diff --git a/Configuration/config.ini b/Configuration/config.ini index 17d779b3923cacaf27347c5be6c623df0d2519bf..19528cd2142f397c6f137c6c8dcd999e7caae9ef 100644 --- a/Configuration/config.ini +++ b/Configuration/config.ini @@ -4,7 +4,7 @@ transformers = 4.16.2 [DATASET_PARAMS] symbols_vocab_size = 26 atom_vocab_size = 18 -max_len_sentence = 83 +max_len_sentence = 290 max_atoms_in_sentence = 900 max_atoms_in_one_type = 360 @@ -24,7 +24,7 @@ sinkhorn_iters = 5 [MODEL_TRAINING] batch_size = 32 -pretrain_linker_epochs = 1 -epoch = 1 +pretrain_linker_epochs = 10 +epoch = 20 seed_val = 42 learning_rate = 2e-3 \ No newline at end of file diff --git a/SuperTagger b/SuperTagger index 4963a6b33a361caf3dd8c458fead6b8352b034cd..ce978e6d389c6e126d162f86a4b627cda167313c 160000 --- a/SuperTagger +++ b/SuperTagger @@ -1 +1 @@ -Subproject commit 4963a6b33a361caf3dd8c458fead6b8352b034cd +Subproject commit ce978e6d389c6e126d162f86a4b627cda167313c diff --git a/train.py b/train.py index fb38519f58d077a28bf9cb6d4a77617e850951ab..e9b395aa5011f43e63fac4c4f11d6f83f3a79fa1 100644 --- a/train.py +++ b/train.py @@ -6,7 +6,7 @@ from utils import read_csv_pgbar from Configuration import Configuration torch.cuda.empty_cache() -nb_sentences = 4*32 +nb_sentences = 10000000 file_path_axiom_links = 'Datasets/goldANDsilver_dataset_links.csv' model_tagger = "models/flaubert_super_98_V2_50e.pt" @@ -28,6 +28,5 @@ print("#" * 20) neural_proof_net = NeuralProofNet(model_tagger) neural_proof_net.train_neuralproofnet(df_axiom_links, validation_rate=0.1, epochs=epochs, batch_size=batch_size, checkpoint=True, tensorboard=True) -neural_proof_net.linker.predict_without_categories("le chat est noir") print("#" * 20) print("#" * 20)