model: <class 'pyabsa.tasks.AspectTermExtraction.models.__lcf__.fast_lcf_atepc.FAST_LCF_ATEPC'>
optimizer: adamw
learning_rate: 2e-05
cache_dataset: True
warmup_step: -1
use_bert_spc: True
max_seq_len: 80
SRD: 3
use_syntax_based_SRD: False
lcf: cdw
dropout: 0.5
l2reg: 1e-05
num_epoch: 10
batch_size: 16
seed: 42
output_dim: 3
log_step: 10
patience: 3
gradient_accumulation_steps: 1
dynamic_truncate: True
evaluate_begin: 5
use_amp: False
cross_validate_fold: -1
pretrained_bert: bert-base-uncased
verbose: True
dataset: c:\Users\noob\Documents\gitProjects\mtadoXNLP\cybersecurity_absa\data\custom_cybersecurity_atepc
from_checkpoint: None
checkpoint_save_mode: 1
auto_device: True
path_to_save: None
load_aug: False
device: cpu
device_name: Unknown
model_name: fast_lcf_atepc
hidden_dim: 768
PyABSAVersion: 2.4.2
TransformersVersion: 4.56.2
TorchVersion: 2.8.0+cpu+cudaNone
dataset_name: custom_dataset
save_mode: 1
logger: <Logger fast_lcf_atepc (INFO)>
task_code: ATEPC
task_name: Aspect Term Extraction and Polarity Classification
dataset_file: {'train': ['cybersecurity_absa\\data\\custom_cybersecurity_atepc\\train.dat.atepc'], 'test': ['cybersecurity_absa\\data\\custom_cybersecurity_atepc\\test.dat.atepc'], 'valid': ['.git\\hooks\\sendemail-validate.sample', 'cybersecurity_absa\\data\\custom_cybersecurity_atepc\\valid.dat.atepc']}
model_path_to_save: checkpoints
spacy_model: en_core_web_sm
IOB_label_to_index: {'B-ASP': 1, 'I-ASP': 2, 'O': 3, '[CLS]': 4, '[SEP]': 5}
index_to_label: {0: '-1', 1: '0', 2: '1'}
label_list: ['B-ASP', 'I-ASP', 'O', '[CLS]', '[SEP]']
num_labels: 6
sep_indices: 102
max_test_metrics: {'max_apc_test_acc': 65.23, 'max_apc_test_f1': 41.24, 'max_ate_test_f1': 91.84}
metrics_of_this_checkpoint: {'apc_acc': 65.23, 'apc_f1': 41.24, 'ate_f1': 90.57}