Learn how to convert legacy YAMLs into the new Trainer YAML configuration.
eval_input
eval_input.micro_batch_size
model
model.compression
model.fp16_type
model.lora_params
model.mixed_precision
model.selective_grad
optimizer
optimizer.grad_accum_steps
optimizer.initial_loss_scale
optimizer.learning_rate
optimizer.log_summaries
optimizer.loss_scaling_factor
optimizer.max_gradient_norm
optimizer.max_gradient_value
optimizer.max_loss_scale
optimizer.min_loss_scale
optimizer.steps_per_increase
runconfig.act_memory_gi
runconfig.autoload_last_checkpoint
runconfig.check_loss_values
runconfig.checkpoint_path
runconfig.checkpoint_steps
runconfig.cmd_memory_gi
runconfig.compile_crd_memory_gi
runconfig.compile_dir
runconfig.compile_only
runconfig.credentials_path
runconfig.debug_args
runconfig.debug_args_path
runconfig.disable_strict_checkpoint_loading
runconfig.disable_version_check
runconfig.dist_backend
runconfig.drop_data
runconfig.dump_activations
runconfig.enable_act_frequency
runconfig.enable_distributed
runconfig.eval_frequency
runconfig.eval_steps
runconfig.execute_crd_memory_gi
runconfig.experimental.listeners
runconfig.init_method
runconfig.job_labels
runconfig.job_priority
runconfig.job_time_sec
runconfig.lazy_initialization
runconfig.load_checkpoint_states
runconfig.log_initialization
runconfig.log_input_summaries
runconfig.log_steps
runconfig.logging
runconfig.main_process_id
runconfig.max_checkpoints
runconfig.max_steps
runconfig.mgmt_address
runconfig.mgmt_namespace
runconfig.model_dir
runconfig.mount_dirs
runconfig.num_act_servers
runconfig.num_csx
runconfig.num_epochs
runconfig.num_steps
runconfig.num_wgt_servers
runconfig.num_workers_per_csx
runconfig.op_profiler_config
runconfig.precision_opt_level
runconfig.python_paths
runconfig.retrace_every_iteration
runconfig.save_initial_checkpoint
runconfig.seed
runconfig.steps_per_epoch
runconfig.sync_batchnorm
runconfig.target_device
runconfig.transfer_processes
runconfig.validate_only
runconfig.wgt_memory_gi
runconfig.wrk_memory_gi
runconfig.wsc_log_level
sparsity
sparsity.add_summaries
train_input
train_input.micro_batch_size
wandb.group
wandb.job_type
wandb.project
wandb.resume
wandb.run_id
wandb.run_name
wandb.tags