1step 0 loss 4.9416 lr 3.33e-06 gn 11.57 (2s)2step 100 loss 1.0250 lr 3.37e-04 gn 6.28 (30s)3step 200 loss 0.3161 lr 6.70e-04 gn 1.37 (49s)4step 300 loss 0.3000 lr 1.00e-03 gn 0.95 (68s)5step 400 loss 0.3070 lr 1.00e-03 gn 0.54 (87s)6step 500 loss 0.2640 lr 1.00e-03 gn 0.28 (106s)7step 600 loss 0.2662 lr 9.99e-04 gn 0.16 (126s)8step 700 loss 0.2637 lr 9.98e-04 gn 0.13 (145s)9step 800 loss 0.2783 lr 9.97e-04 gn 0.15 (164s)10step 900 loss 0.2698 lr 9.96e-04 gn 0.18 (184s)11/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/training/train_editor.py:55: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /Users/runner/work/pytorch/pytorch/torch/csrc/utils/tensor_numpy.cpp:214.)12 return torch.from_numpy(acts).to(device), torch.from_numpy(np.ascontiguousarray(b)).to(device)13 val loss by budget: {0: 0.2595}14step 1000 loss 0.2317 lr 9.95e-04 gn 0.11 (203s)15step 1100 loss 0.2553 lr 9.93e-04 gn 0.39 (223s)16step 1200 loss 0.2368 lr 9.92e-04 gn 0.13 (243s)17step 1300 loss 0.2362 lr 9.90e-04 gn 0.11 (262s)18step 1400 loss 0.2610 lr 9.88e-04 gn 0.15 (282s)19step 1500 loss 0.2479 lr 9.85e-04 gn 0.09 (302s)20step 1600 loss 0.2702 lr 9.83e-04 gn 0.13 (321s)21step 1700 loss 0.2404 lr 9.80e-04 gn 0.12 (340s)22step 1800 loss 0.2340 lr 9.77e-04 gn 0.09 (360s)23step 1900 loss 0.2829 lr 9.74e-04 gn 0.10 (380s)24 val loss by budget: {0: 0.2533}25step 2000 loss 0.2506 lr 9.71e-04 gn 0.12 (400s)26step 2100 loss 0.2389 lr 9.67e-04 gn 0.09 (426s)27step 2200 loss 0.2490 lr 9.63e-04 gn 0.15 (455s)28step 2300 loss 0.2360 lr 9.60e-04 gn 0.16 (484s)29step 2400 loss 0.2411 lr 9.55e-04 gn 0.09 (512s)30step 2500 loss 0.2048 lr 9.51e-04 gn 0.07 (541s)31step 2600 loss 0.2770 lr 9.47e-04 gn 0.11 (570s)32step 2700 loss 0.2219 lr 9.42e-04 gn 0.07 (600s)33step 2800 loss 0.2500 lr 9.37e-04 gn 0.11 (629s)34step 2900 loss 0.2512 lr 9.32e-04 gn 0.08 (658s)35 val loss by budget: {0: 0.2491}36step 3000 loss 0.2259 lr 9.27e-04 gn 0.08 (688s)37step 3100 loss 0.2322 lr 9.22e-04 gn 0.09 (716s)38step 3200 loss 0.2616 lr 9.16e-04 gn 0.10 (743s)39step 3300 loss 0.2512 lr 9.11e-04 gn 0.09 (763s)40step 3400 loss 0.2397 lr 9.05e-04 gn 0.12 (782s)41step 3500 loss 0.2581 lr 8.99e-04 gn 0.10 (804s)42step 3600 loss 0.2327 lr 8.93e-04 gn 0.09 (833s)43step 3700 loss 0.2532 lr 8.86e-04 gn 0.09 (862s)44step 3800 loss 0.2413 lr 8.80e-04 gn 0.08 (893s)45step 3900 loss 0.2293 lr 8.73e-04 gn 0.09 (927s)46 val loss by budget: {0: 0.2467}47step 4000 loss 0.2489 lr 8.66e-04 gn 0.08 (966s)48step 4100 loss 0.2392 lr 8.60e-04 gn 0.09 (1009s)49step 4200 loss 0.2620 lr 8.53e-04 gn 0.10 (1046s)50step 4300 loss 0.2340 lr 8.45e-04 gn 0.10 (1077s)51step 4400 loss 0.2159 lr 8.38e-04 gn 0.09 (1104s)52step 4500 loss 0.2391 lr 8.31e-04 gn 0.11 (1129s)53step 4600 loss 0.2459 lr 8.23e-04 gn 0.10 (1153s)54step 4700 loss 0.2321 lr 8.15e-04 gn 0.08 (1177s)55step 4800 loss 0.2316 lr 8.07e-04 gn 0.08 (1201s)56step 4900 loss 0.2222 lr 8.00e-04 gn 0.09 (1225s)57 val loss by budget: {0: 0.2458}58step 5000 loss 0.2277 lr 7.91e-04 gn 0.08 (1252s)59step 5100 loss 0.2377 lr 7.83e-04 gn 0.11 (1277s)60step 5200 loss 0.2480 lr 7.75e-04 gn 0.10 (1302s)61step 5300 loss 0.2394 lr 7.67e-04 gn 0.09 (1327s)62step 5400 loss 0.2269 lr 7.58e-04 gn 0.09 (1351s)63step 5500 loss 0.2226 lr 7.50e-04 gn 0.07 (1379s)64step 5600 loss 0.2372 lr 7.41e-04 gn 0.10 (1411s)65step 5700 loss 0.2575 lr 7.32e-04 gn 0.15 (1438s)66step 5800 loss 0.2327 lr 7.23e-04 gn 0.09 (1467s)67step 5900 loss 0.2266 lr 7.14e-04 gn 0.08 (1495s)68 val loss by budget: {0: 0.2471}69step 6000 loss 0.2355 lr 7.05e-04 gn 0.09 (1525s)70step 6100 loss 0.2458 lr 6.96e-04 gn 0.09 (1556s)71step 6200 loss 0.2058 lr 6.87e-04 gn 0.08 (1585s)72step 6300 loss 0.2245 lr 6.78e-04 gn 0.10 (1614s)73step 6400 loss 0.2180 lr 6.69e-04 gn 0.10 (1642s)74step 6500 loss 0.2223 lr 6.59e-04 gn 0.08 (1670s)75step 6600 loss 0.2298 lr 6.50e-04 gn 0.09 (1693s)76step 6700 loss 0.2283 lr 6.41e-04 gn 0.09 (1719s)77step 6800 loss 0.2490 lr 6.31e-04 gn 0.11 (1745s)78step 6900 loss 0.2456 lr 6.22e-04 gn 0.11 (1766s)79 val loss by budget: {0: 0.2523}80step 7000 loss 0.2237 lr 6.12e-04 gn 0.10 (1798s)81step 7100 loss 0.2181 lr 6.03e-04 gn 0.10 (1827s)82step 7200 loss 0.1884 lr 5.93e-04 gn 0.10 (1857s)83step 7300 loss 0.2220 lr 5.84e-04 gn 0.09 (1884s)84step 7400 loss 0.2312 lr 5.74e-04 gn 0.10 (1914s)85step 7500 loss 0.2148 lr 5.64e-04 gn 0.10 (1942s)86step 7600 loss 0.2208 lr 5.55e-04 gn 0.09 (1966s)87step 7700 loss 0.2331 lr 5.45e-04 gn 0.11 (1992s)88step 7800 loss 0.2063 lr 5.36e-04 gn 0.11 (2017s)89step 7900 loss 0.2102 lr 5.26e-04 gn 0.10 (2040s)90 val loss by budget: {0: 0.264}91step 8000 loss 0.2142 lr 5.16e-04 gn 0.11 (2066s)92step 8100 loss 0.1659 lr 5.07e-04 gn 0.08 (2095s)93step 8200 loss 0.2003 lr 4.97e-04 gn 0.13 (2124s)94step 8300 loss 0.2093 lr 4.88e-04 gn 0.12 (2152s)95step 8400 loss 0.1932 lr 4.78e-04 gn 0.11 (2181s)96step 8500 loss 0.2004 lr 4.69e-04 gn 0.12 (2207s)97step 8600 loss 0.2052 lr 4.59e-04 gn 0.13 (2233s)98step 8700 loss 0.2038 lr 4.50e-04 gn 0.12 (2261s)99step 8800 loss 0.1986 lr 4.41e-04 gn 0.13 (2290s)100step 8900 loss 0.2058 lr 4.31e-04 gn 0.12 (2321s)101 val loss by budget: {0: 0.2822}102step 9000 loss 0.1914 lr 4.22e-04 gn 0.14 (2351s)103step 9100 loss 0.2039 lr 4.13e-04 gn 0.15 (2380s)104step 9200 loss 0.1904 lr 4.04e-04 gn 0.15 (2407s)105step 9300 loss 0.1848 lr 3.95e-04 gn 0.13 (2432s)106step 9400 loss 0.1662 lr 3.86e-04 gn 0.14 (2455s)107step 9500 loss 0.1821 lr 3.77e-04 gn 0.16 (2475s)108