提交

kongdeqiang

5 天以前 28ccfbfc51068a663a80764e14074df5edf2b5ba

 funasr/bin/train.py

@@ -20,6 +20,7 @@
from torch.distributed.fsdp import FullyShardedDataParallel as FSDP
from torch.distributed.algorithms.join import Join
from torch.distributed.fsdp.sharded_grad_scaler import ShardedGradScaler
from tensorboardX import SummaryWriter
from funasr.train_utils.average_nbest_models import average_checkpoints

from funasr.register import tables
@@ -27,7 +28,7 @@
from funasr.train_utils.trainer import Trainer
from funasr.schedulers import scheduler_classes
from funasr.train_utils.initialize import initialize
from funasr.download.download_from_hub import download_model
from funasr.download.download_model_from_hub import download_model
from funasr.models.lora.utils import mark_only_lora_as_trainable
from funasr.train_utils.set_all_random_seed import set_all_random_seed
from funasr.train_utils.load_pretrained_model import load_pretrained_model
@@ -191,21 +192,19 @@
    tensorboard_dir = os.path.join(kwargs.get("output_dir"), "tensorboard")
    os.makedirs(tensorboard_dir, exist_ok=True)
    try:
        from tensorboardX import SummaryWriter

        writer = SummaryWriter(tensorboard_dir)  # if trainer.rank == 0 else None
    except:
        writer = None

    dataloader_tr, dataloader_val = None, None
    for epoch in range(trainer.start_epoch, trainer.max_epoch + 1):
    for epoch in range(trainer.start_epoch, trainer.max_epoch):
        time1 = time.perf_counter()

        for data_split_i in range(trainer.start_data_split_i, dataloader.data_split_num):
            time_slice_i = time.perf_counter()
            dataloader_tr, dataloader_val = dataloader.build_iter(
                epoch, data_split_i=data_split_i, start_step=trainer.start_step
            )
            trainer.start_step = 0

            trainer.train_epoch(
                model=model,
@@ -218,16 +217,32 @@
                writer=writer,
                data_split_i=data_split_i,
                data_split_num=dataloader.data_split_num,
                start_step=trainer.start_step,
            )
            trainer.start_step = 0

            device = next(model.parameters()).device
            if device.type == "cuda":
                with torch.cuda.device(device):
                    torch.cuda.empty_cache()

            time_escaped = (time.perf_counter() - time_slice_i) / 3600.0
            logging.info(
                f"rank: {local_rank}, "
                f"time_escaped_epoch: {time_escaped:.3f} hours, "
                f"estimated to finish {dataloader.data_split_num} data_slices, remaining: {dataloader.data_split_num-data_split_i} slices, {(dataloader.data_split_num-data_split_i)*time_escaped:.3f} hours, "
                f"epoch: {trainer.max_epoch - epoch} epochs, {((trainer.max_epoch - epoch - 1)*dataloader.data_split_num + dataloader.data_split_num-data_split_i)*time_escaped:.3f} hours\n"
            )

            torch.cuda.empty_cache()

        trainer.start_data_split_i = 0
        trainer.validate_epoch(
            model=model, dataloader_val=dataloader_val, epoch=epoch, writer=writer
            model=model, dataloader_val=dataloader_val, epoch=epoch + 1, writer=writer
        )
        scheduler.step()
        trainer.step_cur_in_epoch = 0
        trainer.save_checkpoint(epoch, model=model, optim=optim, scheduler=scheduler, scaler=scaler)
        trainer.step_in_epoch = 0
        trainer.save_checkpoint(
            epoch + 1, model=model, optim=optim, scheduler=scheduler, scaler=scaler
        )

        time2 = time.perf_counter()
        time_escaped = (time2 - time1) / 3600.0
@@ -237,6 +252,8 @@
            f"estimated to finish {trainer.max_epoch} "
            f"epoch: {(trainer.max_epoch - epoch) * time_escaped:.3f} hours\n"
        )
        trainer.train_acc_avg = 0.0
        trainer.train_loss_avg = 0.0

    if trainer.rank == 0:
        average_checkpoints(trainer.output_dir, trainer.avg_nbest_model)