Training API

RelationalExample

class relational_transformers.RelationalExample(input: 'Any', label: 'Any')
Parameters:

  • input (Any)

  • label (Any)

RelationalTrainingArguments

class relational_transformers.RelationalTrainingArguments(output_dir: 'str' = 'relational_model', num_train_epochs: 'int' = 1, per_device_train_batch_size: 'int' = 8, learning_rate: 'float' = 1e-05, weight_decay: 'float' = 0.01, max_grad_norm: 'float' = 1.0, gradient_accumulation_steps: 'int' = 1, seed: 'int' = 42, logging_steps: 'int' = 10, save_strategy: 'str' = 'epoch')
Parameters:

  • output_dir (str)

  • num_train_epochs (int)

  • per_device_train_batch_size (int)

  • learning_rate (float)

  • weight_decay (float)

  • max_grad_norm (float)

  • gradient_accumulation_steps (int)

  • seed (int)

  • logging_steps (int)

  • save_strategy (str)

RelationalTrainer

class relational_transformers.RelationalTrainer(*, model, args, train_dataset, task=None, problem_type=None)

Small, dependency-free trainer for complete RT-J fine-tuning.

Parameters:

TaskHead

class relational_transformers.TaskHead(d_model, num_labels=1, problem_type='binary')
Parameters:

  • d_model (int)

  • num_labels (int)

  • problem_type (str)

forward(features)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

Parameters:

features (Tensor)

Return type:

Tensor