[examples] bump pl=0.9.0 (#7053)

examples/lightning_base.py

@@ -119,7 +119,7 @@ def load_hf_checkpoint(self, *args, **kwargs):
     def get_lr_scheduler(self):
         get_schedule_func = arg_to_scheduler[self.hparams.lr_scheduler]
         scheduler = get_schedule_func(
-            self.opt, num_warmup_steps=self.hparams.warmup_steps, num_training_steps=self.total_steps
+            self.opt, num_warmup_steps=self.hparams.warmup_steps, num_training_steps=self.total_steps()
         )
         scheduler = {"scheduler": scheduler, "interval": "step", "frequency": 1}
         return scheduler
@@ -159,19 +159,20 @@ def test_step(self, batch, batch_nb):
     def test_epoch_end(self, outputs):
         return self.validation_end(outputs)
 
-    @property
     def total_steps(self) -> int:
         """The number of total training steps that will be run. Used for lr scheduler purposes."""
         num_devices = max(1, self.hparams.gpus)  # TODO: consider num_tpu_cores
         effective_batch_size = self.hparams.train_batch_size * self.hparams.accumulate_grad_batches * num_devices
-        dataset_size = len(self.train_loader.dataset)
-        return (dataset_size / effective_batch_size) * self.hparams.max_epochs
+        return (self.dataset_size / effective_batch_size) * self.hparams.max_epochs
 
     def setup(self, mode):
-        if mode == "fit":
+        if mode == "test":
+            self.dataset_size = len(self.test_dataloader().dataset)
+        else:
             self.train_loader = self.get_dataloader("train", self.hparams.train_batch_size, shuffle=True)
+            self.dataset_size = len(self.train_loader.dataset)
 
-    def get_dataloader(self, type_path, batch_size, shuffle=False):
+    def get_dataloader(self, type_path: str, batch_size: int, shuffle: bool = False):
         raise NotImplementedError("You must implement this for your task")
 
     def train_dataloader(self):

examples/requirements.txt

@@ -5,7 +5,7 @@ psutil
 sacrebleu
 rouge-score
 tensorflow_datasets
-pytorch-lightning==0.8.5
+pytorch-lightning==0.9.0
 matplotlib
 git-python==1.0.3
 faiss-cpu

examples/seq2seq/README.md

@@ -12,7 +12,6 @@ For `bertabs` instructions, see [`bertabs/README.md`](bertabs/README.md).
 - `MBartForConditionalGeneration`
 - `FSMTForConditionalGeneration`
 - `T5ForConditionalGeneration`
-
 
 ## Datasets
 
@@ -100,7 +99,7 @@ All finetuning bash scripts call finetune.py (or distillation.py) with reasonabl
 To see all the possible command line options, run:
 
 ```bash
- ./finetune.py --help 
+./finetune.py --help
 ```
 
 ### Finetuning Training Params
@@ -192,7 +191,7 @@ model = AutoModelForSeq2SeqLM.from_pretrained(f'{output_dir}/best_tfmr')
 ### Fine-tuning using Seq2SeqTrainer
 To use `Seq2SeqTrainer` for fine-tuning you should use the `finetune_trainer.py` script. It subclasses `Trainer` to extend it for seq2seq training. Except the `Trainer` releated `TrainingArguments`, it shares the same argument names as that of `finetune.py` file. One notable difference is that, calculating generative metrics (BLEU, ROUGE) is optional and is controlled using the `--predict_with_generate` argument, set this argument to calculate BLEU and ROUGE metrics.
 
-With PyTorch 1.6+ it'll automatically use `native AMP` when `--fp16` is set. 
+With PyTorch 1.6+ it'll automatically use `native AMP` when `--fp16` is set.
 
 To see all the possible command line options, run:
 
@@ -265,6 +264,7 @@ export DATA_DIR=cnn_dm
     --fp16 \
     --bs 32
 ```
+
 ### Multi-GPU Evaluation
 here is a command to run xsum evaluation on 8 GPUS. It is more than linearly faster than run_eval.py in some cases 
 because it uses SortishSampler to minimize padding. You can also use it on 1 GPU. `data_dir` must have 
@@ -391,6 +391,17 @@ runtime: 13H on V-100 16GB GPU.
 pytest examples/seq2seq/
 ```
 
+### Converting pytorch-lightning checkpoints
+pytorch lightning ``-do_predict`` often fails, after you are done training, the best way to evaluate your model is to convert it.
+
+This should be done for you, with a file called `{save_dir}/best_tfmr`. 
+
+If that file doesn't exist but you have a lightning `.ckpt` file, you can run
+```bash
+python convert_pl_checkpoint_to_hf.py PATH_TO_CKPT  randomly_initialized_hf_model_path save_dir/best_tfmr
+```
+Then either `run_eval` or `run_distributed_eval` with `save_dir/best_tfmr` (see previous sections)
+
 
 ## Experimental Features 
 These features are harder to use and not always useful.
@@ -419,4 +430,3 @@ uses 12,723 batches of length 48 and takes slightly more time 9.5 minutes.
 The feature is still experimental, because:
 + we can make it much more robust if we have memory mapped/preprocessed datasets.
 + The speedup over sortish sampler is not that large at the moment.
-

examples/seq2seq/distillation.py

@@ -17,7 +17,7 @@
 from make_student import create_student_by_copying_alternating_layers, get_layers_to_supervise
 from transformers import AutoModelForSeq2SeqLM, MBartTokenizer, T5ForConditionalGeneration
 from transformers.modeling_bart import shift_tokens_right
-from utils import calculate_bleu, freeze_params, label_smoothed_nll_loss, pickle_load, use_task_specific_params
+from utils import calculate_bleu, freeze_params, label_smoothed_nll_loss, use_task_specific_params
 
 
 # need the parent dir module
@@ -264,30 +264,6 @@ def create_module(args):
     return model
 
 
-def evaluate_checkpoint(ckpt_path: Path, dest_dir=None):
-    # TODO(SS): DELETE? Better to convert_pl_ckpt_to_hf and run_eval.py
-    exp_dir = ckpt_path.parent
-    if dest_dir is None:
-        dest_dir = exp_dir
-    clash = list(dest_dir.glob("test_generations*"))
-    if clash:
-        print(f"SKIPPING to avoid overwriting {clash}")
-    ckpt = torch.load(ckpt_path, map_location="cpu")
-    if "hparams" in ckpt:
-        args = argparse.Namespace(**ckpt["hparams"])
-    else:
-        args = argparse.Namespace(**pickle_load(exp_dir / "hparams.pkl"))
-    args.resume_from_checkpoint = str(ckpt_path)
-    args.do_train = False
-    args.output_dir = str(dest_dir)
-    args.n_gpu = 1
-    args.eval_batch_size = 16
-    Path(args.output_dir).mkdir(exist_ok=True)
-    model = create_module(args)
-    trainer: pl.Trainer = generic_train(model, args, early_stopping_callback=False)
-    trainer.test(model)
-
-
 def distill_main(args):
     Path(args.output_dir).mkdir(exist_ok=True)
     if len(os.listdir(args.output_dir)) > 3 and args.do_train:

examples/seq2seq/finetune.py

@@ -181,6 +181,7 @@ def validation_step(self, batch, batch_idx) -> Dict:
         return self._generative_step(batch)
 
     def validation_epoch_end(self, outputs, prefix="val") -> Dict:
+
         self.step_count += 1
         losses = {k: torch.stack([x[k] for x in outputs]).mean() for k in self.loss_names}
         loss = losses["loss"]

examples/seq2seq/test_seq2seq_examples.py

@@ -13,7 +13,7 @@
 
 import lightning_base
 from convert_pl_checkpoint_to_hf import convert_pl_to_hf
-from distillation import distill_main, evaluate_checkpoint
+from distillation import distill_main
 from finetune import SummarizationModule, main
 from run_eval import generate_summaries_or_translations, run_generate
 from run_eval_search import run_search
@@ -178,7 +178,6 @@ def test_distill_checkpointing_with_teacher(self):
         generate_summaries_or_translations(examples, out_path, str(model.output_dir / "best_tfmr"))
         self.assertTrue(Path(out_path).exists())
 
-        evaluate_checkpoint(ckpts[0], dest_dir=Path(tempfile.mkdtemp()))
         out_path_new = tempfile.mkdtemp()
         convert_pl_to_hf(ckpts[0], transformer_ckpts[0].parent, out_path_new)
         assert os.path.exists(os.path.join(out_path_new, "pytorch_model.bin"))
@@ -227,8 +226,6 @@ def test_distill_mbart(self):
         assert len(all_files) > 2
         self.assertEqual(len(transformer_ckpts), 2)
 
-        evaluate_checkpoint(ckpts[0], dest_dir=Path(tempfile.mkdtemp()))
-
     def test_distill_t5(self):
         updates = dict(
             student_encoder_layers=1,

examples/test_examples.py

@@ -116,8 +116,8 @@ def test_run_pl_glue(self):
             testargs.append("--fp16")
 
         with patch.object(sys, "argv", testargs):
-            result = run_pl_glue.main()
-            # for now just testing that the script can run to a completion
+            result = run_pl_glue.main()[0]
+            # for now just testing that the script can run to completion
             self.assertGreater(result["acc"], 0.25)
             #
             # TODO: this fails on CI - doesn't get acc/f1>=0.75: