1loaded backbone from experiments/runs/p4_tiny_backbone_seed01_20261029232626/checkpoint missing: 352readout_scale set to backbone residual rms = 5.2513/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.)4 return torch.from_numpy(acts).to(device), torch.from_numpy(np.ascontiguousarray(b)).to(device)5step 0 loss 0.2574 lr 1.00e-05 gn 0.02 (1s)6step 50 loss 0.2963 lr 5.10e-04 gn 0.02 (35s)7step 100 loss 0.2928 lr 1.00e-03 gn 0.03 (68s)8step 150 loss 0.2752 lr 9.99e-04 gn 0.04 (101s)9step 200 loss 0.2912 lr 9.97e-04 gn 0.03 (134s)10step 250 loss 0.2685 lr 9.94e-04 gn 0.02 (168s)11step 300 loss 0.2521 lr 9.89e-04 gn 0.02 (200s)12step 350 loss 0.3760 lr 9.84e-04 gn 0.10 (234s)13step 400 loss 0.2934 lr 9.76e-04 gn 0.03 (266s)14step 450 loss 0.2019 lr 9.68e-04 gn 0.06 (299s)15 val loss by budget: {0: 0.4144, 1: 0.4139, 2: 0.4133, 4: 0.4131, 8: 0.4149}16step 500 loss 0.3621 lr 9.58e-04 gn 0.03 (327s)17step 550 loss 0.2949 lr 9.48e-04 gn 0.04 (349s)18step 600 loss 0.3686 lr 9.36e-04 gn 0.07 (372s)19step 650 loss 0.3048 lr 9.22e-04 gn 0.03 (407s)20step 700 loss 0.3155 lr 9.08e-04 gn 0.04 (440s)21step 750 loss 0.2576 lr 8.93e-04 gn 0.02 (478s)22step 800 loss 0.3423 lr 8.77e-04 gn 0.04 (527s)23step 850 loss 0.3550 lr 8.59e-04 gn 0.07 (579s)24step 900 loss 0.3444 lr 8.41e-04 gn 0.06 (627s)25step 950 loss 0.3196 lr 8.22e-04 gn 0.05 (671s)26 val loss by budget: {0: 0.4144, 1: 0.4129, 2: 0.4124, 4: 0.4123, 8: 0.4146}27step 1000 loss 0.3007 lr 8.03e-04 gn 0.06 (751s)28step 1050 loss 0.2752 lr 7.82e-04 gn 0.10 (820s)29step 1100 loss 0.2404 lr 7.61e-04 gn 0.08 (889s)30step 1150 loss 0.3453 lr 7.39e-04 gn 0.05 (948s)31step 1200 loss 0.3205 lr 7.17e-04 gn 0.08 (987s)32step 1250 loss 0.3766 lr 6.94e-04 gn 0.11 (1018s)33step 1300 loss 0.2507 lr 6.70e-04 gn 0.03 (1053s)34step 1350 loss 0.2750 lr 6.47e-04 gn 0.09 (1087s)35step 1400 loss 0.2685 lr 6.23e-04 gn 0.09 (1124s)36step 1450 loss 0.3713 lr 5.99e-04 gn 0.09 (1158s)37 val loss by budget: {0: 0.4144, 1: 0.412, 2: 0.412, 4: 0.4141, 8: 0.4231}38step 1500 loss 0.2672 lr 5.74e-04 gn 0.11 (1197s)39step 1550 loss 0.3123 lr 5.50e-04 gn 0.10 (1231s)40step 1600 loss 0.2820 lr 5.26e-04 gn 0.09 (1259s)41step 1650 loss 0.3476 lr 5.01e-04 gn 0.06 (1289s)42step 1700 loss 0.3768 lr 4.77e-04 gn 0.09 (1318s)43step 1750 loss 0.2676 lr 4.53e-04 gn 0.05 (1347s)44step 1800 loss 0.2471 lr 4.30e-04 gn 0.05 (1382s)45step 1850 loss 0.2802 lr 4.06e-04 gn 0.10 (1418s)46step 1900 loss 0.2870 lr 3.83e-04 gn 0.07 (1452s)47step 1950 loss 0.2158 lr 3.61e-04 gn 0.09 (1488s)48 val loss by budget: {0: 0.4144, 1: 0.4119, 2: 0.4129, 4: 0.4139, 8: 0.4241}49step 2000 loss 0.2418 lr 3.39e-04 gn 0.09 (1524s)50step 2050 loss 0.2704 lr 3.18e-04 gn 0.12 (1553s)51step 2100 loss 0.2859 lr 2.97e-04 gn 0.15 (1583s)52step 2150 loss 0.2684 lr 2.78e-04 gn 0.06 (1611s)53step 2200 loss 0.2357 lr 2.59e-04 gn 0.11 (1640s)54step 2250 loss 0.2331 lr 2.41e-04 gn 0.06 (1674s)55step 2300 loss 0.2750 lr 2.23e-04 gn 0.08 (1709s)56step 2350 loss 0.2091 lr 2.07e-04 gn 0.10 (1742s)57step 2400 loss 0.1803 lr 1.92e-04 gn 0.08 (1774s)58step 2450 loss 0.3071 lr 1.78e-04 gn 0.09 (1804s)59 val loss by budget: {0: 0.4144, 1: 0.41, 2: 0.41, 4: 0.4111, 8: 0.4188}60step 2500 loss 0.3278 lr 1.64e-04 gn 0.13 (1842s)61step 2550 loss 0.2849 lr 1.52e-04 gn 0.09 (1877s)62step 2600 loss 0.2684 lr 1.42e-04 gn 0.12 (1911s)63step 2650 loss 0.2542 lr 1.32e-04 gn 0.16 (1946s)64step 2700 loss 0.1905 lr 1.24e-04 gn 0.08 (1978s)65step 2750 loss 0.2685 lr 1.16e-04 gn 0.13 (2007s)66step 2800 loss 0.2449 lr 1.11e-04 gn 0.10 (2034s)67step 2850 loss 0.2741 lr 1.06e-04 gn 0.17 (2059s)68step 2900 loss 0.2866 lr 1.03e-04 gn 0.13 (2084s)69step 2950 loss 0.2046 lr 1.01e-04 gn 0.07 (2104s)70step 2999 loss 0.3118 lr 1.00e-04 gn 0.08 (2120s)71 val loss by budget: {0: 0.4144, 1: 0.4093, 2: 0.4092, 4: 0.411, 8: 0.4192}72 exact match dev_iid budget 0: 0.4375 (n=400) by family {'fsm': 0.640625, 'bind': 0.38372093023255816, 'arith': 0.22784810126582278, 'excl': 0.27906976744186046, 'sched': 0.6941176470588235}73Traceback (most recent call last):74 File "<frozen runpy>", line 198, in _run_module_as_main75 File "<frozen runpy>", line 88, in _run_code76 File "/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/training/train_editor.py", line 186, in <module>77 metrics_file=str(run.dir / "metrics.jsonl"))78 ^^^^^^79 File "/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/training/train_editor.py", line 173, in main80 for name, vs in val_sets.items():81 ^^^^^^^^^^^^^^^^^^^^82 File "/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 158, in no_grad83 return func(*args, **kwargs)84 ^^^^^^^^^^^^^^^^^^^^^85 File "/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/data/synthetic_dataset.py", line 105, in exact_match86 out = generate(model, prompt, max_new, max_budget=max_budget, cost=cost, temperature=0.0, eos_id=tok.eot_id,87 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^88 File "/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 158, in no_grad89 return func(*args, **kwargs)90 ^^^^^^^^^^^^^^^^^^^^^91 File "/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/prisme/generation.py", line 115, in generate92 logits, _, _ = step_logits(model, prompt, cache, max_budget, cost, fa, lambda_cost, kappa_risk)93 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^94 File "/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 158, in no_grad95 return func(*args, **kwargs)96 ^^^^^^^^^^^^^^^^^^^^^97 File "/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/prisme/generation.py", line 43, in step_logits98 if cfg.ctrl_use_entropy:99 ^^^^^^^^^^^^^^^^^^^^100AttributeError: 'PrismeConfig' object has no attribute 'ctrl_use_entropy'101