1step 0 loss 4.8939 lr 5.00e-06 gn 8.59 (1s)2step 50 loss 2.6652 lr 2.55e-04 gn 1.46 (5s)3step 100 loss 1.3162 lr 5.05e-04 gn 4.86 (8s)4step 150 loss 0.4148 lr 7.55e-04 gn 1.01 (13s)5step 200 loss 0.3202 lr 1.00e-03 gn 1.07 (18s)6step 250 loss 0.3024 lr 1.00e-03 gn 0.78 (25s)7step 300 loss 0.2866 lr 9.99e-04 gn 0.70 (31s)8step 350 loss 0.3067 lr 9.99e-04 gn 0.20 (37s)9step 400 loss 0.3004 lr 9.97e-04 gn 0.33 (43s)10step 450 loss 0.3216 lr 9.96e-04 gn 0.19 (49s)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: 0.3442}14step 500 loss 0.2586 lr 9.94e-04 gn 0.31 (55s)15step 550 loss 0.2762 lr 9.92e-04 gn 0.17 (60s)16step 600 loss 0.2699 lr 9.89e-04 gn 0.41 (65s)17step 650 loss 0.2476 lr 9.87e-04 gn 0.14 (70s)18step 700 loss 0.2661 lr 9.84e-04 gn 0.20 (76s)19step 750 loss 0.2945 lr 9.80e-04 gn 0.60 (83s)20step 800 loss 0.2794 lr 9.76e-04 gn 0.17 (89s)21step 850 loss 0.2734 lr 9.72e-04 gn 0.37 (94s)22step 900 loss 0.2699 lr 9.68e-04 gn 0.13 (100s)23step 950 loss 0.2383 lr 9.63e-04 gn 0.22 (106s)24 val loss by budget: {0: 0.3359}25step 1000 loss 0.2349 lr 9.58e-04 gn 0.16 (113s)26step 1050 loss 0.2839 lr 9.53e-04 gn 0.12 (120s)27step 1100 loss 0.2538 lr 9.48e-04 gn 0.17 (126s)28step 1150 loss 0.2460 lr 9.42e-04 gn 0.11 (132s)29step 1200 loss 0.2379 lr 9.36e-04 gn 0.10 (137s)30step 1250 loss 0.2589 lr 9.29e-04 gn 0.12 (140s)31step 1300 loss 0.2360 lr 9.22e-04 gn 0.12 (143s)32step 1350 loss 0.2176 lr 9.15e-04 gn 0.10 (146s)33step 1400 loss 0.2602 lr 9.08e-04 gn 0.17 (149s)34step 1450 loss 0.2529 lr 9.01e-04 gn 0.28 (153s)35 val loss by budget: {0: 0.3323}36step 1500 loss 0.2497 lr 8.93e-04 gn 0.16 (156s)37step 1550 loss 0.2382 lr 8.85e-04 gn 0.10 (159s)38step 1600 loss 0.2719 lr 8.77e-04 gn 0.14 (162s)39step 1650 loss 0.2541 lr 8.68e-04 gn 0.17 (165s)40step 1700 loss 0.2504 lr 8.59e-04 gn 0.65 (169s)41step 1750 loss 0.2747 lr 8.51e-04 gn 0.13 (172s)42step 1800 loss 0.2351 lr 8.41e-04 gn 0.10 (175s)43step 1850 loss 0.2330 lr 8.32e-04 gn 0.10 (178s)44step 1900 loss 0.2855 lr 8.22e-04 gn 0.25 (181s)45step 1950 loss 0.2553 lr 8.13e-04 gn 0.11 (184s)46 val loss by budget: {0: 0.3302}47step 2000 loss 0.2522 lr 8.03e-04 gn 0.12 (188s)48step 2050 loss 0.2358 lr 7.92e-04 gn 0.10 (191s)49step 2100 loss 0.2425 lr 7.82e-04 gn 0.09 (194s)50step 2150 loss 0.2425 lr 7.71e-04 gn 0.11 (197s)51step 2200 loss 0.2508 lr 7.61e-04 gn 0.12 (200s)52step 2250 loss 0.2491 lr 7.50e-04 gn 0.11 (203s)53step 2300 loss 0.2339 lr 7.39e-04 gn 0.18 (206s)54step 2350 loss 0.2585 lr 7.28e-04 gn 0.11 (209s)55step 2400 loss 0.2410 lr 7.17e-04 gn 0.10 (212s)56step 2450 loss 0.2468 lr 7.05e-04 gn 0.11 (216s)57 val loss by budget: {0: 0.3201}58step 2500 loss 0.2032 lr 6.94e-04 gn 0.07 (222s)59step 2550 loss 0.2504 lr 6.82e-04 gn 0.10 (227s)60step 2600 loss 0.2793 lr 6.70e-04 gn 0.33 (230s)61step 2650 loss 0.2291 lr 6.59e-04 gn 0.10 (233s)62step 2700 loss 0.2244 lr 6.47e-04 gn 0.09 (236s)63step 2750 loss 0.2509 lr 6.35e-04 gn 0.09 (239s)64step 2800 loss 0.2486 lr 6.23e-04 gn 0.15 (243s)65step 2850 loss 0.2506 lr 6.11e-04 gn 0.12 (246s)66step 2900 loss 0.2540 lr 5.99e-04 gn 0.09 (249s)67step 2950 loss 0.2392 lr 5.87e-04 gn 0.14 (252s)68 val loss by budget: {0: 0.321}69step 3000 loss 0.2273 lr 5.74e-04 gn 0.09 (255s)70step 3050 loss 0.2507 lr 5.62e-04 gn 0.11 (258s)71step 3100 loss 0.2325 lr 5.50e-04 gn 0.09 (261s)72step 3150 loss 0.2582 lr 5.38e-04 gn 0.10 (264s)73step 3200 loss 0.2588 lr 5.26e-04 gn 0.09 (267s)74step 3250 loss 0.2254 lr 5.13e-04 gn 0.10 (271s)75step 3300 loss 0.2503 lr 5.01e-04 gn 0.10 (274s)76step 3350 loss 0.2291 lr 4.89e-04 gn 0.11 (277s)77step 3400 loss 0.2388 lr 4.77e-04 gn 0.12 (280s)78step 3450 loss 0.2407 lr 4.65e-04 gn 0.10 (283s)79 val loss by budget: {0: 0.3114}80step 3500 loss 0.2560 lr 4.53e-04 gn 0.11 (286s)81step 3550 loss 0.2474 lr 4.41e-04 gn 0.10 (289s)82step 3600 loss 0.2318 lr 4.30e-04 gn 0.09 (293s)83step 3650 loss 0.2472 lr 4.18e-04 gn 0.14 (296s)84step 3700 loss 0.2499 lr 4.06e-04 gn 0.11 (299s)85step 3750 loss 0.2372 lr 3.95e-04 gn 0.11 (302s)86step 3800 loss 0.2410 lr 3.83e-04 gn 0.09 (305s)87step 3850 loss 0.2248 lr 3.72e-04 gn 0.10 (308s)88step 3900 loss 0.2280 lr 3.61e-04 gn 0.14 (311s)89step 3950 loss 0.2196 lr 3.50e-04 gn 0.11 (314s)90 val loss by budget: {0: 0.3086}91step 4000 loss 0.2459 lr 3.39e-04 gn 0.12 (318s)92step 4050 loss 0.2521 lr 3.29e-04 gn 0.19 (321s)93step 4100 loss 0.2355 lr 3.18e-04 gn 0.11 (324s)94step 4150 loss 0.2322 lr 3.08e-04 gn 0.11 (327s)95step 4200 loss 0.2551 lr 2.97e-04 gn 0.13 (330s)96step 4250 loss 0.2327 lr 2.87e-04 gn 0.11 (333s)97step 4300 loss 0.2298 lr 2.78e-04 gn 0.09 (336s)98step 4350 loss 0.2219 lr 2.68e-04 gn 0.09 (339s)99step 4400 loss 0.2135 lr 2.59e-04 gn 0.10 (342s)100step 4450 loss 0.2403 lr 2.49e-04 gn 0.15 (345s)101 val loss by budget: {0: 0.3071}102step 4500 loss 0.2340 lr 2.41e-04 gn 0.15 (349s)103step 4550 loss 0.2213 lr 2.32e-04 gn 0.10 (352s)104step 4600 loss 0.2408 lr 2.23e-04 gn 0.17 (355s)105step 4650 loss 0.2439 lr 2.15e-04 gn 0.13 (358s)106step 4700 loss 0.2252 lr 2.07e-04 gn 0.10 (361s)107step 4750 loss 0.2516 lr 1.99e-04 gn 0.13 (364s)108step 4800 loss 0.2269 lr 1.92e-04 gn 0.11 (367s)109step 4850 loss 0.2402 lr 1.85e-04 gn 0.12 (370s)110step 4900 loss 0.2151 lr 1.78e-04 gn 0.10 (373s)111step 4950 loss 0.2455 lr 1.71e-04 gn 0.11 (376s)112 val loss by budget: {0: 0.3014}113step 5000 loss 0.2237 lr 1.64e-04 gn 0.11 (380s)114step 5050 loss 0.2350 lr 1.58e-04 gn 0.15 (383s)115step 5100 loss 0.2314 lr 1.52e-04 gn 0.12 (386s)116step 5150 loss 0.2369 lr 1.47e-04 gn 0.18 (389s)117step 5200 loss 0.2397 lr 1.42e-04 gn 0.12 (392s)118step 5250 loss 0.2292 lr 1.37e-04 gn 0.12 (395s)119step 5300 loss 0.2356 lr 1.32e-04 gn 0.14 (398s)120step 5350 loss 0.2255 lr 1.28e-04 gn 0.14 (401s)121step 5400 loss 0.2234 lr 1.24e-04 gn 0.15 (404s)122step 5450 loss 0.2575 lr 1.20e-04 gn 0.14 (407s)123 val loss by budget: {0: 0.2992}124step 5500 loss 0.2173 lr 1.16e-04 gn 0.12 (410s)125step 5550 loss 0.2077 lr 1.13e-04 gn 0.11 (413s)126step 5600 loss 0.2294 lr 1.11e-04 gn 0.12 (416s)127step 5650 loss 0.2250 lr 1.08e-04 gn 0.15 (420s)128step 5700 loss 0.2534 lr 1.06e-04 gn 0.15 (423s)129step 5750 loss 0.2329 lr 1.04e-04 gn 0.14 (427s)130step 5800 loss 0.2255 lr 1.03e-04 gn 0.14 (433s)131step 5850 loss 0.2264 lr 1.01e-04 gn 0.13 (437s)132step 5900 loss 0.2215 lr 1.01e-04 gn 0.14 (440s)133step 5950 loss 0.2278 lr 1.00e-04 gn 0.14 (443s)134step 5999 loss 0.2145 lr 1.00e-04 gn 0.12 (446s)135 val loss by budget: {0: 0.2992}136 exact match dev_iid budget 0: 0.1683 (n=600) by family {'arith': 0.16833333333333333}137 exact match dev_template budget 0: 0.1367 (n=600) by family {'arith': 0.07547169811320754, 'bind': 0.37398373983739835}138 exact match dev_depth budget 0: 0.0300 (n=600) by family {'arith': 0.019444444444444445, 'bind': 0.04583333333333333}139 exact match dev_compose budget 0: 0.0241 (n=540) by family {'compose': 0.024074074074074074}140run p4_tiny_backbone_seed01_20261029232626 done141