//! Training stack (Phase T6): LR schedule, global-norm grad clipping, checkpoint
//! save/load, the GPT-2 BPE data pipeline (reusing xserv's tokenizer), an
//! autoregressive sampler, and the training loop that wires them onto the T5
//! `TinyTransformer` + the hand-written AdamW (`xtrain-optim`).
//!
//! Host-only pieces (LR schedule, grad-norm math) always compile so the crate
//! `cargo check`s on a GPU-less host; everything that touches GPU tensors is
//! gated behind `not(no_cuda)`.

pub mod clip;
pub mod data;
pub mod schedule;

#[cfg(not(no_cuda))]
pub mod checkpoint;
#[cfg(not(no_cuda))]
pub mod sample;
#[cfg(not(no_cuda))]
mod train_loop;

#[cfg(not(no_cuda))]
pub use train_loop::{TrainConfig, TrainResult, eval_loss, train};