From 776eea8612458f60bbe684f38ea34f85fe890486 Mon Sep 17 00:00:00 2001 From: Marc Sun <57196510+SunMarc@users.noreply.github.com> Date: Thu, 9 Oct 2025 18:36:19 +0200 Subject: [PATCH] deprecate `overwrite_output_dir` (#41323) * dep * style * rm * wut * style --- ISSUES.md | 2 +- docs/source/ar/run_scripts.md | 26 ----------------- docs/source/ar/trainer.md | 2 -- docs/source/de/run_scripts.md | 26 ----------------- docs/source/en/deepspeed.md | 4 +-- docs/source/en/run_scripts.md | 7 +---- docs/source/en/trainer.md | 3 +- docs/source/es/run_scripts.md | 26 ----------------- docs/source/es/trainer.md | 2 -- docs/source/fr/run_scripts_fr.md | 28 +------------------ docs/source/it/run_scripts.md | 26 ----------------- docs/source/ja/main_classes/deepspeed.md | 6 ++-- docs/source/ja/main_classes/trainer.md | 3 -- docs/source/ja/run_scripts.md | 27 ------------------ docs/source/ko/deepspeed.md | 4 +-- docs/source/ko/perf_train_special.md | 3 +- docs/source/ko/run_scripts.md | 26 ----------------- docs/source/ko/trainer.md | 2 -- docs/source/pt/run_scripts.md | 26 ----------------- docs/source/zh/main_classes/deepspeed.md | 6 ++-- docs/source/zh/main_classes/trainer.md | 3 -- docs/source/zh/perf_train_special.md | 1 - docs/source/zh/run_scripts.md | 27 ------------------ .../multiple_choice/run_multiple_choice.py | 11 -------- .../legacy/question-answering/run_squad.py | 15 ---------- .../question-answering/run_squad_trainer.py | 11 -------- examples/legacy/run_language_modeling.py | 10 ------- examples/legacy/run_swag.py | 15 ---------- examples/legacy/seq2seq/finetune_trainer.py | 3 -- .../seq2seq/train_distil_marian_enro.sh | 2 +- .../seq2seq/train_distil_marian_enro_tpu.sh | 2 +- .../legacy/seq2seq/train_distilbart_cnn.sh | 2 +- .../legacy/seq2seq/train_mbart_cc25_enro.sh | 2 +- examples/legacy/seq2seq/utils.py | 24 ---------------- .../legacy/token-classification/run_ner.py | 11 -------- examples/pytorch/README.md | 3 +- .../pytorch/audio-classification/README.md | 2 -- .../run_audio_classification.py | 18 ------------ .../pytorch/contrastive-image-text/README.md | 1 - .../contrastive-image-text/run_clip.py | 18 ------------ .../run_image_classification.py | 18 ------------ examples/pytorch/image-pretraining/README.md | 2 -- examples/pytorch/image-pretraining/run_mae.py | 18 ------------ examples/pytorch/image-pretraining/run_mim.py | 18 ------------ .../run_instance_segmentation.py | 13 --------- examples/pytorch/language-modeling/run_clm.py | 18 ------------ examples/pytorch/language-modeling/run_fim.py | 18 ------------ examples/pytorch/language-modeling/run_mlm.py | 18 ------------ examples/pytorch/language-modeling/run_plm.py | 18 ------------ examples/pytorch/multiple-choice/run_swag.py | 18 ------------ .../object-detection/run_object_detection.py | 20 +------------ examples/pytorch/old_test_xla_examples.py | 1 - examples/pytorch/question-answering/run_qa.py | 18 ------------ .../question-answering/run_qa_beam_search.py | 18 ------------ .../question-answering/run_seq2seq_qa.py | 19 +------------ .../run_semantic_segmentation.py | 18 ------------ examples/pytorch/speech-recognition/README.md | 7 ----- .../run_speech_recognition_ctc.py | 23 ++------------- .../run_speech_recognition_ctc_adapter.py | 23 ++------------- .../run_speech_recognition_seq2seq.py | 19 +------------ examples/pytorch/summarization/README.md | 2 -- .../summarization/run_summarization.py | 18 ------------ examples/pytorch/test_pytorch_examples.py | 17 ----------- .../text-classification/run_classification.py | 18 ------------ .../pytorch/text-classification/run_glue.py | 18 ------------ .../pytorch/text-classification/run_xnli.py | 18 ------------ .../pytorch/token-classification/run_ner.py | 18 ------------ examples/pytorch/translation/README.md | 5 ---- .../pytorch/translation/run_translation.py | 18 ------------ .../integrations/integration_utils.py | 2 +- .../models/cwm/configuration_cwm.py | 19 +++++++------ src/transformers/models/cwm/modeling_cwm.py | 8 ++---- src/transformers/training_args.py | 12 -------- .../run_{{cookiecutter.example_shortcut}}.py | 23 ++------------- tests/deepspeed/test_deepspeed.py | 3 -- tests/deepspeed/test_model_zoo.py | 1 - tests/extended/test_trainer_ext.py | 1 - tests/fsdp/test_fsdp.py | 1 - tests/sagemaker/conftest.py | 1 - .../pytorch/run_glue_model_parallelism.py | 20 +------------ tests/trainer/test_trainer.py | 1 - 81 files changed, 46 insertions(+), 939 deletions(-) diff --git a/ISSUES.md b/ISSUES.md index c87bd9fc2c3..77de2998ad0 100644 --- a/ISSUES.md +++ b/ISSUES.md @@ -153,7 +153,7 @@ You are not required to read the following guidelines before opening an issue. H cd examples/seq2seq torchrun --nproc_per_node=2 ./finetune_trainer.py \ --model_name_or_path sshleifer/distill-mbart-en-ro-12-4 --data_dir wmt_en_ro \ - --output_dir output_dir --overwrite_output_dir \ + --output_dir output_dir \ --do_train --n_train 500 --num_train_epochs 1 \ --per_device_train_batch_size 1 --freeze_embeds \ --src_lang en_XX --tgt_lang ro_RO --task translation \ diff --git a/docs/source/ar/run_scripts.md b/docs/source/ar/run_scripts.md index 238844dc055..052e6e1d844 100644 --- a/docs/source/ar/run_scripts.md +++ b/docs/source/ar/run_scripts.md @@ -93,7 +93,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -117,7 +116,6 @@ torchrun \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -140,7 +138,6 @@ python xla_spawn.py --num_cores 8 \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -197,7 +194,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate @@ -225,7 +221,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -239,8 +234,6 @@ examples/pytorch/summarization/run_summarization.py -h خيار آخر مفيد لتمكينه هو استئناف التدريب من نقطة تفتيش سابقة. سيضمن ذلك أنك تستطيع الاستمرار من حيث توقفت دون البدء من جديد إذا تم مقاطعة تدريبك. هناك طريقتان لاستئناف التدريب من نقطة تفتيش. -تستخدم الطريقة الأولى المعلمة `output_dir previous_output_dir` لاستئناف التدريب من أحدث نقطة تفتيش مخزنة في `output_dir`. في هذه الحالة، يجب عليك إزالة `overwrite_output_dir`: - ```bash python examples/pytorch/summarization/run_summarization.py --model_name_or_path google-t5/t5-small \ @@ -252,24 +245,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --output_dir previous_output_dir \ - --predict_with_generate -``` - -تستخدم الطريقة الثانية معلمة `resume_from_checkpoint path_to_specific_checkpoint` لاستئناف التدريب من مجلد نقطة تفتيش محددة. - -```bash -python examples/pytorch/summarization/run_summarization.py - --model_name_or_path google-t5/t5-small \ - --do_train \ - --do_eval \ - --dataset_name cnn_dailymail \ - --dataset_config "3.0.0" \ - --source_prefix "summarize: " \ - --output_dir /tmp/tst-summarization \ - --per_device_train_batch_size=4 \ - --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate ``` @@ -301,6 +276,5 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/docs/source/ar/trainer.md b/docs/source/ar/trainer.md index 1784d76a4ec..be9e44cfa62 100644 --- a/docs/source/ar/trainer.md +++ b/docs/source/ar/trainer.md @@ -611,7 +611,6 @@ accelerate launch \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir ``` يمكنك أيضًا تحديد المعلمات من ملف `config_file.yaml` مباشرة في سطر الأوامر: @@ -634,7 +633,6 @@ accelerate launch --num_processes=2 \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir ``` اطلع على برنامج تعليمي [Launching your Accelerate scripts](https://huggingface.co/docs/accelerate/basic_tutorials/launch) لمعرفة المزيد حول `accelerate_launch` والتكوينات المخصصة. diff --git a/docs/source/de/run_scripts.md b/docs/source/de/run_scripts.md index 004f6729197..833d886c7e8 100644 --- a/docs/source/de/run_scripts.md +++ b/docs/source/de/run_scripts.md @@ -98,7 +98,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -122,7 +121,6 @@ torchrun \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -144,7 +142,6 @@ python xla_spawn.py --num_cores 8 \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -201,7 +198,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate @@ -229,7 +225,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -243,8 +238,6 @@ examples/pytorch/summarization/run_summarization.py -h Eine weitere hilfreiche Option, die Sie aktivieren können, ist die Wiederaufnahme des Trainings von einem früheren Kontrollpunkt aus. Auf diese Weise können Sie im Falle einer Unterbrechung Ihres Trainings dort weitermachen, wo Sie aufgehört haben, ohne von vorne beginnen zu müssen. Es gibt zwei Methoden, um das Training von einem Kontrollpunkt aus wieder aufzunehmen. -Die erste Methode verwendet das Argument `output_dir previous_output_dir`, um das Training ab dem letzten in `output_dir` gespeicherten Kontrollpunkt wieder aufzunehmen. In diesem Fall sollten Sie `overwrite_output_dir` entfernen: - ```bash python examples/pytorch/summarization/run_summarization.py --model_name_or_path google-t5/t5-small \ @@ -256,24 +249,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --output_dir previous_output_dir \ - --predict_with_generate -``` - -Die zweite Methode verwendet das Argument `Resume_from_checkpoint path_to_specific_checkpoint`, um das Training ab einem bestimmten Checkpoint-Ordner wieder aufzunehmen. - -```bash -python examples/pytorch/summarization/run_summarization.py - --model_name_or_path google-t5/t5-small \ - --do_train \ - --do_eval \ - --dataset_name cnn_dailymail \ - --dataset_config "3.0.0" \ - --source_prefix "summarize: " \ - --output_dir /tmp/tst-summarization \ - --per_device_train_batch_size=4 \ - --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate ``` @@ -305,6 +280,5 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/docs/source/en/deepspeed.md b/docs/source/en/deepspeed.md index 55b8408a43b..7971854011e 100644 --- a/docs/source/en/deepspeed.md +++ b/docs/source/en/deepspeed.md @@ -593,7 +593,7 @@ To deploy DeepSpeed on multiple GPUs, add `--num_gpus`. You don't need to add `- deepspeed --num_gpus=2 examples/pytorch/translation/run_translation.py \ --deepspeed tests/deepspeed/ds_config_zero3.json \ --model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \ ---output_dir output_dir --overwrite_output_dir --fp16 \ +--output_dir output_dir --fp16 \ --do_train --max_train_samples 500 --num_train_epochs 1 \ --dataset_name wmt16 --dataset_config "ro-en" \ --source_lang en --target_lang ro @@ -616,7 +616,7 @@ To deploy DeepSpeed on a single GPU, add `--num_gpus`. You don't need to add `-- deepspeed --num_gpus=1 examples/pytorch/translation/run_translation.py \ --deepspeed tests/deepspeed/ds_config_zero2.json \ --model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \ ---output_dir output_dir --overwrite_output_dir --fp16 \ +--output_dir output_dir --fp16 \ --do_train --max_train_samples 500 --num_train_epochs 1 \ --dataset_name wmt16 --dataset_config "ro-en" \ --source_lang en --target_lang ro diff --git a/docs/source/en/run_scripts.md b/docs/source/en/run_scripts.md index 594eb84b02a..74473b5228e 100644 --- a/docs/source/en/run_scripts.md +++ b/docs/source/en/run_scripts.md @@ -61,9 +61,8 @@ The example below fine-tunes [T5-small](https://huggingface.co/google-t5/t5-smal The example script downloads and preprocesses a dataset, and then fine-tunes it with [`Trainer`] with a supported model architecture. -Resuming training from a checkpoint is very useful if training is interrupted because you don't have to start over again. There are two ways to resume training from a checkpoint. +Resuming training from a checkpoint is very useful if training is interrupted because you don't have to start over again: -* `--output dir previous_output_dir` resumes training from the latest checkpoint stored in `output_dir`. Remove the `--overwrite_output_dir` parameter if you're using this method. * `--resume_from_checkpoint path_to_specific_checkpoint` resumes training from a specific checkpoint folder. Share your model on the [Hub](https://huggingface.co/) with the `--push_to_hub` parameter. It creates a repository and uploads the model to the folder name specified in `--output_dir`. You could also use the `--push_to_hub_model_id` parameter to specify the repository name. @@ -85,9 +84,6 @@ python examples/pytorch/summarization/run_summarization.py \ --per_device_eval_batch_size=4 \ --push_to_hub \ --push_to_hub_model_id finetuned-t5-cnn_dailymail \ - # remove if using `output_dir previous_output_dir` - # --overwrite_output_dir \ - --output_dir previous_output_dir \ # --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate \ ``` @@ -168,7 +164,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate \ diff --git a/docs/source/en/trainer.md b/docs/source/en/trainer.md index 32f14bc41da..98b23a3e7b9 100644 --- a/docs/source/en/trainer.md +++ b/docs/source/en/trainer.md @@ -361,8 +361,7 @@ accelerate launch \ --per_device_train_batch_size 16 \ --learning_rate 5e-5 \ --num_train_epochs 3 \ - --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir + --output_dir /tmp/$TASK_NAME/ ``` > [!TIP] diff --git a/docs/source/es/run_scripts.md b/docs/source/es/run_scripts.md index 462eb5bc303..6db78af2ce5 100644 --- a/docs/source/es/run_scripts.md +++ b/docs/source/es/run_scripts.md @@ -98,7 +98,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -122,7 +121,6 @@ torchrun \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -144,7 +142,6 @@ python xla_spawn.py --num_cores 8 \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -201,7 +198,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate @@ -229,7 +225,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -243,8 +238,6 @@ examples/pytorch/summarization/run_summarization.py -h Otra opción útil para habilitar es reanudar el entrenamiento desde un punto de control anterior. Esto asegurará que puedas continuar donde lo dejaste sin comenzar de nuevo si tu entrenamiento se interrumpe. Hay dos métodos para reanudar el entrenamiento desde un punto de control. -El primer método utiliza el argumento `output_dir previous_output_dir` para reanudar el entrenamiento desde el último punto de control almacenado en `output_dir`. En este caso, debes eliminar `overwrite_output_dir`: - ```bash python examples/pytorch/summarization/run_summarization.py --model_name_or_path google-t5/t5-small \ @@ -256,24 +249,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --output_dir previous_output_dir \ - --predict_with_generate -``` - -El segundo método utiliza el argumento `resume_from_checkpoint path_to_specific_checkpoint` para reanudar el entrenamiento desde una carpeta de punto de control específica. - -```bash -python examples/pytorch/summarization/run_summarization.py - --model_name_or_path google-t5/t5-small \ - --do_train \ - --do_eval \ - --dataset_name cnn_dailymail \ - --dataset_config "3.0.0" \ - --source_prefix "summarize: " \ - --output_dir /tmp/tst-summarization \ - --per_device_train_batch_size=4 \ - --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate ``` @@ -305,6 +280,5 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/docs/source/es/trainer.md b/docs/source/es/trainer.md index 4455521f531..335ec54b39b 100644 --- a/docs/source/es/trainer.md +++ b/docs/source/es/trainer.md @@ -381,7 +381,6 @@ accelerate launch \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir ``` También puedes especificar los parámetros del archivo config_file.yaml directamente en la línea de comandos: @@ -404,7 +403,6 @@ accelerate launch --num_processes=2 \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir ``` Consulta el tutorial [Lanzamiento de tus scripts con Accelerate](https://huggingface.co/docs/accelerate/basic_tutorials/launch) para obtener más información sobre `accelerate_launch` y las configuraciones personalizadas. diff --git a/docs/source/fr/run_scripts_fr.md b/docs/source/fr/run_scripts_fr.md index 1acf683253d..43e3ed02415 100644 --- a/docs/source/fr/run_scripts_fr.md +++ b/docs/source/fr/run_scripts_fr.md @@ -100,7 +100,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -124,7 +123,6 @@ torchrun \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -147,7 +145,6 @@ python xla_spawn.py --num_cores 8 \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -204,7 +201,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate @@ -231,7 +227,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -243,9 +238,7 @@ examples/pytorch/summarization/run_summarization.py -h ## Reprendre l'entraînement à partir d'un point de contrôle -Une autre option utile est de reprendre l'entraînement à partir d'un point de contrôle précédent. Cela vous permettra de reprendre là où vous vous étiez arrêté sans recommencer si votre entraînement est interrompu. Il existe deux méthodes pour reprendre l'entraînement à partir d'un point de contrôle. - -La première méthode utilise l'argument `output_dir previous_output_dir` pour reprendre l'entraînement à partir du dernier point de contrôle stocké dans `output_dir`. Dans ce cas, vous devez supprimer l'argument `overwrite_output_dir`. +Une autre option utile est de reprendre l'entraînement à partir d'un point de contrôle précédent. Cela vous permettra de reprendre là où vous vous étiez arrêté sans recommencer si votre entraînement est interrompu: ```bash python examples/pytorch/summarization/run_summarization.py @@ -258,24 +251,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --output_dir previous_output_dir \ - --predict_with_generate -``` - -La seconde méthode utilise l'argument `resume_from_checkpoint path_to_specific_checkpoint` pour reprendre l'entraînement à partir d'un dossier de point de contrôle spécifique. - -```bash -python examples/pytorch/summarization/run_summarization.py - --model_name_or_path google-t5/t5-small \ - --do_train \ - --do_eval \ - --dataset_name cnn_dailymail \ - --dataset_config "3.0.0" \ - --source_prefix "summarize: " \ - --output_dir /tmp/tst-summarization \ - --per_device_train_batch_size=4 \ - --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate ``` @@ -308,6 +283,5 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/docs/source/it/run_scripts.md b/docs/source/it/run_scripts.md index ad7df423cb9..e0986b83977 100644 --- a/docs/source/it/run_scripts.md +++ b/docs/source/it/run_scripts.md @@ -98,7 +98,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -122,7 +121,6 @@ torchrun \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -144,7 +142,6 @@ python xla_spawn.py --num_cores 8 \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -201,7 +198,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate @@ -229,7 +225,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -243,8 +238,6 @@ examples/pytorch/summarization/run_summarization.py -h Un'altra utile opzione è riavviare un addestramento da un checkpoint precedente. Questo garantirà che tu possa riprendere da dove hai interrotto senza ricominciare se l'addestramento viene interrotto. Ci sono due metodi per riavviare l'addestramento da un checkpoint: -Il primo metodo usa l'argomento `output_dir previous_output_dir` per riavviare l'addestramento dall'ultima versione del checkpoint contenuto in `output_dir`. In questo caso, dovresti rimuovere `overwrite_output_dir`: - ```bash python examples/pytorch/summarization/run_summarization.py --model_name_or_path google-t5/t5-small \ @@ -256,24 +249,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --output_dir previous_output_dir \ - --predict_with_generate -``` - -Il secondo metodo usa l'argomento `resume_from_checkpoint path_to_specific_checkpoint` per riavviare un addestramento da una specifica cartella di checkpoint. - -```bash -python examples/pytorch/summarization/run_summarization.py - --model_name_or_path google-t5/t5-small \ - --do_train \ - --do_eval \ - --dataset_name cnn_dailymail \ - --dataset_config "3.0.0" \ - --source_prefix "summarize: " \ - --output_dir /tmp/tst-summarization \ - --per_device_train_batch_size=4 \ - --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate ``` @@ -305,6 +280,5 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/docs/source/ja/main_classes/deepspeed.md b/docs/source/ja/main_classes/deepspeed.md index affb6c0a724..a8801f0379e 100644 --- a/docs/source/ja/main_classes/deepspeed.md +++ b/docs/source/ja/main_classes/deepspeed.md @@ -188,7 +188,7 @@ deepspeed --num_gpus=2 your_program.py --deepspeed ds_config.js deepspeed examples/pytorch/translation/run_translation.py \ --deepspeed tests/deepspeed/ds_config_zero3.json \ --model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \ ---output_dir output_dir --overwrite_output_dir --fp16 \ +--output_dir output_dir --fp16 \ --do_train --max_train_samples 500 --num_train_epochs 1 \ --dataset_name wmt16 --dataset_config "ro-en" \ --source_lang en --target_lang ro @@ -211,7 +211,7 @@ DeepSpeed 関連の引数が 2 つありますが、簡単にするためであ deepspeed --num_gpus=1 examples/pytorch/translation/run_translation.py \ --deepspeed tests/deepspeed/ds_config_zero2.json \ --model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \ ---output_dir output_dir --overwrite_output_dir --fp16 \ +--output_dir output_dir --fp16 \ --do_train --max_train_samples 500 --num_train_epochs 1 \ --dataset_name wmt16 --dataset_config "ro-en" \ --source_lang en --target_lang ro @@ -1789,7 +1789,7 @@ deepspeed examples/pytorch/translation/run_translation.py \ --model_name_or_path google-t5/t5-small --output_dir output_dir \ --do_eval --max_eval_samples 50 --warmup_steps 50 \ --max_source_length 128 --val_max_target_length 128 \ ---overwrite_output_dir --per_device_eval_batch_size 4 \ +--per_device_eval_batch_size 4 \ --predict_with_generate --dataset_config "ro-en" --fp16 \ --source_lang en --target_lang ro --dataset_name wmt16 \ --source_prefix "translate English to Romanian: " diff --git a/docs/source/ja/main_classes/trainer.md b/docs/source/ja/main_classes/trainer.md index e6e6e28d308..e5d55ff77b4 100644 --- a/docs/source/ja/main_classes/trainer.md +++ b/docs/source/ja/main_classes/trainer.md @@ -534,7 +534,6 @@ python examples/pytorch/text-classification/run_glue.py \ --learning_rate 2e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir ``` **注意すべきいくつかの注意事項** @@ -669,7 +668,6 @@ accelerate launch \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ ---overwrite_output_dir ``` 4. `accelerate launch`するための cmd 引数を直接使用することもできます。上の例は次のようにマッピングされます。 @@ -694,7 +692,6 @@ accelerate launch --num_processes=2 \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ ---overwrite_output_dir ``` 詳細については、🤗 Accelerate CLI ガイドを参照してください: [🤗 Accelerate スクリプトの起動](https://huggingface.co/docs/accelerate/basic_tutorials/launch)。 diff --git a/docs/source/ja/run_scripts.md b/docs/source/ja/run_scripts.md index ee738e3e431..bf0ed862702 100644 --- a/docs/source/ja/run_scripts.md +++ b/docs/source/ja/run_scripts.md @@ -104,7 +104,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -131,7 +130,6 @@ torchrun \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -153,7 +151,6 @@ python xla_spawn.py --num_cores 8 \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -212,7 +209,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate @@ -240,7 +236,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -254,8 +249,6 @@ examples/pytorch/summarization/run_summarization.py -h 以前のチェックポイントからトレーニングを再開するための役立つオプションもあります。これにより、トレーニングが中断された場合でも、最初からやり直すことなく、中断したところから再開できます。チェックポイントからトレーニングを再開するための2つの方法があります。 -最初の方法は、`output_dir previous_output_dir` 引数を使用して、`output_dir` に保存された最新のチェックポイントからトレーニングを再開する方法です。この場合、`overwrite_output_dir` を削除する必要があります： - ```bash python examples/pytorch/summarization/run_summarization.py --model_name_or_path google-t5/t5-small \ @@ -267,25 +260,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --output_dir previous_output_dir \ - --predict_with_generate -``` - -2番目の方法では、`resume_from_checkpoint path_to_specific_checkpoint` 引数を使用して、特定のチェックポイントフォルダからトレーニングを再開します。 - - -```bash -python examples/pytorch/summarization/run_summarization.py - --model_name_or_path google-t5/t5-small \ - --do_train \ - --do_eval \ - --dataset_name cnn_dailymail \ - --dataset_config "3.0.0" \ - --source_prefix "summarize: " \ - --output_dir /tmp/tst-summarization \ - --per_device_train_batch_size=4 \ - --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate ``` @@ -319,7 +293,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/docs/source/ko/deepspeed.md b/docs/source/ko/deepspeed.md index d0955ee3db8..823865168be 100644 --- a/docs/source/ko/deepspeed.md +++ b/docs/source/ko/deepspeed.md @@ -590,7 +590,7 @@ bf16은 설정 파일에서 설정하거나 다음 인수를 전달하면 명령 deepspeed --num_gpus=2 examples/pytorch/translation/run_translation.py \ --deepspeed tests/deepspeed/ds_config_zero3.json \ --model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \ ---output_dir output_dir --overwrite_output_dir --fp16 \ +--output_dir output_dir --fp16 \ --do_train --max_train_samples 500 --num_train_epochs 1 \ --dataset_name wmt16 --dataset_config "ro-en" \ --source_lang en --target_lang ro @@ -605,7 +605,7 @@ deepspeed --num_gpus=2 examples/pytorch/translation/run_translation.py \ deepspeed --num_gpus=1 examples/pytorch/translation/run_translation.py \ --deepspeed tests/deepspeed/ds_config_zero2.json \ --model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \ ---output_dir output_dir --overwrite_output_dir --fp16 \ +--output_dir output_dir --fp16 \ --do_train --max_train_samples 500 --num_train_epochs 1 \ --dataset_name wmt16 --dataset_config "ro-en" \ --source_lang en --target_lang ro diff --git a/docs/source/ko/perf_train_special.md b/docs/source/ko/perf_train_special.md index 188db542f7c..7927f3748f0 100644 --- a/docs/source/ko/perf_train_special.md +++ b/docs/source/ko/perf_train_special.md @@ -54,8 +54,7 @@ python examples/pytorch/text-classification/run_glue.py \ --per_device_train_batch_size 32 \ --learning_rate 2e-5 \ --num_train_epochs 3 \ - --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir + --output_dir /tmp/$TASK_NAME/ ``` `gloco`와 `nccl`과 같은 [분산 학습 백엔드](https://pytorch.org/docs/stable/distributed.html#backends)는 `mps` 장치에서 지원되지 않으므로, MPS 백엔드에서는 단일 GPU로만 학습이 가능합니다. diff --git a/docs/source/ko/run_scripts.md b/docs/source/ko/run_scripts.md index 874834a1f32..2db8fe16c60 100644 --- a/docs/source/ko/run_scripts.md +++ b/docs/source/ko/run_scripts.md @@ -106,7 +106,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -131,7 +130,6 @@ torchrun \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -156,7 +154,6 @@ python xla_spawn.py --num_cores 8 \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -216,7 +213,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate @@ -245,7 +241,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -262,8 +257,6 @@ examples/pytorch/summarization/run_summarization.py -h 이렇게 하면 훈련이 중단되더라도 처음부터 다시 시작하지 않고 중단한 부분부터 다시 시작할 수 있습니다. 체크포인트에서 훈련을 재개하는 방법에는 두 가지가 있습니다. -첫 번째는 `output_dir previous_output_dir` 인수를 사용하여 `output_dir`에 저장된 최신 체크포인트부터 훈련을 재개하는 방법입니다. -이 경우 `overwrite_output_dir`을 제거해야 합니다: ```bash python examples/pytorch/summarization/run_summarization.py --model_name_or_path google-t5/t5-small \ @@ -275,24 +268,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --output_dir previous_output_dir \ - --predict_with_generate -``` - -두 번째는 `resume_from_checkpoint path_to_specific_checkpoint` 인수를 사용하여 특정 체크포인트 폴더에서 훈련을 재개하는 방법입니다. - -```bash -python examples/pytorch/summarization/run_summarization.py - --model_name_or_path google-t5/t5-small \ - --do_train \ - --do_eval \ - --dataset_name cnn_dailymail \ - --dataset_config "3.0.0" \ - --source_prefix "summarize: " \ - --output_dir /tmp/tst-summarization \ - --per_device_train_batch_size=4 \ - --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate ``` @@ -325,6 +300,5 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/docs/source/ko/trainer.md b/docs/source/ko/trainer.md index d753627c86f..65c3fbef982 100644 --- a/docs/source/ko/trainer.md +++ b/docs/source/ko/trainer.md @@ -505,7 +505,6 @@ accelerate launch \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir ``` `config_file.yaml` 파일의 매개변수를 직접 지정할 수도 있습니다: @@ -528,7 +527,6 @@ accelerate launch --num_processes=2 \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir ``` `accelerate_launch`와 사용자 정의 구성에 대해 더 알아보려면 [Accelerate 스크립트 실행](https://huggingface.co/docs/accelerate/basic_tutorials/launch) 튜토리얼을 확인하세요. \ No newline at end of file diff --git a/docs/source/pt/run_scripts.md b/docs/source/pt/run_scripts.md index 4b4baf18988..72060f98571 100644 --- a/docs/source/pt/run_scripts.md +++ b/docs/source/pt/run_scripts.md @@ -99,7 +99,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -123,7 +122,6 @@ torchrun \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -145,7 +143,6 @@ python xla_spawn.py --num_cores 8 \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -203,7 +200,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate @@ -231,7 +227,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -245,8 +240,6 @@ examples/pytorch/summarization/run_summarization.py -h Outra opção útil para habilitar é retomar o treinamento de um checkpoint anterior. Isso garantirá que você possa continuar de onde parou sem recomeçar se o seu treinamento for interrompido. Existem dois métodos para retomar o treinamento a partir de um checkpoint. -O primeiro método usa o argumento `output_dir previous_output_dir` para retomar o treinamento do último checkpoint armazenado em `output_dir`. Neste caso, você deve remover `overwrite_output_dir`: - ```bash python examples/pytorch/summarization/run_summarization.py --model_name_or_path google-t5/t5-small \ @@ -258,24 +251,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --output_dir previous_output_dir \ - --predict_with_generate -``` - -O segundo método usa o argumento `resume_from_checkpoint path_to_specific_checkpoint` para retomar o treinamento de uma pasta de checkpoint específica. - -```bash -python examples/pytorch/summarization/run_summarization.py - --model_name_or_path google-t5/t5-small \ - --do_train \ - --do_eval \ - --dataset_name cnn_dailymail \ - --dataset_config "3.0.0" \ - --source_prefix "summarize: " \ - --output_dir /tmp/tst-summarization \ - --per_device_train_batch_size=4 \ - --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate ``` @@ -307,6 +282,5 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/docs/source/zh/main_classes/deepspeed.md b/docs/source/zh/main_classes/deepspeed.md index 8319f5cad4a..2fe0d554a7f 100644 --- a/docs/source/zh/main_classes/deepspeed.md +++ b/docs/source/zh/main_classes/deepspeed.md @@ -179,7 +179,7 @@ deepspeed --num_gpus=2 your_program.py --deepspeed ds_config.js deepspeed examples/pytorch/translation/run_translation.py \ --deepspeed tests/deepspeed/ds_config_zero3.json \ --model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \ ---output_dir output_dir --overwrite_output_dir --fp16 \ +--output_dir output_dir --fp16 \ --do_train --max_train_samples 500 --num_train_epochs 1 \ --dataset_name wmt16 --dataset_config "ro-en" \ --source_lang en --target_lang ro @@ -202,7 +202,7 @@ deepspeed examples/pytorch/translation/run_translation.py \ deepspeed --num_gpus=1 examples/pytorch/translation/run_translation.py \ --deepspeed tests/deepspeed/ds_config_zero2.json \ --model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \ ---output_dir output_dir --overwrite_output_dir --fp16 \ +--output_dir output_dir --fp16 \ --do_train --max_train_samples 500 --num_train_epochs 1 \ --dataset_name wmt16 --dataset_config "ro-en" \ --source_lang en --target_lang ro @@ -1659,7 +1659,7 @@ deepspeed examples/pytorch/translation/run_translation.py \ --model_name_or_path google-t5/t5-small --output_dir output_dir \ --do_eval --max_eval_samples 50 --warmup_steps 50 \ --max_source_length 128 --val_max_target_length 128 \ ---overwrite_output_dir --per_device_eval_batch_size 4 \ +--per_device_eval_batch_size 4 \ --predict_with_generate --dataset_config "ro-en" --fp16 \ --source_lang en --target_lang ro --dataset_name wmt16 \ --source_prefix "translate English to Romanian: " diff --git a/docs/source/zh/main_classes/trainer.md b/docs/source/zh/main_classes/trainer.md index 159477fe64a..5d587fd6d57 100644 --- a/docs/source/zh/main_classes/trainer.md +++ b/docs/source/zh/main_classes/trainer.md @@ -471,7 +471,6 @@ python examples/pytorch/text-classification/run_glue.py \ --learning_rate 2e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir ``` **需要注意的一些注意事项** @@ -606,7 +605,6 @@ accelerate launch \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ ---overwrite_output_dir ``` 4. 你也可以直接使用`accelerate launch`的cmd参数。上面的示例将映射到： @@ -631,7 +629,6 @@ accelerate launch --num_processes=2 \ --learning_rate 5e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ ---overwrite_output_dir ``` 有关更多信息，请参阅 🤗 Accelerate CLI 指南：[启动您的 🤗 Accelerate 脚本](https://huggingface.co/docs/accelerate/basic_tutorials/launch)。 diff --git a/docs/source/zh/perf_train_special.md b/docs/source/zh/perf_train_special.md index ee855347567..8e7929ecb1c 100644 --- a/docs/source/zh/perf_train_special.md +++ b/docs/source/zh/perf_train_special.md @@ -50,7 +50,6 @@ python examples/pytorch/text-classification/run_glue.py \ --learning_rate 2e-5 \ --num_train_epochs 3 \ --output_dir /tmp/$TASK_NAME/ \ - --overwrite_output_dir ``` 用于[分布式设置](https://pytorch.org/docs/stable/distributed.html#backends)的后端(如`gloo`和`nccl`)不支持`mps`设备，这也意味着使用 MPS 后端时只能在单个 GPU 上进行训练。 diff --git a/docs/source/zh/run_scripts.md b/docs/source/zh/run_scripts.md index 32bf2342f9a..60e78fcb9e9 100644 --- a/docs/source/zh/run_scripts.md +++ b/docs/source/zh/run_scripts.md @@ -99,7 +99,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -124,7 +123,6 @@ torchrun \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -145,7 +143,6 @@ python xla_spawn.py --num_cores 8 \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -202,7 +199,6 @@ python examples/pytorch/summarization/run_summarization.py \ --summary_column summary_column_name \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate @@ -231,7 +227,6 @@ python examples/pytorch/summarization/run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -245,8 +240,6 @@ examples/pytorch/summarization/run_summarization.py -h 另一个有用的选项是从之前的checkpoint恢复训练。这将确保在训练中断时，您可以从之前停止的地方继续进行，而无需重新开始。有两种方法可以从checkpoint恢复训练。 -第一种方法使用`output_dir previous_output_dir`参数从存储在`output_dir`中的最新的checkpoint恢复训练。在这种情况下，您应该删除`overwrite_output_dir`： - ```bash python examples/pytorch/summarization/run_summarization.py --model_name_or_path google-t5/t5-small \ @@ -258,25 +251,6 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --output_dir previous_output_dir \ - --predict_with_generate -``` - -第二种方法使用`resume_from_checkpoint path_to_specific_checkpoint`参数从特定的checkpoint文件夹恢复训练。 - - -```bash -python examples/pytorch/summarization/run_summarization.py - --model_name_or_path google-t5/t5-small \ - --do_train \ - --do_eval \ - --dataset_name cnn_dailymail \ - --dataset_config "3.0.0" \ - --source_prefix "summarize: " \ - --output_dir /tmp/tst-summarization \ - --per_device_train_batch_size=4 \ - --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --resume_from_checkpoint path_to_specific_checkpoint \ --predict_with_generate ``` @@ -309,6 +283,5 @@ python examples/pytorch/summarization/run_summarization.py --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/examples/legacy/multiple_choice/run_multiple_choice.py b/examples/legacy/multiple_choice/run_multiple_choice.py index aa1297656a9..92947e2092c 100644 --- a/examples/legacy/multiple_choice/run_multiple_choice.py +++ b/examples/legacy/multiple_choice/run_multiple_choice.py @@ -95,17 +95,6 @@ def main(): parser = HfArgumentParser((ModelArguments, DataTrainingArguments, TrainingArguments)) model_args, data_args, training_args = parser.parse_args_into_dataclasses() - if ( - os.path.exists(training_args.output_dir) - and os.listdir(training_args.output_dir) - and training_args.do_train - and not training_args.overwrite_output_dir - ): - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. Use" - " --overwrite_output_dir to overcome." - ) - # Setup logging logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", diff --git a/examples/legacy/question-answering/run_squad.py b/examples/legacy/question-answering/run_squad.py index 39ba14a12af..126fa197ee2 100644 --- a/examples/legacy/question-answering/run_squad.py +++ b/examples/legacy/question-answering/run_squad.py @@ -641,9 +641,6 @@ def main(): help="Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number", ) parser.add_argument("--no_cuda", action="store_true", help="Whether not to use CUDA when available") - parser.add_argument( - "--overwrite_output_dir", action="store_true", help="Overwrite the content of the output directory" - ) parser.add_argument( "--overwrite_cache", action="store_true", help="Overwrite the cached training and evaluation sets" ) @@ -677,18 +674,6 @@ def main(): "stride or increase the maximum length to ensure the features are correctly built." ) - if ( - os.path.exists(args.output_dir) - and os.listdir(args.output_dir) - and args.do_train - and not args.overwrite_output_dir - ): - raise ValueError( - "Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome.".format( - args.output_dir - ) - ) - # Setup distant debugging if needed if args.server_ip and args.server_port: # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script diff --git a/examples/legacy/question-answering/run_squad_trainer.py b/examples/legacy/question-answering/run_squad_trainer.py index d3730d1bc0b..5288e3019b9 100644 --- a/examples/legacy/question-answering/run_squad_trainer.py +++ b/examples/legacy/question-answering/run_squad_trainer.py @@ -76,17 +76,6 @@ def main(): else: model_args, data_args, training_args = parser.parse_args_into_dataclasses() - if ( - os.path.exists(training_args.output_dir) - and os.listdir(training_args.output_dir) - and training_args.do_train - and not training_args.overwrite_output_dir - ): - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. Use" - " --overwrite_output_dir to overcome." - ) - # Setup logging logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", diff --git a/examples/legacy/run_language_modeling.py b/examples/legacy/run_language_modeling.py index 8a6b8eded34..64c92fa205e 100755 --- a/examples/legacy/run_language_modeling.py +++ b/examples/legacy/run_language_modeling.py @@ -207,16 +207,6 @@ def main(): "Cannot do evaluation without an evaluation data file. Either supply a file to --eval_data_file " "or remove the --do_eval argument." ) - if ( - os.path.exists(training_args.output_dir) - and os.listdir(training_args.output_dir) - and training_args.do_train - and not training_args.overwrite_output_dir - ): - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. Use" - " --overwrite_output_dir to overcome." - ) # Setup logging logging.basicConfig( diff --git a/examples/legacy/run_swag.py b/examples/legacy/run_swag.py index 221f9cc9c98..8c80cf8a347 100755 --- a/examples/legacy/run_swag.py +++ b/examples/legacy/run_swag.py @@ -557,9 +557,6 @@ def main(): help="Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number", ) parser.add_argument("--no_cuda", action="store_true", help="Whether not to use CUDA when available") - parser.add_argument( - "--overwrite_output_dir", action="store_true", help="Overwrite the content of the output directory" - ) parser.add_argument( "--overwrite_cache", action="store_true", help="Overwrite the cached training and evaluation sets" ) @@ -584,18 +581,6 @@ def main(): parser.add_argument("--server_port", type=str, default="", help="Can be used for distant debugging.") args = parser.parse_args() - if ( - os.path.exists(args.output_dir) - and os.listdir(args.output_dir) - and args.do_train - and not args.overwrite_output_dir - ): - raise ValueError( - "Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome.".format( - args.output_dir - ) - ) - # Setup distant debugging if needed if args.server_ip and args.server_port: # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script diff --git a/examples/legacy/seq2seq/finetune_trainer.py b/examples/legacy/seq2seq/finetune_trainer.py index 44f5a75eda0..54ca2c898c8 100755 --- a/examples/legacy/seq2seq/finetune_trainer.py +++ b/examples/legacy/seq2seq/finetune_trainer.py @@ -39,7 +39,6 @@ from utils import ( Seq2SeqDataset, assert_all_frozen, build_compute_metrics_fn, - check_output_dir, freeze_embeds, freeze_params, lmap, @@ -168,8 +167,6 @@ def main(): else: model_args, data_args, training_args = parser.parse_args_into_dataclasses() - check_output_dir(training_args) - # Setup logging logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", diff --git a/examples/legacy/seq2seq/train_distil_marian_enro.sh b/examples/legacy/seq2seq/train_distil_marian_enro.sh index 5e86a6991c5..d0e1075bb07 100644 --- a/examples/legacy/seq2seq/train_distil_marian_enro.sh +++ b/examples/legacy/seq2seq/train_distil_marian_enro.sh @@ -20,7 +20,7 @@ export MAX_LEN=128 python finetune_trainer.py \ --tokenizer_name $m --model_name_or_path $m \ --data_dir $ENRO_DIR \ - --output_dir marian_en_ro_6_3 --overwrite_output_dir \ + --output_dir marian_en_ro_6_3 \ --learning_rate=3e-4 \ --warmup_steps 500 --sortish_sampler \ --fp16 \ diff --git a/examples/legacy/seq2seq/train_distil_marian_enro_tpu.sh b/examples/legacy/seq2seq/train_distil_marian_enro_tpu.sh index 00ef6722619..fcf4ea13698 100644 --- a/examples/legacy/seq2seq/train_distil_marian_enro_tpu.sh +++ b/examples/legacy/seq2seq/train_distil_marian_enro_tpu.sh @@ -22,7 +22,7 @@ python xla_spawn.py --num_cores $TPU_NUM_CORES \ finetune_trainer.py \ --tokenizer_name $m --model_name_or_path $m \ --data_dir $ENRO_DIR \ - --output_dir marian_en_ro_6_3 --overwrite_output_dir \ + --output_dir marian_en_ro_6_3 \ --learning_rate=3e-4 \ --warmup_steps 500 \ --per_device_train_batch_size=$BS --per_device_eval_batch_size=$BS \ diff --git a/examples/legacy/seq2seq/train_distilbart_cnn.sh b/examples/legacy/seq2seq/train_distilbart_cnn.sh index 42f34e0cb6e..a490019588c 100644 --- a/examples/legacy/seq2seq/train_distilbart_cnn.sh +++ b/examples/legacy/seq2seq/train_distilbart_cnn.sh @@ -21,7 +21,7 @@ export MAX_TGT_LEN=142 python finetune_trainer.py \ --model_name_or_path $m --tokenizer_name $tok \ --data_dir cnn_dm \ - --output_dir distilbart-cnn-12-6 --overwrite_output_dir \ + --output_dir distilbart-cnn-12-6 \ --learning_rate=3e-5 \ --warmup_steps 500 --sortish_sampler \ --fp16 \ diff --git a/examples/legacy/seq2seq/train_mbart_cc25_enro.sh b/examples/legacy/seq2seq/train_mbart_cc25_enro.sh index 63c8051b47d..fb31790a2c1 100644 --- a/examples/legacy/seq2seq/train_mbart_cc25_enro.sh +++ b/examples/legacy/seq2seq/train_mbart_cc25_enro.sh @@ -15,7 +15,7 @@ python finetune_trainer.py \ --model_name_or_path=facebook/mbart-large-cc25 \ --data_dir $ENRO_DIR \ - --output_dir mbart_cc25_enro --overwrite_output_dir \ + --output_dir mbart_cc25_enro \ --learning_rate=3e-5 \ --warmup_steps 500 \ --fp16 \ diff --git a/examples/legacy/seq2seq/utils.py b/examples/legacy/seq2seq/utils.py index 221b1405aa2..43d66128360 100644 --- a/examples/legacy/seq2seq/utils.py +++ b/examples/legacy/seq2seq/utils.py @@ -639,27 +639,3 @@ def chunks(lst, n): """Yield successive n-sized chunks from lst.""" for i in range(0, len(lst), n): yield lst[i : i + n] - - -def check_output_dir(args, expected_items=0): - """ - Checks whether to bail out if output_dir already exists and has more than expected_items in it - - `args`: needs to have the following attributes of `args`: - - output_dir - - do_train - - overwrite_output_dir - - `expected_items`: normally 0 (default) - i.e. empty dir, but in some cases a few files are expected (e.g. recovery from OOM) - """ - if ( - os.path.exists(args.output_dir) - and len(os.listdir(args.output_dir)) > expected_items - and args.do_train - and not args.overwrite_output_dir - ): - raise ValueError( - f"Output directory ({args.output_dir}) already exists and " - f"has {len(os.listdir(args.output_dir))} items in it (expected {expected_items} items). " - "Use --overwrite_output_dir to overcome." - ) diff --git a/examples/legacy/token-classification/run_ner.py b/examples/legacy/token-classification/run_ner.py index 69b8a27ac79..1e6e5e40231 100644 --- a/examples/legacy/token-classification/run_ner.py +++ b/examples/legacy/token-classification/run_ner.py @@ -111,17 +111,6 @@ def main(): else: model_args, data_args, training_args = parser.parse_args_into_dataclasses() - if ( - os.path.exists(training_args.output_dir) - and os.listdir(training_args.output_dir) - and training_args.do_train - and not training_args.overwrite_output_dir - ): - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. Use" - " --overwrite_output_dir to overcome." - ) - module = import_module("tasks") try: token_classification_task_clazz = getattr(module, model_args.task_type) diff --git a/examples/pytorch/README.md b/examples/pytorch/README.md index 18ed7ae8e38..f803f71525e 100644 --- a/examples/pytorch/README.md +++ b/examples/pytorch/README.md @@ -72,8 +72,7 @@ token-classification/run_ner.py -h You can resume training from a previous checkpoint like this: -1. Pass `--output_dir previous_output_dir` without `--overwrite_output_dir` to resume training from the latest checkpoint in `output_dir` (what you would use if the training was interrupted, for instance). -2. Pass `--resume_from_checkpoint path_to_a_specific_checkpoint` to resume training from that checkpoint folder. +1. Pass `--resume_from_checkpoint path_to_a_specific_checkpoint` to resume training from that checkpoint folder. Should you want to turn an example into a notebook where you'd no longer have access to the command line, 🤗 Trainer supports resuming from a checkpoint via `trainer.train(resume_from_checkpoint)`. diff --git a/examples/pytorch/audio-classification/README.md b/examples/pytorch/audio-classification/README.md index 6f9069b331a..2910b358762 100644 --- a/examples/pytorch/audio-classification/README.md +++ b/examples/pytorch/audio-classification/README.md @@ -34,7 +34,6 @@ python run_audio_classification.py \ --dataset_name superb \ --dataset_config_name ks \ --output_dir wav2vec2-base-ft-keyword-spotting \ - --overwrite_output_dir \ --remove_unused_columns False \ --do_train \ --do_eval \ @@ -76,7 +75,6 @@ python run_audio_classification.py \ --audio_column_name audio \ --label_column_name language \ --output_dir wav2vec2-base-lang-id \ - --overwrite_output_dir \ --remove_unused_columns False \ --do_train \ --do_eval \ diff --git a/examples/pytorch/audio-classification/run_audio_classification.py b/examples/pytorch/audio-classification/run_audio_classification.py index bd190e80152..3abd6e158d3 100644 --- a/examples/pytorch/audio-classification/run_audio_classification.py +++ b/examples/pytorch/audio-classification/run_audio_classification.py @@ -47,7 +47,6 @@ from transformers import ( TrainingArguments, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -245,21 +244,6 @@ def main(): # Set seed before initializing model. set_seed(training_args.seed) - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to train from scratch." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Initialize our dataset and prepare it for the audio classification task. raw_datasets = DatasetDict() raw_datasets["train"] = load_dataset( @@ -408,8 +392,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() trainer.log_metrics("train", train_result.metrics) diff --git a/examples/pytorch/contrastive-image-text/README.md b/examples/pytorch/contrastive-image-text/README.md index 864a31b6037..9211c0cc59f 100644 --- a/examples/pytorch/contrastive-image-text/README.md +++ b/examples/pytorch/contrastive-image-text/README.md @@ -97,6 +97,5 @@ python run_clip.py \ --per_device_train_batch_size="64" \ --per_device_eval_batch_size="64" \ --learning_rate="5e-5" --warmup_steps="0" --weight_decay 0.1 \ - --overwrite_output_dir \ --push_to_hub ``` diff --git a/examples/pytorch/contrastive-image-text/run_clip.py b/examples/pytorch/contrastive-image-text/run_clip.py index d9bfe47dd0e..eac0977a212 100644 --- a/examples/pytorch/contrastive-image-text/run_clip.py +++ b/examples/pytorch/contrastive-image-text/run_clip.py @@ -55,7 +55,6 @@ from transformers import ( TrainingArguments, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -271,21 +270,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # 3. Detecting last checkpoint and eventually continue from last checkpoint - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # 4. Load dataset # Get the datasets: you can either provide your own CSV/JSON training and evaluation files (see below) # or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/ @@ -497,8 +481,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() tokenizer.save_pretrained(training_args.output_dir) diff --git a/examples/pytorch/image-classification/run_image_classification.py b/examples/pytorch/image-classification/run_image_classification.py index 8b498b545c4..04107ffdfb3 100755 --- a/examples/pytorch/image-classification/run_image_classification.py +++ b/examples/pytorch/image-classification/run_image_classification.py @@ -58,7 +58,6 @@ from transformers import ( TrainingArguments, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -225,21 +224,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -418,8 +402,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() trainer.log_metrics("train", train_result.metrics) diff --git a/examples/pytorch/image-pretraining/README.md b/examples/pytorch/image-pretraining/README.md index bca37f24135..9e1eae48f83 100644 --- a/examples/pytorch/image-pretraining/README.md +++ b/examples/pytorch/image-pretraining/README.md @@ -44,7 +44,6 @@ Alternatively, one can decide to further pre-train an already pre-trained (or fi !python run_mim.py \ --model_type vit \ --output_dir ./outputs/ \ - --overwrite_output_dir \ --remove_unused_columns False \ --label_names bool_masked_pos \ --do_train \ @@ -95,7 +94,6 @@ Next, we can run the script by providing the path to this custom configuration ( --config_name_or_path path_to_config \ --model_type swin \ --output_dir ./outputs/ \ - --overwrite_output_dir \ --remove_unused_columns False \ --label_names bool_masked_pos \ --do_train \ diff --git a/examples/pytorch/image-pretraining/run_mae.py b/examples/pytorch/image-pretraining/run_mae.py index 2d92d8ab434..ea350a855fe 100644 --- a/examples/pytorch/image-pretraining/run_mae.py +++ b/examples/pytorch/image-pretraining/run_mae.py @@ -41,7 +41,6 @@ from transformers import ( ViTMAEConfig, ViTMAEForPreTraining, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -217,21 +216,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Initialize our dataset. ds = load_dataset( data_args.dataset_name, @@ -377,8 +361,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() trainer.log_metrics("train", train_result.metrics) diff --git a/examples/pytorch/image-pretraining/run_mim.py b/examples/pytorch/image-pretraining/run_mim.py index 5a636bbad58..c0b86d009ba 100644 --- a/examples/pytorch/image-pretraining/run_mim.py +++ b/examples/pytorch/image-pretraining/run_mim.py @@ -44,7 +44,6 @@ from transformers import ( Trainer, TrainingArguments, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -281,21 +280,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Initialize our dataset. ds = load_dataset( data_args.dataset_name, @@ -456,8 +440,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() trainer.log_metrics("train", train_result.metrics) diff --git a/examples/pytorch/instance-segmentation/run_instance_segmentation.py b/examples/pytorch/instance-segmentation/run_instance_segmentation.py index ddfd05e0f66..8e6342a3160 100644 --- a/examples/pytorch/instance-segmentation/run_instance_segmentation.py +++ b/examples/pytorch/instance-segmentation/run_instance_segmentation.py @@ -49,7 +49,6 @@ from transformers import ( ) from transformers.image_processing_utils import BatchFeature from transformers.trainer import EvalPrediction -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -334,18 +333,6 @@ def find_last_checkpoint(training_args: TrainingArguments) -> Optional[str]: checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif os.path.isdir(training_args.output_dir) and not training_args.overwrite_output_dir: - checkpoint = get_last_checkpoint(training_args.output_dir) - if checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) return checkpoint diff --git a/examples/pytorch/language-modeling/run_clm.py b/examples/pytorch/language-modeling/run_clm.py index 8c677b40463..986f873870d 100755 --- a/examples/pytorch/language-modeling/run_clm.py +++ b/examples/pytorch/language-modeling/run_clm.py @@ -63,7 +63,6 @@ from transformers import ( set_seed, ) from transformers.testing_utils import CaptureLogger -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -317,21 +316,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -665,8 +649,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload diff --git a/examples/pytorch/language-modeling/run_fim.py b/examples/pytorch/language-modeling/run_fim.py index 134d741f6b6..14457275811 100644 --- a/examples/pytorch/language-modeling/run_fim.py +++ b/examples/pytorch/language-modeling/run_fim.py @@ -66,7 +66,6 @@ from transformers import ( ) from transformers.integrations import is_deepspeed_zero3_enabled from transformers.testing_utils import CaptureLogger -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -344,21 +343,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -806,8 +790,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload diff --git a/examples/pytorch/language-modeling/run_mlm.py b/examples/pytorch/language-modeling/run_mlm.py index 9c0bf50ede2..80ad49bef98 100755 --- a/examples/pytorch/language-modeling/run_mlm.py +++ b/examples/pytorch/language-modeling/run_mlm.py @@ -62,7 +62,6 @@ from transformers import ( is_torch_xla_available, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -290,21 +289,6 @@ def main(): # Set the verbosity to info of the Transformers logger (on main process only): logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -631,8 +615,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload metrics = train_result.metrics diff --git a/examples/pytorch/language-modeling/run_plm.py b/examples/pytorch/language-modeling/run_plm.py index 86bc31beedf..f81fd37d5e4 100755 --- a/examples/pytorch/language-modeling/run_plm.py +++ b/examples/pytorch/language-modeling/run_plm.py @@ -55,7 +55,6 @@ from transformers import ( XLNetLMHeadModel, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -269,21 +268,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -528,8 +512,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload metrics = train_result.metrics diff --git a/examples/pytorch/multiple-choice/run_swag.py b/examples/pytorch/multiple-choice/run_swag.py index a8679f2b739..d1f785d51ca 100755 --- a/examples/pytorch/multiple-choice/run_swag.py +++ b/examples/pytorch/multiple-choice/run_swag.py @@ -52,7 +52,6 @@ from transformers import ( default_data_collator, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version @@ -213,21 +212,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -401,8 +385,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload metrics = train_result.metrics diff --git a/examples/pytorch/object-detection/run_object_detection.py b/examples/pytorch/object-detection/run_object_detection.py index ee0bd66cae9..e2018bf9722 100644 --- a/examples/pytorch/object-detection/run_object_detection.py +++ b/examples/pytorch/object-detection/run_object_detection.py @@ -51,7 +51,6 @@ from transformers import ( from transformers.image_processing_utils import BatchFeature from transformers.image_transforms import center_to_corners_format from transformers.trainer import EvalPrediction -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -373,23 +372,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - checkpoint = None - if training_args.resume_from_checkpoint is not None: - checkpoint = training_args.resume_from_checkpoint - elif os.path.isdir(training_args.output_dir) and not training_args.overwrite_output_dir: - checkpoint = get_last_checkpoint(training_args.output_dir) - if checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # ------------------------------------------------------------------------------------------------ # Load dataset, prepare splits # ------------------------------------------------------------------------------------------------ @@ -510,7 +492,7 @@ def main(): # Training if training_args.do_train: - train_result = trainer.train(resume_from_checkpoint=checkpoint) + train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint) trainer.save_model() trainer.log_metrics("train", train_result.metrics) trainer.save_metrics("train", train_result.metrics) diff --git a/examples/pytorch/old_test_xla_examples.py b/examples/pytorch/old_test_xla_examples.py index b3101aa06b9..d0bcb1c8478 100644 --- a/examples/pytorch/old_test_xla_examples.py +++ b/examples/pytorch/old_test_xla_examples.py @@ -55,7 +55,6 @@ class TorchXLAExamplesTests(TestCasePlus): ./examples/pytorch/text-classification/run_glue.py --model_name_or_path distilbert/distilbert-base-uncased --output_dir {tmp_dir} - --overwrite_output_dir --train_file ./tests/fixtures/tests_samples/MRPC/train.csv --validation_file ./tests/fixtures/tests_samples/MRPC/dev.csv --do_train diff --git a/examples/pytorch/question-answering/run_qa.py b/examples/pytorch/question-answering/run_qa.py index be93a526b80..ab5bf3267b7 100755 --- a/examples/pytorch/question-answering/run_qa.py +++ b/examples/pytorch/question-answering/run_qa.py @@ -43,7 +43,6 @@ from transformers import ( default_data_collator, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -262,21 +261,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -646,8 +630,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload diff --git a/examples/pytorch/question-answering/run_qa_beam_search.py b/examples/pytorch/question-answering/run_qa_beam_search.py index 4bcf4f9af8c..882f4fa9b27 100755 --- a/examples/pytorch/question-answering/run_qa_beam_search.py +++ b/examples/pytorch/question-answering/run_qa_beam_search.py @@ -41,7 +41,6 @@ from transformers import ( default_data_collator, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -260,21 +259,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -672,8 +656,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload diff --git a/examples/pytorch/question-answering/run_seq2seq_qa.py b/examples/pytorch/question-answering/run_seq2seq_qa.py index a9956159304..10827108b93 100644 --- a/examples/pytorch/question-answering/run_seq2seq_qa.py +++ b/examples/pytorch/question-answering/run_seq2seq_qa.py @@ -39,7 +39,7 @@ from transformers import ( Seq2SeqTrainingArguments, set_seed, ) -from transformers.trainer_utils import EvalLoopOutput, EvalPrediction, get_last_checkpoint +from transformers.trainer_utils import EvalLoopOutput, EvalPrediction from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -307,21 +307,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -669,8 +654,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload diff --git a/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py b/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py index cc45239f75c..6fd83df7aa8 100644 --- a/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py +++ b/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py @@ -52,7 +52,6 @@ from transformers import ( TrainingArguments, default_data_collator, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -221,21 +220,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Load dataset # In distributed training, the load_dataset function guarantees that only one local process can concurrently # download the dataset. @@ -419,8 +403,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() trainer.log_metrics("train", train_result.metrics) diff --git a/examples/pytorch/speech-recognition/README.md b/examples/pytorch/speech-recognition/README.md index 41df41880b5..24595492064 100644 --- a/examples/pytorch/speech-recognition/README.md +++ b/examples/pytorch/speech-recognition/README.md @@ -70,7 +70,6 @@ python run_speech_recognition_ctc.py \ --model_name_or_path="facebook/wav2vec2-large-xlsr-53" \ --dataset_config_name="tr" \ --output_dir="./wav2vec2-common_voice-tr-demo" \ - --overwrite_output_dir \ --num_train_epochs="15" \ --per_device_train_batch_size="16" \ --gradient_accumulation_steps="2" \ @@ -106,7 +105,6 @@ torchrun \ --model_name_or_path="facebook/wav2vec2-large-xlsr-53" \ --dataset_config_name="tr" \ --output_dir="./wav2vec2-common_voice-tr-demo-dist" \ - --overwrite_output_dir \ --num_train_epochs="15" \ --per_device_train_batch_size="4" \ --learning_rate="3e-4" \ @@ -156,7 +154,6 @@ However, the `--shuffle_buffer_size` argument controls how many examples we can --train_split_name="train+validation" \ --eval_split_name="test" \ --output_dir="wav2vec2-xls-r-common_voice-tr-ft" \ - --overwrite_output_dir \ --max_steps="5000" \ --per_device_train_batch_size="8" \ --gradient_accumulation_steps="2" \ @@ -390,7 +387,6 @@ python run_speech_recognition_seq2seq.py \ --freeze_feature_encoder="False" \ --gradient_checkpointing \ --fp16 \ - --overwrite_output_dir \ --do_train \ --do_eval \ --predict_with_generate \ @@ -431,7 +427,6 @@ torchrun \ --freeze_feature_encoder="False" \ --gradient_checkpointing \ --fp16 \ - --overwrite_output_dir \ --do_train \ --do_eval \ --predict_with_generate \ @@ -539,7 +534,6 @@ python run_speech_recognition_seq2seq.py \ --output_dir="./" \ --preprocessing_num_workers="16" \ --length_column_name="input_length" \ - --overwrite_output_dir \ --num_train_epochs="5" \ --per_device_train_batch_size="8" \ --per_device_eval_batch_size="8" \ @@ -581,7 +575,6 @@ torchrun \ --output_dir="./" \ --preprocessing_num_workers="16" \ --length_column_name="input_length" \ - --overwrite_output_dir \ --num_train_epochs="5" \ --per_device_train_batch_size="8" \ --per_device_eval_batch_size="8" \ diff --git a/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py b/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py index c756a666618..f94105cd1d1 100755 --- a/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py +++ b/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py @@ -55,7 +55,7 @@ from transformers import ( Wav2Vec2Processor, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint, is_main_process +from transformers.trainer_utils import is_main_process from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -429,21 +429,6 @@ def main(): else: model_args, data_args, training_args = parser.parse_args_into_dataclasses() - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Setup logging logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", @@ -558,7 +543,7 @@ def main(): vocab_file = os.path.join(tokenizer_name_or_path, "vocab.json") with training_args.main_process_first(): - if training_args.overwrite_output_dir and os.path.isfile(vocab_file): + if os.path.isfile(vocab_file): try: os.remove(vocab_file) except OSError: @@ -781,9 +766,7 @@ def main(): # Training if training_args.do_train: # use last checkpoint if exist - if last_checkpoint is not None: - checkpoint = last_checkpoint - elif os.path.isdir(model_args.model_name_or_path): + if os.path.isdir(model_args.model_name_or_path): checkpoint = model_args.model_name_or_path else: checkpoint = None diff --git a/examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py b/examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py index aaebf59c866..adfe91a31d5 100755 --- a/examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py +++ b/examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py @@ -58,7 +58,7 @@ from transformers import ( set_seed, ) from transformers.models.wav2vec2.modeling_wav2vec2 import WAV2VEC2_ADAPTER_SAFE_FILE -from transformers.trainer_utils import get_last_checkpoint, is_main_process +from transformers.trainer_utils import is_main_process from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -406,21 +406,6 @@ def main(): else: model_args, data_args, training_args = parser.parse_args_into_dataclasses() - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Setup logging logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", @@ -557,7 +542,7 @@ def main(): vocab_file = os.path.join(tokenizer_name_or_path, "vocab.json") with training_args.main_process_first(): - if training_args.overwrite_output_dir and os.path.isfile(vocab_file): + if os.path.isfile(vocab_file): try: os.remove(vocab_file) except OSError: @@ -773,9 +758,7 @@ def main(): # Training if training_args.do_train: # use last checkpoint if exist - if last_checkpoint is not None: - checkpoint = last_checkpoint - elif os.path.isdir(model_args.model_name_or_path): + if os.path.isdir(model_args.model_name_or_path): checkpoint = model_args.model_name_or_path else: checkpoint = None diff --git a/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py b/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py index 4b6cda49925..7e124d4326f 100755 --- a/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py +++ b/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py @@ -54,7 +54,7 @@ from transformers import ( Seq2SeqTrainingArguments, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint, is_main_process +from transformers.trainer_utils import is_main_process from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -340,21 +340,6 @@ def main(): transformers.utils.logging.set_verbosity_info() logger.info("Training/evaluation parameters %s", training_args) - # 3. Detecting last checkpoint and eventually continue from last checkpoint - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -603,8 +588,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the feature extractor too for easy upload diff --git a/examples/pytorch/summarization/README.md b/examples/pytorch/summarization/README.md index 26561df2424..e47f0912051 100644 --- a/examples/pytorch/summarization/README.md +++ b/examples/pytorch/summarization/README.md @@ -50,7 +50,6 @@ python run_summarization.py \ --output_dir /tmp/tst-summarization \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -72,7 +71,6 @@ python run_summarization.py \ --validation_file path_to_csv_or_jsonlines_file \ --source_prefix "summarize: " \ --output_dir /tmp/tst-summarization \ - --overwrite_output_dir \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ --predict_with_generate diff --git a/examples/pytorch/summarization/run_summarization.py b/examples/pytorch/summarization/run_summarization.py index 7888a2b55eb..c27f5dc8221 100755 --- a/examples/pytorch/summarization/run_summarization.py +++ b/examples/pytorch/summarization/run_summarization.py @@ -61,7 +61,6 @@ from transformers import ( Seq2SeqTrainingArguments, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version, is_offline_mode from transformers.utils.versions import require_version @@ -374,21 +373,6 @@ def main(): "`--source_prefix 'summarize: ' `" ) - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -698,8 +682,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload diff --git a/examples/pytorch/test_pytorch_examples.py b/examples/pytorch/test_pytorch_examples.py index d27cc305d6a..8bfadac779d 100644 --- a/examples/pytorch/test_pytorch_examples.py +++ b/examples/pytorch/test_pytorch_examples.py @@ -104,7 +104,6 @@ class ExamplesTests(TestCasePlus): run_glue.py --model_name_or_path distilbert/distilbert-base-uncased --output_dir {tmp_dir} - --overwrite_output_dir --train_file ./tests/fixtures/tests_samples/MRPC/train.csv --validation_file ./tests/fixtures/tests_samples/MRPC/dev.csv --do_train @@ -140,7 +139,6 @@ class ExamplesTests(TestCasePlus): --per_device_eval_batch_size 5 --num_train_epochs 2 --output_dir {tmp_dir} - --overwrite_output_dir """.split() if backend_device_count(torch_device) > 1: @@ -188,7 +186,6 @@ class ExamplesTests(TestCasePlus): --train_file ./tests/fixtures/sample_text.txt --validation_file ./tests/fixtures/sample_text.txt --output_dir {tmp_dir} - --overwrite_output_dir --do_train --do_eval --prediction_loss_only @@ -214,7 +211,6 @@ class ExamplesTests(TestCasePlus): --train_file tests/fixtures/tests_samples/conll/sample.json --validation_file tests/fixtures/tests_samples/conll/sample.json --output_dir {tmp_dir} - --overwrite_output_dir --do_train --do_eval --warmup_steps=2 @@ -243,7 +239,6 @@ class ExamplesTests(TestCasePlus): --train_file tests/fixtures/tests_samples/SQUAD/sample.json --validation_file tests/fixtures/tests_samples/SQUAD/sample.json --output_dir {tmp_dir} - --overwrite_output_dir --max_steps=10 --warmup_steps=2 --do_train @@ -271,7 +266,6 @@ class ExamplesTests(TestCasePlus): --train_file tests/fixtures/tests_samples/SQUAD/sample.json --validation_file tests/fixtures/tests_samples/SQUAD/sample.json --output_dir {tmp_dir} - --overwrite_output_dir --max_steps=10 --warmup_steps=2 --do_train @@ -296,7 +290,6 @@ class ExamplesTests(TestCasePlus): --train_file tests/fixtures/tests_samples/swag/sample.json --validation_file tests/fixtures/tests_samples/swag/sample.json --output_dir {tmp_dir} - --overwrite_output_dir --max_steps=20 --warmup_steps=2 --do_train @@ -334,7 +327,6 @@ class ExamplesTests(TestCasePlus): --train_file tests/fixtures/tests_samples/xsum/sample.json --validation_file tests/fixtures/tests_samples/xsum/sample.json --output_dir {tmp_dir} - --overwrite_output_dir --max_steps=50 --warmup_steps=8 --do_train @@ -364,7 +356,6 @@ class ExamplesTests(TestCasePlus): --train_file tests/fixtures/tests_samples/wmt16/sample.json --validation_file tests/fixtures/tests_samples/wmt16/sample.json --output_dir {tmp_dir} - --overwrite_output_dir --max_steps=50 --warmup_steps=8 --do_train @@ -396,7 +387,6 @@ class ExamplesTests(TestCasePlus): --per_device_train_batch_size 2 --per_device_eval_batch_size 1 --remove_unused_columns False - --overwrite_output_dir True --dataloader_num_workers 16 --metric_for_best_model accuracy --max_steps 10 @@ -429,7 +419,6 @@ class ExamplesTests(TestCasePlus): --per_device_train_batch_size 2 --per_device_eval_batch_size 1 --remove_unused_columns False - --overwrite_output_dir True --preprocessing_num_workers 16 --max_steps 10 --seed 42 @@ -459,7 +448,6 @@ class ExamplesTests(TestCasePlus): --per_device_train_batch_size 2 --per_device_eval_batch_size 1 --remove_unused_columns False - --overwrite_output_dir True --preprocessing_num_workers 16 --max_steps 10 --target_language tur @@ -491,7 +479,6 @@ class ExamplesTests(TestCasePlus): --per_device_train_batch_size 2 --per_device_eval_batch_size 4 --remove_unused_columns False - --overwrite_output_dir True --preprocessing_num_workers 16 --max_steps 10 --seed 42 @@ -523,7 +510,6 @@ class ExamplesTests(TestCasePlus): --per_device_train_batch_size 2 --per_device_eval_batch_size 1 --remove_unused_columns False - --overwrite_output_dir True --num_train_epochs 10 --max_steps 50 --seed 42 @@ -572,7 +558,6 @@ class ExamplesTests(TestCasePlus): --per_device_train_batch_size 2 --per_device_eval_batch_size 1 --remove_unused_columns False - --overwrite_output_dir True --dataloader_num_workers 16 --metric_for_best_model accuracy --max_steps 10 @@ -597,7 +582,6 @@ class ExamplesTests(TestCasePlus): --do_train --do_eval --remove_unused_columns False - --overwrite_output_dir True --max_steps 10 --learning_rate=2e-4 --per_device_train_batch_size=2 @@ -624,7 +608,6 @@ class ExamplesTests(TestCasePlus): --do_train --do_eval --remove_unused_columns False - --overwrite_output_dir True --eval_do_concat_batches False --max_steps 10 --learning_rate=1e-6 diff --git a/examples/pytorch/text-classification/run_classification.py b/examples/pytorch/text-classification/run_classification.py index 35413cd7875..78a9d009491 100755 --- a/examples/pytorch/text-classification/run_classification.py +++ b/examples/pytorch/text-classification/run_classification.py @@ -55,7 +55,6 @@ from transformers import ( default_data_collator, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -321,21 +320,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -693,8 +677,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) metrics = train_result.metrics max_train_samples = ( diff --git a/examples/pytorch/text-classification/run_glue.py b/examples/pytorch/text-classification/run_glue.py index 866044bdce2..0272eef968f 100755 --- a/examples/pytorch/text-classification/run_glue.py +++ b/examples/pytorch/text-classification/run_glue.py @@ -57,7 +57,6 @@ from transformers import ( default_data_collator, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -266,21 +265,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -566,8 +550,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) metrics = train_result.metrics max_train_samples = ( diff --git a/examples/pytorch/text-classification/run_xnli.py b/examples/pytorch/text-classification/run_xnli.py index 3027da5feae..b64ac29552f 100755 --- a/examples/pytorch/text-classification/run_xnli.py +++ b/examples/pytorch/text-classification/run_xnli.py @@ -56,7 +56,6 @@ from transformers import ( default_data_collator, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -224,21 +223,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -412,8 +396,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) metrics = train_result.metrics max_train_samples = ( diff --git a/examples/pytorch/token-classification/run_ner.py b/examples/pytorch/token-classification/run_ner.py index 1482394321c..f21ea058d07 100755 --- a/examples/pytorch/token-classification/run_ner.py +++ b/examples/pytorch/token-classification/run_ner.py @@ -54,7 +54,6 @@ from transformers import ( TrainingArguments, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -263,21 +262,6 @@ def main(): ) logger.info(f"Training/evaluation parameters {training_args}") - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -587,8 +571,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) metrics = train_result.metrics trainer.save_model() # Saves the tokenizer too for easy upload diff --git a/examples/pytorch/translation/README.md b/examples/pytorch/translation/README.md index 4659843c66a..2aab14e2e05 100644 --- a/examples/pytorch/translation/README.md +++ b/examples/pytorch/translation/README.md @@ -53,7 +53,6 @@ python run_translation.py \ --output_dir /tmp/tst-translation \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -74,7 +73,6 @@ python run_translation.py \ --output_dir /tmp/tst-translation \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -96,7 +94,6 @@ python run_translation.py \ --output_dir /tmp/tst-translation \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -118,7 +115,6 @@ python run_translation.py \ --output_dir /tmp/tst-translation \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` @@ -144,7 +140,6 @@ python run_translation.py \ --output_dir /tmp/tst-translation \ --per_device_train_batch_size=4 \ --per_device_eval_batch_size=4 \ - --overwrite_output_dir \ --predict_with_generate ``` diff --git a/examples/pytorch/translation/run_translation.py b/examples/pytorch/translation/run_translation.py index 8e005e0d732..b068cd3ce2d 100755 --- a/examples/pytorch/translation/run_translation.py +++ b/examples/pytorch/translation/run_translation.py @@ -60,7 +60,6 @@ from transformers import ( default_data_collator, set_seed, ) -from transformers.trainer_utils import get_last_checkpoint from transformers.utils import check_min_version from transformers.utils.versions import require_version @@ -322,21 +321,6 @@ def main(): "`--source_prefix 'translate English to German: ' `" ) - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Set seed before initializing model. set_seed(training_args.seed) @@ -617,8 +601,6 @@ def main(): checkpoint = None if training_args.resume_from_checkpoint is not None: checkpoint = training_args.resume_from_checkpoint - elif last_checkpoint is not None: - checkpoint = last_checkpoint train_result = trainer.train(resume_from_checkpoint=checkpoint) trainer.save_model() # Saves the tokenizer too for easy upload diff --git a/src/transformers/integrations/integration_utils.py b/src/transformers/integrations/integration_utils.py index 73d3a1ab3b7..06a064b86f5 100755 --- a/src/transformers/integrations/integration_utils.py +++ b/src/transformers/integrations/integration_utils.py @@ -1644,7 +1644,7 @@ class NeptuneCallback(TrainerCallback): def on_init_end(self, args, state, control, **kwargs): self._volatile_checkpoints_dir = None - if self._log_checkpoints and (args.overwrite_output_dir or args.save_total_limit is not None): + if self._log_checkpoints and args.save_total_limit is not None: self._volatile_checkpoints_dir = tempfile.TemporaryDirectory().name if self._log_checkpoints == "best" and not args.load_best_model_at_end: diff --git a/src/transformers/models/cwm/configuration_cwm.py b/src/transformers/models/cwm/configuration_cwm.py index 8dd2887722f..573956a5bca 100644 --- a/src/transformers/models/cwm/configuration_cwm.py +++ b/src/transformers/models/cwm/configuration_cwm.py @@ -21,11 +21,11 @@ from typing import Optional -from ...configuration_utils import PretrainedConfig, layer_type_validation +from ...configuration_utils import PreTrainedConfig, layer_type_validation from ...modeling_rope_utils import rope_config_validation -class CwmConfig(PretrainedConfig): +class CwmConfig(PreTrainedConfig): """ Configuration for Code World Model (CWM). This is an inherited Llama3-compatible configuration with layer-interleaved @@ -136,13 +136,6 @@ class CwmConfig(PretrainedConfig): layer_types: Optional[list[str]] = None, # ["full_attention"|"sliding_attention"] per layer **kwargs, ): - super().__init__( - pad_token_id=pad_token_id, - bos_token_id=bos_token_id, - eos_token_id=eos_token_id, - tie_word_embeddings=tie_word_embeddings, - **kwargs, - ) if rope_scaling is None: rope_scaling = { "factor": 16.0, @@ -189,6 +182,14 @@ class CwmConfig(PretrainedConfig): self.rope_scaling["rope_type"] = self.rope_scaling["type"] rope_config_validation(self) + super().__init__( + pad_token_id=pad_token_id, + bos_token_id=bos_token_id, + eos_token_id=eos_token_id, + tie_word_embeddings=tie_word_embeddings, + **kwargs, + ) + self.sliding_window = int(sliding_window) if sliding_window else None self.layer_types = list(layer_types) diff --git a/src/transformers/models/cwm/modeling_cwm.py b/src/transformers/models/cwm/modeling_cwm.py index 1f0c0999608..5ab732e7d65 100644 --- a/src/transformers/models/cwm/modeling_cwm.py +++ b/src/transformers/models/cwm/modeling_cwm.py @@ -19,7 +19,8 @@ # See the License for the specific language governing permissions and # limitations under the License. -from typing import Callable, Optional, Union +from collections.abc import Callable +from typing import Optional, Union import torch from torch import nn @@ -36,7 +37,6 @@ from ...modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update from ...modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel from ...processing_utils import Unpack from ...utils import TransformersKwargs, auto_docstring, can_return_tuple -from ...utils.deprecation import deprecate_kwarg from ...utils.generic import check_model_inputs from .configuration_cwm import CwmConfig @@ -131,7 +131,6 @@ class CwmAttention(nn.Module): self.o_proj = nn.Linear(config.num_attention_heads * self.head_dim, config.hidden_size, bias=False) self.sliding_window = config.sliding_window if config.layer_types[layer_idx] == "sliding_attention" else None - @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58") def forward( self, hidden_states: torch.Tensor, @@ -225,7 +224,6 @@ class CwmDecoderLayer(GradientCheckpointingLayer): self.post_attention_layernorm = CwmRMSNorm(config.hidden_size, eps=config.rms_norm_eps) self.attention_type = config.layer_types[layer_idx] - @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58") def forward( self, hidden_states: torch.Tensor, @@ -339,7 +337,7 @@ class CwmModel(CwmPreTrainedModel): # Initialize weights and apply final processing self.post_init() - @check_model_inputs + @check_model_inputs() @auto_docstring def forward( self, diff --git a/src/transformers/training_args.py b/src/transformers/training_args.py index 0d77e0ee441..83944c5c841 100644 --- a/src/transformers/training_args.py +++ b/src/transformers/training_args.py @@ -208,9 +208,6 @@ class TrainingArguments: Parameters: output_dir (`str`, *optional*, defaults to `"trainer_output"`): The output directory where the model predictions and checkpoints will be written. - overwrite_output_dir (`bool`, *optional*, defaults to `False`): - If `True`, overwrite the content of the output directory. Use this to continue training if `output_dir` - points to a checkpoint directory. do_train (`bool`, *optional*, defaults to `False`): Whether to run training or not. This argument is not directly used by [`Trainer`], it's intended to be used by your training/evaluation scripts instead. See the [example @@ -787,15 +784,6 @@ class TrainingArguments: "help": "The output directory where the model predictions and checkpoints will be written. Defaults to 'trainer_output' if not provided." }, ) - overwrite_output_dir: bool = field( - default=False, - metadata={ - "help": ( - "Overwrite the content of the output directory. " - "Use this to continue training if output_dir points to a checkpoint directory." - ) - }, - ) do_train: bool = field(default=False, metadata={"help": "Whether to run training."}) do_eval: bool = field(default=False, metadata={"help": "Whether to run eval on the dev set."}) diff --git a/templates/adding_a_new_example_script/{{cookiecutter.directory_name}}/run_{{cookiecutter.example_shortcut}}.py b/templates/adding_a_new_example_script/{{cookiecutter.directory_name}}/run_{{cookiecutter.example_shortcut}}.py index 6a4941e47e5..89ee64a5d88 100755 --- a/templates/adding_a_new_example_script/{{cookiecutter.directory_name}}/run_{{cookiecutter.example_shortcut}}.py +++ b/templates/adding_a_new_example_script/{{cookiecutter.directory_name}}/run_{{cookiecutter.example_shortcut}}.py @@ -219,21 +219,6 @@ def main(): else: model_args, data_args, training_args = parser.parse_args_into_dataclasses() - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Setup logging logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", @@ -452,16 +437,12 @@ def main(): # Training if training_args.do_train: {%- if cookiecutter.can_train_from_scratch == "False" %} - if last_checkpoint is not None: - checkpoint = last_checkpoint - elif os.path.isdir(model_args.model_name_or_path): + if os.path.isdir(model_args.model_name_or_path): checkpoint = model_args.model_name_or_path else: checkpoint = None {%- elif cookiecutter.can_train_from_scratch == "True" %} - if last_checkpoint is not None: - checkpoint = last_checkpoint - elif model_args.model_name_or_path is not None and os.path.isdir(model_args.model_name_or_path): + if model_args.model_name_or_path is not None and os.path.isdir(model_args.model_name_or_path): checkpoint = model_args.model_name_or_path else: checkpoint = None diff --git a/tests/deepspeed/test_deepspeed.py b/tests/deepspeed/test_deepspeed.py index 99b1450a0d5..bf3aba7e1a4 100644 --- a/tests/deepspeed/test_deepspeed.py +++ b/tests/deepspeed/test_deepspeed.py @@ -1303,7 +1303,6 @@ class TestDeepSpeedWithLauncher(TestCasePlus): --train_file {data_dir}/train.json --validation_file {data_dir}/val.json --output_dir {output_dir} - --overwrite_output_dir --max_source_length {max_len} --max_target_length {max_len} --val_max_target_length {max_len} @@ -1373,7 +1372,6 @@ class TestDeepSpeedWithLauncher(TestCasePlus): --train_file {data_dir}/sample_text.txt --validation_file {data_dir}/sample_text.txt --output_dir {output_dir} - --overwrite_output_dir --do_train --do_eval --max_train_samples 16 @@ -1410,7 +1408,6 @@ class TestDeepSpeedWithLauncher(TestCasePlus): --train_file {data_dir}/sample_text.txt --validation_file {data_dir}/sample_text.txt --output_dir {output_dir} - --overwrite_output_dir --do_train --max_train_samples 4 --per_device_train_batch_size 2 diff --git a/tests/deepspeed/test_model_zoo.py b/tests/deepspeed/test_model_zoo.py index 2195bee01cc..a7201ef7f9a 100644 --- a/tests/deepspeed/test_model_zoo.py +++ b/tests/deepspeed/test_model_zoo.py @@ -161,7 +161,6 @@ def make_task_cmds(): --num_train_epochs 1 --fp16 --report_to none - --overwrite_output_dir """.split() # try to cover as many models as possible once (it's enough to run on one task per model) diff --git a/tests/extended/test_trainer_ext.py b/tests/extended/test_trainer_ext.py index 1789f9f6c98..80e71691bbb 100644 --- a/tests/extended/test_trainer_ext.py +++ b/tests/extended/test_trainer_ext.py @@ -267,7 +267,6 @@ class TestTrainerExt(TestCasePlus): --validation_file {data_dir}/val.json --test_file {data_dir}/test.json --output_dir {output_dir} - --overwrite_output_dir --max_train_samples 8 --max_source_length {max_len} --max_target_length {max_len} diff --git a/tests/fsdp/test_fsdp.py b/tests/fsdp/test_fsdp.py index 93b4adcd8a8..16f010947b5 100644 --- a/tests/fsdp/test_fsdp.py +++ b/tests/fsdp/test_fsdp.py @@ -447,7 +447,6 @@ class TrainerIntegrationFSDP(TestCasePlus, TrainerIntegrationCommon): --model_name_or_path google-bert/bert-base-cased --task_name mrpc --output_dir {output_dir} - --overwrite_output_dir --do_train --max_seq_length 128 --per_device_train_batch_size 16 diff --git a/tests/sagemaker/conftest.py b/tests/sagemaker/conftest.py index 5daf3c4147f..879cfff1c5e 100644 --- a/tests/sagemaker/conftest.py +++ b/tests/sagemaker/conftest.py @@ -21,7 +21,6 @@ class SageMakerTestEnvironment: "do_eval": True, "do_predict": True, "output_dir": "/opt/ml/model", - "overwrite_output_dir": True, "max_steps": 500, "save_steps": 5500, } diff --git a/tests/sagemaker/scripts/pytorch/run_glue_model_parallelism.py b/tests/sagemaker/scripts/pytorch/run_glue_model_parallelism.py index a5e81a93c83..bb7a263a0eb 100644 --- a/tests/sagemaker/scripts/pytorch/run_glue_model_parallelism.py +++ b/tests/sagemaker/scripts/pytorch/run_glue_model_parallelism.py @@ -38,7 +38,6 @@ from transformers import ( set_seed, ) from transformers.trainer import Trainer -from transformers.trainer_utils import get_last_checkpoint from transformers.training_args import TrainingArguments from transformers.utils import check_min_version @@ -198,21 +197,6 @@ def main(): else: model_args, data_args, training_args = parser.parse_args_into_dataclasses() - # Detecting last checkpoint. - last_checkpoint = None - if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir: - last_checkpoint = get_last_checkpoint(training_args.output_dir) - if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0: - raise ValueError( - f"Output directory ({training_args.output_dir}) already exists and is not empty. " - "Use --overwrite_output_dir to overcome." - ) - elif last_checkpoint is not None: - logger.info( - f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change " - "the `--output_dir` or add `--overwrite_output_dir` to train from scratch." - ) - # Setup logging logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", @@ -459,9 +443,7 @@ def main(): # Training if training_args.do_train: checkpoint = None - if last_checkpoint is not None: - checkpoint = last_checkpoint - elif os.path.isdir(model_args.model_name_or_path): + if os.path.isdir(model_args.model_name_or_path): # Check the config from that potential checkpoint has the right number of labels before using it as a # checkpoint. if AutoConfig.from_pretrained(model_args.model_name_or_path).num_labels == num_labels: diff --git a/tests/trainer/test_trainer.py b/tests/trainer/test_trainer.py index 7d295cc5652..ebb2d1699be 100644 --- a/tests/trainer/test_trainer.py +++ b/tests/trainer/test_trainer.py @@ -4455,7 +4455,6 @@ class TrainerIntegrationTest(TestCasePlus, TrainerIntegrationCommon): "1", "--output_dir", tmpdir, - "--overwrite_output_dir", "--do_train", "--max_train_samples", "64",