| | |
|---|
| | | ): |
|---|
| | | torch.cuda.empty_cache() |
|---|
| | | |
|---|
| | | time3 = time.perf_counter() |
|---|
| | | speed_stats["forward_time"] = f"{time3 - time2:0.3f}" |
|---|
| | | loss, stats, weight = retval |
|---|
| | | stats = {k: v for k, v in stats.items() if v is not None} |
|---|
| | | if self.use_ddp or self.use_fsdp: |
|---|
| | |
|---|
| | | # Multiply world_size because DistributedDataParallel |
|---|
| | | # automatically normalizes the gradient by world_size. |
|---|
| | | loss *= self.world_size |
|---|
| | | # loss *= self.world_size |
|---|
| | | # Scale the loss since we're not updating for every mini-batch |
|---|
| | | loss = loss / accum_grad |
|---|
| | | |
|---|
| | | time3 = time.perf_counter() |
|---|
| | | speed_stats["forward_time"] = f"{time3 - time2:0.3f}" |
|---|
| | | if self.use_fp16: |
|---|
| | | scaler.scale(loss).backward() |
|---|
| | | else: |
|---|
| | | loss.backward() |
|---|
| | | time4 = time.perf_counter() |
|---|
| | | speed_stats["backward_time"] = f"{time4 - time3:0.3f}" |
|---|
| | | speed_stats["backward_and_AllReaduce_time"] = f"{time4 - time3:0.3f}" |
|---|
| | | |
|---|
| | | self.train_loss_avg = ( |
|---|
| | | self.train_loss_avg * (self.step_in_epoch - 1) + loss.detach().cpu().item() |
|---|
| | |
|---|
| | | scheduler.step() |
|---|
| | | # Clear gradients for the next accumulation stage |
|---|
| | | optim.zero_grad(set_to_none=True) |
|---|
| | | total_time = f"{time.perf_counter() - time5:0.3f}" |
|---|
| | | total_time = f"{(time.perf_counter() - time5)/accum_grad:0.3f}" |
|---|
| | | time5 = time.perf_counter() |
|---|
| | | |
|---|
| | | speed_stats["optim_time"] = f"{time5 - time4:0.3f}" |
|---|
| | | |
|---|
| | | speed_stats["total_time"] = total_time |
|---|
| | |
|---|
| | | batch_num_epoch = len(dataloader_train) |
|---|
| | | self.log( |
|---|
| | | epoch, |
|---|
| | | batch_idx + kwargs.get("start_step", 0), |
|---|
| | | batch_idx, |
|---|
| | | log_step=batch_idx + kwargs.get("start_step", 0), |
|---|
| | | step_in_epoch=self.step_in_epoch, |
|---|
| | | batch_num_epoch=batch_num_epoch, |
|---|
| | | lr=lr, |
|---|
| | |
|---|
| | | tag="train", |
|---|
| | | data_split_i=0, |
|---|
| | | data_split_num=1, |
|---|
| | | log_step=None, |
|---|
| | | **kwargs, |
|---|
| | | ): |
|---|
| | | |
|---|
| | | if (batch_idx + 1) % self.log_interval == 0: |
|---|
| | | |
|---|
| | | batch_idx = log_step if log_step is not None else batch_idx |
|---|
| | | gpu_info = ( |
|---|
| | | "GPU, memory: usage: {:.3f} GB, " |
|---|
| | | "peak: {:.3f} GB, " |
|---|
| | |
|---|
| | | f"data_slice: {data_split_i}/{data_split_num}, " |
|---|
| | | f"step_in_slice: {batch_idx + 1}/{batch_num_epoch}, step_in_epoch: {step_in_epoch}, total step: {self.batch_total}, " |
|---|
| | | f"(loss_avg_rank: {loss:.3f}), " |
|---|
| | | f"(loss_avg_epoch: {loss_avg_epoch:.3f}), " |
|---|
| | | f"(ppl_avg_epoch: {math.exp(loss_avg_epoch):.3e}), " |
|---|
| | | f"(acc_avg_epoch: {acc_avg_epoch:.3f}), " |
|---|
| | | f"(loss_avg_slice: {loss_avg_epoch:.3f}), " |
|---|
| | | f"(ppl_avg_slice: {math.exp(loss_avg_epoch):.3e}), " |
|---|
| | | f"(acc_avg_slice: {acc_avg_epoch:.3f}), " |
|---|
| | | f"(lr: {lr:.3e}), " |
|---|
| | | f"{[(k, round(v.detach().cpu().item(), 3)) for k, v in stats.items()]}, " |
|---|
| | | f"{speed_stats}, " |
|---|
