| | |
|---|
| | | 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 |
|---|
| | | ) |
|---|
| | |
|---|
| | | |
|---|
| | | torch.cuda.empty_cache() |
|---|
| | | |
|---|
| | | time_escaped = (time.perf_counter() - time1) / 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)*time_escaped:.3f} hours" |
|---|
| | | f"epoch: {((trainer.max_epoch - epoch - 1)*dataloader.data_split_num + dataloader.data_split_num-data_split_i)*time_escaped:.3f} hours\n" |
|---|
| | | ) |
|---|
| | | |
|---|
| | | trainer.start_data_split_i = 0 |
|---|
| | | trainer.validate_epoch(model=model, dataloader_val=dataloader_val, epoch=epoch + 1) |
|---|
| | | scheduler.step() |
|---|
