| | |
|---|
| | | # open tf32 |
|---|
| | | torch.backends.cuda.matmul.allow_tf32 = kwargs.get("enable_tf32", True) |
|---|
| | | |
|---|
| | | rank = int(os.environ.get("RANK", 0)) |
|---|
| | | local_rank = int(os.environ.get("LOCAL_RANK", 0)) |
|---|
| | | world_size = int(os.environ.get("WORLD_SIZE", 1)) |
|---|
| | | |
|---|
| | |
|---|
| | | dist.init_process_group(backend=kwargs.get("backend", "nccl"), init_method="env://") |
|---|
| | | torch.cuda.set_device(local_rank) |
|---|
| | | |
|---|
| | | rank = dist.get_rank() |
|---|
| | | # rank = dist.get_rank() |
|---|
| | | |
|---|
| | | logging.info("Build model, frontend, tokenizer") |
|---|
| | | device = kwargs.get("device", "cuda") |
|---|
| | |
|---|
| | | dataloader = dataloader_class(**kwargs) |
|---|
| | | # dataloader_tr, dataloader_val = dataloader_class(**kwargs) |
|---|
| | | |
|---|
| | | scaler = GradScaler(enabled=trainer.use_fp16) if trainer.use_fp16 else None |
|---|
| | | scaler = GradScaler(enabled=True) if trainer.use_fp16 or trainer.use_bf16 else None |
|---|
| | | scaler = ShardedGradScaler(enabled=trainer.use_fp16) if trainer.use_fsdp else scaler |
|---|
| | | |
|---|
| | | trainer.resume_checkpoint( |
|---|
