Method__init__(self, params, inner_optimizer, lookahead_stepsize=0, use_scheduled_lookahead_stepsize=True, lookahead_ema=0.9
records/track_3_optimization/results/20260529_tail_phase_readout_2850/train_gpt_tail_phase_readout_2850.py:924
Method__init__(self, params, lr=0.018, mu=0.95, beta2=0.95, eps=1e-10)
records/track_3_optimization/results/20260504_muloco_normuonh/train_gpt_simple_muloco_normuonh.py:234
Method__init__(
self, params, lr=0.018, beta1=0.95, beta2=0.9,
shampoo_beta=0.9, eps=1e-8, precondition_freq
records/track_3_optimization/results/20260511_klsoap_h_lr_power_decay/train_gpt_simple_klsoap_h_lr_power_decay.py:270
Method__init__(self, params, lr=0.01, betas=(0.8, 0.99), eps=1e-10)
records/track_3_optimization/results/20260619_cwd_rowfloor_tailema/train_gpt_cwd_SOTA.py:531
Method__init__(self, params, inner_optimizer, lookahead_stepsize=0, use_scheduled_lookahead_stepsize=True, lookahead_ema=0.9
records/track_3_optimization/results/20260619_cwd_rowfloor_tailema/train_gpt_cwd_SOTA.py:557
Method__init__(
self,
params: ParamsT,
lr: float = 1e-2,
betas: tuple[float, float] = (0.9,
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributed_shampoo.py:350
Method__init__(
self,
block_list: tuple[Tensor, ...],
state: Mapping[Tensor, _StateValueType],
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/preconditioner/adagrad_preconditioner_list.py:58