Fix error with global step in run_squad.py

examples/run_squad.py

@@ -170,15 +170,19 @@ def train(args, train_dataset, model, tokenizer):
     steps_trained_in_current_epoch = 0
     # Check if continuing training from a checkpoint
     if os.path.exists(args.model_name_or_path):
-        # set global_step to gobal_step of last saved checkpoint from model path
-        global_step = int(args.model_name_or_path.split("-")[-1].split("/")[0])
-        epochs_trained = global_step // (len(train_dataloader) // args.gradient_accumulation_steps)
-        steps_trained_in_current_epoch = global_step % (len(train_dataloader) // args.gradient_accumulation_steps)
-
-        logger.info("  Continuing training from checkpoint, will skip to saved global_step")
-        logger.info("  Continuing training from epoch %d", epochs_trained)
-        logger.info("  Continuing training from global step %d", global_step)
-        logger.info("  Will skip the first %d steps in the first epoch", steps_trained_in_current_epoch)
+        try:
+            # set global_step to gobal_step of last saved checkpoint from model path
+            checkpoint_suffix = args.model_name_or_path.split("-")[-1].split("/")[0]
+            global_step = int(checkpoint_suffix)
+            epochs_trained = global_step // (len(train_dataloader) // args.gradient_accumulation_steps)
+            steps_trained_in_current_epoch = global_step % (len(train_dataloader) // args.gradient_accumulation_steps)
+
+            logger.info("  Continuing training from checkpoint, will skip to saved global_step")
+            logger.info("  Continuing training from epoch %d", epochs_trained)
+            logger.info("  Continuing training from global step %d", global_step)
+            logger.info("  Will skip the first %d steps in the first epoch", steps_trained_in_current_epoch)
+        except ValueError:
+            logger.info("  Starting fine-tuning.")
 
     tr_loss, logging_loss = 0.0, 0.0
     model.zero_grad()