step 0 loss 4.9416 lr 3.33e-06 gn 11.57 (2s) step 100 loss 1.0250 lr 3.37e-04 gn 6.28 (30s) step 200 loss 0.3161 lr 6.70e-04 gn 1.37 (49s) step 300 loss 0.3000 lr 1.00e-03 gn 0.95 (68s) step 400 loss 0.3070 lr 1.00e-03 gn 0.54 (87s) step 500 loss 0.2640 lr 1.00e-03 gn 0.28 (106s) step 600 loss 0.2662 lr 9.99e-04 gn 0.16 (126s) step 700 loss 0.2637 lr 9.98e-04 gn 0.13 (145s) step 800 loss 0.2783 lr 9.97e-04 gn 0.15 (164s) step 900 loss 0.2698 lr 9.96e-04 gn 0.18 (184s) /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.) return torch.from_numpy(acts).to(device), torch.from_numpy(np.ascontiguousarray(b)).to(device) val loss by budget: {0: 0.2595} step 1000 loss 0.2317 lr 9.95e-04 gn 0.11 (203s) step 1100 loss 0.2553 lr 9.93e-04 gn 0.39 (223s) step 1200 loss 0.2368 lr 9.92e-04 gn 0.13 (243s) step 1300 loss 0.2362 lr 9.90e-04 gn 0.11 (262s) step 1400 loss 0.2610 lr 9.88e-04 gn 0.15 (282s) step 1500 loss 0.2479 lr 9.85e-04 gn 0.09 (302s) step 1600 loss 0.2702 lr 9.83e-04 gn 0.13 (321s) step 1700 loss 0.2404 lr 9.80e-04 gn 0.12 (340s) step 1800 loss 0.2340 lr 9.77e-04 gn 0.09 (360s) step 1900 loss 0.2829 lr 9.74e-04 gn 0.10 (380s) val loss by budget: {0: 0.2533} step 2000 loss 0.2506 lr 9.71e-04 gn 0.12 (400s) step 2100 loss 0.2389 lr 9.67e-04 gn 0.09 (426s) step 2200 loss 0.2490 lr 9.63e-04 gn 0.15 (455s) step 2300 loss 0.2360 lr 9.60e-04 gn 0.16 (484s) step 2400 loss 0.2411 lr 9.55e-04 gn 0.09 (512s) step 2500 loss 0.2048 lr 9.51e-04 gn 0.07 (541s) step 2600 loss 0.2770 lr 9.47e-04 gn 0.11 (570s) step 2700 loss 0.2219 lr 9.42e-04 gn 0.07 (600s) step 2800 loss 0.2500 lr 9.37e-04 gn 0.11 (629s) step 2900 loss 0.2512 lr 9.32e-04 gn 0.08 (658s) val loss by budget: {0: 0.2491} step 3000 loss 0.2259 lr 9.27e-04 gn 0.08 (688s) step 3100 loss 0.2322 lr 9.22e-04 gn 0.09 (716s) step 3200 loss 0.2616 lr 9.16e-04 gn 0.10 (743s) step 3300 loss 0.2512 lr 9.11e-04 gn 0.09 (763s) step 3400 loss 0.2397 lr 9.05e-04 gn 0.12 (782s) step 3500 loss 0.2581 lr 8.99e-04 gn 0.10 (804s) step 3600 loss 0.2327 lr 8.93e-04 gn 0.09 (833s) step 3700 loss 0.2532 lr 8.86e-04 gn 0.09 (862s) step 3800 loss 0.2413 lr 8.80e-04 gn 0.08 (893s) step 3900 loss 0.2293 lr 8.73e-04 gn 0.09 (927s) val loss by budget: {0: 0.2467} step 4000 loss 0.2489 lr 8.66e-04 gn 0.08 (966s) step 4100 loss 0.2392 lr 8.60e-04 gn 0.09 (1009s) step 4200 loss 0.2620 lr 8.53e-04 gn 0.10 (1046s) step 4300 loss 0.2340 lr 8.45e-04 gn 0.10 (1077s) step 4400 loss 0.2159 lr 8.38e-04 gn 0.09 (1104s) step 4500 loss 0.2391 lr 8.31e-04 gn 0.11 (1129s) step 4600 loss 0.2459 lr 8.23e-04 gn 0.10 (1153s) step 4700 loss 0.2321 lr 8.15e-04 gn 0.08 (1177s) step 4800 loss 0.2316 lr 8.07e-04 gn 0.08 (1201s) step 4900 loss 0.2222 lr 8.00e-04 gn 0.09 (1225s) val loss by budget: {0: 0.2458} step 5000 loss 0.2277 lr 7.91e-04 gn 0.08 (1252s) step 5100 loss 0.2377 lr 7.83e-04 gn 0.11 (1277s) step 5200 loss 0.2480 lr 7.75e-04 gn 0.10 (1302s) step 5300 loss 0.2394 lr 7.67e-04 gn 0.09 (1327s) step 5400 loss 0.2269 lr 7.58e-04 gn 0.09 (1351s) step 5500 loss 0.2226 lr 7.50e-04 gn 0.07 (1379s) step 5600 loss 0.2372 lr 7.41e-04 gn 0.10 (1411s) step 5700 loss 0.2575 lr 7.32e-04 gn 0.15 (1438s) step 5800 loss 0.2327 lr 7.23e-04 gn 0.09 (1467s) step 5900 loss 0.2266 lr 7.14e-04 gn 0.08 (1495s) val loss by budget: {0: 0.2471} step 6000 loss 0.2355 lr 7.05e-04 gn 0.09 (1525s) step 6100 loss 0.2458 lr 6.96e-04 gn 0.09 (1556s) step 6200 loss 0.2058 lr 6.87e-04 gn 0.08 (1585s) step 6300 loss 0.2245 lr 6.78e-04 gn 0.10 (1614s) step 6400 loss 0.2180 lr 6.69e-04 gn 0.10 (1642s) step 6500 loss 0.2223 lr 6.59e-04 gn 0.08 (1670s) step 6600 loss 0.2298 lr 6.50e-04 gn 0.09 (1693s) step 6700 loss 0.2283 lr 6.41e-04 gn 0.09 (1719s) step 6800 loss 0.2490 lr 6.31e-04 gn 0.11 (1745s) step 6900 loss 0.2456 lr 6.22e-04 gn 0.11 (1766s) val loss by budget: {0: 0.2523} step 7000 loss 0.2237 lr 6.12e-04 gn 0.10 (1798s) step 7100 loss 0.2181 lr 6.03e-04 gn 0.10 (1827s) step 7200 loss 0.1884 lr 5.93e-04 gn 0.10 (1857s) step 7300 loss 0.2220 lr 5.84e-04 gn 0.09 (1884s) step 7400 loss 0.2312 lr 5.74e-04 gn 0.10 (1914s) step 7500 loss 0.2148 lr 5.64e-04 gn 0.10 (1942s) step 7600 loss 0.2208 lr 5.55e-04 gn 0.09 (1966s) step 7700 loss 0.2331 lr 5.45e-04 gn 0.11 (1992s) step 7800 loss 0.2063 lr 5.36e-04 gn 0.11 (2017s) step 7900 loss 0.2102 lr 5.26e-04 gn 0.10 (2040s) val loss by budget: {0: 0.264} step 8000 loss 0.2142 lr 5.16e-04 gn 0.11 (2066s) step 8100 loss 0.1659 lr 5.07e-04 gn 0.08 (2095s) step 8200 loss 0.2003 lr 4.97e-04 gn 0.13 (2124s) step 8300 loss 0.2093 lr 4.88e-04 gn 0.12 (2152s) step 8400 loss 0.1932 lr 4.78e-04 gn 0.11 (2181s) step 8500 loss 0.2004 lr 4.69e-04 gn 0.12 (2207s) step 8600 loss 0.2052 lr 4.59e-04 gn 0.13 (2233s) step 8700 loss 0.2038 lr 4.50e-04 gn 0.12 (2261s) step 8800 loss 0.1986 lr 4.41e-04 gn 0.13 (2290s) step 8900 loss 0.2058 lr 4.31e-04 gn 0.12 (2321s) val loss by budget: {0: 0.2822} step 9000 loss 0.1914 lr 4.22e-04 gn 0.14 (2351s) step 9100 loss 0.2039 lr 4.13e-04 gn 0.15 (2380s) step 9200 loss 0.1904 lr 4.04e-04 gn 0.15 (2407s) step 9300 loss 0.1848 lr 3.95e-04 gn 0.13 (2432s) step 9400 loss 0.1662 lr 3.86e-04 gn 0.14 (2455s) step 9500 loss 0.1821 lr 3.77e-04 gn 0.16 (2475s)