phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9419 val_bars=536
phase1: epoch 0 train=0.25789 val=0.28957
phase1: early stop at epoch 23 (best val MSE 0.22188)
/Users/jameslopez/projects/TradingBot25/.venv/lib/python3.12/site-packages/cma/s.py:16: UserWarning: Could not import matplotlib.pyplot, therefore ``cma.plot()`` etc. is not available
  _warnings.warn('Could not import matplotlib.pyplot, therefore'
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-1.4678 fold_calmars=[4.28, -1.35]
phase2: gen 7/8 best_fitness=-3.0847 fold_calmars=[7.44, -1.27]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9419 val_bars=536
phase1: epoch 0 train=0.29321 val=0.21207
phase1: early stop at epoch 20 (best val MSE 0.21207)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-0.2719 fold_calmars=[1.83, -1.28]
phase2: gen 7/8 best_fitness=-3.2471 fold_calmars=[7.68, -1.18]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=4856 val_bars=536
phase1: epoch 0 train=0.25880 val=0.28218
phase1: early stop at epoch 24 (best val MSE 0.21784)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-2.1483 fold_calmars=[5.57, -1.28]
phase2: gen 7/8 best_fitness=-4.1372 fold_calmars=[9.55, -1.27]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=4856 val_bars=536
phase1: epoch 0 train=0.29897 val=0.21481
phase1: early stop at epoch 20 (best val MSE 0.21481)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-3.3797 fold_calmars=[7.71, -0.95]
phase2: gen 7/8 best_fitness=-8.2740 fold_calmars=[17.92, -1.37]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9233 val_bars=536
phase1: epoch 0 train=0.25854 val=0.28976
phase1: early stop at epoch 23 (best val MSE 0.22196)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-1.6649 fold_calmars=[4.55, -1.22]
phase2: gen 7/8 best_fitness=-3.0608 fold_calmars=[7.46, -1.34]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9233 val_bars=536
phase1: epoch 0 train=0.29407 val=0.21198
phase1: early stop at epoch 20 (best val MSE 0.21198)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-0.0717 fold_calmars=[1.44, -1.3]
phase2: gen 7/8 best_fitness=-5.3422 fold_calmars=[11.97, -1.29]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=11609 val_bars=536
phase1: epoch 0 train=0.25763 val=0.22407
phase1: early stop at epoch 20 (best val MSE 0.22407)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-2.9630 fold_calmars=[1.2, 4.73]
phase2: gen 7/8 best_fitness=-5.9169 fold_calmars=[-1.0, 12.83]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=11609 val_bars=536
phase1: epoch 0 train=0.28814 val=0.26158
phase1: early stop at epoch 22 (best val MSE 0.23635)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-4.1147 fold_calmars=[-0.92, 9.15]
phase2: gen 7/8 best_fitness=-6.5171 fold_calmars=[1.21, 11.82]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=4850 val_bars=536
phase1: epoch 0 train=0.24787 val=0.23325
phase1: early stop at epoch 21 (best val MSE 0.23183)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-5.9682 fold_calmars=[-0.83, 12.76]
phase2: gen 7/8 best_fitness=-9.5594 fold_calmars=[-1.21, 20.33]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=4850 val_bars=536
phase1: epoch 0 train=0.27606 val=0.26445
phase1: early stop at epoch 22 (best val MSE 0.23549)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-6.8141 fold_calmars=[-1.39, 15.02]
phase2: gen 7/8 best_fitness=-35.7912 fold_calmars=[1.84, 69.74]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9236 val_bars=536
phase1: epoch 0 train=0.25778 val=0.21996
phase1: early stop at epoch 20 (best val MSE 0.21996)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-4.2724 fold_calmars=[-0.91, 9.46]
phase2: gen 7/8 best_fitness=-8.3285 fold_calmars=[-0.8, 17.45]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9236 val_bars=536
phase1: epoch 0 train=0.29121 val=0.26223
phase1: early stop at epoch 24 (best val MSE 0.23543)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-4.3717 fold_calmars=[-0.6, 9.35]
phase2: gen 7/8 best_fitness=-7.8477 fold_calmars=[0.4, 15.29]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=13805 val_bars=536
phase1: epoch 0 train=0.25869 val=0.20418
phase1: early stop at epoch 22 (best val MSE 0.20070)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-3.6824 fold_calmars=[4.31, 3.05]
phase2: gen 7/8 best_fitness=-8.8322 fold_calmars=[15.8, 1.86]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=13805 val_bars=536
phase1: epoch 0 train=0.29063 val=0.24686
phase1: early stop at epoch 27 (best val MSE 0.19236)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-4.0110 fold_calmars=[5.84, 2.18]
phase2: gen 7/8 best_fitness=-12.8870 fold_calmars=[20.73, 5.04]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=4856 val_bars=536
phase1: epoch 0 train=0.26169 val=0.21124
phase1: early stop at epoch 20 (best val MSE 0.21124)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-0.6728 fold_calmars=[2.56, -1.22]
phase2: gen 7/8 best_fitness=-5.7755 fold_calmars=[1.67, 9.88]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=4856 val_bars=536
phase1: epoch 0 train=0.28692 val=0.23451
phase1: early stop at epoch 28 (best val MSE 0.19972)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-3.9966 fold_calmars=[2.52, 5.48]
phase2: gen 7/8 best_fitness=-10.5559 fold_calmars=[8.86, 12.25]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9242 val_bars=536
phase1: epoch 0 train=0.25957 val=0.20951
phase1: early stop at epoch 35 (best val MSE 0.20833)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-3.6978 fold_calmars=[2.78, 4.62]
phase2: gen 7/8 best_fitness=-10.7171 fold_calmars=[16.47, 4.97]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9242 val_bars=536
phase1: epoch 0 train=0.29237 val=0.24675
phase1: early stop at epoch 28 (best val MSE 0.19424)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-3.1932 fold_calmars=[2.28, 4.11]
phase2: gen 7/8 best_fitness=-12.4503 fold_calmars=[19.59, 5.31]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=15995 val_bars=536
phase1: epoch 0 train=0.25893 val=0.22058
phase1: early stop at epoch 27 (best val MSE 0.20593)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-2.3312 fold_calmars=[3.79, 0.87]
phase2: gen 7/8 best_fitness=-7.8375 fold_calmars=[12.8, 2.88]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=15995 val_bars=536
phase1: epoch 0 train=0.29313 val=0.25684
phase1: early stop at epoch 37 (best val MSE 0.20695)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-7.0300 fold_calmars=[14.0, 0.06]
phase2: gen 7/8 best_fitness=-7.3226 fold_calmars=[8.11, 6.54]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=4856 val_bars=536
phase1: epoch 0 train=0.26393 val=0.21952
phase1: early stop at epoch 29 (best val MSE 0.21374)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-2.6484 fold_calmars=[4.39, 0.91]
phase2: gen 7/8 best_fitness=-5.6799 fold_calmars=[10.75, 0.61]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=4856 val_bars=536
phase1: epoch 0 train=0.30509 val=0.26834
phase1: early stop at epoch 45 (best val MSE 0.21136)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-3.6830 fold_calmars=[7.82, -0.46]
phase2: gen 7/8 best_fitness=-4.9174 fold_calmars=[10.11, -0.28]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9236 val_bars=536
phase1: epoch 0 train=0.25476 val=0.21816
phase1: early stop at epoch 45 (best val MSE 0.20839)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-3.8578 fold_calmars=[6.89, 0.82]
phase2: gen 7/8 best_fitness=-8.0435 fold_calmars=[15.93, 0.15]
phase1: device=cpu arch=[55, 16, 8, 1] train_bars=9236 val_bars=536
phase1: epoch 0 train=0.29043 val=0.26383
phase1: early stop at epoch 38 (best val MSE 0.20832)
phase2: evaluating CMA-ES population sequentially
phase2: gen 0/8 best_fitness=-3.3458 fold_calmars=[5.16, 1.53]
phase2: gen 7/8 best_fitness=-5.7441 fold_calmars=[10.24, 1.25]