from tqdm import tqdm from src.recover_schedules import recover_schedules params = [ { "testing": False, "seed": 97, "init_mode": "random", "n_optimization_steps": 2000, "epsilon": 0.01, "nb_sinkhorn_iters": 40, "decay_ls": False, "ls_partitions_ratios": [0.66], "init_ls": 2.0, "max_ls": 10, "min_ls": 0.1, "ls_warmup_iters_ratio": 0.2, "ls_decay_iters_ratio": 0.90, "decay_lr": True, "lr_partitions_ratios": [0.66], "init_lr": 1e-2, "max_lr": 1e-1, "min_lr": 1e-4, "lr_warmup_iters_ratio": 0.1, "lr_decay_iters_ratio": 0.90, "checkpoint_interval": 1, "data_dir": f"outputs/exhaustive_{nb_jobs}_{nb_machines}/top_{top_k}", "model_dir": f"outputs/exhaustive_{nb_jobs}_{nb_machines}/top_{top_k}/train_nEmbd{n_embd}_nHead{n_head}_nLayer{n_layer}", "output_dir": f"outputs/exhaustive_{nb_jobs}_{nb_machines}/top_{top_k}/train_nEmbd{n_embd}_nHead{n_head}_nLayer{n_layer}/recover_{yes_or_no_mf}_mf", "apply_metropolized_filling": apply_mf, "mf_patience": 10, "mf_fifo_size": 50, "mf_penalty_strength": 1.0, "mf_min_delta": 0.05, } for yes_or_no_mf, apply_mf in [("no", False)] for nb_jobs in [9] for nb_machines in [6] for top_k in [0] for n_embd in [6, 8, 12, 24, 36, 48, 64] for n_head in [1, 2] for n_layer in [1, 2, 3, 4] ] for param in (pbar:=tqdm(params)): config = ( f"n_embd={param['model_dir'].split('nEmbd')[1].split('_')[0]}, " f"n_head={param['model_dir'].split('nHead')[1].split('_')[0]}, " f"n_layer={param['model_dir'].split('nLayer')[1].split('/')[0]}, " f"apply_metropolized_filling={param['apply_metropolized_filling']}" ) pbar.set_description(f"Section 1. Recovering schedules for {config}") recover_schedules(**param) params = [ { "testing": False, "seed": 97, "init_mode": "random", "n_optimization_steps": 2000, "epsilon": 0.01, "nb_sinkhorn_iters": 40, "decay_ls": False, "ls_partitions_ratios": [0.66], "init_ls": 2.0, "max_ls": 10, "min_ls": 0.1, "ls_warmup_iters_ratio": 0.2, "ls_decay_iters_ratio": 0.90, "decay_lr": True, "lr_partitions_ratios": [0.66], "init_lr": 1e-2, "max_lr": 1e-1, "min_lr": 1e-4, "lr_warmup_iters_ratio": 0.1, "lr_decay_iters_ratio": 0.90, "checkpoint_interval": 1, "data_dir": f"outputs/exhaustive_{nb_jobs}_{nb_machines}/top_{top_k}", "model_dir": f"outputs/exhaustive_{nb_jobs}_{nb_machines}/top_{top_k}/train_nEmbd{n_embd}_nHead{n_head}_nLayer{n_layer}", "output_dir": f"outputs/exhaustive_{nb_jobs}_{nb_machines}/top_{top_k}/train_nEmbd{n_embd}_nHead{n_head}_nLayer{n_layer}/recover_{yes_or_no_mf}_mf", "apply_metropolized_filling": apply_mf, "mf_patience": 10, "mf_fifo_size": 50, "mf_penalty_strength": 1.0, "mf_min_delta": 0.05, } for yes_or_no_mf, apply_mf in [("no", False)] for nb_jobs in [9] for nb_machines in [6] for top_k in [0] for n_embd in [6 + 3*i for i in range(0, 21)] for n_head in [3] for n_layer in [1, 2, 3, 4] ] for param in (pbar:=tqdm(params)): config = ( f"n_embd={param['model_dir'].split('nEmbd')[1].split('_')[0]}, " f"n_head={param['model_dir'].split('nHead')[1].split('_')[0]}, " f"n_layer={param['model_dir'].split('nLayer')[1].split('/')[0]}, " f"apply_metropolized_filling={param['apply_metropolized_filling']}" ) pbar.set_description(f"Section 2. Recovering schedules for {config}") recover_schedules(**param) params = [ { "testing": False, "seed": 97, "init_mode": "random", "n_optimization_steps": 2000, "epsilon": 0.01, "nb_sinkhorn_iters": 40, "decay_ls": False, "ls_partitions_ratios": [0.66], "init_ls": 2.0, "max_ls": 10, "min_ls": 0.1, "ls_warmup_iters_ratio": 0.2, "ls_decay_iters_ratio": 0.90, "decay_lr": True, "lr_partitions_ratios": [0.66], "init_lr": 1e-2, "max_lr": 1e-1, "min_lr": 1e-4, "lr_warmup_iters_ratio": 0.1, "lr_decay_iters_ratio": 0.90, "checkpoint_interval": 1, "data_dir": f"outputs/exhaustive_{nb_jobs}_{nb_machines}/top_{top_k}", "model_dir": f"outputs/exhaustive_{nb_jobs}_{nb_machines}/top_{top_k}/train_nEmbd{n_embd}_nHead{n_head}_nLayer{n_layer}", "output_dir": f"outputs/exhaustive_{nb_jobs}_{nb_machines}/top_{top_k}/train_nEmbd{n_embd}_nHead{n_head}_nLayer{n_layer}/recover_{yes_or_no_mf}_mf", "apply_metropolized_filling": apply_mf, "mf_patience": 10, "mf_fifo_size": 50, "mf_penalty_strength": 1.0, "mf_min_delta": 0.05, } for yes_or_no_mf, apply_mf in [("no", False)] for nb_jobs in [9] for nb_machines in [6] for top_k in [0] for n_embd in [8 + 4*i for i in range(0, 15)] for n_head in [4] for n_layer in [1, 2, 3, 4] ] for param in (pbar:=tqdm(params)): config = ( f"n_embd={param['model_dir'].split('nEmbd')[1].split('_')[0]}, " f"n_head={param['model_dir'].split('nHead')[1].split('_')[0]}, " f"n_layer={param['model_dir'].split('nLayer')[1].split('/')[0]}, " f"apply_metropolized_filling={param['apply_metropolized_filling']}" ) pbar.set_description(f"Section 3. Recovering schedules for {config}") recover_schedules(**param)