Spaces:
Runtime error
Runtime error
File size: 1,671 Bytes
0558aa4 |
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 |
# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import torch
from lightning.pytorch import Trainer
from omegaconf import OmegaConf
from nemo.collections.speechlm2 import SALM, DataModule, SALMDataset
from nemo.core.config import hydra_runner
from nemo.utils.exp_manager import exp_manager
from nemo.utils.trainer_utils import resolve_trainer_cfg
torch.cuda.set_device(int(os.environ["LOCAL_RANK"]))
@hydra_runner(config_path="conf", config_name="salm")
def train(cfg):
OmegaConf.resolve(cfg)
torch.distributed.init_process_group(backend="nccl")
torch.set_float32_matmul_precision("medium")
trainer = Trainer(**resolve_trainer_cfg(cfg.trainer))
log_dir = exp_manager(trainer, cfg.get("exp_manager", None))
OmegaConf.save(cfg, log_dir / "exp_config.yaml")
with trainer.init_module():
model = SALM(OmegaConf.to_container(cfg.model, resolve=True))
dataset = SALMDataset(tokenizer=model.tokenizer)
datamodule = DataModule(cfg.data, tokenizer=model.tokenizer, dataset=dataset)
trainer.fit(model, datamodule)
if __name__ == "__main__":
train()
|