Joosep Pata
add cms model v2.4.0
d303317
{"num_mlpf_params": 5133603, "train": true, "test": null, "make_plots": null, "comet": true, "save_attention": false, "dataset": "cms", "sort_data": true, "data_dir": "/scratch/persistent/joosep/tensorflow_datasets", "gpus": 1, "gpu_batch_multiplier": 5, "load": null, "finetune": null, "num_epochs": 10, "patience": 20, "lr": 0.0001, "lr_schedule": "cosinedecay", "conv_type": "attention", "ntrain": null, "ntest": 1000, "nvalid": null, "num_workers": 8, "prefetch_factor": 50, "checkpoint_freq": 1, "comet_name": "particleflow-pt", "comet_offline": false, "comet_step_freq": 10, "dtype": "bfloat16", "val_freq": null, "model": {"trainable": "all", "learned_representation_mode": "last", "input_encoding": "split", "pt_mode": "direct-elemtype-split", "eta_mode": "linear", "sin_phi_mode": "linear", "cos_phi_mode": "linear", "energy_mode": "direct-elemtype-split", "gnn_lsh": {"conv_type": "gnn_lsh", "embedding_dim": 512, "width": 512, "num_convs": 8, "dropout_ff": 0.0, "activation": "elu", "bin_size": 320, "max_num_bins": 200, "distance_dim": 128, "layernorm": true, "num_node_messages": 2, "ffn_dist_hidden_dim": 128, "ffn_dist_num_layers": 2}, "attention": {"conv_type": "attention", "num_convs": 3, "dropout_ff": 0.0, "dropout_conv_id_mha": 0.0, "dropout_conv_id_ff": 0.0, "dropout_conv_reg_mha": 0.0, "dropout_conv_reg_ff": 0.0, "activation": "relu", "head_dim": 16, "num_heads": 16, "attention_type": "flash", "use_pre_layernorm": true}, "mamba": {"conv_type": "mamba", "embedding_dim": 1024, "width": 1024, "num_convs": 4, "dropout_ff": 0.0, "activation": "elu", "d_state": 32, "d_conv": 4, "expand": 2}}, "lr_schedule_config": {"onecycle": {"pct_start": 0.3}}, "raytune": {"local_dir": null, "sched": "asha", "search_alg": "hyperopt", "default_metric": "val_loss", "default_mode": "min", "asha": {"max_t": 200, "reduction_factor": 4, "brackets": 1, "grace_period": 10}, "hyperband": {"max_t": 200, "reduction_factor": 4}, "hyperopt": {"n_random_steps": 10}, "nevergrad": {"n_random_steps": 10}}, "train_dataset": {"cms": {"physical_pu": {"batch_size": 1, "samples": {"cms_pf_ttbar": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_qcd": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_ztt": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}}}, "physical_nopu": {"batch_size": 8, "samples": {"cms_pf_ttbar_nopu": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_qcd_nopu": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_ztt_nopu": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}}}}}, "valid_dataset": {"cms": {"physical_pu": {"batch_size": 1, "samples": {"cms_pf_ttbar": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_qcd": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_ztt": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}}}, "physical_nopu": {"batch_size": 8, "samples": {"cms_pf_ttbar_nopu": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_qcd_nopu": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_ztt_nopu": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}}}}}, "test_dataset": {"cms_pf_ttbar": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_qcd": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_ztt": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_ttbar_nopu": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_qcd_nopu": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_ztt_nopu": {"version": "2.5.0", "splits": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}, "cms_pf_single_ele": {"version": "2.5.0", "splits": [1]}}, "enabled_test_datasets": ["cms_pf_qcd"], "start_epoch": 1}