INNER CODE UNIT · Python

train

JackHCC/Chinese-Text-Classification-PyTorch · pretrain_eval.py:31

def train(config, model, train_iter, dev_iter, test_iter):
    start_time = time.time()
    model.train()
    param_optimizer = list(model.named_parameters())
    no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight']
    optimizer_grouped_parameters = [
        {'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay': 0.01},
        {'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}]
    # optimizer = torch.optim.Adam(model.parameters(), lr=config.learning_rate)
    optimizer = BertAdam(optimizer_grouped_parameters,
                         lr=config.learning_rate,
                         warmup=0.05,
                         t_total=len(train_iter) * config.num_epochs)
    total_batch = 0  # 记录进行到多少batch
    dev_best_loss = float('inf')
    last_improve = 0  # 记录上次验证集loss下降的batch数
    flag = False  # 记录是否很久没有效果提升
    model.train()

View source record →