| | |
|---|
| | | self.validate_interval = kwargs.get("validate_interval", 5000) |
|---|
| | | self.keep_nbest_models = kwargs.get("keep_nbest_models", 500) |
|---|
| | | self.avg_keep_nbest_models_type = kwargs.get("avg_keep_nbest_models_type", "acc") |
|---|
| | | self.avg_nbest_model = kwargs.get("avg_nbest_model", 5) |
|---|
| | | self.avg_nbest_model = kwargs.get("avg_nbest_model", 10) |
|---|
| | | self.accum_grad = kwargs.get("accum_grad", 1) |
|---|
| | | self.grad_clip = kwargs.get("grad_clip", 10.0) |
|---|
| | | self.grad_clip_type = kwargs.get("grad_clip_type", 2.0) |
|---|
| | |
|---|
| | | "val_acc_step_or_eoch": self.val_acc_step_or_eoch, |
|---|
| | | "val_loss_step_or_eoch": self.val_loss_step_or_eoch, |
|---|
| | | "best_step_or_epoch": self.best_step_or_epoch, |
|---|
| | | "avg_keep_nbest_models_type": slef.avg_keep_nbest_models_type, |
|---|
| | | "avg_keep_nbest_models_type": self.avg_keep_nbest_models_type, |
|---|
| | | } |
|---|
| | | if hasattr(model, "module"): |
|---|
| | | state["state_dict"] = model.module.state_dict() |
|---|
| | |
|---|
| | | self.saved_ckpts = checkpoint["saved_ckpts"] |
|---|
| | | self.val_acc_step_or_eoch = checkpoint["val_acc_step_or_eoch"] if "val_acc_step_or_eoch" in checkpoint else {} |
|---|
| | | self.val_loss_step_or_eoch = checkpoint["val_loss_step_or_eoch"] if "val_loss_step_or_eoch" in checkpoint else {} |
|---|
| | | self.val_loss_step_or_eoch = checkpoint["best_step_or_epoch"] if "best_step_or_epoch" in checkpoint else "" |
|---|
| | | self.best_step_or_epoch = checkpoint["best_step_or_epoch"] if "best_step_or_epoch" in checkpoint else "" |
|---|
| | | model.to(self.device) |
|---|
| | | print(f"Checkpoint loaded successfully from '{ckpt}'") |
|---|
| | | else: |
|---|
| | |
|---|
| | | model=model, |
|---|
| | | dataloader_val=dataloader_val, |
|---|
| | | epoch=epoch, |
|---|
| | | writer=writer |
|---|
| | | writer=writer, |
|---|
| | | step=batch_idx+1, |
|---|
| | | ) |
|---|
| | | |
|---|
| | | if (batch_idx+1) % self.save_checkpoint_interval == 0: |
|---|
| | |
|---|
| | | f"step: {batch_idx + 1}/{batch_num_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):.3f}), " |
|---|
| | | f"(ppl_avg_epoch: {math.exp(loss_avg_epoch):.3e}), " |
|---|
| | | f"(acc_avg_epoch: {acc_avg_epoch:.3f}), " |
|---|
| | | f"(lr: {lr:.3e}), " |
|---|
| | | f"{[(k, round(v.detach().cpu().item(), 3)) for k, v in stats.items()]}, " |
|---|
