attention_type: math backend: pytorch checkpoint_freq: 1 comet_name: particleflow-pt comet_offline: false comet_step_freq: 100 config: parameters/pytorch/pyg-clic-ttbar.yaml conv_type: attention data_dir: tensorflow_datasets dataset: clic dtype: float32 gpu_batch_multiplier: 20 gpus: 4 load: /pfvol/experiments/MLPF_clic_backbone_pyg-clic_20240429_101112_971749/best_weights.pth lr: 1.0e-05 lr_schedule: constant lr_schedule_config: onecycle: pct_start: 0.3 model: attention: activation: relu attention_type: math conv_type: attention dropout_conv_id_ff: 0.0 dropout_conv_id_mha: 0.0 dropout_conv_reg_ff: 0.0 dropout_conv_reg_mha: 0.0 dropout_ff: 0.0 head_dim: 16 num_convs: 3 num_heads: 32 cos_phi_mode: linear energy_mode: linear eta_mode: linear gnn_lsh: activation: elu bin_size: 640 conv_type: gnn_lsh distance_dim: 128 dropout: 0.0 embedding_dim: 512 ffn_dist_hidden_dim: 128 ffn_dist_num_layers: 2 layernorm: true max_num_bins: 200 num_convs: 3 num_node_messages: 2 width: 512 input_encoding: joint learned_representation_mode: last mamba: activation: elu conv_type: mamba d_conv: 4 d_state: 16 dropout: 0.0 embedding_dim: 128 expand: 2 num_convs: 2 num_heads: 2 width: 128 pt_mode: linear sin_phi_mode: linear trainable: all ntest: null ntrain: null num_epochs: 200 num_workers: 2 numtrain: 10000 numvalid: 1000 nvalid: null patience: 50 prefetch_factor: 2 prefix: MLPF_4GTX_MET_latentX_ReinitializeBackbone raytune: asha: brackets: 1 grace_period: 10 max_t: 200 reduction_factor: 4 default_metric: val_loss default_mode: min hyperband: max_t: 200 reduction_factor: 4 hyperopt: n_random_steps: 10 local_dir: null nevergrad: n_random_steps: 10 sched: asha search_alg: null reinitialize_backbone: true sort_data: false test_dataset: clic_edm_ttbar_pf: version: 1.5.0 train: true train_dataset: clic: physical: batch_size: 1 samples: clic_edm_ttbar_pf: version: 1.5.0 use_latentX: true val_freq: null valid_dataset: clic: physical: batch_size: 1 samples: clic_edm_ttbar_pf: version: 1.5.0