batch 0/300 r_pre=0 mean gain 0.00397 frac>0 0.494
/Users/simon-pierreboucher/Desktop/Recherche-UQO/ia/prisme-slm/training/train_editor.py:57: 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)
batch 10/300 r_pre=3 mean gain 0.00043 frac>0 0.333
batch 20/300 r_pre=3 mean gain -0.00053 frac>0 0.284
batch 30/300 r_pre=2 mean gain -0.00279 frac>0 0.385
batch 40/300 r_pre=3 mean gain -0.00303 frac>0 0.271
batch 50/300 r_pre=3 mean gain -0.00278 frac>0 0.304
batch 60/300 r_pre=0 mean gain 0.01724 frac>0 0.510
batch 70/300 r_pre=0 mean gain 0.01201 frac>0 0.533
batch 80/300 r_pre=2 mean gain 0.00534 frac>0 0.412
batch 90/300 r_pre=2 mean gain -0.00454 frac>0 0.328
batch 100/300 r_pre=3 mean gain -0.00403 frac>0 0.245
batch 110/300 r_pre=2 mean gain -0.00116 frac>0 0.529
batch 120/300 r_pre=0 mean gain 0.00268 frac>0 0.514
batch 130/300 r_pre=3 mean gain 0.00058 frac>0 0.299
batch 140/300 r_pre=2 mean gain -0.00481 frac>0 0.346
batch 150/300 r_pre=3 mean gain 0.00099 frac>0 0.309
batch 160/300 r_pre=2 mean gain 0.00548 frac>0 0.443
batch 170/300 r_pre=3 mean gain 0.00025 frac>0 0.290
batch 180/300 r_pre=0 mean gain 0.01394 frac>0 0.509
batch 190/300 r_pre=3 mean gain -0.00209 frac>0 0.278
batch 200/300 r_pre=1 mean gain 0.00116 frac>0 0.443
batch 210/300 r_pre=1 mean gain -0.00147 frac>0 0.419
batch 220/300 r_pre=2 mean gain 0.00312 frac>0 0.407
batch 230/300 r_pre=0 mean gain -0.00251 frac>0 0.477
batch 240/300 r_pre=1 mean gain -0.00129 frac>0 0.400
batch 250/300 r_pre=3 mean gain -0.00223 frac>0 0.282
batch 260/300 r_pre=3 mean gain -0.00351 frac>0 0.275
batch 270/300 r_pre=1 mean gain 0.00268 frac>0 0.470
batch 280/300 r_pre=1 mean gain 0.00504 frac>0 0.511
batch 290/300 r_pre=2 mean gain -0.00309 frac>0 0.369
train {'file': 'experiments/runs/labels_v1ctrl_seed01_20261030004018/labels_train.pt', 'n_states': 49965, 'n_labels': 199860, 'mean_gain': 0.0013899323530495167, 'frac_positive': 0.40608927607536316, 'frac_harm': 0.38673070073127747, 'seconds': 61.8, 'n_audit_batches': 75}
batch 0/40 r_pre=3 mean gain 0.00410 frac>0 0.273
batch 10/40 r_pre=3 mean gain -0.00087 frac>0 0.303
batch 20/40 r_pre=1 mean gain -0.00083 frac>0 0.502
batch 30/40 r_pre=2 mean gain 0.00212 frac>0 0.446
calib {'file': 'experiments/runs/labels_v1ctrl_seed01_20261030004018/labels_calib.pt', 'n_states': 6729, 'n_labels': 26916, 'mean_gain': -0.00023525116557721049, 'frac_positive': 0.40730419754981995, 'frac_harm': 0.38687026500701904, 'seconds': 10.2, 'n_audit_batches': 10}
run labels_v1ctrl_seed01_20261030004018