4.117e-01] jy: 78%|#######7 | 2333/3000 [1:07:34<14:57, 1.35s/it, lr: 1.0e-04 loss: 1.469e-01] jy: 78%|#######7 | 2333/3000 [1:07:34<14:57, 1.35s/it, lr: 1.0e-04 loss: 1.469e-01] jy: 78%|#######7 | 2334/3000 [1:07:34<18:47, 1.69s/it, lr: 1.0e-04 loss: 1.469e-01] jy: 78%|#######7 | 2334/3000 [1:07:34<18:47, 1.69s/it, lr: 1.0e-04 loss: 1.469e-01] jy: 78%|#######7 | 2334/3000 [1:07:35<18:47, 1.69s/it, lr: 1.0e-04 loss: 2.994e-01] jy: 78%|#######7 | 2334/3000 [1:07:35<18:47, 1.69s/it, lr: 1.0e-04 loss: 2.994e-01] jy: 78%|#######7 | 2335/3000 [1:07:35<18:15, 1.65s/it, lr: 1.0e-04 loss: 2.994e-01] jy: 78%|#######7 | 2335/3000 [1:07:35<18:15, 1.65s/it, lr: 1.0e-04 loss: 2.994e-01] jy: 78%|#######7 | 2335/3000 [1:07:36<18:15, 1.65s/it, lr: 1.0e-04 loss: 5.181e-01] jy: 78%|#######7 | 2335/3000 [1:07:36<18:15, 1.65s/it, lr: 1.0e-04 loss: 5.181e-01] jy: 78%|#######7 | 2336/3000 [1:07:36<15:44, 1.42s/it, lr: 1.0e-04 loss: 5.181e-01] jy: 78%|#######7 | 2336/3000 [1:07:36<15:44, 1.42s/it, lr: 1.0e-04 loss: 5.181e-01] jy: 78%|#######7 | 2336/3000 [1:07:37<15:44, 1.42s/it, lr: 1.0e-04 loss: 8.501e-02] jy: 78%|#######7 | 2336/3000 [1:07:37<15:44, 1.42s/it, lr: 1.0e-04 loss: 8.501e-02] jy: 78%|#######7 | 2337/3000 [1:07:37<13:54, 1.26s/it, lr: 1.0e-04 loss: 8.501e-02] jy: 78%|#######7 | 2337/3000 [1:07:37<13:54, 1.26s/it, lr: 1.0e-04 loss: 8.501e-02] jy: 78%|#######7 | 2337/3000 [1:07:40<13:54, 1.26s/it, lr: 1.0e-04 loss: 3.846e-01] jy: 78%|#######7 | 2337/3000 [1:07:40<13:54, 1.26s/it, lr: 1.0e-04 loss: 3.846e-01] jy: 78%|#######7 | 2338/3000 [1:07:40<18:18, 1.66s/it, lr: 1.0e-04 loss: 3.846e-01] jy: 78%|#######7 | 2338/3000 [1:07:40<18:18, 1.66s/it, lr: 1.0e-04 loss: 3.846e-01] jy: 78%|#######7 | 2338/3000 [1:07:42<18:18, 1.66s/it, lr: 1.0e-04 loss: 6.512e-01] jy: 78%|#######7 | 2338/3000 [1:07:42<18:18, 1.66s/it, lr: 1.0e-04 loss: 6.512e-01] jy: 78%|#######7 | 2339/3000 [1:07:42<21:25, 1.95s/it, lr: 1.0e-04 loss: 6.512e-01] jy: 78%|#######7 | 2339/3000 [1:07:42<21:25, 1.95s/it, lr: 1.0e-04 loss: 6.512e-01] jy: 78%|#######7 | 2339/3000 [1:07:43<21:25, 1.95s/it, lr: 1.0e-04 loss: 5.993e-01] jy: 78%|#######7 | 2339/3000 [1:07:43<21:25, 1.95s/it, lr: 1.0e-04 loss: 5.993e-01] jy: 78%|#######8 | 2340/3000 [1:07:45<21:24, 1.95s/it, lr: 1.0e-04 loss: 9.332e-02] jy: 78%|#######8 | 2340/3000 [1:07:45<21:24, 1.95s/it, lr: 1.0e-04 loss: 9.332e-02] jy: 78%|#######8 | 2341/3000 [1:07:45<15:25, 1.40s/it, lr: 1.0e-04 loss: 9.332e-02] jy: 78%|#######8 | 2341/3000 [1:07:45<15:25, 1.40s/it, lr: 1.0e-04 loss: 9.332e-02] jy: 78%|#######8 | 2341/3000 [1:07:45<15:25, 1.40s/it, lr: 1.0e-04 loss: 6.659e-02] jy: 78%|#######8 | 2341/3000 [1:07:45<15:25, 1.40s/it, lr: 1.0e-04 loss: 6.659e-02] jy: 78%|#######8 | 2342/3000 [1:07:45<13:55, 1.27s/it, lr: 1.0e-04 loss: 6.659e-02] jy: 78%|#######8 | 2342/3000 [1:07:45<13:55, 1.27s/it, lr: 1.0e-04 loss: 6.659e-02] jy: 78%|#######8 | 2342/3000 [1:07:47<13:55, 1.27s/it, lr: 1.0e-04 loss: 2.643e-01] jy: 78%|#######8 | 2342/3000 [1:07:47<13:55, 1.27s/it, lr: 1.0e-04 loss: 2.643e-01] jy: 78%|#######8 | 2343/3000 [1:07:47<14:37, 1.34s/it, lr: 1.0e-04 loss: 2.643e-01] jy: 78%|#######8 | 2343/3000 [1:07:47<14:37, 1.34s/it, lr: 1.0e-04 loss: 2.643e-01] jy: 78%|#######8 | 2343/3000 [1:07:49<14:37, 1.34s/it, lr: 1.0e-04 loss: 4.887e-01] jy: 78%|#######8 | 2343/3000 [1:07:49<14:37, 1.34s/it, lr: 1.0e-04 loss: 4.887e-01] jy: 78%|#######8 | 2344/3000 [1:07:49<15:28, 1.41s/it, lr: 1.0e-04 loss: 4.887e-01] jy: 78%|#######8 | 2344/3000 [1:07:49<15:28, 1.41s/it, lr: 1.0e-04 loss: 4.887e-01] jy: 78%|#######8 | 2344/3000 [1:07:51<15:28, 1.41s/it, lr: 1.0e-04 loss: 5.379e-01] jy: 78%|#######8 | 2344/3000 [1:07:51<15:28, 1.41s/it, lr: 1.0e-04 loss: 5.379e-01] jy: 78%|#######8 | 2345/3000 [1:07:51<19:31, 1.79s/it, lr: 1.0e-04 loss: 5.379e-01] jy: 78%|#######8 | 2345/3000 [1:07:51<19:31, 1.79s/it, lr: 1.0e-04 loss: 5.379e-01] jy: 78%|#######8 | 2345/3000 [1:07:53<19:31, 1.79s/it, lr: 1.0e-04 loss: 2.052e-01] jy: 78%|#######8 | 2345/3000 [1:07:53<19:31, 1.79s/it, lr: 1.0e-04 loss: 2.052e-01] jy: 78%|#######8 | 2346/3000 [1:07:53<19:00, 1.74s/it, lr: 1.0e-04 loss: 2.052e-01] jy: 78%|#######8 | 2346/3000 [1:07:53<19:00, 1.74s/it, lr: 1.0e-04 loss: 2.052e-01] jy: 78%|#######8 | 2346/3000 [1:07:55<19:00, 1.74s/it, lr: 1.0e-04 loss: 2.587e-02] jy: 78%|#######8 | 2346/3000 [1:07:55<19:00, 1.74s/it, lr: 1.0e-04 loss: 2.587e-02] jy: 78%|#######8 | 2347/3000 [1:07:55<19:18, 1.77s/it, lr: 1.0e-04 loss: 2.587e-02] jy: 78%|#######8 | 2347/3000 [1:07:55<19:18, 1.77s/it, lr: 1.0e-04 loss: 2.587e-02] jy: 78%|#######8 | 2347/3000 [1:07:57<19:18, 1.77s/it, lr: 1.0e-04 loss: 5.557e-01] jy: 78%|#######8 | 2347/3000 [1:07:57<19:18, 1.77s/it, lr: 1.0e-04 loss: 5.557e-01] jy: 78%|#######8 | 2348/3000 [1:07:57<22:00, 2.02s/it, lr: 1.0e-04 loss: 5.557e-01] jy: 78%|#######8 | 2348/3000 [1:07:57<22:00, 2.02s/it, lr: 1.0e-04 loss: 5.557e-01] jy: 78%|#######8 | 2348/3000 [1:08:00<22:00, 2.02s/it, lr: 1.0e-04 loss: 5.285e-01] jy: 78%|#######8 | 2348/3000 [1:08:00<22:00, 2.02s/it, lr: 1.0e-04 loss: 5.285e-01] jy: 78%|#######8 | 2349/3000 [1:08:00<24:29, 2.26s/it, lr: 1.0e-04 loss: 5.285e-01] jy: 78%|#######8 | 2349/3000 [1:08:00<24:29, 2.26s/it, lr: 1.0e-04 loss: 5.285e-01] jy: 78%|#######8 | 2349/3000 [1:08:01<24:29, 2.26s/it, lr: 1.0e-04 loss: 6.814e-02] jy: 78%|#######8 | 2349/3000 [1:08:01<24:29, 2.26s/it, lr: 1.0e-04 loss: 6.814e-02] jy: 78%|#######8 | 2350/3000 [1:08:04<24:26, 2.26s/it, lr: 1.0e-04 loss: 6.107e-01] jy: 78%|#######8 | 2350/3000 [1:08:04<24:26, 2.26s/it, lr: 1.0e-04 loss: 6.107e-01] jy: 78%|#######8 | 2351/3000 [1:08:04<20:17, 1.88s/it, lr: 1.0e-04 loss: 6.107e-01] jy: 78%|#######8 | 2351/3000 [1:08:04<20:17, 1.88s/it, lr: 1.0e-04 loss: 6.107e-01] jy: 78%|#######8 | 2351/3000 [1:08:05<20:17, 1.88s/it, lr: 1.0e-04 loss: 1.235e-01] jy: 78%|#######8 | 2351/3000 [1:08:05<20:17, 1.88s/it, lr: 1.0e-04 loss: 1.235e-01] jy: 78%|#######8 | 2352/3000 [1:08:05<17:31, 1.62s/it, lr: 1.0e-04 loss: 1.235e-01] jy: 78%|#######8 | 2352/3000 [1:08:05<17:31, 1.62s/it, lr: 1.0e-04 loss: 1.235e-01] jy: 78%|#######8 | 2352/3000 [1:08:06<17:31, 1.62s/it, lr: 1.0e-04 loss: 3.633e-01] jy: 78%|#######8 | 2352/3000 [1:08:06<17:31, 1.62s/it, lr: 1.0e-04 loss: 3.633e-01] jy: 78%|#######8 | 2353/3000 [1:08:06<17:17, 1.60s/it, lr: 1.0e-04 loss: 3.633e-01] jy: 78%|#######8 | 2353/3000 [1:08:06<17:17, 1.60s/it, lr: 1.0e-04 loss: 3.633e-01] jy: 78%|#######8 | 2353/3000 [1:08:08<17:17, 1.60s/it, lr: 1.0e-04 loss: 1.383e-01] jy: 78%|#######8 | 2353/3000 [1:08:08<17:17, 1.60s/it, lr: 1.0e-04 loss: 1.383e-01] jy: 78%|#######8 | 2354/3000 [1:08:08<16:56, 1.57s/it, lr: 1.0e-04 loss: 1.383e-01] jy: 78%|#######8 | 2354/3000 [1:08:08<16:56, 1.57s/it, lr: 1.0e-04 loss: 1.383e-01] jy: 78%|#######8 | 2354/3000 [1:08:09<16:56, 1.57s/it, lr: 1.0e-04 loss: 2.513e-01] jy: 78%|#######8 | 2354/3000 [1:08:09<16:56, 1.57s/it, lr: 1.0e-04 loss: 2.513e-01] jy: 78%|#######8 | 2355/3000 [1:08:09<14:47, 1.38s/it, lr: 1.0e-04 loss: 2.513e-01] jy: 78%|#######8 | 2355/3000 [1:08:09<14:47, 1.38s/it, lr: 1.0e-04 loss: 2.513e-01] jy: 78%|#######8 | 2355/3000 [1:08:10<14:47, 1.38s/it, lr: 1.0e-04 loss: 2.414e-01] jy: 78%|#######8 | 2355/3000 [1:08:10<14:47, 1.38s/it, lr: 1.0e-04 loss: 2.414e-01] jy: 79%|#######8 | 2356/3000 [1:08:10<15:31, 1.45s/it, lr: 1.0e-04 loss: 2.414e-01] jy: 79%|#######8 | 2356/3000 [1:08:10<15:31, 1.45s/it, lr: 1.0e-04 loss: 2.414e-01] jy: 79%|#######8 | 2356/3000 [1:08:11<15:31, 1.45s/it, lr: 1.0e-04 loss: 1.074e-01] jy: 79%|#######8 | 2356/3000 [1:08:11<15:31, 1.45s/it, lr: 1.0e-04 loss: 1.074e-01] jy: 79%|#######8 | 2357/3000 [1:08:11<13:41, 1.28s/it, lr: 1.0e-04 loss: 1.074e-01] jy: 79%|#######8 | 2357/3000 [1:08:11<13:41, 1.28s/it, lr: 1.0e-04 loss: 1.074e-01] jy: 79%|#######8 | 2357/3000 [1:08:12<13:41, 1.28s/it, lr: 1.0e-04 loss: 3.233e-01] jy: 79%|#######8 | 2357/3000 [1:08:12<13:41, 1.28s/it, lr: 1.0e-04 loss: 3.233e-01] jy: 79%|#######8 | 2358/3000 [1:08:12<12:13, 1.14s/it, lr: 1.0e-04 loss: 3.233e-01] jy: 79%|#######8 | 2358/3000 [1:08:12<12:13, 1.14s/it, lr: 1.0e-04 loss: 3.233e-01] jy: 79%|#######8 | 2358/3000 [1:08:15<12:13, 1.14s/it, lr: 1.0e-04 loss: 2.633e-01] jy: 79%|#######8 | 2358/3000 [1:08:15<12:13, 1.14s/it, lr: 1.0e-04 loss: 2.633e-01] jy: 79%|#######8 | 2359/3000 [1:08:15<17:28, 1.64s/it, lr: 1.0e-04 loss: 2.633e-01] jy: 79%|#######8 | 2359/3000 [1:08:15<17:28, 1.64s/it, lr: 1.0e-04 loss: 2.633e-01] jy: 79%|#######8 | 2359/3000 [1:08:17<17:28, 1.64s/it, lr: 1.0e-04 loss: 4.397e-01] jy: 79%|#######8 | 2359/3000 [1:08:17<17:28, 1.64s/it, lr: 1.0e-04 loss: 4.397e-01] jy: 79%|#######8 | 2360/3000 [1:08:20<17:26, 1.64s/it, lr: 1.0e-04 loss: 2.461e-01] jy: 79%|#######8 | 2360/3000 [1:08:20<17:26, 1.64s/it, lr: 1.0e-04 loss: 2.461e-01] jy: 79%|#######8 | 2361/3000 [1:08:20<16:19, 1.53s/it, lr: 1.0e-04 loss: 2.461e-01] jy: 79%|#######8 | 2361/3000 [1:08:20<16:19, 1.53s/it, lr: 1.0e-04 loss: 2.461e-01] jy: 79%|#######8 | 2361/3000 [1:08:20<16:19, 1.53s/it, lr: 1.0e-04 loss: 4.784e-01] jy: 79%|#######8 | 2361/3000 [1:08:20<16:19, 1.53s/it, lr: 1.0e-04 loss: 4.784e-01] jy: 79%|#######8 | 2362/3000 [1:08:20<14:25, 1.36s/it, lr: 1.0e-04 loss: 4.784e-01] jy: 79%|#######8 | 2362/3000 [1:08:20<14:25, 1.36s/it, lr: 1.0e-04 loss: 4.784e-01] jy: 79%|#######8 | 2362/3000 [1:08:22<14:25, 1.36s/it, lr: 1.0e-04 loss: 1.001e-01] jy: 79%|#######8 | 2362/3000 [1:08:22<14:25, 1.36s/it, lr: 1.0e-04 loss: 1.001e-01] jy: 79%|#######8 | 2363/3000 [1:08:22<15:09, 1.43s/it, lr: 1.0e-04 loss: 1.001e-01] jy: 79%|#######8 | 2363/3000 [1:08:22<15:09, 1.43s/it, lr: 1.0e-04 loss: 1.001e-01] jy: 79%|#######8 | 2363/3000 [1:08:25<15:09, 1.43s/it, lr: 1.0e-04 loss: 3.804e-01] jy: 79%|#######8 | 2363/3000 [1:08:25<15:09, 1.43s/it, lr: 1.0e-04 loss: 3.804e-01] jy: 79%|#######8 | 2364/3000 [1:08:25<19:06, 1.80s/it, lr: 1.0e-04 loss: 3.804e-01] jy: 79%|#######8 | 2364/3000 [1:08:25<19:06, 1.80s/it, lr: 1.0e-04 loss: 3.804e-01] jy: 79%|#######8 | 2364/3000 [1:08:27<19:06, 1.80s/it, lr: 1.0e-04 loss: 1.166e-01] jy: 79%|#######8 | 2364/3000 [1:08:27<19:06, 1.80s/it, lr: 1.0e-04 loss: 1.166e-01] jy: 79%|#######8 | 2365/3000 [1:08:27<21:31, 2.03s/it, lr: 1.0e-04 loss: 1.166e-01] jy: 79%|#######8 | 2365/3000 [1:08:27<21:31, 2.03s/it, lr: 1.0e-04 loss: 1.166e-01] jy: 79%|#######8 | 2365/3000 [1:08:30<21:31, 2.03s/it, lr: 1.0e-04 loss: 3.603e-01] jy: 79%|#######8 | 2365/3000 [1:08:30<21:31, 2.03s/it, lr: 1.0e-04 loss: 3.603e-01] jy: 79%|#######8 | 2366/3000 [1:08:30<23:17, 2.20s/it, lr: 1.0e-04 loss: 3.603e-01] jy: 79%|#######8 | 2366/3000 [1:08:30<23:17, 2.20s/it, lr: 1.0e-04 loss: 3.603e-01] jy: 79%|#######8 | 2366/3000 [1:08:32<23:17, 2.20s/it, lr: 1.0e-04 loss: 1.179e-01] jy: 79%|#######8 | 2366/3000 [1:08:32<23:17, 2.20s/it, lr: 1.0e-04 loss: 1.179e-01] jy: 79%|#######8 | 2367/3000 [1:08:32<21:30, 2.04s/it, lr: 1.0e-04 loss: 1.179e-01] jy: 79%|#######8 | 2367/3000 [1:08:32<21:30, 2.04s/it, lr: 1.0e-04 loss: 1.179e-01] jy: 79%|#######8 | 2367/3000 [1:08:33<21:30, 2.04s/it, lr: 1.0e-04 loss: 1.735e-01] jy: 79%|#######8 | 2367/3000 [1:08:33<21:30, 2.04s/it, lr: 1.0e-04 loss: 1.735e-01] jy: 79%|#######8 | 2368/3000 [1:08:33<19:58, 1.90s/it, lr: 1.0e-04 loss: 1.735e-01] jy: 79%|#######8 | 2368/3000 [1:08:33<19:58, 1.90s/it, lr: 1.0e-04 loss: 1.735e-01] jy: 79%|#######8 | 2368/3000 [1:08:36<19:58, 1.90s/it, lr: 1.0e-04 loss: 3.767e-01] jy: 79%|#######8 | 2368/3000 [1:08:36<19:58, 1.90s/it, lr: 1.0e-04 loss: 3.767e-01] jy: 79%|#######8 | 2369/3000 [1:08:36<22:13, 2.11s/it, lr: 1.0e-04 loss: 3.767e-01] jy: 79%|#######8 | 2369/3000 [1:08:36<22:13, 2.11s/it, lr: 1.0e-04 loss: 3.767e-01] jy: 79%|#######8 | 2369/3000 [1:08:39<22:13, 2.11s/it, lr: 1.0e-04 loss: 2.655e-01] jy: 79%|#######8 | 2369/3000 [1:08:39<22:13, 2.11s/it, lr: 1.0e-04 loss: 2.655e-01] jy: 79%|#######9 | 2370/3000 [1:08:40<22:11, 2.11s/it, lr: 1.0e-04 loss: 5.668e-01] jy: 79%|#######9 | 2370/3000 [1:08:40<22:11, 2.11s/it, lr: 1.0e-04 loss: 5.668e-01] jy: 79%|#######9 | 2371/3000 [1:08:40<14:09, 1.35s/it, lr: 1.0e-04 loss: 5.668e-01] jy: 79%|#######9 | 2371/3000 [1:08:40<14:09, 1.35s/it, lr: 1.0e-04 loss: 5.668e-01] jy: 79%|#######9 | 2371/3000 [1:08:41<14:09, 1.35s/it, lr: 1.0e-04 loss: 2.042e-01] jy: 79%|#######9 | 2371/3000 [1:08:41<14:09, 1.35s/it, lr: 1.0e-04 loss: 2.042e-01] jy: 79%|#######9 | 2372/3000 [1:08:41<13:02, 1.25s/it, lr: 1.0e-04 loss: 2.042e-01] jy: 79%|#######9 | 2372/3000 [1:08:41<13:02, 1.25s/it, lr: 1.0e-04 loss: 2.042e-01] jy: 79%|#######9 | 2372/3000 [1:08:42<13:02, 1.25s/it, lr: 1.0e-04 loss: 3.398e-01] jy: 79%|#######9 | 2372/3000 [1:08:42<13:02, 1.25s/it, lr: 1.0e-04 loss: 3.398e-01] jy: 79%|#######9 | 2373/3000 [1:08:42<12:34, 1.20s/it, lr: 1.0e-04 loss: 3.398e-01] jy: 79%|#######9 | 2373/3000 [1:08:42<12:34, 1.20s/it, lr: 1.0e-04 loss: 3.398e-01] jy: 79%|#######9 | 2373/3000 [1:08:43<12:34, 1.20s/it, lr: 1.0e-04 loss: 5.072e-01] jy: 79%|#######9 | 2373/3000 [1:08:43<12:34, 1.20s/it, lr: 1.0e-04 loss: 5.072e-01] jy: 79%|#######9 | 2374/3000 [1:08:43<13:43, 1.32s/it, lr: 1.0e-04 loss: 5.072e-01] jy: 79%|#######9 | 2374/3000 [1:08:43<13:43, 1.32s/it, lr: 1.0e-04 loss: 5.072e-01] jy: 79%|#######9 | 2374/3000 [1:08:45<13:43, 1.32s/it, lr: 1.0e-04 loss: 3.341e-02] jy: 79%|#######9 | 2374/3000 [1:08:45<13:43, 1.32s/it, lr: 1.0e-04 loss: 3.341e-02] jy: 79%|#######9 | 2375/3000 [1:08:45<14:16, 1.37s/it, lr: 1.0e-04 loss: 3.341e-02] jy: 79%|#######9 | 2375/3000 [1:08:45<14:16, 1.37s/it, lr: 1.0e-04 loss: 3.341e-02] jy: 79%|#######9 | 2375/3000 [1:08:47<14:16, 1.37s/it, lr: 1.0e-04 loss: 1.499e-01] jy: 79%|#######9 | 2375/3000 [1:08:47<14:16, 1.37s/it, lr: 1.0e-04 loss: 1.499e-01] jy: 79%|#######9 | 2376/3000 [1:08:47<15:03, 1.45s/it, lr: 1.0e-04 loss: 1.499e-01] jy: 79%|#######9 | 2376/3000 [1:08:47<15:03, 1.45s/it, lr: 1.0e-04 loss: 1.499e-01] jy: 79%|#######9 | 2376/3000 [1:08:48<15:03, 1.45s/it, lr: 1.0e-04 loss: 1.592e-01] jy: 79%|#######9 | 2376/3000 [1:08:48<15:03, 1.45s/it, lr: 1.0e-04 loss: 1.592e-01] jy: 79%|#######9 | 2377/3000 [1:08:48<15:33, 1.50s/it, lr: 1.0e-04 loss: 1.592e-01] jy: 79%|#######9 | 2377/3000 [1:08:48<15:33, 1.50s/it, lr: 1.0e-04 loss: 1.592e-01] jy: 79%|#######9 | 2377/3000 [1:08:50<15:33, 1.50s/it, lr: 1.0e-04 loss: 6.075e-01] jy: 79%|#######9 | 2377/3000 [1:08:50<15:33, 1.50s/it, lr: 1.0e-04 loss: 6.075e-01] jy: 79%|#######9 | 2378/3000 [1:08:50<15:55, 1.54s/it, lr: 1.0e-04 loss: 6.075e-01] jy: 79%|#######9 | 2378/3000 [1:08:50<15:55, 1.54s/it, lr: 1.0e-04 loss: 6.075e-01] jy: 79%|#######9 | 2378/3000 [1:08:53<15:55, 1.54s/it, lr: 1.0e-04 loss: 4.646e-01] jy: 79%|#######9 | 2378/3000 [1:08:53<15:55, 1.54s/it, lr: 1.0e-04 loss: 4.646e-01] jy: 79%|#######9 | 2379/3000 [1:08:53<19:13, 1.86s/it, lr: 1.0e-04 loss: 4.646e-01] jy: 79%|#######9 | 2379/3000 [1:08:53<19:13, 1.86s/it, lr: 1.0e-04 loss: 4.646e-01] jy: 79%|#######9 | 2379/3000 [1:08:53<19:13, 1.86s/it, lr: 1.0e-04 loss: 1.953e-01] jy: 79%|#######9 | 2379/3000 [1:08:53<19:13, 1.86s/it, lr: 1.0e-04 loss: 1.953e-01] jy: 79%|#######9 | 2380/3000 [1:08:56<19:11, 1.86s/it, lr: 1.0e-04 loss: 4.572e-01] jy: 79%|#######9 | 2380/3000 [1:08:56<19:11, 1.86s/it, lr: 1.0e-04 loss: 4.572e-01] jy: 79%|#######9 | 2381/3000 [1:08:56<17:02, 1.65s/it, lr: 1.0e-04 loss: 4.572e-01] jy: 79%|#######9 | 2381/3000 [1:08:56<17:02, 1.65s/it, lr: 1.0e-04 loss: 4.572e-01] jy: 79%|#######9 | 2381/3000 [1:08:58<17:02, 1.65s/it, lr: 1.0e-04 loss: 1.217e-01] jy: 79%|#######9 | 2381/3000 [1:08:58<17:02, 1.65s/it, lr: 1.0e-04 loss: 1.217e-01] jy: 79%|#######9 | 2382/3000 [1:08:58<16:57, 1.65s/it, lr: 1.0e-04 loss: 1.217e-01] jy: 79%|#######9 | 2382/3000 [1:08:58<16:57, 1.65s/it, lr: 1.0e-04 loss: 1.217e-01] jy: 79%|#######9 | 2382/3000 [1:08:59<16:57, 1.65s/it, lr: 1.0e-04 loss: 5.658e-02] jy: 79%|#######9 | 2382/3000 [1:08:59<16:57, 1.65s/it, lr: 1.0e-04 loss: 5.658e-02] jy: 79%|#######9 | 2383/3000 [1:08:59<16:35, 1.61s/it, lr: 1.0e-04 loss: 5.658e-02] jy: 79%|#######9 | 2383/3000 [1:08:59<16:35, 1.61s/it, lr: 1.0e-04 loss: 5.658e-02] jy: 79%|#######9 | 2383/3000 [1:09:02<16:35, 1.61s/it, lr: 1.0e-04 loss: 2.645e-01] jy: 79%|#######9 | 2383/3000 [1:09:02<16:35, 1.61s/it, lr: 1.0e-04 loss: 2.645e-01] jy: 79%|#######9 | 2384/3000 [1:09:02<19:22, 1.89s/it, lr: 1.0e-04 loss: 2.645e-01] jy: 79%|#######9 | 2384/3000 [1:09:02<19:22, 1.89s/it, lr: 1.0e-04 loss: 2.645e-01] jy: 79%|#######9 | 2384/3000 [1:09:04<19:22, 1.89s/it, lr: 1.0e-04 loss: 1.102e-01] jy: 79%|#######9 | 2384/3000 [1:09:04<19:22, 1.89s/it, lr: 1.0e-04 loss: 1.102e-01] jy: 80%|#######9 | 2385/3000 [1:09:04<18:17, 1.78s/it, lr: 1.0e-04 loss: 1.102e-01] jy: 80%|#######9 | 2385/3000 [1:09:04<18:17, 1.78s/it, lr: 1.0e-04 loss: 1.102e-01] jy: 80%|#######9 | 2385/3000 [1:09:04<18:17, 1.78s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2385/3000 [1:09:04<18:17, 1.78s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2386/3000 [1:09:04<15:33, 1.52s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2386/3000 [1:09:04<15:33, 1.52s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2386/3000 [1:09:05<15:33, 1.52s/it, lr: 1.0e-04 loss: 7.385e-01] jy: 80%|#######9 | 2386/3000 [1:09:05<15:33, 1.52s/it, lr: 1.0e-04 loss: 7.385e-01] jy: 80%|#######9 | 2387/3000 [1:09:05<13:33, 1.33s/it, lr: 1.0e-04 loss: 7.385e-01] jy: 80%|#######9 | 2387/3000 [1:09:05<13:33, 1.33s/it, lr: 1.0e-04 loss: 7.385e-01] jy: 80%|#######9 | 2387/3000 [1:09:07<13:33, 1.33s/it, lr: 1.0e-04 loss: 2.122e-01] jy: 80%|#######9 | 2387/3000 [1:09:07<13:33, 1.33s/it, lr: 1.0e-04 loss: 2.122e-01] jy: 80%|#######9 | 2388/3000 [1:09:07<15:07, 1.48s/it, lr: 1.0e-04 loss: 2.122e-01] jy: 80%|#######9 | 2388/3000 [1:09:07<15:07, 1.48s/it, lr: 1.0e-04 loss: 2.122e-01] jy: 80%|#######9 | 2388/3000 [1:09:08<15:07, 1.48s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 80%|#######9 | 2388/3000 [1:09:08<15:07, 1.48s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 80%|#######9 | 2389/3000 [1:09:08<13:13, 1.30s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 80%|#######9 | 2389/3000 [1:09:08<13:13, 1.30s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 80%|#######9 | 2389/3000 [1:09:10<13:13, 1.30s/it, lr: 1.0e-04 loss: 5.407e-01] jy: 80%|#######9 | 2389/3000 [1:09:10<13:13, 1.30s/it, lr: 1.0e-04 loss: 5.407e-01] jy: 80%|#######9 | 2390/3000 [1:09:10<13:11, 1.30s/it, lr: 1.0e-04 loss: 5.632e-01] jy: 80%|#######9 | 2390/3000 [1:09:10<13:11, 1.30s/it, lr: 1.0e-04 loss: 5.632e-01] jy: 80%|#######9 | 2391/3000 [1:09:10<09:09, 1.11it/s, lr: 1.0e-04 loss: 5.632e-01] jy: 80%|#######9 | 2391/3000 [1:09:10<09:09, 1.11it/s, lr: 1.0e-04 loss: 5.632e-01] jy: 80%|#######9 | 2391/3000 [1:09:12<09:09, 1.11it/s, lr: 1.0e-04 loss: 1.864e-01] jy: 80%|#######9 | 2391/3000 [1:09:12<09:09, 1.11it/s, lr: 1.0e-04 loss: 1.864e-01] jy: 80%|#######9 | 2392/3000 [1:09:12<10:41, 1.05s/it, lr: 1.0e-04 loss: 1.864e-01] jy: 80%|#######9 | 2392/3000 [1:09:12<10:41, 1.05s/it, lr: 1.0e-04 loss: 1.864e-01] jy: 80%|#######9 | 2392/3000 [1:09:15<10:41, 1.05s/it, lr: 1.0e-04 loss: 4.914e-01] jy: 80%|#######9 | 2392/3000 [1:09:15<10:41, 1.05s/it, lr: 1.0e-04 loss: 4.914e-01] jy: 80%|#######9 | 2393/3000 [1:09:15<15:17, 1.51s/it, lr: 1.0e-04 loss: 4.914e-01] jy: 80%|#######9 | 2393/3000 [1:09:15<15:17, 1.51s/it, lr: 1.0e-04 loss: 4.914e-01] jy: 80%|#######9 | 2393/3000 [1:09:16<15:17, 1.51s/it, lr: 1.0e-04 loss: 1.634e-01] jy: 80%|#######9 | 2393/3000 [1:09:16<15:17, 1.51s/it, lr: 1.0e-04 loss: 1.634e-01] jy: 80%|#######9 | 2394/3000 [1:09:16<13:29, 1.34s/it, lr: 1.0e-04 loss: 1.634e-01] jy: 80%|#######9 | 2394/3000 [1:09:16<13:29, 1.34s/it, lr: 1.0e-04 loss: 1.634e-01] jy: 80%|#######9 | 2394/3000 [1:09:18<13:29, 1.34s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2394/3000 [1:09:18<13:29, 1.34s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2395/3000 [1:09:18<17:07, 1.70s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2395/3000 [1:09:18<17:07, 1.70s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2395/3000 [1:09:19<17:07, 1.70s/it, lr: 1.0e-04 loss: 4.601e-01] jy: 80%|#######9 | 2395/3000 [1:09:19<17:07, 1.70s/it, lr: 1.0e-04 loss: 4.601e-01] jy: 80%|#######9 | 2396/3000 [1:09:19<14:42, 1.46s/it, lr: 1.0e-04 loss: 4.601e-01] jy: 80%|#######9 | 2396/3000 [1:09:19<14:42, 1.46s/it, lr: 1.0e-04 loss: 4.601e-01] jy: 80%|#######9 | 2396/3000 [1:09:22<14:42, 1.46s/it, lr: 1.0e-04 loss: 9.151e-02] jy: 80%|#######9 | 2396/3000 [1:09:22<14:42, 1.46s/it, lr: 1.0e-04 loss: 9.151e-02] jy: 80%|#######9 | 2397/3000 [1:09:22<18:04, 1.80s/it, lr: 1.0e-04 loss: 9.151e-02] jy: 80%|#######9 | 2397/3000 [1:09:22<18:04, 1.80s/it, lr: 1.0e-04 loss: 9.151e-02] jy: 80%|#######9 | 2397/3000 [1:09:25<18:04, 1.80s/it, lr: 1.0e-04 loss: 2.820e-01] jy: 80%|#######9 | 2397/3000 [1:09:25<18:04, 1.80s/it, lr: 1.0e-04 loss: 2.820e-01] jy: 80%|#######9 | 2398/3000 [1:09:25<21:01, 2.09s/it, lr: 1.0e-04 loss: 2.820e-01] jy: 80%|#######9 | 2398/3000 [1:09:25<21:01, 2.09s/it, lr: 1.0e-04 loss: 2.820e-01] jy: 80%|#######9 | 2398/3000 [1:09:25<21:01, 2.09s/it, lr: 1.0e-04 loss: 1.475e-01] jy: 80%|#######9 | 2398/3000 [1:09:25<21:01, 2.09s/it, lr: 1.0e-04 loss: 1.475e-01] jy: 80%|#######9 | 2399/3000 [1:09:25<17:19, 1.73s/it, lr: 1.0e-04 loss: 1.475e-01] jy: 80%|#######9 | 2399/3000 [1:09:25<17:19, 1.73s/it, lr: 1.0e-04 loss: 1.475e-01] jy: 80%|#######9 | 2399/3000 [1:09:27<17:19, 1.73s/it, lr: 1.0e-04 loss: 1.553e-01] jy: 80%|#######9 | 2399/3000 [1:09:27<17:19, 1.73s/it, lr: 1.0e-04 loss: 1.553e-01] jy: 80%|######## | 2400/3000 [1:09:28<17:17, 1.73s/it, lr: 1.0e-04 loss: 3.751e-01] jy: 80%|######## | 2400/3000 [1:09:28<17:17, 1.73s/it, lr: 1.0e-04 loss: 3.751e-01] jy: 80%|######## | 2401/3000 [1:09:28<11:19, 1.13s/it, lr: 1.0e-04 loss: 3.751e-01] jy: 80%|######## | 2401/3000 [1:09:28<11:19, 1.13s/it, lr: 1.0e-04 loss: 3.751e-01] jy: 80%|######## | 2401/3000 [1:09:29<11:19, 1.13s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 80%|######## | 2401/3000 [1:09:29<11:19, 1.13s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 80%|######## | 2402/3000 [1:09:29<11:31, 1.16s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 80%|######## | 2402/3000 [1:09:29<11:31, 1.16s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 80%|######## | 2402/3000 [1:09:31<11:31, 1.16s/it, lr: 1.0e-04 loss: 3.953e-01] jy: 80%|######## | 2402/3000 [1:09:31<11:31, 1.16s/it, lr: 1.0e-04 loss: 3.953e-01] jy: 80%|######## | 2403/3000 [1:09:31<12:22, 1.24s/it, lr: 1.0e-04 loss: 3.953e-01] jy: 80%|######## | 2403/3000 [1:09:31<12:22, 1.24s/it, lr: 1.0e-04 loss: 3.953e-01] jy: 80%|######## | 2403/3000 [1:09:32<12:22, 1.24s/it, lr: 1.0e-04 loss: 4.769e-01] jy: 80%|######## | 2403/3000 [1:09:32<12:22, 1.24s/it, lr: 1.0e-04 loss: 4.769e-01] jy: 80%|######## | 2404/3000 [1:09:32<12:58, 1.31s/it, lr: 1.0e-04 loss: 4.769e-01] jy: 80%|######## | 2404/3000 [1:09:32<12:58, 1.31s/it, lr: 1.0e-04 loss: 4.769e-01] jy: 80%|######## | 2404/3000 [1:09:33<12:58, 1.31s/it, lr: 1.0e-04 loss: 3.676e-01] jy: 80%|######## | 2404/3000 [1:09:33<12:58, 1.31s/it, lr: 1.0e-04 loss: 3.676e-01] jy: 80%|######## | 2405/3000 [1:09:33<11:42, 1.18s/it, lr: 1.0e-04 loss: 3.676e-01] jy: 80%|######## | 2405/3000 [1:09:33<11:42, 1.18s/it, lr: 1.0e-04 loss: 3.676e-01] jy: 80%|######## | 2405/3000 [1:09:36<11:42, 1.18s/it, lr: 1.0e-04 loss: 5.722e-01] jy: 80%|######## | 2405/3000 [1:09:36<11:42, 1.18s/it, lr: 1.0e-04 loss: 5.722e-01] jy: 80%|######## | 2406/3000 [1:09:36<15:46, 1.59s/it, lr: 1.0e-04 loss: 5.722e-01] jy: 80%|######## | 2406/3000 [1:09:36<15:46, 1.59s/it, lr: 1.0e-04 loss: 5.722e-01] jy: 80%|######## | 2406/3000 [1:09:37<15:46, 1.59s/it, lr: 1.0e-04 loss: 5.383e-01] jy: 80%|######## | 2406/3000 [1:09:37<15:46, 1.59s/it, lr: 1.0e-04 loss: 5.383e-01] jy: 80%|######## | 2407/3000 [1:09:37<15:31, 1.57s/it, lr: 1.0e-04 loss: 5.383e-01] jy: 80%|######## | 2407/3000 [1:09:37<15:31, 1.57s/it, lr: 1.0e-04 loss: 5.383e-01] jy: 80%|######## | 2407/3000 [1:09:38<15:31, 1.57s/it, lr: 1.0e-04 loss: 2.757e-01] jy: 80%|######## | 2407/3000 [1:09:38<15:31, 1.57s/it, lr: 1.0e-04 loss: 2.757e-01] jy: 80%|######## | 2408/3000 [1:09:38<13:26, 1.36s/it, lr: 1.0e-04 loss: 2.757e-01] jy: 80%|######## | 2408/3000 [1:09:38<13:26, 1.36s/it, lr: 1.0e-04 loss: 2.757e-01] jy: 80%|######## | 2408/3000 [1:09:39<13:26, 1.36s/it, lr: 1.0e-04 loss: 5.411e-02] jy: 80%|######## | 2408/3000 [1:09:39<13:26, 1.36s/it, lr: 1.0e-04 loss: 5.411e-02] jy: 80%|######## | 2409/3000 [1:09:39<12:00, 1.22s/it, lr: 1.0e-04 loss: 5.411e-02] jy: 80%|######## | 2409/3000 [1:09:39<12:00, 1.22s/it, lr: 1.0e-04 loss: 5.411e-02] jy: 80%|######## | 2409/3000 [1:09:40<12:00, 1.22s/it, lr: 1.0e-04 loss: 1.203e-01] jy: 80%|######## | 2409/3000 [1:09:40<12:00, 1.22s/it, lr: 1.0e-04 loss: 1.203e-01] jy: 80%|######## | 2410/3000 [1:09:42<11:58, 1.22s/it, lr: 1.0e-04 loss: 3.483e-01] jy: 80%|######## | 2410/3000 [1:09:42<11:58, 1.22s/it, lr: 1.0e-04 loss: 3.483e-01] jy: 80%|######## | 2411/3000 [1:09:42<10:09, 1.04s/it, lr: 1.0e-04 loss: 3.483e-01] jy: 80%|######## | 2411/3000 [1:09:42<10:09, 1.04s/it, lr: 1.0e-04 loss: 3.483e-01] \ No newline at end of file + jy: 75%|#######5 | 2250/3000 [1:05:12<20:19, 1.63s/it, lr: 1.0e-04 loss: 1.705e-01] jy: 75%|#######5 | 2250/3000 [1:05:12<20:19, 1.63s/it, lr: 1.0e-04 loss: 1.705e-01] jy: 75%|#######5 | 2251/3000 [1:05:12<16:00, 1.28s/it, lr: 1.0e-04 loss: 1.705e-01] jy: 75%|#######5 | 2251/3000 [1:05:12<16:00, 1.28s/it, lr: 1.0e-04 loss: 1.705e-01] jy: 75%|#######5 | 2251/3000 [1:05:14<16:00, 1.28s/it, lr: 1.0e-04 loss: 5.153e-01] jy: 75%|#######5 | 2251/3000 [1:05:14<16:00, 1.28s/it, lr: 1.0e-04 loss: 5.153e-01] jy: 75%|#######5 | 2252/3000 [1:05:14<20:06, 1.61s/it, lr: 1.0e-04 loss: 5.153e-01] jy: 75%|#######5 | 2252/3000 [1:05:14<20:06, 1.61s/it, lr: 1.0e-04 loss: 5.153e-01] jy: 75%|#######5 | 2252/3000 [1:05:15<20:06, 1.61s/it, lr: 1.0e-04 loss: 2.807e-01] jy: 75%|#######5 | 2252/3000 [1:05:15<20:06, 1.61s/it, lr: 1.0e-04 loss: 2.807e-01] jy: 75%|#######5 | 2253/3000 [1:05:15<17:37, 1.42s/it, lr: 1.0e-04 loss: 2.807e-01] jy: 75%|#######5 | 2253/3000 [1:05:15<17:37, 1.42s/it, lr: 1.0e-04 loss: 2.807e-01] jy: 75%|#######5 | 2253/3000 [1:05:17<17:37, 1.42s/it, lr: 1.0e-04 loss: 1.068e-01] jy: 75%|#######5 | 2253/3000 [1:05:17<17:37, 1.42s/it, lr: 1.0e-04 loss: 1.068e-01] jy: 75%|#######5 | 2254/3000 [1:05:17<18:18, 1.47s/it, lr: 1.0e-04 loss: 1.068e-01] jy: 75%|#######5 | 2254/3000 [1:05:17<18:18, 1.47s/it, lr: 1.0e-04 loss: 1.068e-01] jy: 75%|#######5 | 2254/3000 [1:05:20<18:18, 1.47s/it, lr: 1.0e-04 loss: 6.404e-02] jy: 75%|#######5 | 2254/3000 [1:05:20<18:18, 1.47s/it, lr: 1.0e-04 loss: 6.404e-02] jy: 75%|#######5 | 2255/3000 [1:05:20<22:17, 1.80s/it, lr: 1.0e-04 loss: 6.404e-02] jy: 75%|#######5 | 2255/3000 [1:05:20<22:17, 1.80s/it, lr: 1.0e-04 loss: 6.404e-02] jy: 75%|#######5 | 2255/3000 [1:05:21<22:17, 1.80s/it, lr: 1.0e-04 loss: 2.320e-01] jy: 75%|#######5 | 2255/3000 [1:05:21<22:17, 1.80s/it, lr: 1.0e-04 loss: 2.320e-01] jy: 75%|#######5 | 2256/3000 [1:05:21<21:39, 1.75s/it, lr: 1.0e-04 loss: 2.320e-01] jy: 75%|#######5 | 2256/3000 [1:05:21<21:39, 1.75s/it, lr: 1.0e-04 loss: 2.320e-01] jy: 75%|#######5 | 2256/3000 [1:05:24<21:39, 1.75s/it, lr: 1.0e-04 loss: 4.885e-01] jy: 75%|#######5 | 2256/3000 [1:05:24<21:39, 1.75s/it, lr: 1.0e-04 loss: 4.885e-01] jy: 75%|#######5 | 2257/3000 [1:05:24<24:46, 2.00s/it, lr: 1.0e-04 loss: 4.885e-01] jy: 75%|#######5 | 2257/3000 [1:05:24<24:46, 2.00s/it, lr: 1.0e-04 loss: 4.885e-01] jy: 75%|#######5 | 2257/3000 [1:05:26<24:46, 2.00s/it, lr: 1.0e-04 loss: 2.842e-02] jy: 75%|#######5 | 2257/3000 [1:05:26<24:46, 2.00s/it, lr: 1.0e-04 loss: 2.842e-02] jy: 75%|#######5 | 2258/3000 [1:05:26<27:01, 2.19s/it, lr: 1.0e-04 loss: 2.842e-02] jy: 75%|#######5 | 2258/3000 [1:05:26<27:01, 2.19s/it, lr: 1.0e-04 loss: 2.842e-02] jy: 75%|#######5 | 2258/3000 [1:05:29<27:01, 2.19s/it, lr: 1.0e-04 loss: 2.209e-01] jy: 75%|#######5 | 2258/3000 [1:05:29<27:01, 2.19s/it, lr: 1.0e-04 loss: 2.209e-01] jy: 75%|#######5 | 2259/3000 [1:05:29<28:36, 2.32s/it, lr: 1.0e-04 loss: 2.209e-01] jy: 75%|#######5 | 2259/3000 [1:05:29<28:36, 2.32s/it, lr: 1.0e-04 loss: 2.209e-01] jy: 75%|#######5 | 2259/3000 [1:05:31<28:36, 2.32s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 75%|#######5 | 2259/3000 [1:05:31<28:36, 2.32s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 75%|#######5 | 2260/3000 [1:05:31<28:34, 2.32s/it, lr: 1.0e-04 loss: 4.859e-01] jy: 75%|#######5 | 2260/3000 [1:05:31<28:34, 2.32s/it, lr: 1.0e-04 loss: 4.859e-01] jy: 75%|#######5 | 2261/3000 [1:05:31<17:47, 1.44s/it, lr: 1.0e-04 loss: 4.859e-01] jy: 75%|#######5 | 2261/3000 [1:05:31<17:47, 1.44s/it, lr: 1.0e-04 loss: 4.859e-01] jy: 75%|#######5 | 2261/3000 [1:05:33<17:47, 1.44s/it, lr: 1.0e-04 loss: 4.190e-01] jy: 75%|#######5 | 2261/3000 [1:05:33<17:47, 1.44s/it, lr: 1.0e-04 loss: 4.190e-01] jy: 75%|#######5 | 2262/3000 [1:05:33<18:18, 1.49s/it, lr: 1.0e-04 loss: 4.190e-01] jy: 75%|#######5 | 2262/3000 [1:05:33<18:18, 1.49s/it, lr: 1.0e-04 loss: 4.190e-01] jy: 75%|#######5 | 2262/3000 [1:05:34<18:18, 1.49s/it, lr: 1.0e-04 loss: 3.349e-01] jy: 75%|#######5 | 2262/3000 [1:05:34<18:18, 1.49s/it, lr: 1.0e-04 loss: 3.349e-01] jy: 75%|#######5 | 2263/3000 [1:05:34<17:00, 1.38s/it, lr: 1.0e-04 loss: 3.349e-01] jy: 75%|#######5 | 2263/3000 [1:05:34<17:00, 1.38s/it, lr: 1.0e-04 loss: 3.349e-01] jy: 75%|#######5 | 2263/3000 [1:05:37<17:00, 1.38s/it, lr: 1.0e-04 loss: 5.037e-01] jy: 75%|#######5 | 2263/3000 [1:05:37<17:00, 1.38s/it, lr: 1.0e-04 loss: 5.037e-01] jy: 75%|#######5 | 2264/3000 [1:05:37<21:07, 1.72s/it, lr: 1.0e-04 loss: 5.037e-01] jy: 75%|#######5 | 2264/3000 [1:05:37<21:07, 1.72s/it, lr: 1.0e-04 loss: 5.037e-01] jy: 75%|#######5 | 2264/3000 [1:05:39<21:07, 1.72s/it, lr: 1.0e-04 loss: 3.929e-01] jy: 75%|#######5 | 2264/3000 [1:05:39<21:07, 1.72s/it, lr: 1.0e-04 loss: 3.929e-01] jy: 76%|#######5 | 2265/3000 [1:05:39<24:11, 1.98s/it, lr: 1.0e-04 loss: 3.929e-01] jy: 76%|#######5 | 2265/3000 [1:05:39<24:11, 1.98s/it, lr: 1.0e-04 loss: 3.929e-01] jy: 76%|#######5 | 2265/3000 [1:05:41<24:11, 1.98s/it, lr: 1.0e-04 loss: 3.969e-01] jy: 76%|#######5 | 2265/3000 [1:05:41<24:11, 1.98s/it, lr: 1.0e-04 loss: 3.969e-01] jy: 76%|#######5 | 2266/3000 [1:05:41<22:50, 1.87s/it, lr: 1.0e-04 loss: 3.969e-01] jy: 76%|#######5 | 2266/3000 [1:05:41<22:50, 1.87s/it, lr: 1.0e-04 loss: 3.969e-01] jy: 76%|#######5 | 2266/3000 [1:05:42<22:50, 1.87s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 76%|#######5 | 2266/3000 [1:05:42<22:50, 1.87s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 76%|#######5 | 2267/3000 [1:05:42<19:17, 1.58s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 76%|#######5 | 2267/3000 [1:05:42<19:17, 1.58s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 76%|#######5 | 2267/3000 [1:05:43<19:17, 1.58s/it, lr: 1.0e-04 loss: 2.980e-01] jy: 76%|#######5 | 2267/3000 [1:05:43<19:17, 1.58s/it, lr: 1.0e-04 loss: 2.980e-01] jy: 76%|#######5 | 2268/3000 [1:05:43<16:47, 1.38s/it, lr: 1.0e-04 loss: 2.980e-01] jy: 76%|#######5 | 2268/3000 [1:05:43<16:47, 1.38s/it, lr: 1.0e-04 loss: 2.980e-01] jy: 76%|#######5 | 2268/3000 [1:05:44<16:47, 1.38s/it, lr: 1.0e-04 loss: 5.504e-01] jy: 76%|#######5 | 2268/3000 [1:05:44<16:47, 1.38s/it, lr: 1.0e-04 loss: 5.504e-01] jy: 76%|#######5 | 2269/3000 [1:05:44<17:48, 1.46s/it, lr: 1.0e-04 loss: 5.504e-01] jy: 76%|#######5 | 2269/3000 [1:05:44<17:48, 1.46s/it, lr: 1.0e-04 loss: 5.504e-01] jy: 76%|#######5 | 2269/3000 [1:05:45<17:48, 1.46s/it, lr: 1.0e-04 loss: 4.291e-02] jy: 76%|#######5 | 2269/3000 [1:05:45<17:48, 1.46s/it, lr: 1.0e-04 loss: 4.291e-02] jy: 76%|#######5 | 2270/3000 [1:05:46<17:46, 1.46s/it, lr: 1.0e-04 loss: 9.681e-02] jy: 76%|#######5 | 2270/3000 [1:05:46<17:46, 1.46s/it, lr: 1.0e-04 loss: 9.681e-02] jy: 76%|#######5 | 2271/3000 [1:05:46<12:01, 1.01it/s, lr: 1.0e-04 loss: 9.681e-02] jy: 76%|#######5 | 2271/3000 [1:05:46<12:01, 1.01it/s, lr: 1.0e-04 loss: 9.681e-02] jy: 76%|#######5 | 2271/3000 [1:05:48<12:01, 1.01it/s, lr: 1.0e-04 loss: 3.683e-01] jy: 76%|#######5 | 2271/3000 [1:05:48<12:01, 1.01it/s, lr: 1.0e-04 loss: 3.683e-01] jy: 76%|#######5 | 2272/3000 [1:05:48<13:30, 1.11s/it, lr: 1.0e-04 loss: 3.683e-01] jy: 76%|#######5 | 2272/3000 [1:05:48<13:30, 1.11s/it, lr: 1.0e-04 loss: 3.683e-01] jy: 76%|#######5 | 2272/3000 [1:05:49<13:30, 1.11s/it, lr: 1.0e-04 loss: 9.999e-02] jy: 76%|#######5 | 2272/3000 [1:05:49<13:30, 1.11s/it, lr: 1.0e-04 loss: 9.999e-02] jy: 76%|#######5 | 2273/3000 [1:05:49<12:41, 1.05s/it, lr: 1.0e-04 loss: 9.999e-02] jy: 76%|#######5 | 2273/3000 [1:05:49<12:41, 1.05s/it, lr: 1.0e-04 loss: 9.999e-02] jy: 76%|#######5 | 2273/3000 [1:05:49<12:41, 1.05s/it, lr: 1.0e-04 loss: 2.190e-01] jy: 76%|#######5 | 2273/3000 [1:05:49<12:41, 1.05s/it, lr: 1.0e-04 loss: 2.190e-01] jy: 76%|#######5 | 2274/3000 [1:05:49<12:02, 1.01it/s, lr: 1.0e-04 loss: 2.190e-01] jy: 76%|#######5 | 2274/3000 [1:05:49<12:02, 1.01it/s, lr: 1.0e-04 loss: 2.190e-01] jy: 76%|#######5 | 2274/3000 [1:05:51<12:02, 1.01it/s, lr: 1.0e-04 loss: 3.513e-01] jy: 76%|#######5 | 2274/3000 [1:05:51<12:02, 1.01it/s, lr: 1.0e-04 loss: 3.513e-01] jy: 76%|#######5 | 2275/3000 [1:05:51<14:09, 1.17s/it, lr: 1.0e-04 loss: 3.513e-01] jy: 76%|#######5 | 2275/3000 [1:05:51<14:09, 1.17s/it, lr: 1.0e-04 loss: 3.513e-01] jy: 76%|#######5 | 2275/3000 [1:05:52<14:09, 1.17s/it, lr: 1.0e-04 loss: 3.321e-01] jy: 76%|#######5 | 2275/3000 [1:05:52<14:09, 1.17s/it, lr: 1.0e-04 loss: 3.321e-01] jy: 76%|#######5 | 2276/3000 [1:05:52<13:05, 1.09s/it, lr: 1.0e-04 loss: 3.321e-01] jy: 76%|#######5 | 2276/3000 [1:05:52<13:05, 1.09s/it, lr: 1.0e-04 loss: 3.321e-01] jy: 76%|#######5 | 2276/3000 [1:05:53<13:05, 1.09s/it, lr: 1.0e-04 loss: 6.727e-01] jy: 76%|#######5 | 2276/3000 [1:05:53<13:05, 1.09s/it, lr: 1.0e-04 loss: 6.727e-01] jy: 76%|#######5 | 2277/3000 [1:05:53<12:24, 1.03s/it, lr: 1.0e-04 loss: 6.727e-01] jy: 76%|#######5 | 2277/3000 [1:05:53<12:24, 1.03s/it, lr: 1.0e-04 loss: 6.727e-01] jy: 76%|#######5 | 2277/3000 [1:05:55<12:24, 1.03s/it, lr: 1.0e-04 loss: 3.293e-01] jy: 76%|#######5 | 2277/3000 [1:05:55<12:24, 1.03s/it, lr: 1.0e-04 loss: 3.293e-01] jy: 76%|#######5 | 2278/3000 [1:05:55<15:18, 1.27s/it, lr: 1.0e-04 loss: 3.293e-01] jy: 76%|#######5 | 2278/3000 [1:05:55<15:18, 1.27s/it, lr: 1.0e-04 loss: 3.293e-01] jy: 76%|#######5 | 2278/3000 [1:05:58<15:18, 1.27s/it, lr: 1.0e-04 loss: 3.790e-01] jy: 76%|#######5 | 2278/3000 [1:05:58<15:18, 1.27s/it, lr: 1.0e-04 loss: 3.790e-01] jy: 76%|#######5 | 2279/3000 [1:05:58<20:04, 1.67s/it, lr: 1.0e-04 loss: 3.790e-01] jy: 76%|#######5 | 2279/3000 [1:05:58<20:04, 1.67s/it, lr: 1.0e-04 loss: 3.790e-01] jy: 76%|#######5 | 2279/3000 [1:06:00<20:04, 1.67s/it, lr: 1.0e-04 loss: 4.740e-01] jy: 76%|#######5 | 2279/3000 [1:06:00<20:04, 1.67s/it, lr: 1.0e-04 loss: 4.740e-01] jy: 76%|#######6 | 2280/3000 [1:06:01<20:03, 1.67s/it, lr: 1.0e-04 loss: 3.486e-01] jy: 76%|#######6 | 2280/3000 [1:06:01<20:03, 1.67s/it, lr: 1.0e-04 loss: 3.486e-01] jy: 76%|#######6 | 2281/3000 [1:06:01<13:14, 1.11s/it, lr: 1.0e-04 loss: 3.486e-01] jy: 76%|#######6 | 2281/3000 [1:06:01<13:14, 1.11s/it, lr: 1.0e-04 loss: 3.486e-01] jy: 76%|#######6 | 2281/3000 [1:06:04<13:14, 1.11s/it, lr: 1.0e-04 loss: 1.271e-01] jy: 76%|#######6 | 2281/3000 [1:06:04<13:14, 1.11s/it, lr: 1.0e-04 loss: 1.271e-01] jy: 76%|#######6 | 2282/3000 [1:06:04<18:15, 1.53s/it, lr: 1.0e-04 loss: 1.271e-01] jy: 76%|#######6 | 2282/3000 [1:06:04<18:15, 1.53s/it, lr: 1.0e-04 loss: 1.271e-01] jy: 76%|#######6 | 2282/3000 [1:06:05<18:15, 1.53s/it, lr: 1.0e-04 loss: 2.238e-01] jy: 76%|#######6 | 2282/3000 [1:06:05<18:15, 1.53s/it, lr: 1.0e-04 loss: 2.238e-01] jy: 76%|#######6 | 2283/3000 [1:06:05<16:10, 1.35s/it, lr: 1.0e-04 loss: 2.238e-01] jy: 76%|#######6 | 2283/3000 [1:06:05<16:10, 1.35s/it, lr: 1.0e-04 loss: 2.238e-01] jy: 76%|#######6 | 2283/3000 [1:06:06<16:10, 1.35s/it, lr: 1.0e-04 loss: 4.430e-01] jy: 76%|#######6 | 2283/3000 [1:06:06<16:10, 1.35s/it, lr: 1.0e-04 loss: 4.430e-01] jy: 76%|#######6 | 2284/3000 [1:06:06<14:34, 1.22s/it, lr: 1.0e-04 loss: 4.430e-01] jy: 76%|#######6 | 2284/3000 [1:06:06<14:34, 1.22s/it, lr: 1.0e-04 loss: 4.430e-01] jy: 76%|#######6 | 2284/3000 [1:06:07<14:34, 1.22s/it, lr: 1.0e-04 loss: 2.886e-02] jy: 76%|#######6 | 2284/3000 [1:06:07<14:34, 1.22s/it, lr: 1.0e-04 loss: 2.886e-02] jy: 76%|#######6 | 2285/3000 [1:06:07<15:34, 1.31s/it, lr: 1.0e-04 loss: 2.886e-02] jy: 76%|#######6 | 2285/3000 [1:06:07<15:34, 1.31s/it, lr: 1.0e-04 loss: 2.886e-02] jy: 76%|#######6 | 2285/3000 [1:06:08<15:34, 1.31s/it, lr: 1.0e-04 loss: 1.931e-01] jy: 76%|#######6 | 2285/3000 [1:06:08<15:34, 1.31s/it, lr: 1.0e-04 loss: 1.931e-01] jy: 76%|#######6 | 2286/3000 [1:06:08<14:05, 1.18s/it, lr: 1.0e-04 loss: 1.931e-01] jy: 76%|#######6 | 2286/3000 [1:06:08<14:05, 1.18s/it, lr: 1.0e-04 loss: 1.931e-01] jy: 76%|#######6 | 2286/3000 [1:06:11<14:05, 1.18s/it, lr: 1.0e-04 loss: 6.574e-02] jy: 76%|#######6 | 2286/3000 [1:06:11<14:05, 1.18s/it, lr: 1.0e-04 loss: 6.574e-02] jy: 76%|#######6 | 2287/3000 [1:06:11<19:39, 1.65s/it, lr: 1.0e-04 loss: 6.574e-02] jy: 76%|#######6 | 2287/3000 [1:06:11<19:39, 1.65s/it, lr: 1.0e-04 loss: 6.574e-02] jy: 76%|#######6 | 2287/3000 [1:06:12<19:39, 1.65s/it, lr: 1.0e-04 loss: 2.645e-02] jy: 76%|#######6 | 2287/3000 [1:06:12<19:39, 1.65s/it, lr: 1.0e-04 loss: 2.645e-02] jy: 76%|#######6 | 2288/3000 [1:06:12<16:56, 1.43s/it, lr: 1.0e-04 loss: 2.645e-02] jy: 76%|#######6 | 2288/3000 [1:06:12<16:56, 1.43s/it, lr: 1.0e-04 loss: 2.645e-02] jy: 76%|#######6 | 2288/3000 [1:06:13<16:56, 1.43s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 76%|#######6 | 2288/3000 [1:06:13<16:56, 1.43s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 76%|#######6 | 2289/3000 [1:06:13<14:56, 1.26s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 76%|#######6 | 2289/3000 [1:06:13<14:56, 1.26s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 76%|#######6 | 2289/3000 [1:06:14<14:56, 1.26s/it, lr: 1.0e-04 loss: 6.294e-01] jy: 76%|#######6 | 2289/3000 [1:06:14<14:56, 1.26s/it, lr: 1.0e-04 loss: 6.294e-01] jy: 76%|#######6 | 2290/3000 [1:06:15<14:55, 1.26s/it, lr: 1.0e-04 loss: 0.000e+00] jy: 76%|#######6 | 2290/3000 [1:06:15<14:55, 1.26s/it, lr: 1.0e-04 loss: 0.000e+00] jy: 76%|#######6 | 2291/3000 [1:06:15<12:27, 1.05s/it, lr: 1.0e-04 loss: 0.000e+00] jy: 76%|#######6 | 2291/3000 [1:06:15<12:27, 1.05s/it, lr: 1.0e-04 loss: 0.000e+00] jy: 76%|#######6 | 2291/3000 [1:06:17<12:27, 1.05s/it, lr: 1.0e-04 loss: 1.386e-01] jy: 76%|#######6 | 2291/3000 [1:06:17<12:27, 1.05s/it, lr: 1.0e-04 loss: 1.386e-01] jy: 76%|#######6 | 2292/3000 [1:06:17<14:42, 1.25s/it, lr: 1.0e-04 loss: 1.386e-01] jy: 76%|#######6 | 2292/3000 [1:06:17<14:42, 1.25s/it, lr: 1.0e-04 loss: 1.386e-01] jy: 76%|#######6 | 2292/3000 [1:06:20<14:42, 1.25s/it, lr: 1.0e-04 loss: 1.679e-01] jy: 76%|#######6 | 2292/3000 [1:06:20<14:42, 1.25s/it, lr: 1.0e-04 loss: 1.679e-01] jy: 76%|#######6 | 2293/3000 [1:06:20<18:54, 1.61s/it, lr: 1.0e-04 loss: 1.679e-01] jy: 76%|#######6 | 2293/3000 [1:06:20<18:54, 1.61s/it, lr: 1.0e-04 loss: 1.679e-01] jy: 76%|#######6 | 2293/3000 [1:06:21<18:54, 1.61s/it, lr: 1.0e-04 loss: 4.141e-01] jy: 76%|#######6 | 2293/3000 [1:06:21<18:54, 1.61s/it, lr: 1.0e-04 loss: 4.141e-01] jy: 76%|#######6 | 2294/3000 [1:06:21<16:29, 1.40s/it, lr: 1.0e-04 loss: 4.141e-01] jy: 76%|#######6 | 2294/3000 [1:06:21<16:29, 1.40s/it, lr: 1.0e-04 loss: 4.141e-01] jy: 76%|#######6 | 2294/3000 [1:06:21<16:29, 1.40s/it, lr: 1.0e-04 loss: 1.065e-01] jy: 76%|#######6 | 2294/3000 [1:06:21<16:29, 1.40s/it, lr: 1.0e-04 loss: 1.065e-01] jy: 76%|#######6 | 2295/3000 [1:06:21<14:41, 1.25s/it, lr: 1.0e-04 loss: 1.065e-01] jy: 76%|#######6 | 2295/3000 [1:06:21<14:41, 1.25s/it, lr: 1.0e-04 loss: 1.065e-01] jy: 76%|#######6 | 2295/3000 [1:06:23<14:41, 1.25s/it, lr: 1.0e-04 loss: 2.995e-01] jy: 76%|#######6 | 2295/3000 [1:06:23<14:41, 1.25s/it, lr: 1.0e-04 loss: 2.995e-01] jy: 77%|#######6 | 2296/3000 [1:06:23<15:55, 1.36s/it, lr: 1.0e-04 loss: 2.995e-01] jy: 77%|#######6 | 2296/3000 [1:06:23<15:55, 1.36s/it, lr: 1.0e-04 loss: 2.995e-01] jy: 77%|#######6 | 2296/3000 [1:06:26<15:55, 1.36s/it, lr: 1.0e-04 loss: 4.474e-01] jy: 77%|#######6 | 2296/3000 [1:06:26<15:55, 1.36s/it, lr: 1.0e-04 loss: 4.474e-01] jy: 77%|#######6 | 2297/3000 [1:06:26<20:12, 1.72s/it, lr: 1.0e-04 loss: 4.474e-01] jy: 77%|#######6 | 2297/3000 [1:06:26<20:12, 1.72s/it, lr: 1.0e-04 loss: 4.474e-01] jy: 77%|#######6 | 2297/3000 [1:06:27<20:12, 1.72s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 77%|#######6 | 2297/3000 [1:06:27<20:12, 1.72s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 77%|#######6 | 2298/3000 [1:06:27<19:50, 1.70s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 77%|#######6 | 2298/3000 [1:06:27<19:50, 1.70s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 77%|#######6 | 2298/3000 [1:06:30<19:50, 1.70s/it, lr: 1.0e-04 loss: 4.578e-01] jy: 77%|#######6 | 2298/3000 [1:06:30<19:50, 1.70s/it, lr: 1.0e-04 loss: 4.578e-01] jy: 77%|#######6 | 2299/3000 [1:06:30<23:02, 1.97s/it, lr: 1.0e-04 loss: 4.578e-01] jy: 77%|#######6 | 2299/3000 [1:06:30<23:02, 1.97s/it, lr: 1.0e-04 loss: 4.578e-01] jy: 77%|#######6 | 2299/3000 [1:06:33<23:02, 1.97s/it, lr: 1.0e-04 loss: 4.425e-01] jy: 77%|#######6 | 2299/3000 [1:06:33<23:02, 1.97s/it, lr: 1.0e-04 loss: 4.425e-01] jy: 77%|#######6 | 2300/3000 [1:06:34<23:00, 1.97s/it, lr: 1.0e-04 loss: 4.776e-01] jy: 77%|#######6 | 2300/3000 [1:06:34<23:00, 1.97s/it, lr: 1.0e-04 loss: 4.776e-01] jy: 77%|#######6 | 2301/3000 [1:06:34<16:48, 1.44s/it, lr: 1.0e-04 loss: 4.776e-01] jy: 77%|#######6 | 2301/3000 [1:06:34<16:48, 1.44s/it, lr: 1.0e-04 loss: 4.776e-01] jy: 77%|#######6 | 2301/3000 [1:06:35<16:48, 1.44s/it, lr: 1.0e-04 loss: 5.443e-01] jy: 77%|#######6 | 2301/3000 [1:06:35<16:48, 1.44s/it, lr: 1.0e-04 loss: 5.443e-01] jy: 77%|#######6 | 2302/3000 [1:06:35<15:05, 1.30s/it, lr: 1.0e-04 loss: 5.443e-01] jy: 77%|#######6 | 2302/3000 [1:06:35<15:05, 1.30s/it, lr: 1.0e-04 loss: 5.443e-01] jy: 77%|#######6 | 2302/3000 [1:06:37<15:05, 1.30s/it, lr: 1.0e-04 loss: 1.244e-01] jy: 77%|#######6 | 2302/3000 [1:06:37<15:05, 1.30s/it, lr: 1.0e-04 loss: 1.244e-01] jy: 77%|#######6 | 2303/3000 [1:06:37<16:04, 1.38s/it, lr: 1.0e-04 loss: 1.244e-01] jy: 77%|#######6 | 2303/3000 [1:06:37<16:04, 1.38s/it, lr: 1.0e-04 loss: 1.244e-01] jy: 77%|#######6 | 2303/3000 [1:06:38<16:04, 1.38s/it, lr: 1.0e-04 loss: 5.456e-01] jy: 77%|#######6 | 2303/3000 [1:06:38<16:04, 1.38s/it, lr: 1.0e-04 loss: 5.456e-01] jy: 77%|#######6 | 2304/3000 [1:06:38<16:24, 1.41s/it, lr: 1.0e-04 loss: 5.456e-01] jy: 77%|#######6 | 2304/3000 [1:06:38<16:24, 1.41s/it, lr: 1.0e-04 loss: 5.456e-01] jy: 77%|#######6 | 2304/3000 [1:06:40<16:24, 1.41s/it, lr: 1.0e-04 loss: 4.360e-01] jy: 77%|#######6 | 2304/3000 [1:06:40<16:24, 1.41s/it, lr: 1.0e-04 loss: 4.360e-01] jy: 77%|#######6 | 2305/3000 [1:06:40<17:53, 1.54s/it, lr: 1.0e-04 loss: 4.360e-01] jy: 77%|#######6 | 2305/3000 [1:06:40<17:53, 1.54s/it, lr: 1.0e-04 loss: 4.360e-01] jy: 77%|#######6 | 2305/3000 [1:06:43<17:53, 1.54s/it, lr: 1.0e-04 loss: 3.303e-01] jy: 77%|#######6 | 2305/3000 [1:06:43<17:53, 1.54s/it, lr: 1.0e-04 loss: 3.303e-01] jy: 77%|#######6 | 2306/3000 [1:06:43<21:26, 1.85s/it, lr: 1.0e-04 loss: 3.303e-01] jy: 77%|#######6 | 2306/3000 [1:06:43<21:26, 1.85s/it, lr: 1.0e-04 loss: 3.303e-01] jy: 77%|#######6 | 2306/3000 [1:06:45<21:26, 1.85s/it, lr: 1.0e-04 loss: 1.863e-01] jy: 77%|#######6 | 2306/3000 [1:06:45<21:26, 1.85s/it, lr: 1.0e-04 loss: 1.863e-01] jy: 77%|#######6 | 2307/3000 [1:06:45<24:00, 2.08s/it, lr: 1.0e-04 loss: 1.863e-01] jy: 77%|#######6 | 2307/3000 [1:06:45<24:00, 2.08s/it, lr: 1.0e-04 loss: 1.863e-01] jy: 77%|#######6 | 2307/3000 [1:06:47<24:00, 2.08s/it, lr: 1.0e-04 loss: 3.780e-01] jy: 77%|#######6 | 2307/3000 [1:06:47<24:00, 2.08s/it, lr: 1.0e-04 loss: 3.780e-01] jy: 77%|#######6 | 2308/3000 [1:06:47<22:26, 1.95s/it, lr: 1.0e-04 loss: 3.780e-01] jy: 77%|#######6 | 2308/3000 [1:06:47<22:26, 1.95s/it, lr: 1.0e-04 loss: 3.780e-01] jy: 77%|#######6 | 2308/3000 [1:06:49<22:26, 1.95s/it, lr: 1.0e-04 loss: 2.993e-01] jy: 77%|#######6 | 2308/3000 [1:06:49<22:26, 1.95s/it, lr: 1.0e-04 loss: 2.993e-01] jy: 77%|#######6 | 2309/3000 [1:06:49<20:58, 1.82s/it, lr: 1.0e-04 loss: 2.993e-01] jy: 77%|#######6 | 2309/3000 [1:06:49<20:58, 1.82s/it, lr: 1.0e-04 loss: 2.993e-01] jy: 77%|#######6 | 2309/3000 [1:06:50<20:58, 1.82s/it, lr: 1.0e-04 loss: 2.558e-01] jy: 77%|#######6 | 2309/3000 [1:06:50<20:58, 1.82s/it, lr: 1.0e-04 loss: 2.558e-01] jy: 77%|#######7 | 2310/3000 [1:06:51<20:56, 1.82s/it, lr: 1.0e-04 loss: 3.508e-01] jy: 77%|#######7 | 2310/3000 [1:06:51<20:56, 1.82s/it, lr: 1.0e-04 loss: 3.508e-01] jy: 77%|#######7 | 2311/3000 [1:06:51<13:36, 1.18s/it, lr: 1.0e-04 loss: 3.508e-01] jy: 77%|#######7 | 2311/3000 [1:06:51<13:36, 1.18s/it, lr: 1.0e-04 loss: 3.508e-01] jy: 77%|#######7 | 2311/3000 [1:06:54<13:36, 1.18s/it, lr: 1.0e-04 loss: 4.603e-01] jy: 77%|#######7 | 2311/3000 [1:06:54<13:36, 1.18s/it, lr: 1.0e-04 loss: 4.603e-01] jy: 77%|#######7 | 2312/3000 [1:06:54<17:38, 1.54s/it, lr: 1.0e-04 loss: 4.603e-01] jy: 77%|#######7 | 2312/3000 [1:06:54<17:38, 1.54s/it, lr: 1.0e-04 loss: 4.603e-01] jy: 77%|#######7 | 2312/3000 [1:06:57<17:38, 1.54s/it, lr: 1.0e-04 loss: 4.475e-01] jy: 77%|#######7 | 2312/3000 [1:06:57<17:38, 1.54s/it, lr: 1.0e-04 loss: 4.475e-01] jy: 77%|#######7 | 2313/3000 [1:06:57<21:23, 1.87s/it, lr: 1.0e-04 loss: 4.475e-01] jy: 77%|#######7 | 2313/3000 [1:06:57<21:23, 1.87s/it, lr: 1.0e-04 loss: 4.475e-01] jy: 77%|#######7 | 2313/3000 [1:06:58<21:23, 1.87s/it, lr: 1.0e-04 loss: 6.922e-01] jy: 77%|#######7 | 2313/3000 [1:06:58<21:23, 1.87s/it, lr: 1.0e-04 loss: 6.922e-01] jy: 77%|#######7 | 2314/3000 [1:06:58<20:36, 1.80s/it, lr: 1.0e-04 loss: 6.922e-01] jy: 77%|#######7 | 2314/3000 [1:06:58<20:36, 1.80s/it, lr: 1.0e-04 loss: 6.922e-01] jy: 77%|#######7 | 2314/3000 [1:06:59<20:36, 1.80s/it, lr: 1.0e-04 loss: 5.251e-01] jy: 77%|#######7 | 2314/3000 [1:06:59<20:36, 1.80s/it, lr: 1.0e-04 loss: 5.251e-01] jy: 77%|#######7 | 2315/3000 [1:06:59<17:33, 1.54s/it, lr: 1.0e-04 loss: 5.251e-01] jy: 77%|#######7 | 2315/3000 [1:06:59<17:33, 1.54s/it, lr: 1.0e-04 loss: 5.251e-01] jy: 77%|#######7 | 2315/3000 [1:07:00<17:33, 1.54s/it, lr: 1.0e-04 loss: 4.309e-01] jy: 77%|#######7 | 2315/3000 [1:07:00<17:33, 1.54s/it, lr: 1.0e-04 loss: 4.309e-01] jy: 77%|#######7 | 2316/3000 [1:07:00<15:19, 1.34s/it, lr: 1.0e-04 loss: 4.309e-01] jy: 77%|#######7 | 2316/3000 [1:07:00<15:19, 1.34s/it, lr: 1.0e-04 loss: 4.309e-01] jy: 77%|#######7 | 2316/3000 [1:07:03<15:19, 1.34s/it, lr: 1.0e-04 loss: 1.328e-01] jy: 77%|#######7 | 2316/3000 [1:07:03<15:19, 1.34s/it, lr: 1.0e-04 loss: 1.328e-01] jy: 77%|#######7 | 2317/3000 [1:07:03<20:10, 1.77s/it, lr: 1.0e-04 loss: 1.328e-01] jy: 77%|#######7 | 2317/3000 [1:07:03<20:10, 1.77s/it, lr: 1.0e-04 loss: 1.328e-01] jy: 77%|#######7 | 2317/3000 [1:07:04<20:10, 1.77s/it, lr: 1.0e-04 loss: 8.238e-02] jy: 77%|#######7 | 2317/3000 [1:07:04<20:10, 1.77s/it, lr: 1.0e-04 loss: 8.238e-02] jy: 77%|#######7 | 2318/3000 [1:07:04<18:22, 1.62s/it, lr: 1.0e-04 loss: 8.238e-02] jy: 77%|#######7 | 2318/3000 [1:07:04<18:22, 1.62s/it, lr: 1.0e-04 loss: 8.238e-02] jy: 77%|#######7 | 2318/3000 [1:07:05<18:22, 1.62s/it, lr: 1.0e-04 loss: 3.402e-01] jy: 77%|#######7 | 2318/3000 [1:07:05<18:22, 1.62s/it, lr: 1.0e-04 loss: 3.402e-01] jy: 77%|#######7 | 2319/3000 [1:07:05<15:56, 1.41s/it, lr: 1.0e-04 loss: 3.402e-01] jy: 77%|#######7 | 2319/3000 [1:07:05<15:56, 1.41s/it, lr: 1.0e-04 loss: 3.402e-01] jy: 77%|#######7 | 2319/3000 [1:07:06<15:56, 1.41s/it, lr: 1.0e-04 loss: 5.240e-01] jy: 77%|#######7 | 2319/3000 [1:07:06<15:56, 1.41s/it, lr: 1.0e-04 loss: 5.240e-01] jy: 77%|#######7 | 2320/3000 [1:07:07<15:55, 1.41s/it, lr: 1.0e-04 loss: 5.502e-01] jy: 77%|#######7 | 2320/3000 [1:07:07<15:55, 1.41s/it, lr: 1.0e-04 loss: 5.502e-01] jy: 77%|#######7 | 2321/3000 [1:07:07<10:53, 1.04it/s, lr: 1.0e-04 loss: 5.502e-01] jy: 77%|#######7 | 2321/3000 [1:07:07<10:53, 1.04it/s, lr: 1.0e-04 loss: 5.502e-01] jy: 77%|#######7 | 2321/3000 [1:07:10<10:53, 1.04it/s, lr: 1.0e-04 loss: 3.549e-01] jy: 77%|#######7 | 2321/3000 [1:07:10<10:53, 1.04it/s, lr: 1.0e-04 loss: 3.549e-01] jy: 77%|#######7 | 2322/3000 [1:07:10<15:31, 1.37s/it, lr: 1.0e-04 loss: 3.549e-01] jy: 77%|#######7 | 2322/3000 [1:07:10<15:31, 1.37s/it, lr: 1.0e-04 loss: 3.549e-01] jy: 77%|#######7 | 2322/3000 [1:07:12<15:31, 1.37s/it, lr: 1.0e-04 loss: 4.201e-01] jy: 77%|#######7 | 2322/3000 [1:07:12<15:31, 1.37s/it, lr: 1.0e-04 loss: 4.201e-01] jy: 77%|#######7 | 2323/3000 [1:07:12<16:14, 1.44s/it, lr: 1.0e-04 loss: 4.201e-01] jy: 77%|#######7 | 2323/3000 [1:07:12<16:14, 1.44s/it, lr: 1.0e-04 loss: 4.201e-01] jy: 77%|#######7 | 2323/3000 [1:07:12<16:14, 1.44s/it, lr: 1.0e-04 loss: 5.171e-01] jy: 77%|#######7 | 2323/3000 [1:07:12<16:14, 1.44s/it, lr: 1.0e-04 loss: 5.171e-01] jy: 77%|#######7 | 2324/3000 [1:07:12<14:26, 1.28s/it, lr: 1.0e-04 loss: 5.171e-01] jy: 77%|#######7 | 2324/3000 [1:07:12<14:26, 1.28s/it, lr: 1.0e-04 loss: 5.171e-01] jy: 77%|#######7 | 2324/3000 [1:07:15<14:26, 1.28s/it, lr: 1.0e-04 loss: 1.431e-01] jy: 77%|#######7 | 2324/3000 [1:07:15<14:26, 1.28s/it, lr: 1.0e-04 loss: 1.431e-01] jy: 78%|#######7 | 2325/3000 [1:07:15<19:13, 1.71s/it, lr: 1.0e-04 loss: 1.431e-01] jy: 78%|#######7 | 2325/3000 [1:07:15<19:13, 1.71s/it, lr: 1.0e-04 loss: 1.431e-01] jy: 78%|#######7 | 2325/3000 [1:07:18<19:13, 1.71s/it, lr: 1.0e-04 loss: 2.330e-01] jy: 78%|#######7 | 2325/3000 [1:07:18<19:13, 1.71s/it, lr: 1.0e-04 loss: 2.330e-01] jy: 78%|#######7 | 2326/3000 [1:07:18<22:39, 2.02s/it, lr: 1.0e-04 loss: 2.330e-01] jy: 78%|#######7 | 2326/3000 [1:07:18<22:39, 2.02s/it, lr: 1.0e-04 loss: 2.330e-01] jy: 78%|#######7 | 2326/3000 [1:07:21<22:39, 2.02s/it, lr: 1.0e-04 loss: 4.824e-01] jy: 78%|#######7 | 2326/3000 [1:07:21<22:39, 2.02s/it, lr: 1.0e-04 loss: 4.824e-01] jy: 78%|#######7 | 2327/3000 [1:07:21<24:37, 2.19s/it, lr: 1.0e-04 loss: 4.824e-01] jy: 78%|#######7 | 2327/3000 [1:07:21<24:37, 2.19s/it, lr: 1.0e-04 loss: 4.824e-01] jy: 78%|#######7 | 2327/3000 [1:07:23<24:37, 2.19s/it, lr: 1.0e-04 loss: 4.821e-02] jy: 78%|#######7 | 2327/3000 [1:07:23<24:37, 2.19s/it, lr: 1.0e-04 loss: 4.821e-02] jy: 78%|#######7 | 2328/3000 [1:07:23<26:01, 2.32s/it, lr: 1.0e-04 loss: 4.821e-02] jy: 78%|#######7 | 2328/3000 [1:07:23<26:01, 2.32s/it, lr: 1.0e-04 loss: 4.821e-02] jy: 78%|#######7 | 2328/3000 [1:07:24<26:01, 2.32s/it, lr: 1.0e-04 loss: 3.708e-02] jy: 78%|#######7 | 2328/3000 [1:07:24<26:01, 2.32s/it, lr: 1.0e-04 loss: 3.708e-02] jy: 78%|#######7 | 2329/3000 [1:07:24<21:09, 1.89s/it, lr: 1.0e-04 loss: 3.708e-02] jy: 78%|#######7 | 2329/3000 [1:07:24<21:09, 1.89s/it, lr: 1.0e-04 loss: 3.708e-02] jy: 78%|#######7 | 2329/3000 [1:07:27<21:09, 1.89s/it, lr: 1.0e-04 loss: 4.997e-01] jy: 78%|#######7 | 2329/3000 [1:07:27<21:09, 1.89s/it, lr: 1.0e-04 loss: 4.997e-01] jy: 78%|#######7 | 2330/3000 [1:07:28<21:07, 1.89s/it, lr: 1.0e-04 loss: 2.512e-01] jy: 78%|#######7 | 2330/3000 [1:07:28<21:07, 1.89s/it, lr: 1.0e-04 loss: 2.512e-01] jy: 78%|#######7 | 2331/3000 [1:07:28<15:16, 1.37s/it, lr: 1.0e-04 loss: 2.512e-01] jy: 78%|#######7 | 2331/3000 [1:07:28<15:16, 1.37s/it, lr: 1.0e-04 loss: 2.512e-01] jy: 78%|#######7 | 2331/3000 [1:07:30<15:16, 1.37s/it, lr: 1.0e-04 loss: 6.639e-01] jy: 78%|#######7 | 2331/3000 [1:07:30<15:16, 1.37s/it, lr: 1.0e-04 loss: 6.639e-01] jy: 78%|#######7 | 2332/3000 [1:07:30<15:57, 1.43s/it, lr: 1.0e-04 loss: 6.639e-01] jy: 78%|#######7 | 2332/3000 [1:07:30<15:57, 1.43s/it, lr: 1.0e-04 loss: 6.639e-01] jy: 78%|#######7 | 2332/3000 [1:07:31<15:57, 1.43s/it, lr: 1.0e-04 loss: 4.117e-01] jy: 78%|#######7 | 2332/3000 [1:07:31<15:57, 1.43s/it, lr: 1.0e-04 loss: 4.117e-01] jy: 78%|#######7 | 2333/3000 [1:07:31<14:57, 1.35s/it, lr: 1.0e-04 loss: 4.117e-01] jy: 78%|#######7 | 2333/3000 [1:07:31<14:57, 1.35s/it, lr: 1.0e-04 loss: 4.117e-01] jy: 78%|#######7 | 2333/3000 [1:07:34<14:57, 1.35s/it, lr: 1.0e-04 loss: 1.469e-01] jy: 78%|#######7 | 2333/3000 [1:07:34<14:57, 1.35s/it, lr: 1.0e-04 loss: 1.469e-01] jy: 78%|#######7 | 2334/3000 [1:07:34<18:47, 1.69s/it, lr: 1.0e-04 loss: 1.469e-01] jy: 78%|#######7 | 2334/3000 [1:07:34<18:47, 1.69s/it, lr: 1.0e-04 loss: 1.469e-01] jy: 78%|#######7 | 2334/3000 [1:07:35<18:47, 1.69s/it, lr: 1.0e-04 loss: 2.994e-01] jy: 78%|#######7 | 2334/3000 [1:07:35<18:47, 1.69s/it, lr: 1.0e-04 loss: 2.994e-01] jy: 78%|#######7 | 2335/3000 [1:07:35<18:15, 1.65s/it, lr: 1.0e-04 loss: 2.994e-01] jy: 78%|#######7 | 2335/3000 [1:07:35<18:15, 1.65s/it, lr: 1.0e-04 loss: 2.994e-01] jy: 78%|#######7 | 2335/3000 [1:07:36<18:15, 1.65s/it, lr: 1.0e-04 loss: 5.181e-01] jy: 78%|#######7 | 2335/3000 [1:07:36<18:15, 1.65s/it, lr: 1.0e-04 loss: 5.181e-01] jy: 78%|#######7 | 2336/3000 [1:07:36<15:44, 1.42s/it, lr: 1.0e-04 loss: 5.181e-01] jy: 78%|#######7 | 2336/3000 [1:07:36<15:44, 1.42s/it, lr: 1.0e-04 loss: 5.181e-01] jy: 78%|#######7 | 2336/3000 [1:07:37<15:44, 1.42s/it, lr: 1.0e-04 loss: 8.501e-02] jy: 78%|#######7 | 2336/3000 [1:07:37<15:44, 1.42s/it, lr: 1.0e-04 loss: 8.501e-02] jy: 78%|#######7 | 2337/3000 [1:07:37<13:54, 1.26s/it, lr: 1.0e-04 loss: 8.501e-02] jy: 78%|#######7 | 2337/3000 [1:07:37<13:54, 1.26s/it, lr: 1.0e-04 loss: 8.501e-02] jy: 78%|#######7 | 2337/3000 [1:07:40<13:54, 1.26s/it, lr: 1.0e-04 loss: 3.846e-01] jy: 78%|#######7 | 2337/3000 [1:07:40<13:54, 1.26s/it, lr: 1.0e-04 loss: 3.846e-01] jy: 78%|#######7 | 2338/3000 [1:07:40<18:18, 1.66s/it, lr: 1.0e-04 loss: 3.846e-01] jy: 78%|#######7 | 2338/3000 [1:07:40<18:18, 1.66s/it, lr: 1.0e-04 loss: 3.846e-01] jy: 78%|#######7 | 2338/3000 [1:07:42<18:18, 1.66s/it, lr: 1.0e-04 loss: 6.512e-01] jy: 78%|#######7 | 2338/3000 [1:07:42<18:18, 1.66s/it, lr: 1.0e-04 loss: 6.512e-01] jy: 78%|#######7 | 2339/3000 [1:07:42<21:25, 1.95s/it, lr: 1.0e-04 loss: 6.512e-01] jy: 78%|#######7 | 2339/3000 [1:07:42<21:25, 1.95s/it, lr: 1.0e-04 loss: 6.512e-01] jy: 78%|#######7 | 2339/3000 [1:07:43<21:25, 1.95s/it, lr: 1.0e-04 loss: 5.993e-01] jy: 78%|#######7 | 2339/3000 [1:07:43<21:25, 1.95s/it, lr: 1.0e-04 loss: 5.993e-01] jy: 78%|#######8 | 2340/3000 [1:07:45<21:24, 1.95s/it, lr: 1.0e-04 loss: 9.332e-02] jy: 78%|#######8 | 2340/3000 [1:07:45<21:24, 1.95s/it, lr: 1.0e-04 loss: 9.332e-02] jy: 78%|#######8 | 2341/3000 [1:07:45<15:25, 1.40s/it, lr: 1.0e-04 loss: 9.332e-02] jy: 78%|#######8 | 2341/3000 [1:07:45<15:25, 1.40s/it, lr: 1.0e-04 loss: 9.332e-02] jy: 78%|#######8 | 2341/3000 [1:07:45<15:25, 1.40s/it, lr: 1.0e-04 loss: 6.659e-02] jy: 78%|#######8 | 2341/3000 [1:07:45<15:25, 1.40s/it, lr: 1.0e-04 loss: 6.659e-02] jy: 78%|#######8 | 2342/3000 [1:07:45<13:55, 1.27s/it, lr: 1.0e-04 loss: 6.659e-02] jy: 78%|#######8 | 2342/3000 [1:07:45<13:55, 1.27s/it, lr: 1.0e-04 loss: 6.659e-02] jy: 78%|#######8 | 2342/3000 [1:07:47<13:55, 1.27s/it, lr: 1.0e-04 loss: 2.643e-01] jy: 78%|#######8 | 2342/3000 [1:07:47<13:55, 1.27s/it, lr: 1.0e-04 loss: 2.643e-01] jy: 78%|#######8 | 2343/3000 [1:07:47<14:37, 1.34s/it, lr: 1.0e-04 loss: 2.643e-01] jy: 78%|#######8 | 2343/3000 [1:07:47<14:37, 1.34s/it, lr: 1.0e-04 loss: 2.643e-01] jy: 78%|#######8 | 2343/3000 [1:07:49<14:37, 1.34s/it, lr: 1.0e-04 loss: 4.887e-01] jy: 78%|#######8 | 2343/3000 [1:07:49<14:37, 1.34s/it, lr: 1.0e-04 loss: 4.887e-01] jy: 78%|#######8 | 2344/3000 [1:07:49<15:28, 1.41s/it, lr: 1.0e-04 loss: 4.887e-01] jy: 78%|#######8 | 2344/3000 [1:07:49<15:28, 1.41s/it, lr: 1.0e-04 loss: 4.887e-01] jy: 78%|#######8 | 2344/3000 [1:07:51<15:28, 1.41s/it, lr: 1.0e-04 loss: 5.379e-01] jy: 78%|#######8 | 2344/3000 [1:07:51<15:28, 1.41s/it, lr: 1.0e-04 loss: 5.379e-01] jy: 78%|#######8 | 2345/3000 [1:07:51<19:31, 1.79s/it, lr: 1.0e-04 loss: 5.379e-01] jy: 78%|#######8 | 2345/3000 [1:07:51<19:31, 1.79s/it, lr: 1.0e-04 loss: 5.379e-01] jy: 78%|#######8 | 2345/3000 [1:07:53<19:31, 1.79s/it, lr: 1.0e-04 loss: 2.052e-01] jy: 78%|#######8 | 2345/3000 [1:07:53<19:31, 1.79s/it, lr: 1.0e-04 loss: 2.052e-01] jy: 78%|#######8 | 2346/3000 [1:07:53<19:00, 1.74s/it, lr: 1.0e-04 loss: 2.052e-01] jy: 78%|#######8 | 2346/3000 [1:07:53<19:00, 1.74s/it, lr: 1.0e-04 loss: 2.052e-01] jy: 78%|#######8 | 2346/3000 [1:07:55<19:00, 1.74s/it, lr: 1.0e-04 loss: 2.587e-02] jy: 78%|#######8 | 2346/3000 [1:07:55<19:00, 1.74s/it, lr: 1.0e-04 loss: 2.587e-02] jy: 78%|#######8 | 2347/3000 [1:07:55<19:18, 1.77s/it, lr: 1.0e-04 loss: 2.587e-02] jy: 78%|#######8 | 2347/3000 [1:07:55<19:18, 1.77s/it, lr: 1.0e-04 loss: 2.587e-02] jy: 78%|#######8 | 2347/3000 [1:07:57<19:18, 1.77s/it, lr: 1.0e-04 loss: 5.557e-01] jy: 78%|#######8 | 2347/3000 [1:07:57<19:18, 1.77s/it, lr: 1.0e-04 loss: 5.557e-01] jy: 78%|#######8 | 2348/3000 [1:07:57<22:00, 2.02s/it, lr: 1.0e-04 loss: 5.557e-01] jy: 78%|#######8 | 2348/3000 [1:07:57<22:00, 2.02s/it, lr: 1.0e-04 loss: 5.557e-01] jy: 78%|#######8 | 2348/3000 [1:08:00<22:00, 2.02s/it, lr: 1.0e-04 loss: 5.285e-01] jy: 78%|#######8 | 2348/3000 [1:08:00<22:00, 2.02s/it, lr: 1.0e-04 loss: 5.285e-01] jy: 78%|#######8 | 2349/3000 [1:08:00<24:29, 2.26s/it, lr: 1.0e-04 loss: 5.285e-01] jy: 78%|#######8 | 2349/3000 [1:08:00<24:29, 2.26s/it, lr: 1.0e-04 loss: 5.285e-01] jy: 78%|#######8 | 2349/3000 [1:08:01<24:29, 2.26s/it, lr: 1.0e-04 loss: 6.814e-02] jy: 78%|#######8 | 2349/3000 [1:08:01<24:29, 2.26s/it, lr: 1.0e-04 loss: 6.814e-02] jy: 78%|#######8 | 2350/3000 [1:08:04<24:26, 2.26s/it, lr: 1.0e-04 loss: 6.107e-01] jy: 78%|#######8 | 2350/3000 [1:08:04<24:26, 2.26s/it, lr: 1.0e-04 loss: 6.107e-01] jy: 78%|#######8 | 2351/3000 [1:08:04<20:17, 1.88s/it, lr: 1.0e-04 loss: 6.107e-01] jy: 78%|#######8 | 2351/3000 [1:08:04<20:17, 1.88s/it, lr: 1.0e-04 loss: 6.107e-01] jy: 78%|#######8 | 2351/3000 [1:08:05<20:17, 1.88s/it, lr: 1.0e-04 loss: 1.235e-01] jy: 78%|#######8 | 2351/3000 [1:08:05<20:17, 1.88s/it, lr: 1.0e-04 loss: 1.235e-01] jy: 78%|#######8 | 2352/3000 [1:08:05<17:31, 1.62s/it, lr: 1.0e-04 loss: 1.235e-01] jy: 78%|#######8 | 2352/3000 [1:08:05<17:31, 1.62s/it, lr: 1.0e-04 loss: 1.235e-01] jy: 78%|#######8 | 2352/3000 [1:08:06<17:31, 1.62s/it, lr: 1.0e-04 loss: 3.633e-01] jy: 78%|#######8 | 2352/3000 [1:08:06<17:31, 1.62s/it, lr: 1.0e-04 loss: 3.633e-01] jy: 78%|#######8 | 2353/3000 [1:08:06<17:17, 1.60s/it, lr: 1.0e-04 loss: 3.633e-01] jy: 78%|#######8 | 2353/3000 [1:08:06<17:17, 1.60s/it, lr: 1.0e-04 loss: 3.633e-01] jy: 78%|#######8 | 2353/3000 [1:08:08<17:17, 1.60s/it, lr: 1.0e-04 loss: 1.383e-01] jy: 78%|#######8 | 2353/3000 [1:08:08<17:17, 1.60s/it, lr: 1.0e-04 loss: 1.383e-01] jy: 78%|#######8 | 2354/3000 [1:08:08<16:56, 1.57s/it, lr: 1.0e-04 loss: 1.383e-01] jy: 78%|#######8 | 2354/3000 [1:08:08<16:56, 1.57s/it, lr: 1.0e-04 loss: 1.383e-01] jy: 78%|#######8 | 2354/3000 [1:08:09<16:56, 1.57s/it, lr: 1.0e-04 loss: 2.513e-01] jy: 78%|#######8 | 2354/3000 [1:08:09<16:56, 1.57s/it, lr: 1.0e-04 loss: 2.513e-01] jy: 78%|#######8 | 2355/3000 [1:08:09<14:47, 1.38s/it, lr: 1.0e-04 loss: 2.513e-01] jy: 78%|#######8 | 2355/3000 [1:08:09<14:47, 1.38s/it, lr: 1.0e-04 loss: 2.513e-01] jy: 78%|#######8 | 2355/3000 [1:08:10<14:47, 1.38s/it, lr: 1.0e-04 loss: 2.414e-01] jy: 78%|#######8 | 2355/3000 [1:08:10<14:47, 1.38s/it, lr: 1.0e-04 loss: 2.414e-01] jy: 79%|#######8 | 2356/3000 [1:08:10<15:31, 1.45s/it, lr: 1.0e-04 loss: 2.414e-01] jy: 79%|#######8 | 2356/3000 [1:08:10<15:31, 1.45s/it, lr: 1.0e-04 loss: 2.414e-01] jy: 79%|#######8 | 2356/3000 [1:08:11<15:31, 1.45s/it, lr: 1.0e-04 loss: 1.074e-01] jy: 79%|#######8 | 2356/3000 [1:08:11<15:31, 1.45s/it, lr: 1.0e-04 loss: 1.074e-01] jy: 79%|#######8 | 2357/3000 [1:08:11<13:41, 1.28s/it, lr: 1.0e-04 loss: 1.074e-01] jy: 79%|#######8 | 2357/3000 [1:08:11<13:41, 1.28s/it, lr: 1.0e-04 loss: 1.074e-01] jy: 79%|#######8 | 2357/3000 [1:08:12<13:41, 1.28s/it, lr: 1.0e-04 loss: 3.233e-01] jy: 79%|#######8 | 2357/3000 [1:08:12<13:41, 1.28s/it, lr: 1.0e-04 loss: 3.233e-01] jy: 79%|#######8 | 2358/3000 [1:08:12<12:13, 1.14s/it, lr: 1.0e-04 loss: 3.233e-01] jy: 79%|#######8 | 2358/3000 [1:08:12<12:13, 1.14s/it, lr: 1.0e-04 loss: 3.233e-01] jy: 79%|#######8 | 2358/3000 [1:08:15<12:13, 1.14s/it, lr: 1.0e-04 loss: 2.633e-01] jy: 79%|#######8 | 2358/3000 [1:08:15<12:13, 1.14s/it, lr: 1.0e-04 loss: 2.633e-01] jy: 79%|#######8 | 2359/3000 [1:08:15<17:28, 1.64s/it, lr: 1.0e-04 loss: 2.633e-01] jy: 79%|#######8 | 2359/3000 [1:08:15<17:28, 1.64s/it, lr: 1.0e-04 loss: 2.633e-01] jy: 79%|#######8 | 2359/3000 [1:08:17<17:28, 1.64s/it, lr: 1.0e-04 loss: 4.397e-01] jy: 79%|#######8 | 2359/3000 [1:08:17<17:28, 1.64s/it, lr: 1.0e-04 loss: 4.397e-01] jy: 79%|#######8 | 2360/3000 [1:08:20<17:26, 1.64s/it, lr: 1.0e-04 loss: 2.461e-01] jy: 79%|#######8 | 2360/3000 [1:08:20<17:26, 1.64s/it, lr: 1.0e-04 loss: 2.461e-01] jy: 79%|#######8 | 2361/3000 [1:08:20<16:19, 1.53s/it, lr: 1.0e-04 loss: 2.461e-01] jy: 79%|#######8 | 2361/3000 [1:08:20<16:19, 1.53s/it, lr: 1.0e-04 loss: 2.461e-01] jy: 79%|#######8 | 2361/3000 [1:08:20<16:19, 1.53s/it, lr: 1.0e-04 loss: 4.784e-01] jy: 79%|#######8 | 2361/3000 [1:08:20<16:19, 1.53s/it, lr: 1.0e-04 loss: 4.784e-01] jy: 79%|#######8 | 2362/3000 [1:08:20<14:25, 1.36s/it, lr: 1.0e-04 loss: 4.784e-01] jy: 79%|#######8 | 2362/3000 [1:08:20<14:25, 1.36s/it, lr: 1.0e-04 loss: 4.784e-01] jy: 79%|#######8 | 2362/3000 [1:08:22<14:25, 1.36s/it, lr: 1.0e-04 loss: 1.001e-01] jy: 79%|#######8 | 2362/3000 [1:08:22<14:25, 1.36s/it, lr: 1.0e-04 loss: 1.001e-01] jy: 79%|#######8 | 2363/3000 [1:08:22<15:09, 1.43s/it, lr: 1.0e-04 loss: 1.001e-01] jy: 79%|#######8 | 2363/3000 [1:08:22<15:09, 1.43s/it, lr: 1.0e-04 loss: 1.001e-01] jy: 79%|#######8 | 2363/3000 [1:08:25<15:09, 1.43s/it, lr: 1.0e-04 loss: 3.804e-01] jy: 79%|#######8 | 2363/3000 [1:08:25<15:09, 1.43s/it, lr: 1.0e-04 loss: 3.804e-01] jy: 79%|#######8 | 2364/3000 [1:08:25<19:06, 1.80s/it, lr: 1.0e-04 loss: 3.804e-01] jy: 79%|#######8 | 2364/3000 [1:08:25<19:06, 1.80s/it, lr: 1.0e-04 loss: 3.804e-01] jy: 79%|#######8 | 2364/3000 [1:08:27<19:06, 1.80s/it, lr: 1.0e-04 loss: 1.166e-01] jy: 79%|#######8 | 2364/3000 [1:08:27<19:06, 1.80s/it, lr: 1.0e-04 loss: 1.166e-01] jy: 79%|#######8 | 2365/3000 [1:08:27<21:31, 2.03s/it, lr: 1.0e-04 loss: 1.166e-01] jy: 79%|#######8 | 2365/3000 [1:08:27<21:31, 2.03s/it, lr: 1.0e-04 loss: 1.166e-01] jy: 79%|#######8 | 2365/3000 [1:08:30<21:31, 2.03s/it, lr: 1.0e-04 loss: 3.603e-01] jy: 79%|#######8 | 2365/3000 [1:08:30<21:31, 2.03s/it, lr: 1.0e-04 loss: 3.603e-01] jy: 79%|#######8 | 2366/3000 [1:08:30<23:17, 2.20s/it, lr: 1.0e-04 loss: 3.603e-01] jy: 79%|#######8 | 2366/3000 [1:08:30<23:17, 2.20s/it, lr: 1.0e-04 loss: 3.603e-01] jy: 79%|#######8 | 2366/3000 [1:08:32<23:17, 2.20s/it, lr: 1.0e-04 loss: 1.179e-01] jy: 79%|#######8 | 2366/3000 [1:08:32<23:17, 2.20s/it, lr: 1.0e-04 loss: 1.179e-01] jy: 79%|#######8 | 2367/3000 [1:08:32<21:30, 2.04s/it, lr: 1.0e-04 loss: 1.179e-01] jy: 79%|#######8 | 2367/3000 [1:08:32<21:30, 2.04s/it, lr: 1.0e-04 loss: 1.179e-01] jy: 79%|#######8 | 2367/3000 [1:08:33<21:30, 2.04s/it, lr: 1.0e-04 loss: 1.735e-01] jy: 79%|#######8 | 2367/3000 [1:08:33<21:30, 2.04s/it, lr: 1.0e-04 loss: 1.735e-01] jy: 79%|#######8 | 2368/3000 [1:08:33<19:58, 1.90s/it, lr: 1.0e-04 loss: 1.735e-01] jy: 79%|#######8 | 2368/3000 [1:08:33<19:58, 1.90s/it, lr: 1.0e-04 loss: 1.735e-01] jy: 79%|#######8 | 2368/3000 [1:08:36<19:58, 1.90s/it, lr: 1.0e-04 loss: 3.767e-01] jy: 79%|#######8 | 2368/3000 [1:08:36<19:58, 1.90s/it, lr: 1.0e-04 loss: 3.767e-01] jy: 79%|#######8 | 2369/3000 [1:08:36<22:13, 2.11s/it, lr: 1.0e-04 loss: 3.767e-01] jy: 79%|#######8 | 2369/3000 [1:08:36<22:13, 2.11s/it, lr: 1.0e-04 loss: 3.767e-01] jy: 79%|#######8 | 2369/3000 [1:08:39<22:13, 2.11s/it, lr: 1.0e-04 loss: 2.655e-01] jy: 79%|#######8 | 2369/3000 [1:08:39<22:13, 2.11s/it, lr: 1.0e-04 loss: 2.655e-01] jy: 79%|#######9 | 2370/3000 [1:08:40<22:11, 2.11s/it, lr: 1.0e-04 loss: 5.668e-01] jy: 79%|#######9 | 2370/3000 [1:08:40<22:11, 2.11s/it, lr: 1.0e-04 loss: 5.668e-01] jy: 79%|#######9 | 2371/3000 [1:08:40<14:09, 1.35s/it, lr: 1.0e-04 loss: 5.668e-01] jy: 79%|#######9 | 2371/3000 [1:08:40<14:09, 1.35s/it, lr: 1.0e-04 loss: 5.668e-01] jy: 79%|#######9 | 2371/3000 [1:08:41<14:09, 1.35s/it, lr: 1.0e-04 loss: 2.042e-01] jy: 79%|#######9 | 2371/3000 [1:08:41<14:09, 1.35s/it, lr: 1.0e-04 loss: 2.042e-01] jy: 79%|#######9 | 2372/3000 [1:08:41<13:02, 1.25s/it, lr: 1.0e-04 loss: 2.042e-01] jy: 79%|#######9 | 2372/3000 [1:08:41<13:02, 1.25s/it, lr: 1.0e-04 loss: 2.042e-01] jy: 79%|#######9 | 2372/3000 [1:08:42<13:02, 1.25s/it, lr: 1.0e-04 loss: 3.398e-01] jy: 79%|#######9 | 2372/3000 [1:08:42<13:02, 1.25s/it, lr: 1.0e-04 loss: 3.398e-01] jy: 79%|#######9 | 2373/3000 [1:08:42<12:34, 1.20s/it, lr: 1.0e-04 loss: 3.398e-01] jy: 79%|#######9 | 2373/3000 [1:08:42<12:34, 1.20s/it, lr: 1.0e-04 loss: 3.398e-01] jy: 79%|#######9 | 2373/3000 [1:08:43<12:34, 1.20s/it, lr: 1.0e-04 loss: 5.072e-01] jy: 79%|#######9 | 2373/3000 [1:08:43<12:34, 1.20s/it, lr: 1.0e-04 loss: 5.072e-01] jy: 79%|#######9 | 2374/3000 [1:08:43<13:43, 1.32s/it, lr: 1.0e-04 loss: 5.072e-01] jy: 79%|#######9 | 2374/3000 [1:08:43<13:43, 1.32s/it, lr: 1.0e-04 loss: 5.072e-01] jy: 79%|#######9 | 2374/3000 [1:08:45<13:43, 1.32s/it, lr: 1.0e-04 loss: 3.341e-02] jy: 79%|#######9 | 2374/3000 [1:08:45<13:43, 1.32s/it, lr: 1.0e-04 loss: 3.341e-02] jy: 79%|#######9 | 2375/3000 [1:08:45<14:16, 1.37s/it, lr: 1.0e-04 loss: 3.341e-02] jy: 79%|#######9 | 2375/3000 [1:08:45<14:16, 1.37s/it, lr: 1.0e-04 loss: 3.341e-02] jy: 79%|#######9 | 2375/3000 [1:08:47<14:16, 1.37s/it, lr: 1.0e-04 loss: 1.499e-01] jy: 79%|#######9 | 2375/3000 [1:08:47<14:16, 1.37s/it, lr: 1.0e-04 loss: 1.499e-01] jy: 79%|#######9 | 2376/3000 [1:08:47<15:03, 1.45s/it, lr: 1.0e-04 loss: 1.499e-01] jy: 79%|#######9 | 2376/3000 [1:08:47<15:03, 1.45s/it, lr: 1.0e-04 loss: 1.499e-01] jy: 79%|#######9 | 2376/3000 [1:08:48<15:03, 1.45s/it, lr: 1.0e-04 loss: 1.592e-01] jy: 79%|#######9 | 2376/3000 [1:08:48<15:03, 1.45s/it, lr: 1.0e-04 loss: 1.592e-01] jy: 79%|#######9 | 2377/3000 [1:08:48<15:33, 1.50s/it, lr: 1.0e-04 loss: 1.592e-01] jy: 79%|#######9 | 2377/3000 [1:08:48<15:33, 1.50s/it, lr: 1.0e-04 loss: 1.592e-01] jy: 79%|#######9 | 2377/3000 [1:08:50<15:33, 1.50s/it, lr: 1.0e-04 loss: 6.075e-01] jy: 79%|#######9 | 2377/3000 [1:08:50<15:33, 1.50s/it, lr: 1.0e-04 loss: 6.075e-01] jy: 79%|#######9 | 2378/3000 [1:08:50<15:55, 1.54s/it, lr: 1.0e-04 loss: 6.075e-01] jy: 79%|#######9 | 2378/3000 [1:08:50<15:55, 1.54s/it, lr: 1.0e-04 loss: 6.075e-01] jy: 79%|#######9 | 2378/3000 [1:08:53<15:55, 1.54s/it, lr: 1.0e-04 loss: 4.646e-01] jy: 79%|#######9 | 2378/3000 [1:08:53<15:55, 1.54s/it, lr: 1.0e-04 loss: 4.646e-01] jy: 79%|#######9 | 2379/3000 [1:08:53<19:13, 1.86s/it, lr: 1.0e-04 loss: 4.646e-01] jy: 79%|#######9 | 2379/3000 [1:08:53<19:13, 1.86s/it, lr: 1.0e-04 loss: 4.646e-01] jy: 79%|#######9 | 2379/3000 [1:08:53<19:13, 1.86s/it, lr: 1.0e-04 loss: 1.953e-01] jy: 79%|#######9 | 2379/3000 [1:08:53<19:13, 1.86s/it, lr: 1.0e-04 loss: 1.953e-01] jy: 79%|#######9 | 2380/3000 [1:08:56<19:11, 1.86s/it, lr: 1.0e-04 loss: 4.572e-01] jy: 79%|#######9 | 2380/3000 [1:08:56<19:11, 1.86s/it, lr: 1.0e-04 loss: 4.572e-01] jy: 79%|#######9 | 2381/3000 [1:08:56<17:02, 1.65s/it, lr: 1.0e-04 loss: 4.572e-01] jy: 79%|#######9 | 2381/3000 [1:08:56<17:02, 1.65s/it, lr: 1.0e-04 loss: 4.572e-01] jy: 79%|#######9 | 2381/3000 [1:08:58<17:02, 1.65s/it, lr: 1.0e-04 loss: 1.217e-01] jy: 79%|#######9 | 2381/3000 [1:08:58<17:02, 1.65s/it, lr: 1.0e-04 loss: 1.217e-01] jy: 79%|#######9 | 2382/3000 [1:08:58<16:57, 1.65s/it, lr: 1.0e-04 loss: 1.217e-01] jy: 79%|#######9 | 2382/3000 [1:08:58<16:57, 1.65s/it, lr: 1.0e-04 loss: 1.217e-01] jy: 79%|#######9 | 2382/3000 [1:08:59<16:57, 1.65s/it, lr: 1.0e-04 loss: 5.658e-02] jy: 79%|#######9 | 2382/3000 [1:08:59<16:57, 1.65s/it, lr: 1.0e-04 loss: 5.658e-02] jy: 79%|#######9 | 2383/3000 [1:08:59<16:35, 1.61s/it, lr: 1.0e-04 loss: 5.658e-02] jy: 79%|#######9 | 2383/3000 [1:08:59<16:35, 1.61s/it, lr: 1.0e-04 loss: 5.658e-02] jy: 79%|#######9 | 2383/3000 [1:09:02<16:35, 1.61s/it, lr: 1.0e-04 loss: 2.645e-01] jy: 79%|#######9 | 2383/3000 [1:09:02<16:35, 1.61s/it, lr: 1.0e-04 loss: 2.645e-01] jy: 79%|#######9 | 2384/3000 [1:09:02<19:22, 1.89s/it, lr: 1.0e-04 loss: 2.645e-01] jy: 79%|#######9 | 2384/3000 [1:09:02<19:22, 1.89s/it, lr: 1.0e-04 loss: 2.645e-01] jy: 79%|#######9 | 2384/3000 [1:09:04<19:22, 1.89s/it, lr: 1.0e-04 loss: 1.102e-01] jy: 79%|#######9 | 2384/3000 [1:09:04<19:22, 1.89s/it, lr: 1.0e-04 loss: 1.102e-01] jy: 80%|#######9 | 2385/3000 [1:09:04<18:17, 1.78s/it, lr: 1.0e-04 loss: 1.102e-01] jy: 80%|#######9 | 2385/3000 [1:09:04<18:17, 1.78s/it, lr: 1.0e-04 loss: 1.102e-01] jy: 80%|#######9 | 2385/3000 [1:09:04<18:17, 1.78s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2385/3000 [1:09:04<18:17, 1.78s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2386/3000 [1:09:04<15:33, 1.52s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2386/3000 [1:09:04<15:33, 1.52s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2386/3000 [1:09:05<15:33, 1.52s/it, lr: 1.0e-04 loss: 7.385e-01] jy: 80%|#######9 | 2386/3000 [1:09:05<15:33, 1.52s/it, lr: 1.0e-04 loss: 7.385e-01] jy: 80%|#######9 | 2387/3000 [1:09:05<13:33, 1.33s/it, lr: 1.0e-04 loss: 7.385e-01] jy: 80%|#######9 | 2387/3000 [1:09:05<13:33, 1.33s/it, lr: 1.0e-04 loss: 7.385e-01] jy: 80%|#######9 | 2387/3000 [1:09:07<13:33, 1.33s/it, lr: 1.0e-04 loss: 2.122e-01] jy: 80%|#######9 | 2387/3000 [1:09:07<13:33, 1.33s/it, lr: 1.0e-04 loss: 2.122e-01] jy: 80%|#######9 | 2388/3000 [1:09:07<15:07, 1.48s/it, lr: 1.0e-04 loss: 2.122e-01] jy: 80%|#######9 | 2388/3000 [1:09:07<15:07, 1.48s/it, lr: 1.0e-04 loss: 2.122e-01] jy: 80%|#######9 | 2388/3000 [1:09:08<15:07, 1.48s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 80%|#######9 | 2388/3000 [1:09:08<15:07, 1.48s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 80%|#######9 | 2389/3000 [1:09:08<13:13, 1.30s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 80%|#######9 | 2389/3000 [1:09:08<13:13, 1.30s/it, lr: 1.0e-04 loss: 2.882e-01] jy: 80%|#######9 | 2389/3000 [1:09:10<13:13, 1.30s/it, lr: 1.0e-04 loss: 5.407e-01] jy: 80%|#######9 | 2389/3000 [1:09:10<13:13, 1.30s/it, lr: 1.0e-04 loss: 5.407e-01] jy: 80%|#######9 | 2390/3000 [1:09:10<13:11, 1.30s/it, lr: 1.0e-04 loss: 5.632e-01] jy: 80%|#######9 | 2390/3000 [1:09:10<13:11, 1.30s/it, lr: 1.0e-04 loss: 5.632e-01] jy: 80%|#######9 | 2391/3000 [1:09:10<09:09, 1.11it/s, lr: 1.0e-04 loss: 5.632e-01] jy: 80%|#######9 | 2391/3000 [1:09:10<09:09, 1.11it/s, lr: 1.0e-04 loss: 5.632e-01] jy: 80%|#######9 | 2391/3000 [1:09:12<09:09, 1.11it/s, lr: 1.0e-04 loss: 1.864e-01] jy: 80%|#######9 | 2391/3000 [1:09:12<09:09, 1.11it/s, lr: 1.0e-04 loss: 1.864e-01] jy: 80%|#######9 | 2392/3000 [1:09:12<10:41, 1.05s/it, lr: 1.0e-04 loss: 1.864e-01] jy: 80%|#######9 | 2392/3000 [1:09:12<10:41, 1.05s/it, lr: 1.0e-04 loss: 1.864e-01] jy: 80%|#######9 | 2392/3000 [1:09:15<10:41, 1.05s/it, lr: 1.0e-04 loss: 4.914e-01] jy: 80%|#######9 | 2392/3000 [1:09:15<10:41, 1.05s/it, lr: 1.0e-04 loss: 4.914e-01] jy: 80%|#######9 | 2393/3000 [1:09:15<15:17, 1.51s/it, lr: 1.0e-04 loss: 4.914e-01] jy: 80%|#######9 | 2393/3000 [1:09:15<15:17, 1.51s/it, lr: 1.0e-04 loss: 4.914e-01] jy: 80%|#######9 | 2393/3000 [1:09:16<15:17, 1.51s/it, lr: 1.0e-04 loss: 1.634e-01] jy: 80%|#######9 | 2393/3000 [1:09:16<15:17, 1.51s/it, lr: 1.0e-04 loss: 1.634e-01] jy: 80%|#######9 | 2394/3000 [1:09:16<13:29, 1.34s/it, lr: 1.0e-04 loss: 1.634e-01] jy: 80%|#######9 | 2394/3000 [1:09:16<13:29, 1.34s/it, lr: 1.0e-04 loss: 1.634e-01] jy: 80%|#######9 | 2394/3000 [1:09:18<13:29, 1.34s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2394/3000 [1:09:18<13:29, 1.34s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2395/3000 [1:09:18<17:07, 1.70s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2395/3000 [1:09:18<17:07, 1.70s/it, lr: 1.0e-04 loss: 4.660e-01] jy: 80%|#######9 | 2395/3000 [1:09:19<17:07, 1.70s/it, lr: 1.0e-04 loss: 4.601e-01] jy: 80%|#######9 | 2395/3000 [1:09:19<17:07, 1.70s/it, lr: 1.0e-04 loss: 4.601e-01] jy: 80%|#######9 | 2396/3000 [1:09:19<14:42, 1.46s/it, lr: 1.0e-04 loss: 4.601e-01] jy: 80%|#######9 | 2396/3000 [1:09:19<14:42, 1.46s/it, lr: 1.0e-04 loss: 4.601e-01] jy: 80%|#######9 | 2396/3000 [1:09:22<14:42, 1.46s/it, lr: 1.0e-04 loss: 9.151e-02] jy: 80%|#######9 | 2396/3000 [1:09:22<14:42, 1.46s/it, lr: 1.0e-04 loss: 9.151e-02] jy: 80%|#######9 | 2397/3000 [1:09:22<18:04, 1.80s/it, lr: 1.0e-04 loss: 9.151e-02] jy: 80%|#######9 | 2397/3000 [1:09:22<18:04, 1.80s/it, lr: 1.0e-04 loss: 9.151e-02] jy: 80%|#######9 | 2397/3000 [1:09:25<18:04, 1.80s/it, lr: 1.0e-04 loss: 2.820e-01] jy: 80%|#######9 | 2397/3000 [1:09:25<18:04, 1.80s/it, lr: 1.0e-04 loss: 2.820e-01] jy: 80%|#######9 | 2398/3000 [1:09:25<21:01, 2.09s/it, lr: 1.0e-04 loss: 2.820e-01] jy: 80%|#######9 | 2398/3000 [1:09:25<21:01, 2.09s/it, lr: 1.0e-04 loss: 2.820e-01] jy: 80%|#######9 | 2398/3000 [1:09:25<21:01, 2.09s/it, lr: 1.0e-04 loss: 1.475e-01] jy: 80%|#######9 | 2398/3000 [1:09:25<21:01, 2.09s/it, lr: 1.0e-04 loss: 1.475e-01] jy: 80%|#######9 | 2399/3000 [1:09:25<17:19, 1.73s/it, lr: 1.0e-04 loss: 1.475e-01] jy: 80%|#######9 | 2399/3000 [1:09:25<17:19, 1.73s/it, lr: 1.0e-04 loss: 1.475e-01] jy: 80%|#######9 | 2399/3000 [1:09:27<17:19, 1.73s/it, lr: 1.0e-04 loss: 1.553e-01] jy: 80%|#######9 | 2399/3000 [1:09:27<17:19, 1.73s/it, lr: 1.0e-04 loss: 1.553e-01] jy: 80%|######## | 2400/3000 [1:09:28<17:17, 1.73s/it, lr: 1.0e-04 loss: 3.751e-01] jy: 80%|######## | 2400/3000 [1:09:28<17:17, 1.73s/it, lr: 1.0e-04 loss: 3.751e-01] jy: 80%|######## | 2401/3000 [1:09:28<11:19, 1.13s/it, lr: 1.0e-04 loss: 3.751e-01] jy: 80%|######## | 2401/3000 [1:09:28<11:19, 1.13s/it, lr: 1.0e-04 loss: 3.751e-01] jy: 80%|######## | 2401/3000 [1:09:29<11:19, 1.13s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 80%|######## | 2401/3000 [1:09:29<11:19, 1.13s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 80%|######## | 2402/3000 [1:09:29<11:31, 1.16s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 80%|######## | 2402/3000 [1:09:29<11:31, 1.16s/it, lr: 1.0e-04 loss: 4.304e-01] jy: 80%|######## | 2402/3000 [1:09:31<11:31, 1.16s/it, lr: 1.0e-04 loss: 3.953e-01] jy: 80%|######## | 2402/3000 [1:09:31<11:31, 1.16s/it, lr: 1.0e-04 loss: 3.953e-01] jy: 80%|######## | 2403/3000 [1:09:31<12:22, 1.24s/it, lr: 1.0e-04 loss: 3.953e-01] jy: 80%|######## | 2403/3000 [1:09:31<12:22, 1.24s/it, lr: 1.0e-04 loss: 3.953e-01] jy: 80%|######## | 2403/3000 [1:09:32<12:22, 1.24s/it, lr: 1.0e-04 loss: 4.769e-01] jy: 80%|######## | 2403/3000 [1:09:32<12:22, 1.24s/it, lr: 1.0e-04 loss: 4.769e-01] jy: 80%|######## | 2404/3000 [1:09:32<12:58, 1.31s/it, lr: 1.0e-04 loss: 4.769e-01] jy: 80%|######## | 2404/3000 [1:09:32<12:58, 1.31s/it, lr: 1.0e-04 loss: 4.769e-01] jy: 80%|######## | 2404/3000 [1:09:33<12:58, 1.31s/it, lr: 1.0e-04 loss: 3.676e-01] jy: 80%|######## | 2404/3000 [1:09:33<12:58, 1.31s/it, lr: 1.0e-04 loss: 3.676e-01] jy: 80%|######## | 2405/3000 [1:09:33<11:42, 1.18s/it, lr: 1.0e-04 loss: 3.676e-01] jy: 80%|######## | 2405/3000 [1:09:33<11:42, 1.18s/it, lr: 1.0e-04 loss: 3.676e-01] jy: 80%|######## | 2405/3000 [1:09:36<11:42, 1.18s/it, lr: 1.0e-04 loss: 5.722e-01] jy: 80%|######## | 2405/3000 [1:09:36<11:42, 1.18s/it, lr: 1.0e-04 loss: 5.722e-01] jy: 80%|######## | 2406/3000 [1:09:36<15:46, 1.59s/it, lr: 1.0e-04 loss: 5.722e-01] jy: 80%|######## | 2406/3000 [1:09:36<15:46, 1.59s/it, lr: 1.0e-04 loss: 5.722e-01] jy: 80%|######## | 2406/3000 [1:09:37<15:46, 1.59s/it, lr: 1.0e-04 loss: 5.383e-01] jy: 80%|######## | 2406/3000 [1:09:37<15:46, 1.59s/it, lr: 1.0e-04 loss: 5.383e-01] jy: 80%|######## | 2407/3000 [1:09:37<15:31, 1.57s/it, lr: 1.0e-04 loss: 5.383e-01] jy: 80%|######## | 2407/3000 [1:09:37<15:31, 1.57s/it, lr: 1.0e-04 loss: 5.383e-01] jy: 80%|######## | 2407/3000 [1:09:38<15:31, 1.57s/it, lr: 1.0e-04 loss: 2.757e-01] jy: 80%|######## | 2407/3000 [1:09:38<15:31, 1.57s/it, lr: 1.0e-04 loss: 2.757e-01] jy: 80%|######## | 2408/3000 [1:09:38<13:26, 1.36s/it, lr: 1.0e-04 loss: 2.757e-01] jy: 80%|######## | 2408/3000 [1:09:38<13:26, 1.36s/it, lr: 1.0e-04 loss: 2.757e-01] jy: 80%|######## | 2408/3000 [1:09:39<13:26, 1.36s/it, lr: 1.0e-04 loss: 5.411e-02] jy: 80%|######## | 2408/3000 [1:09:39<13:26, 1.36s/it, lr: 1.0e-04 loss: 5.411e-02] jy: 80%|######## | 2409/3000 [1:09:39<12:00, 1.22s/it, lr: 1.0e-04 loss: 5.411e-02] jy: 80%|######## | 2409/3000 [1:09:39<12:00, 1.22s/it, lr: 1.0e-04 loss: 5.411e-02] jy: 80%|######## | 2409/3000 [1:09:40<12:00, 1.22s/it, lr: 1.0e-04 loss: 1.203e-01] jy: 80%|######## | 2409/3000 [1:09:40<12:00, 1.22s/it, lr: 1.0e-04 loss: 1.203e-01] jy: 80%|######## | 2410/3000 [1:09:42<11:58, 1.22s/it, lr: 1.0e-04 loss: 3.483e-01] jy: 80%|######## | 2410/3000 [1:09:42<11:58, 1.22s/it, lr: 1.0e-04 loss: 3.483e-01] jy: 80%|######## | 2411/3000 [1:09:42<10:09, 1.04s/it, lr: 1.0e-04 loss: 3.483e-01] jy: 80%|######## | 2411/3000 [1:09:42<10:09, 1.04s/it, lr: 1.0e-04 loss: 3.483e-01] jy: 80%|######## | 2411/3000 [1:09:45<10:09, 1.04s/it, lr: 1.0e-04 loss: 2.004e-01] jy: 80%|######## | 2411/3000 [1:09:45<10:09, 1.04s/it, lr: 1.0e-04 loss: 2.004e-01] jy: 80%|######## | 2412/3000 [1:09:45<14:27, 1.47s/it, lr: 1.0e-04 loss: 2.004e-01] jy: 80%|######## | 2412/3000 [1:09:45<14:27, 1.47s/it, lr: 1.0e-04 loss: 2.004e-01] jy: 80%|######## | 2412/3000 [1:09:46<14:27, 1.47s/it, lr: 1.0e-04 loss: 1.883e-01] jy: 80%|######## | 2412/3000 [1:09:46<14:27, 1.47s/it, lr: 1.0e-04 loss: 1.883e-01] jy: 80%|######## | 2413/3000 [1:09:46<12:53, 1.32s/it, lr: 1.0e-04 loss: 1.883e-01] jy: 80%|######## | 2413/3000 [1:09:46<12:53, 1.32s/it, lr: 1.0e-04 loss: 1.883e-01] jy: 80%|######## | 2413/3000 [1:09:47<12:53, 1.32s/it, lr: 1.0e-04 loss: 5.130e-01] jy: 80%|######## | 2413/3000 [1:09:47<12:53, 1.32s/it, lr: 1.0e-04 loss: 5.130e-01] jy: 80%|######## | 2414/3000 [1:09:47<13:42, 1.40s/it, lr: 1.0e-04 loss: 5.130e-01] jy: 80%|######## | 2414/3000 [1:09:47<13:42, 1.40s/it, lr: 1.0e-04 loss: 5.130e-01] jy: 80%|######## | 2414/3000 [1:09:50<13:42, 1.40s/it, lr: 1.0e-04 loss: 3.269e-01] jy: 80%|######## | 2414/3000 [1:09:50<13:42, 1.40s/it, lr: 1.0e-04 loss: 3.269e-01] jy: 80%|######## | 2415/3000 [1:09:50<18:05, 1.86s/it, lr: 1.0e-04 loss: 3.269e-01] jy: 80%|######## | 2415/3000 [1:09:50<18:05, 1.86s/it, lr: 1.0e-04 loss: 3.269e-01] jy: 80%|######## | 2415/3000 [1:09:53<18:05, 1.86s/it, lr: 1.0e-04 loss: 3.723e-01] jy: 80%|######## | 2415/3000 [1:09:53<18:05, 1.86s/it, lr: 1.0e-04 loss: 3.723e-01] jy: 81%|######## | 2416/3000 [1:09:53<20:11, 2.07s/it, lr: 1.0e-04 loss: 3.723e-01] jy: 81%|######## | 2416/3000 [1:09:53<20:11, 2.07s/it, lr: 1.0e-04 loss: 3.723e-01] jy: 81%|######## | 2416/3000 [1:09:54<20:11, 2.07s/it, lr: 1.0e-04 loss: 6.426e-01] jy: 81%|######## | 2416/3000 [1:09:54<20:11, 2.07s/it, lr: 1.0e-04 loss: 6.426e-01] jy: 81%|######## | 2417/3000 [1:09:54<16:43, 1.72s/it, lr: 1.0e-04 loss: 6.426e-01] jy: 81%|######## | 2417/3000 [1:09:54<16:43, 1.72s/it, lr: 1.0e-04 loss: 6.426e-01] jy: 81%|######## | 2417/3000 [1:09:55<16:43, 1.72s/it, lr: 1.0e-04 loss: 1.656e-01] jy: 81%|######## | 2417/3000 [1:09:55<16:43, 1.72s/it, lr: 1.0e-04 loss: 1.656e-01] jy: 81%|######## | 2418/3000 [1:09:55<14:15, 1.47s/it, lr: 1.0e-04 loss: 1.656e-01] jy: 81%|######## | 2418/3000 [1:09:55<14:15, 1.47s/it, lr: 1.0e-04 loss: 1.656e-01] jy: 81%|######## | 2418/3000 [1:09:56<14:15, 1.47s/it, lr: 1.0e-04 loss: 5.974e-01] jy: 81%|######## | 2418/3000 [1:09:56<14:15, 1.47s/it, lr: 1.0e-04 loss: 5.974e-01] jy: 81%|######## | 2419/3000 [1:09:56<12:29, 1.29s/it, lr: 1.0e-04 loss: 5.974e-01] jy: 81%|######## | 2419/3000 [1:09:56<12:29, 1.29s/it, lr: 1.0e-04 loss: 5.974e-01] jy: 81%|######## | 2419/3000 [1:09:58<12:29, 1.29s/it, lr: 1.0e-04 loss: 4.721e-01] jy: 81%|######## | 2419/3000 [1:09:58<12:29, 1.29s/it, lr: 1.0e-04 loss: 4.721e-01] jy: 81%|######## | 2420/3000 [1:10:01<12:27, 1.29s/it, lr: 1.0e-04 loss: 1.993e-01] jy: 81%|######## | 2420/3000 [1:10:01<12:27, 1.29s/it, lr: 1.0e-04 loss: 1.993e-01] jy: 81%|######## | 2421/3000 [1:10:01<12:33, 1.30s/it, lr: 1.0e-04 loss: 1.993e-01] jy: 81%|######## | 2421/3000 [1:10:01<12:33, 1.30s/it, lr: 1.0e-04 loss: 1.993e-01] jy: 81%|######## | 2421/3000 [1:10:03<12:33, 1.30s/it, lr: 1.0e-04 loss: 1.197e-01] jy: 81%|######## | 2421/3000 [1:10:03<12:33, 1.30s/it, lr: 1.0e-04 loss: 1.197e-01] jy: 81%|######## | 2422/3000 [1:10:03<15:40, 1.63s/it, lr: 1.0e-04 loss: 1.197e-01] jy: 81%|######## | 2422/3000 [1:10:03<15:40, 1.63s/it, lr: 1.0e-04 loss: 1.197e-01] jy: 81%|######## | 2422/3000 [1:10:05<15:40, 1.63s/it, lr: 1.0e-04 loss: 2.439e-01] jy: 81%|######## | 2422/3000 [1:10:05<15:40, 1.63s/it, lr: 1.0e-04 loss: 2.439e-01] jy: 81%|######## | 2423/3000 [1:10:05<15:38, 1.63s/it, lr: 1.0e-04 loss: 2.439e-01] jy: 81%|######## | 2423/3000 [1:10:05<15:38, 1.63s/it, lr: 1.0e-04 loss: 2.439e-01] jy: 81%|######## | 2423/3000 [1:10:06<15:38, 1.63s/it, lr: 1.0e-04 loss: 4.001e-01] jy: 81%|######## | 2423/3000 [1:10:06<15:38, 1.63s/it, lr: 1.0e-04 loss: 4.001e-01] jy: 81%|######## | 2424/3000 [1:10:06<13:35, 1.42s/it, lr: 1.0e-04 loss: 4.001e-01] jy: 81%|######## | 2424/3000 [1:10:06<13:35, 1.42s/it, lr: 1.0e-04 loss: 4.001e-01] jy: 81%|######## | 2424/3000 [1:10:07<13:35, 1.42s/it, lr: 1.0e-04 loss: 4.544e-01] jy: 81%|######## | 2424/3000 [1:10:07<13:35, 1.42s/it, lr: 1.0e-04 loss: 4.544e-01] jy: 81%|######## | 2425/3000 [1:10:07<12:05, 1.26s/it, lr: 1.0e-04 loss: 4.544e-01] jy: 81%|######## | 2425/3000 [1:10:07<12:05, 1.26s/it, lr: 1.0e-04 loss: 4.544e-01] jy: 81%|######## | 2425/3000 [1:10:08<12:05, 1.26s/it, lr: 1.0e-04 loss: 3.546e-01] jy: 81%|######## | 2425/3000 [1:10:08<12:05, 1.26s/it, lr: 1.0e-04 loss: 3.546e-01] jy: 81%|######## | 2426/3000 [1:10:08<13:04, 1.37s/it, lr: 1.0e-04 loss: 3.546e-01] jy: 81%|######## | 2426/3000 [1:10:08<13:04, 1.37s/it, lr: 1.0e-04 loss: 3.546e-01] jy: 81%|######## | 2426/3000 [1:10:11<13:04, 1.37s/it, lr: 1.0e-04 loss: 4.204e-01] jy: 81%|######## | 2426/3000 [1:10:11<13:04, 1.37s/it, lr: 1.0e-04 loss: 4.204e-01] jy: 81%|######## | 2427/3000 [1:10:11<16:31, 1.73s/it, lr: 1.0e-04 loss: 4.204e-01] jy: 81%|######## | 2427/3000 [1:10:11<16:31, 1.73s/it, lr: 1.0e-04 loss: 4.204e-01] jy: 81%|######## | 2427/3000 [1:10:12<16:31, 1.73s/it, lr: 1.0e-04 loss: 5.152e-01] jy: 81%|######## | 2427/3000 [1:10:12<16:31, 1.73s/it, lr: 1.0e-04 loss: 5.152e-01] jy: 81%|######## | 2428/3000 [1:10:12<15:01, 1.58s/it, lr: 1.0e-04 loss: 5.152e-01] jy: 81%|######## | 2428/3000 [1:10:12<15:01, 1.58s/it, lr: 1.0e-04 loss: 5.152e-01] jy: 81%|######## | 2428/3000 [1:10:14<15:01, 1.58s/it, lr: 1.0e-04 loss: 4.772e-01] jy: 81%|######## | 2428/3000 [1:10:14<15:01, 1.58s/it, lr: 1.0e-04 loss: 4.772e-01] jy: 81%|######## | 2429/3000 [1:10:14<15:07, 1.59s/it, lr: 1.0e-04 loss: 4.772e-01] jy: 81%|######## | 2429/3000 [1:10:14<15:07, 1.59s/it, lr: 1.0e-04 loss: 4.772e-01] jy: 81%|######## | 2429/3000 [1:10:15<15:07, 1.59s/it, lr: 1.0e-04 loss: 5.076e-01] jy: 81%|######## | 2429/3000 [1:10:15<15:07, 1.59s/it, lr: 1.0e-04 loss: 5.076e-01] jy: 81%|########1 | 2430/3000 [1:10:17<15:06, 1.59s/it, lr: 1.0e-04 loss: 4.700e-01] jy: 81%|########1 | 2430/3000 [1:10:17<15:06, 1.59s/it, lr: 1.0e-04 loss: 4.700e-01] jy: 81%|########1 | 2431/3000 [1:10:17<11:42, 1.23s/it, lr: 1.0e-04 loss: 4.700e-01] jy: 81%|########1 | 2431/3000 [1:10:17<11:42, 1.23s/it, lr: 1.0e-04 loss: 4.700e-01] jy: 81%|########1 | 2431/3000 [1:10:18<11:42, 1.23s/it, lr: 1.0e-04 loss: 1.642e-01] jy: 81%|########1 | 2431/3000 [1:10:18<11:42, 1.23s/it, lr: 1.0e-04 loss: 1.642e-01] jy: 81%|########1 | 2432/3000 [1:10:18<10:48, 1.14s/it, lr: 1.0e-04 loss: 1.642e-01] jy: 81%|########1 | 2432/3000 [1:10:18<10:48, 1.14s/it, lr: 1.0e-04 loss: 1.642e-01] jy: 81%|########1 | 2432/3000 [1:10:21<10:48, 1.14s/it, lr: 1.0e-04 loss: 3.993e-01] jy: 81%|########1 | 2432/3000 [1:10:21<10:48, 1.14s/it, lr: 1.0e-04 loss: 3.993e-01] jy: 81%|########1 | 2433/3000 [1:10:21<14:53, 1.58s/it, lr: 1.0e-04 loss: 3.993e-01] jy: 81%|########1 | 2433/3000 [1:10:21<14:53, 1.58s/it, lr: 1.0e-04 loss: 3.993e-01] jy: 81%|########1 | 2433/3000 [1:10:24<14:53, 1.58s/it, lr: 1.0e-04 loss: 4.968e-01] jy: 81%|########1 | 2433/3000 [1:10:24<14:53, 1.58s/it, lr: 1.0e-04 loss: 4.968e-01] jy: 81%|########1 | 2434/3000 [1:10:24<18:00, 1.91s/it, lr: 1.0e-04 loss: 4.968e-01] jy: 81%|########1 | 2434/3000 [1:10:24<18:00, 1.91s/it, lr: 1.0e-04 loss: 4.968e-01] jy: 81%|########1 | 2434/3000 [1:10:25<18:00, 1.91s/it, lr: 1.0e-04 loss: 4.583e-01] jy: 81%|########1 | 2434/3000 [1:10:25<18:00, 1.91s/it, lr: 1.0e-04 loss: 4.583e-01] jy: 81%|########1 | 2435/3000 [1:10:25<17:38, 1.87s/it, lr: 1.0e-04 loss: 4.583e-01] jy: 81%|########1 | 2435/3000 [1:10:25<17:38, 1.87s/it, lr: 1.0e-04 loss: 4.583e-01] jy: 81%|########1 | 2435/3000 [1:10:26<17:38, 1.87s/it, lr: 1.0e-04 loss: 4.749e-01] jy: 81%|########1 | 2435/3000 [1:10:26<17:38, 1.87s/it, lr: 1.0e-04 loss: 4.749e-01] jy: 81%|########1 | 2436/3000 [1:10:26<14:53, 1.58s/it, lr: 1.0e-04 loss: 4.749e-01] jy: 81%|########1 | 2436/3000 [1:10:26<14:53, 1.58s/it, lr: 1.0e-04 loss: 4.749e-01] jy: 81%|########1 | 2436/3000 [1:10:27<14:53, 1.58s/it, lr: 1.0e-04 loss: 1.381e-01] jy: 81%|########1 | 2436/3000 [1:10:27<14:53, 1.58s/it, lr: 1.0e-04 loss: 1.381e-01] jy: 81%|########1 | 2437/3000 [1:10:27<12:53, 1.37s/it, lr: 1.0e-04 loss: 1.381e-01] jy: 81%|########1 | 2437/3000 [1:10:27<12:53, 1.37s/it, lr: 1.0e-04 loss: 1.381e-01] jy: 81%|########1 | 2437/3000 [1:10:30<12:53, 1.37s/it, lr: 1.0e-04 loss: 6.754e-01] jy: 81%|########1 | 2437/3000 [1:10:30<12:53, 1.37s/it, lr: 1.0e-04 loss: 6.754e-01] jy: 81%|########1 | 2438/3000 [1:10:30<16:18, 1.74s/it, lr: 1.0e-04 loss: 6.754e-01] jy: 81%|########1 | 2438/3000 [1:10:30<16:18, 1.74s/it, lr: 1.0e-04 loss: 6.754e-01] jy: 81%|########1 | 2438/3000 [1:10:31<16:18, 1.74s/it, lr: 1.0e-04 loss: 1.518e-01] jy: 81%|########1 | 2438/3000 [1:10:31<16:18, 1.74s/it, lr: 1.0e-04 loss: 1.518e-01] jy: 81%|########1 | 2439/3000 [1:10:31<13:50, 1.48s/it, lr: 1.0e-04 loss: 1.518e-01] jy: 81%|########1 | 2439/3000 [1:10:31<13:50, 1.48s/it, lr: 1.0e-04 loss: 1.518e-01] jy: 81%|########1 | 2439/3000 [1:10:33<13:50, 1.48s/it, lr: 1.0e-04 loss: 3.319e-01] jy: 81%|########1 | 2439/3000 [1:10:33<13:50, 1.48s/it, lr: 1.0e-04 loss: 3.319e-01] jy: 81%|########1 | 2440/3000 [1:10:36<13:49, 1.48s/it, lr: 1.0e-04 loss: 4.893e-01] jy: 81%|########1 | 2440/3000 [1:10:36<13:49, 1.48s/it, lr: 1.0e-04 loss: 4.893e-01] jy: 81%|########1 | 2441/3000 [1:10:36<13:28, 1.45s/it, lr: 1.0e-04 loss: 4.893e-01] jy: 81%|########1 | 2441/3000 [1:10:36<13:28, 1.45s/it, lr: 1.0e-04 loss: 4.893e-01] jy: 81%|########1 | 2441/3000 [1:10:38<13:28, 1.45s/it, lr: 1.0e-04 loss: 1.298e-01] jy: 81%|########1 | 2441/3000 [1:10:38<13:28, 1.45s/it, lr: 1.0e-04 loss: 1.298e-01] jy: 81%|########1 | 2442/3000 [1:10:38<13:51, 1.49s/it, lr: 1.0e-04 loss: 1.298e-01] jy: 81%|########1 | 2442/3000 [1:10:38<13:51, 1.49s/it, lr: 1.0e-04 loss: 1.298e-01] jy: 81%|########1 | 2442/3000 [1:10:41<13:51, 1.49s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 81%|########1 | 2442/3000 [1:10:41<13:51, 1.49s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 81%|########1 | 2443/3000 [1:10:41<17:41, 1.91s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 81%|########1 | 2443/3000 [1:10:41<17:41, 1.91s/it, lr: 1.0e-04 loss: 4.561e-01] jy: 81%|########1 | 2443/3000 [1:10:42<17:41, 1.91s/it, lr: 1.0e-04 loss: 2.374e-01] jy: 81%|########1 | 2443/3000 [1:10:42<17:41, 1.91s/it, lr: 1.0e-04 loss: 2.374e-01] jy: 81%|########1 | 2444/3000 [1:10:42<15:01, 1.62s/it, lr: 1.0e-04 loss: 2.374e-01] jy: 81%|########1 | 2444/3000 [1:10:42<15:01, 1.62s/it, lr: 1.0e-04 loss: 2.374e-01] jy: 81%|########1 | 2444/3000 [1:10:44<15:01, 1.62s/it, lr: 1.0e-04 loss: 1.505e-01] jy: 81%|########1 | 2444/3000 [1:10:44<15:01, 1.62s/it, lr: 1.0e-04 loss: 1.505e-01] jy: 82%|########1 | 2445/3000 [1:10:44<17:35, 1.90s/it, lr: 1.0e-04 loss: 1.505e-01] jy: 82%|########1 | 2445/3000 [1:10:44<17:35, 1.90s/it, lr: 1.0e-04 loss: 1.505e-01] jy: 82%|########1 | 2445/3000 [1:10:46<17:35, 1.90s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 82%|########1 | 2445/3000 [1:10:46<17:35, 1.90s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 82%|########1 | 2446/3000 [1:10:46<16:49, 1.82s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 82%|########1 | 2446/3000 [1:10:46<16:49, 1.82s/it, lr: 1.0e-04 loss: 1.465e-01] jy: 82%|########1 | 2446/3000 [1:10:47<16:49, 1.82s/it, lr: 1.0e-04 loss: 6.686e-01] jy: 82%|########1 | 2446/3000 [1:10:47<16:49, 1.82s/it, lr: 1.0e-04 loss: 6.686e-01] jy: 82%|########1 | 2447/3000 [1:10:47<16:16, 1.77s/it, lr: 1.0e-04 loss: 6.686e-01] jy: 82%|########1 | 2447/3000 [1:10:47<16:16, 1.77s/it, lr: 1.0e-04 loss: 6.686e-01] jy: 82%|########1 | 2447/3000 [1:10:48<16:16, 1.77s/it, lr: 1.0e-04 loss: 4.063e-01] jy: 82%|########1 | 2447/3000 [1:10:48<16:16, 1.77s/it, lr: 1.0e-04 loss: 4.063e-01] jy: 82%|########1 | 2448/3000 [1:10:48<13:48, 1.50s/it, lr: 1.0e-04 loss: 4.063e-01] jy: 82%|########1 | 2448/3000 [1:10:48<13:48, 1.50s/it, lr: 1.0e-04 loss: 4.063e-01] jy: 82%|########1 | 2448/3000 [1:10:51<13:48, 1.50s/it, lr: 1.0e-04 loss: 1.751e-01] jy: 82%|########1 | 2448/3000 [1:10:51<13:48, 1.50s/it, lr: 1.0e-04 loss: 1.751e-01] jy: 82%|########1 | 2449/3000 [1:10:51<16:49, 1.83s/it, lr: 1.0e-04 loss: 1.751e-01] jy: 82%|########1 | 2449/3000 [1:10:51<16:49, 1.83s/it, lr: 1.0e-04 loss: 1.751e-01] jy: 82%|########1 | 2449/3000 [1:10:53<16:49, 1.83s/it, lr: 1.0e-04 loss: 6.011e-01] jy: 82%|########1 | 2449/3000 [1:10:53<16:49, 1.83s/it, lr: 1.0e-04 loss: 6.011e-01] jy: 82%|########1 | 2450/3000 [1:10:53<16:47, 1.83s/it, lr: 1.0e-04 loss: 3.972e-01] jy: 82%|########1 | 2450/3000 [1:10:53<16:47, 1.83s/it, lr: 1.0e-04 loss: 3.972e-01] jy: 82%|########1 | 2451/3000 [1:10:53<10:53, 1.19s/it, lr: 1.0e-04 loss: 3.972e-01] jy: 82%|########1 | 2451/3000 [1:10:53<10:53, 1.19s/it, lr: 1.0e-04 loss: 3.972e-01] jy: 82%|########1 | 2451/3000 [1:10:54<10:53, 1.19s/it, lr: 1.0e-04 loss: 1.061e-01] jy: 82%|########1 | 2451/3000 [1:10:54<10:53, 1.19s/it, lr: 1.0e-04 loss: 1.061e-01] jy: 82%|########1 | 2452/3000 [1:10:54<10:11, 1.12s/it, lr: 1.0e-04 loss: 1.061e-01] jy: 82%|########1 | 2452/3000 [1:10:54<10:11, 1.12s/it, lr: 1.0e-04 loss: 1.061e-01] jy: 82%|########1 | 2452/3000 [1:10:55<10:11, 1.12s/it, lr: 1.0e-04 loss: 1.507e-01] jy: 82%|########1 | 2452/3000 [1:10:55<10:11, 1.12s/it, lr: 1.0e-04 loss: 1.507e-01] jy: 82%|########1 | 2453/3000 [1:10:55<09:33, 1.05s/it, lr: 1.0e-04 loss: 1.507e-01] jy: 82%|########1 | 2453/3000 [1:10:55<09:33, 1.05s/it, lr: 1.0e-04 loss: 1.507e-01] jy: 82%|########1 | 2453/3000 [1:10:57<09:33, 1.05s/it, lr: 1.0e-04 loss: 3.070e-01] jy: 82%|########1 | 2453/3000 [1:10:57<09:33, 1.05s/it, lr: 1.0e-04 loss: 3.070e-01] jy: 82%|########1 | 2454/3000 [1:10:57<10:42, 1.18s/it, lr: 1.0e-04 loss: 3.070e-01] jy: 82%|########1 | 2454/3000 [1:10:57<10:42, 1.18s/it, lr: 1.0e-04 loss: 3.070e-01] jy: 82%|########1 | 2454/3000 [1:10:58<10:42, 1.18s/it, lr: 1.0e-04 loss: 2.702e-01] jy: 82%|########1 | 2454/3000 [1:10:58<10:42, 1.18s/it, lr: 1.0e-04 loss: 2.702e-01] jy: 82%|########1 | 2455/3000 [1:10:58<09:52, 1.09s/it, lr: 1.0e-04 loss: 2.702e-01] jy: 82%|########1 | 2455/3000 [1:10:58<09:52, 1.09s/it, lr: 1.0e-04 loss: 2.702e-01] jy: 82%|########1 | 2455/3000 [1:11:00<09:52, 1.09s/it, lr: 1.0e-04 loss: 4.334e-01] jy: 82%|########1 | 2455/3000 [1:11:00<09:52, 1.09s/it, lr: 1.0e-04 loss: 4.334e-01] jy: 82%|########1 | 2456/3000 [1:11:00<14:17, 1.58s/it, lr: 1.0e-04 loss: 4.334e-01] jy: 82%|########1 | 2456/3000 [1:11:00<14:17, 1.58s/it, lr: 1.0e-04 loss: 4.334e-01] jy: 82%|########1 | 2456/3000 [1:11:03<14:17, 1.58s/it, lr: 1.0e-04 loss: 4.219e-01] jy: 82%|########1 | 2456/3000 [1:11:03<14:17, 1.58s/it, lr: 1.0e-04 loss: 4.219e-01] jy: 82%|########1 | 2457/3000 [1:11:03<17:44, 1.96s/it, lr: 1.0e-04 loss: 4.219e-01] jy: 82%|########1 | 2457/3000 [1:11:03<17:44, 1.96s/it, lr: 1.0e-04 loss: 4.219e-01] jy: 82%|########1 | 2457/3000 [1:11:06<17:44, 1.96s/it, lr: 1.0e-04 loss: 2.469e-02] jy: 82%|########1 | 2457/3000 [1:11:06<17:44, 1.96s/it, lr: 1.0e-04 loss: 2.469e-02] jy: 82%|########1 | 2458/3000 [1:11:06<19:27, 2.15s/it, lr: 1.0e-04 loss: 2.469e-02] jy: 82%|########1 | 2458/3000 [1:11:06<19:27, 2.15s/it, lr: 1.0e-04 loss: 2.469e-02] jy: 82%|########1 | 2458/3000 [1:11:09<19:27, 2.15s/it, lr: 1.0e-04 loss: 5.065e-01] jy: 82%|########1 | 2458/3000 [1:11:09<19:27, 2.15s/it, lr: 1.0e-04 loss: 5.065e-01] jy: 82%|########1 | 2459/3000 [1:11:09<21:09, 2.35s/it, lr: 1.0e-04 loss: 5.065e-01] jy: 82%|########1 | 2459/3000 [1:11:09<21:09, 2.35s/it, lr: 1.0e-04 loss: 5.065e-01] jy: 82%|########1 | 2459/3000 [1:11:10<21:09, 2.35s/it, lr: 1.0e-04 loss: 4.265e-01] jy: 82%|########1 | 2459/3000 [1:11:10<21:09, 2.35s/it, lr: 1.0e-04 loss: 4.265e-01] jy: 82%|########2 | 2460/3000 [1:11:12<21:07, 2.35s/it, lr: 1.0e-04 loss: 3.661e-01] jy: 82%|########2 | 2460/3000 [1:11:12<21:07, 2.35s/it, lr: 1.0e-04 loss: 3.661e-01] jy: 82%|########2 | 2461/3000 [1:11:12<14:47, 1.65s/it, lr: 1.0e-04 loss: 3.661e-01] jy: 82%|########2 | 2461/3000 [1:11:12<14:47, 1.65s/it, lr: 1.0e-04 loss: 3.661e-01] jy: 82%|########2 | 2461/3000 [1:11:15<14:47, 1.65s/it, lr: 1.0e-04 loss: 1.696e-01] jy: 82%|########2 | 2461/3000 [1:11:15<14:47, 1.65s/it, lr: 1.0e-04 loss: 1.696e-01] jy: 82%|########2 | 2462/3000 [1:11:15<17:25, 1.94s/it, lr: 1.0e-04 loss: 1.696e-01] jy: 82%|########2 | 2462/3000 [1:11:15<17:25, 1.94s/it, lr: 1.0e-04 loss: 1.696e-01] jy: 82%|########2 | 2462/3000 [1:11:16<17:25, 1.94s/it, lr: 1.0e-04 loss: 3.666e-01] jy: 82%|########2 | 2462/3000 [1:11:16<17:25, 1.94s/it, lr: 1.0e-04 loss: 3.666e-01] jy: 82%|########2 | 2463/3000 [1:11:16<14:46, 1.65s/it, lr: 1.0e-04 loss: 3.666e-01] jy: 82%|########2 | 2463/3000 [1:11:16<14:46, 1.65s/it, lr: 1.0e-04 loss: 3.666e-01] jy: 82%|########2 | 2463/3000 [1:11:17<14:46, 1.65s/it, lr: 1.0e-04 loss: 1.570e-01] jy: 82%|########2 | 2463/3000 [1:11:17<14:46, 1.65s/it, lr: 1.0e-04 loss: 1.570e-01] jy: 82%|########2 | 2464/3000 [1:11:17<14:40, 1.64s/it, lr: 1.0e-04 loss: 1.570e-01] jy: 82%|########2 | 2464/3000 [1:11:17<14:40, 1.64s/it, lr: 1.0e-04 loss: 1.570e-01] jy: 82%|########2 | 2464/3000 [1:11:20<14:40, 1.64s/it, lr: 1.0e-04 loss: 2.263e-01] jy: 82%|########2 | 2464/3000 [1:11:20<14:40, 1.64s/it, lr: 1.0e-04 loss: 2.263e-01] jy: 82%|########2 | 2465/3000 [1:11:20<17:32, 1.97s/it, lr: 1.0e-04 loss: 2.263e-01] jy: 82%|########2 | 2465/3000 [1:11:20<17:32, 1.97s/it, lr: 1.0e-04 loss: 2.263e-01] jy: 82%|########2 | 2465/3000 [1:11:23<17:32, 1.97s/it, lr: 1.0e-04 loss: 5.587e-01] jy: 82%|########2 | 2465/3000 [1:11:23<17:32, 1.97s/it, lr: 1.0e-04 loss: 5.587e-01] jy: 82%|########2 | 2466/3000 [1:11:23<19:13, 2.16s/it, lr: 1.0e-04 loss: 5.587e-01] jy: 82%|########2 | 2466/3000 [1:11:23<19:13, 2.16s/it, lr: 1.0e-04 loss: 5.587e-01] jy: 82%|########2 | 2466/3000 [1:11:24<19:13, 2.16s/it, lr: 1.0e-04 loss: 6.668e-01] jy: 82%|########2 | 2466/3000 [1:11:24<19:13, 2.16s/it, lr: 1.0e-04 loss: 6.668e-01] jy: 82%|########2 | 2467/3000 [1:11:24<17:50, 2.01s/it, lr: 1.0e-04 loss: 6.668e-01] jy: 82%|########2 | 2467/3000 [1:11:24<17:50, 2.01s/it, lr: 1.0e-04 loss: 6.668e-01] jy: 82%|########2 | 2467/3000 [1:11:25<17:50, 2.01s/it, lr: 1.0e-04 loss: 3.237e-01] jy: 82%|########2 | 2467/3000 [1:11:25<17:50, 2.01s/it, lr: 1.0e-04 loss: 3.237e-01] jy: 82%|########2 | 2468/3000 [1:11:25<14:48, 1.67s/it, lr: 1.0e-04 loss: 3.237e-01] jy: 82%|########2 | 2468/3000 [1:11:25<14:48, 1.67s/it, lr: 1.0e-04 loss: 3.237e-01] jy: 82%|########2 | 2468/3000 [1:11:28<14:48, 1.67s/it, lr: 1.0e-04 loss: 3.626e-02] jy: 82%|########2 | 2468/3000 [1:11:28<14:48, 1.67s/it, lr: 1.0e-04 loss: 3.626e-02] jy: 82%|########2 | 2469/3000 [1:11:28<17:50, 2.02s/it, lr: 1.0e-04 loss: 3.626e-02] jy: 82%|########2 | 2469/3000 [1:11:28<17:50, 2.02s/it, lr: 1.0e-04 loss: 3.626e-02] jy: 82%|########2 | 2469/3000 [1:11:31<17:50, 2.02s/it, lr: 1.0e-04 loss: 2.528e-01] jy: 82%|########2 | 2469/3000 [1:11:31<17:50, 2.02s/it, lr: 1.0e-04 loss: 2.528e-01] jy: 82%|########2 | 2470/3000 [1:11:33<17:48, 2.02s/it, lr: 1.0e-04 loss: 7.254e-02] jy: 82%|########2 | 2470/3000 [1:11:33<17:48, 2.02s/it, lr: 1.0e-04 loss: 7.254e-02] jy: 82%|########2 | 2471/3000 [1:11:33<12:45, 1.45s/it, lr: 1.0e-04 loss: 7.254e-02] jy: 82%|########2 | 2471/3000 [1:11:33<12:45, 1.45s/it, lr: 1.0e-04 loss: 7.254e-02] jy: 82%|########2 | 2471/3000 [1:11:33<12:45, 1.45s/it, lr: 1.0e-04 loss: 5.025e-01] jy: 82%|########2 | 2471/3000 [1:11:33<12:45, 1.45s/it, lr: 1.0e-04 loss: 5.025e-01] jy: 82%|########2 | 2472/3000 [1:11:33<11:26, 1.30s/it, lr: 1.0e-04 loss: 5.025e-01] jy: 82%|########2 | 2472/3000 [1:11:33<11:26, 1.30s/it, lr: 1.0e-04 loss: 5.025e-01] jy: 82%|########2 | 2472/3000 [1:11:36<11:26, 1.30s/it, lr: 1.0e-04 loss: 4.293e-01] jy: 82%|########2 | 2472/3000 [1:11:36<11:26, 1.30s/it, lr: 1.0e-04 loss: 4.293e-01] jy: 82%|########2 | 2473/3000 [1:11:36<14:52, 1.69s/it, lr: 1.0e-04 loss: 4.293e-01] jy: 82%|########2 | 2473/3000 [1:11:36<14:52, 1.69s/it, lr: 1.0e-04 loss: 4.293e-01] jy: 82%|########2 | 2473/3000 [1:11:38<14:52, 1.69s/it, lr: 1.0e-04 loss: 4.031e-01] jy: 82%|########2 | 2473/3000 [1:11:38<14:52, 1.69s/it, lr: 1.0e-04 loss: 4.031e-01] jy: 82%|########2 | 2474/3000 [1:11:38<14:23, 1.64s/it, lr: 1.0e-04 loss: 4.031e-01] jy: 82%|########2 | 2474/3000 [1:11:38<14:23, 1.64s/it, lr: 1.0e-04 loss: 4.031e-01] jy: 82%|########2 | 2474/3000 [1:11:40<14:23, 1.64s/it, lr: 1.0e-04 loss: 1.180e-01] jy: 82%|########2 | 2474/3000 [1:11:40<14:23, 1.64s/it, lr: 1.0e-04 loss: 1.180e-01] jy: 82%|########2 | 2475/3000 [1:11:40<14:07, 1.61s/it, lr: 1.0e-04 loss: 1.180e-01] jy: 82%|########2 | 2475/3000 [1:11:40<14:07, 1.61s/it, lr: 1.0e-04 loss: 1.180e-01] jy: 82%|########2 | 2475/3000 [1:11:41<14:07, 1.61s/it, lr: 1.0e-04 loss: 1.243e-01] jy: 82%|########2 | 2475/3000 [1:11:41<14:07, 1.61s/it, lr: 1.0e-04 loss: 1.243e-01] jy: 83%|########2 | 2476/3000 [1:11:41<13:52, 1.59s/it, lr: 1.0e-04 loss: 1.243e-01] jy: 83%|########2 | 2476/3000 [1:11:41<13:52, 1.59s/it, lr: 1.0e-04 loss: 1.243e-01] jy: 83%|########2 | 2476/3000 [1:11:43<13:52, 1.59s/it, lr: 1.0e-04 loss: 1.903e-01] jy: 83%|########2 | 2476/3000 [1:11:43<13:52, 1.59s/it, lr: 1.0e-04 loss: 1.903e-01] jy: 83%|########2 | 2477/3000 [1:11:43<13:55, 1.60s/it, lr: 1.0e-04 loss: 1.903e-01] jy: 83%|########2 | 2477/3000 [1:11:43<13:55, 1.60s/it, lr: 1.0e-04 loss: 1.903e-01] jy: 83%|########2 | 2477/3000 [1:11:44<13:55, 1.60s/it, lr: 1.0e-04 loss: 2.248e-01] jy: 83%|########2 | 2477/3000 [1:11:44<13:55, 1.60s/it, lr: 1.0e-04 loss: 2.248e-01] jy: 83%|########2 | 2478/3000 [1:11:44<12:01, 1.38s/it, lr: 1.0e-04 loss: 2.248e-01] jy: 83%|########2 | 2478/3000 [1:11:44<12:01, 1.38s/it, lr: 1.0e-04 loss: 2.248e-01] jy: 83%|########2 | 2478/3000 [1:11:46<12:01, 1.38s/it, lr: 1.0e-04 loss: 4.814e-01] jy: 83%|########2 | 2478/3000 [1:11:46<12:01, 1.38s/it, lr: 1.0e-04 loss: 4.814e-01] jy: 83%|########2 | 2479/3000 [1:11:46<15:44, 1.81s/it, lr: 1.0e-04 loss: 4.814e-01] jy: 83%|########2 | 2479/3000 [1:11:46<15:44, 1.81s/it, lr: 1.0e-04 loss: 4.814e-01] jy: 83%|########2 | 2479/3000 [1:11:49<15:44, 1.81s/it, lr: 1.0e-04 loss: 6.718e-02] jy: 83%|########2 | 2479/3000 [1:11:49<15:44, 1.81s/it, lr: 1.0e-04 loss: 6.718e-02] jy: 83%|########2 | 2480/3000 [1:11:52<15:42, 1.81s/it, lr: 1.0e-04 loss: 4.305e-01] jy: 83%|########2 | 2480/3000 [1:11:52<15:42, 1.81s/it, lr: 1.0e-04 loss: 4.305e-01] jy: 83%|########2 | 2481/3000 [1:11:52<13:42, 1.58s/it, lr: 1.0e-04 loss: 4.305e-01] jy: 83%|########2 | 2481/3000 [1:11:52<13:42, 1.58s/it, lr: 1.0e-04 loss: 4.305e-01] jy: 83%|########2 | 2481/3000 [1:11:53<13:42, 1.58s/it, lr: 1.0e-04 loss: 9.317e-02] jy: 83%|########2 | 2481/3000 [1:11:53<13:42, 1.58s/it, lr: 1.0e-04 loss: 9.317e-02] jy: 83%|########2 | 2482/3000 [1:11:53<13:46, 1.60s/it, lr: 1.0e-04 loss: 9.317e-02] jy: 83%|########2 | 2482/3000 [1:11:53<13:46, 1.60s/it, lr: 1.0e-04 loss: 9.317e-02] jy: 83%|########2 | 2482/3000 [1:11:55<13:46, 1.60s/it, lr: 1.0e-04 loss: 2.464e-01] jy: 83%|########2 | 2482/3000 [1:11:55<13:46, 1.60s/it, lr: 1.0e-04 loss: 2.464e-01] jy: 83%|########2 | 2483/3000 [1:11:55<12:44, 1.48s/it, lr: 1.0e-04 loss: 2.464e-01] jy: 83%|########2 | 2483/3000 [1:11:55<12:44, 1.48s/it, lr: 1.0e-04 loss: 2.464e-01] jy: 83%|########2 | 2483/3000 [1:11:56<12:44, 1.48s/it, lr: 1.0e-04 loss: 1.743e-02] jy: 83%|########2 | 2483/3000 [1:11:56<12:44, 1.48s/it, lr: 1.0e-04 loss: 1.743e-02] jy: 83%|########2 | 2484/3000 [1:11:56<13:03, 1.52s/it, lr: 1.0e-04 loss: 1.743e-02] jy: 83%|########2 | 2484/3000 [1:11:56<13:03, 1.52s/it, lr: 1.0e-04 loss: 1.743e-02] jy: 83%|########2 | 2484/3000 [1:11:57<13:03, 1.52s/it, lr: 1.0e-04 loss: 3.182e-01] jy: 83%|########2 | 2484/3000 [1:11:57<13:03, 1.52s/it, lr: 1.0e-04 loss: 3.182e-01] jy: 83%|########2 | 2485/3000 [1:11:57<11:27, 1.33s/it, lr: 1.0e-04 loss: 3.182e-01] jy: 83%|########2 | 2485/3000 [1:11:57<11:27, 1.33s/it, lr: 1.0e-04 loss: 3.182e-01] jy: 83%|########2 | 2485/3000 [1:11:58<11:27, 1.33s/it, lr: 1.0e-04 loss: 8.744e-02] jy: 83%|########2 | 2485/3000 [1:11:58<11:27, 1.33s/it, lr: 1.0e-04 loss: 8.744e-02] jy: 83%|########2 | 2486/3000 [1:11:58<10:15, 1.20s/it, lr: 1.0e-04 loss: 8.744e-02] jy: 83%|########2 | 2486/3000 [1:11:58<10:15, 1.20s/it, lr: 1.0e-04 loss: 8.744e-02] jy: 83%|########2 | 2486/3000 [1:11:59<10:15, 1.20s/it, lr: 1.0e-04 loss: 1.785e-01] jy: 83%|########2 | 2486/3000 [1:11:59<10:15, 1.20s/it, lr: 1.0e-04 loss: 1.785e-01] jy: 83%|########2 | 2487/3000 [1:11:59<11:06, 1.30s/it, lr: 1.0e-04 loss: 1.785e-01] jy: 83%|########2 | 2487/3000 [1:11:59<11:06, 1.30s/it, lr: 1.0e-04 loss: 1.785e-01] jy: 83%|########2 | 2487/3000 [1:12:01<11:06, 1.30s/it, lr: 1.0e-04 loss: 1.520e-01] jy: 83%|########2 | 2487/3000 [1:12:01<11:06, 1.30s/it, lr: 1.0e-04 loss: 1.520e-01] jy: 83%|########2 | 2488/3000 [1:12:01<11:55, 1.40s/it, lr: 1.0e-04 loss: 1.520e-01] jy: 83%|########2 | 2488/3000 [1:12:01<11:55, 1.40s/it, lr: 1.0e-04 loss: 1.520e-01] jy: 83%|########2 | 2488/3000 [1:12:04<11:55, 1.40s/it, lr: 1.0e-04 loss: 5.327e-01] jy: 83%|########2 | 2488/3000 [1:12:04<11:55, 1.40s/it, lr: 1.0e-04 loss: 5.327e-01] jy: 83%|########2 | 2489/3000 [1:12:04<15:00, 1.76s/it, lr: 1.0e-04 loss: 5.327e-01] jy: 83%|########2 | 2489/3000 [1:12:04<15:00, 1.76s/it, lr: 1.0e-04 loss: 5.327e-01] jy: 83%|########2 | 2489/3000 [1:12:05<15:00, 1.76s/it, lr: 1.0e-04 loss: 3.626e-01] jy: 83%|########2 | 2489/3000 [1:12:05<15:00, 1.76s/it, lr: 1.0e-04 loss: 3.626e-01] jy: 83%|########2 | 2490/3000 [1:12:07<14:58, 1.76s/it, lr: 1.0e-04 loss: 6.853e-02] jy: 83%|########2 | 2490/3000 [1:12:07<14:58, 1.76s/it, lr: 1.0e-04 loss: 6.853e-02] jy: 83%|########3 | 2491/3000 [1:12:07<13:15, 1.56s/it, lr: 1.0e-04 loss: 6.853e-02] jy: 83%|########3 | 2491/3000 [1:12:07<13:15, 1.56s/it, lr: 1.0e-04 loss: 6.853e-02] jy: 83%|########3 | 2491/3000 [1:12:10<13:15, 1.56s/it, lr: 1.0e-04 loss: 3.944e-01] jy: 83%|########3 | 2491/3000 [1:12:10<13:15, 1.56s/it, lr: 1.0e-04 loss: 3.944e-01] jy: 83%|########3 | 2492/3000 [1:12:10<15:51, 1.87s/it, lr: 1.0e-04 loss: 3.944e-01] jy: 83%|########3 | 2492/3000 [1:12:10<15:51, 1.87s/it, lr: 1.0e-04 loss: 3.944e-01] jy: 83%|########3 | 2492/3000 [1:12:12<15:51, 1.87s/it, lr: 1.0e-04 loss: 2.608e-01] jy: 83%|########3 | 2492/3000 [1:12:12<15:51, 1.87s/it, lr: 1.0e-04 loss: 2.608e-01] jy: 83%|########3 | 2493/3000 [1:12:12<15:17, 1.81s/it, lr: 1.0e-04 loss: 2.608e-01] jy: 83%|########3 | 2493/3000 [1:12:12<15:17, 1.81s/it, lr: 1.0e-04 loss: 2.608e-01] jy: 83%|########3 | 2493/3000 [1:12:13<15:17, 1.81s/it, lr: 1.0e-04 loss: 1.811e-01] jy: 83%|########3 | 2493/3000 [1:12:13<15:17, 1.81s/it, lr: 1.0e-04 loss: 1.811e-01] jy: 83%|########3 | 2494/3000 [1:12:13<13:05, 1.55s/it, lr: 1.0e-04 loss: 1.811e-01] jy: 83%|########3 | 2494/3000 [1:12:13<13:05, 1.55s/it, lr: 1.0e-04 loss: 1.811e-01] jy: 83%|########3 | 2494/3000 [1:12:14<13:05, 1.55s/it, lr: 1.0e-04 loss: 1.190e-01] jy: 83%|########3 | 2494/3000 [1:12:14<13:05, 1.55s/it, lr: 1.0e-04 loss: 1.190e-01] jy: 83%|########3 | 2495/3000 [1:12:14<13:14, 1.57s/it, lr: 1.0e-04 loss: 1.190e-01] jy: 83%|########3 | 2495/3000 [1:12:14<13:14, 1.57s/it, lr: 1.0e-04 loss: 1.190e-01] jy: 83%|########3 | 2495/3000 [1:12:16<13:14, 1.57s/it, lr: 1.0e-04 loss: 1.694e-01] jy: 83%|########3 | 2495/3000 [1:12:16<13:14, 1.57s/it, lr: 1.0e-04 loss: 1.694e-01] jy: 83%|########3 | 2496/3000 [1:12:16<13:19, 1.59s/it, lr: 1.0e-04 loss: 1.694e-01] jy: 83%|########3 | 2496/3000 [1:12:16<13:19, 1.59s/it, lr: 1.0e-04 loss: 1.694e-01] jy: 83%|########3 | 2496/3000 [1:12:17<13:19, 1.59s/it, lr: 1.0e-04 loss: 1.910e-01] jy: 83%|########3 | 2496/3000 [1:12:17<13:19, 1.59s/it, lr: 1.0e-04 loss: 1.910e-01] jy: 83%|########3 | 2497/3000 [1:12:17<11:31, 1.38s/it, lr: 1.0e-04 loss: 1.910e-01] jy: 83%|########3 | 2497/3000 [1:12:17<11:31, 1.38s/it, lr: 1.0e-04 loss: 1.910e-01] jy: 83%|########3 | 2497/3000 [1:12:18<11:31, 1.38s/it, lr: 1.0e-04 loss: 4.436e-01] jy: 83%|########3 | 2497/3000 [1:12:18<11:31, 1.38s/it, lr: 1.0e-04 loss: 4.436e-01] jy: 83%|########3 | 2498/3000 [1:12:18<10:47, 1.29s/it, lr: 1.0e-04 loss: 4.436e-01] jy: 83%|########3 | 2498/3000 [1:12:18<10:47, 1.29s/it, lr: 1.0e-04 loss: 4.436e-01] jy: 83%|########3 | 2498/3000 [1:12:19<10:47, 1.29s/it, lr: 1.0e-04 loss: 6.063e-01] jy: 83%|########3 | 2498/3000 [1:12:19<10:47, 1.29s/it, lr: 1.0e-04 loss: 6.063e-01] jy: 83%|########3 | 2499/3000 [1:12:19<09:44, 1.17s/it, lr: 1.0e-04 loss: 6.063e-01] jy: 83%|########3 | 2499/3000 [1:12:19<09:44, 1.17s/it, lr: 1.0e-04 loss: 6.063e-01] jy: 83%|########3 | 2499/3000 [1:12:20<09:44, 1.17s/it, lr: 1.0e-04 loss: 9.804e-02] jy: 83%|########3 | 2499/3000 [1:12:20<09:44, 1.17s/it, lr: 1.0e-04 loss: 9.804e-02] +Saving at step 2500 +Saved checkpoint to /workspace/ai-toolkit/output/jy/jy_000002500.safetensors +Saved optimizer to /workspace/ai-toolkit/output/jy/optimizer.pt +Removing old save: /workspace/ai-toolkit/output/jy/jy_000001500.safetensors +Unloading assistant lora + + + Generating Images: 0%| | 0/3 [00:00