File size: 2,083 Bytes
c5bcbe7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 | from dataclasses import dataclass, field
# ---- Hyperparameter configuration ----
@dataclass
class HPARAMS:
# common
seed: int = 42
url: str = "https://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz"
scheduler_hparams: dict = field(default_factory=lambda: {
"factor": 0.5,
"patience": 2,
"mode": "min"
})
# BiGRU hparams
max_seq_len_gru: int = 256
batch_size_gru: int = 128
vocab_size: int = 10000
glove_txt_path: str = ("/mnt/e/ML_Files/PreTrained_Models/GloVe_Embeddings/glove.2024.wikigiga"
".200d/wiki_giga_2024_200_MFT20_vectors_seed_2024_alpha_0.75_eta_0.05_combined.txt")
model_hparams_gru: dict = field(default_factory=lambda: {
"embedding_dim": 128,
"hidden_size": 128,
"dropout": 0.12,
"num_gru_layers": 2,
"use_dense": False,
"dense_dropout_prob": 0.1
})
optimizer_hparams_gru: dict = field(default_factory=lambda: {
"lr": 1e-3,
"weight_decay": 5e-4
})
trainer_hparams_gru: dict = field(default_factory=lambda: {
"n_epochs": 20,
"use_early_stopping" : True,
"early_stopping_patience" : 3,
"scheduler_monitor" : "val_loss",
"restore_best_model": True,
})
# Transformer hparams
max_seq_len_transformer:int = 288
#transformer_path: str = "/mnt/e/ML_Files/PreTrained_Models/HuggingFace/deberta-v3-base/"
transformer_path: str = "/mnt/d/ML-Files/PreTrained-Models/HuggingFace/Transformer-Encoder/microsoft_deberta-v3-base/"
batch_size_transformer: int = 32
transformer_fc_dropout: float = 0.1
optimizer_hparams_transformer: dict = field(default_factory=lambda: {
"lr": 3e-5,
"weight_decay": 5e-4
})
trainer_hparams_transformer: dict = field(default_factory=lambda: {
"n_epochs": 5,
"use_early_stopping" : True,
"early_stopping_patience" : 2,
"scheduler_monitor" : "val_loss",
"restore_best_model": False,
})
hp = HPARAMS() |