fix(train): complete PipelineSession support for V3 trainers (SFT/DPO/RLAIF/RLVR)

Add @runnable_by_pipeline decorator and PascalCase request serialization
so TrainingStep can consume step_args from V3 fine-tuning trainers.

Changes:
- Add @runnable_by_pipeline decorator on train() for all 4 trainers
- Build PascalCase serialized request (remove session/region, pop job name)
- Fix Tags to PascalCase (JumpStart returns lowercase key/value)
- Add source_code=None to BaseTrainer (required by get_code_hash)
- Add consumer tests (TrainingStep.arguments validation)
- Add regular session regression tests

Fixes: #6163

Author: nayan3107

sagemaker-mlops/tests/integ/data/v3_trainer/preference_train.jsonl

@@ -0,0 +1,20 @@
+{"chosen": [{"role": "user", "content": "What is ML?"}, {"role": "assistant", "content": "ML is a subset of AI that enables systems to learn from data."}], "rejected": [{"role": "user", "content": "What is ML?"}, {"role": "assistant", "content": "I don't know."}]}
+{"chosen": [{"role": "user", "content": "What is SageMaker?"}, {"role": "assistant", "content": "SageMaker is a managed machine learning service by AWS."}], "rejected": [{"role": "user", "content": "What is SageMaker?"}, {"role": "assistant", "content": "It's a thing."}]}
+{"chosen": [{"role": "user", "content": "What is fine-tuning?"}, {"role": "assistant", "content": "Fine-tuning adapts a pre-trained model to a specific task."}], "rejected": [{"role": "user", "content": "What is fine-tuning?"}, {"role": "assistant", "content": "Making things fine."}]}
+{"chosen": [{"role": "user", "content": "What is LoRA?"}, {"role": "assistant", "content": "LoRA is Low-Rank Adaptation for efficient model fine-tuning."}], "rejected": [{"role": "user", "content": "What is LoRA?"}, {"role": "assistant", "content": "A name."}]}
+{"chosen": [{"role": "user", "content": "What is RLHF?"}, {"role": "assistant", "content": "RLHF is Reinforcement Learning from Human Feedback."}], "rejected": [{"role": "user", "content": "What is RLHF?"}, {"role": "assistant", "content": "An acronym."}]}
+{"chosen": [{"role": "user", "content": "What is DPO?"}, {"role": "assistant", "content": "DPO is Direct Preference Optimization for alignment."}], "rejected": [{"role": "user", "content": "What is DPO?"}, {"role": "assistant", "content": "Something."}]}
+{"chosen": [{"role": "user", "content": "What is a transformer?"}, {"role": "assistant", "content": "A neural network architecture using self-attention mechanisms."}], "rejected": [{"role": "user", "content": "What is a transformer?"}, {"role": "assistant", "content": "A robot."}]}
+{"chosen": [{"role": "user", "content": "What is tokenization?"}, {"role": "assistant", "content": "Splitting text into smaller units called tokens."}], "rejected": [{"role": "user", "content": "What is tokenization?"}, {"role": "assistant", "content": "Tokens."}]}
+{"chosen": [{"role": "user", "content": "What is inference?"}, {"role": "assistant", "content": "Using a trained model to generate predictions on new data."}], "rejected": [{"role": "user", "content": "What is inference?"}, {"role": "assistant", "content": "Guessing."}]}
+{"chosen": [{"role": "user", "content": "What is a GPU?"}, {"role": "assistant", "content": "A processor for parallel computation used in ML training."}], "rejected": [{"role": "user", "content": "What is a GPU?"}, {"role": "assistant", "content": "A card."}]}
+{"chosen": [{"role": "user", "content": "What is backpropagation?"}, {"role": "assistant", "content": "An algorithm for computing gradients in neural networks."}], "rejected": [{"role": "user", "content": "What is backpropagation?"}, {"role": "assistant", "content": "Going back."}]}
+{"chosen": [{"role": "user", "content": "What is an epoch?"}, {"role": "assistant", "content": "One complete pass through the training dataset."}], "rejected": [{"role": "user", "content": "What is an epoch?"}, {"role": "assistant", "content": "A time period."}]}
+{"chosen": [{"role": "user", "content": "What is overfitting?"}, {"role": "assistant", "content": "When a model memorizes training data instead of learning."}], "rejected": [{"role": "user", "content": "What is overfitting?"}, {"role": "assistant", "content": "Too much fitting."}]}
+{"chosen": [{"role": "user", "content": "What is a loss function?"}, {"role": "assistant", "content": "Measures how far predictions are from actual values."}], "rejected": [{"role": "user", "content": "What is a loss function?"}, {"role": "assistant", "content": "Loss."}]}
+{"chosen": [{"role": "user", "content": "What is batch size?"}, {"role": "assistant", "content": "Number of samples processed before updating weights."}], "rejected": [{"role": "user", "content": "What is batch size?"}, {"role": "assistant", "content": "A size."}]}
+{"chosen": [{"role": "user", "content": "What is learning rate?"}, {"role": "assistant", "content": "Controls how much weights change during training."}], "rejected": [{"role": "user", "content": "What is learning rate?"}, {"role": "assistant", "content": "A rate."}]}
+{"chosen": [{"role": "user", "content": "What is regularization?"}, {"role": "assistant", "content": "Techniques to prevent overfitting in models."}], "rejected": [{"role": "user", "content": "What is regularization?"}, {"role": "assistant", "content": "Making regular."}]}
+{"chosen": [{"role": "user", "content": "What is an embedding?"}, {"role": "assistant", "content": "A dense vector representation of discrete data."}], "rejected": [{"role": "user", "content": "What is an embedding?"}, {"role": "assistant", "content": "A vector."}]}
+{"chosen": [{"role": "user", "content": "What is attention?"}, {"role": "assistant", "content": "A mechanism that weighs importance of different inputs."}], "rejected": [{"role": "user", "content": "What is attention?"}, {"role": "assistant", "content": "Focus."}]}
+{"chosen": [{"role": "user", "content": "What is a pipeline?"}, {"role": "assistant", "content": "An automated workflow for ML model development."}], "rejected": [{"role": "user", "content": "What is a pipeline?"}, {"role": "assistant", "content": "A pipe."}]}

sagemaker-mlops/tests/integ/data/v3_trainer/sft_train.jsonl

@@ -0,0 +1,20 @@
+{"messages": [{"role": "user", "content": "What is ML?"}, {"role": "assistant", "content": "ML is a subset of AI that enables systems to learn from data."}]}
+{"messages": [{"role": "user", "content": "What is SageMaker?"}, {"role": "assistant", "content": "SageMaker is a managed machine learning service by AWS."}]}
+{"messages": [{"role": "user", "content": "What is fine-tuning?"}, {"role": "assistant", "content": "Fine-tuning adapts a pre-trained model to a specific task."}]}
+{"messages": [{"role": "user", "content": "What is LoRA?"}, {"role": "assistant", "content": "LoRA is Low-Rank Adaptation for efficient model fine-tuning."}]}
+{"messages": [{"role": "user", "content": "What is RLHF?"}, {"role": "assistant", "content": "RLHF is Reinforcement Learning from Human Feedback."}]}
+{"messages": [{"role": "user", "content": "What is DPO?"}, {"role": "assistant", "content": "DPO is Direct Preference Optimization for alignment."}]}
+{"messages": [{"role": "user", "content": "What is a transformer?"}, {"role": "assistant", "content": "A neural network architecture using self-attention mechanisms."}]}
+{"messages": [{"role": "user", "content": "What is tokenization?"}, {"role": "assistant", "content": "Splitting text into smaller units called tokens for processing."}]}
+{"messages": [{"role": "user", "content": "What is inference?"}, {"role": "assistant", "content": "Using a trained model to generate predictions on new data."}]}
+{"messages": [{"role": "user", "content": "What is a GPU?"}, {"role": "assistant", "content": "A processor designed for parallel computation used in ML training."}]}
+{"messages": [{"role": "user", "content": "What is backpropagation?"}, {"role": "assistant", "content": "An algorithm for computing gradients to update neural network weights."}]}
+{"messages": [{"role": "user", "content": "What is an epoch?"}, {"role": "assistant", "content": "One complete pass through the entire training dataset."}]}
+{"messages": [{"role": "user", "content": "What is overfitting?"}, {"role": "assistant", "content": "When a model memorizes training data instead of learning patterns."}]}
+{"messages": [{"role": "user", "content": "What is a loss function?"}, {"role": "assistant", "content": "A function that measures how far predictions are from actual values."}]}
+{"messages": [{"role": "user", "content": "What is batch size?"}, {"role": "assistant", "content": "The number of training samples processed before updating model weights."}]}
+{"messages": [{"role": "user", "content": "What is learning rate?"}, {"role": "assistant", "content": "A hyperparameter controlling how much weights change during training."}]}
+{"messages": [{"role": "user", "content": "What is regularization?"}, {"role": "assistant", "content": "Techniques to prevent overfitting by adding constraints to the model."}]}
+{"messages": [{"role": "user", "content": "What is an embedding?"}, {"role": "assistant", "content": "A dense vector representation of discrete data like words or items."}]}
+{"messages": [{"role": "user", "content": "What is attention?"}, {"role": "assistant", "content": "A mechanism that weighs the importance of different input elements."}]}
+{"messages": [{"role": "user", "content": "What is a pipeline?"}, {"role": "assistant", "content": "An automated workflow for building and deploying ML models."}]}