train_path: /scratch/tbe/nesymres/raw_datasets/200000000 val_path: data/validation raw_test_path: ??? max_description_seq_len: 500 checkpointing: true number_of_test: 20 val_check_interval: 5 name: results benchmark_path: test_set/nc.csv model_path: run/False/2022-11-07/13-46-03/Exp_weights/1000000_log_-epoch=104-val_loss=0.00.ckpt test_path: data/validation/nc resume_from_checkpoint: '' wandb: false num_of_workers: 5 batch_size: 400 num_sanity_val_steps: 0 epochs: 10000 precision: 16 gpu: 3 path_to_candidate: data/conditioning/equations_ops_3_5000.json dataset: len: 1000000 total_variables: null total_coefficients: null max_number_of_points: 1000 type_of_sampling_points: uniform noise: false fun_support: max: 10 min: -10 min_len: 1 constants: enabled: true num_constants: 6 additive: max: 10 min: -10 multiplicative: max: 10 min: 0.05 number_of_complexity_classes: 30 conditioning: mode: false name: train prob_symmetry: 0.2 prob_complexity: 0.3 prob_noise: 0 positive: prob: 0.3 min_percent: 0 max_percent: 1 prob_pointers: 0.15 negative: prob: 0.3 min_percent: 0 max_percent: 1 architecture: sinuisodal_embeddings: false dec_pf_dim: 512 dec_layers: 5 dim_hidden: 512 lr: 0.0001 dropout: 0 cond_num_layers: 3 num_features: 32 ln: true N_p: 0 num_inds: 100 activation: relu bit16: true norm: true linear: false input_normalization: false src_pad_idx: 0 trg_pad_idx: 0 length_eq: 60 n_l_enc: 5 mean: 0.5 std: 0.5 dim_input: 6 num_heads: 8 number_possible_tokens: 80 num_tokens_condition: 150 embedding_dim_condition: 512 conditioning: false concat: true predict_constants: c wupsteps: 4000 inference: beam_size: 10 word2id: ?? id2word: ?? total_variables: ?? n_jobs: 1 bfgs: activated: false not_activated_no_fit: true n_restarts: 10 add_coefficients_if_not_existing: false normalization_o: false idx_remove: true normalization_type: MSE stop_time: 1000000000.0