assignment_loss_scale: 1.0
balance_classifications: false
balance_jets: 0
balance_losses: true
balance_particles: 0
batch_size: 1024
classification_loss_scale: 0.0
combinatorial_scale: 0.0
combine_pair_loss: min
dataset_limit: 1.0
dataset_randomization: 0
detection_loss_scale: 1.0
dropout: 0.2797850073316285
epochs: 100
event_info_file: /data/spatop/event_files/v11/tt_hadronic_v7_full.yaml
focal_gamma: 0.0
gradient_clip: 10.0
hidden_dim: 128
initial_embedding_dim: 128
initial_embedding_skip_connections: 1
kl_loss_scale: 0.0
l2_penalty: 0.0002
learning_rate: 0.0003407775643879822
learning_rate_cycles: 1
learning_rate_warmup_epochs: 1.0
limit_to_num_jets: 0
limit_val_batches: 1.0
linear_activation: gelu
linear_block_type: GRU
linear_prelu_activation: true
mask_sequence_vectors: 1
masking: Filling
mass_classes: []
moe_loss_scale: 0.01
normalization: LayerNorm
normalize_features: 1
num_attention_heads: 8
num_branch_embedding_layers: 3
num_branch_encoder_layers: 3
num_classification_layers: 3
num_dataloader_workers: 8
num_detector_layers: 2
num_embedding_layers: 10
num_encoder_layers: 4
num_experts: 8
num_experts_per_tok: 2
num_gpu: 1
num_jet_embedding_layers: 0
num_jet_encoder_layers: 2
num_pairwise_features: 4
num_regression_layers: 3
optimizer: AdamW
pairwise_embedding_dim: 8
pairwise_input_source: ''
partial_events: 1
position_embedding_dim: 128
regression_loss_scale: 0.0
skip_connections: 1
split_symmetric_attention: 1
testing_file: ''
train_validation_split: 0.95
training_file: /data/spatop/tpm70_wpm30_FB350_fixed/all_merged.h5
transformer_activation: gelu
transformer_dim: 128
transformer_dim_scale: 2.0
transformer_type: Gated
trial_output_dir: ./test_output
trial_time: ''
usable_gpus: ''
use_mass_classification: false
use_moe: false
use_pairwise_interactions: false
validation_file: ''
verbose_output: false