diff --git a/crates/ml/src/trainers/dqn/fused_training.rs b/crates/ml/src/trainers/dqn/fused_training.rs
index 071ff8291..9ebcc6a49 100644
--- a/crates/ml/src/trainers/dqn/fused_training.rs
+++ b/crates/ml/src/trainers/dqn/fused_training.rs
@@ -701,6 +701,7 @@ impl FusedTrainingCtx {
         ).map_err(|e| anyhow::anyhow!("Fused train_step_gpu (forward only): {e}"))?;
 
         self.trainer.run_nan_checks_post_forward(self.batch_size)?;
+        eprintln!("FUSED_DIAG: step {} — post-forward NaN checks done", self.steps_since_varmap_sync);
 
         // ── Step 2b: HER donor computation (outside graph_aux) ───────────
         // Donor indices vary per step (random/future/final). The computation
@@ -726,6 +727,7 @@ impl FusedTrainingCtx {
             }
         }
 
+        eprintln!("FUSED_DIAG: step {} — HER done, entering aux ops", self.steps_since_varmap_sync);
         // ── Step 3: Auxiliary ops (graph_aux captured or replayed) ────────
         if self.graph_aux.is_some() {
             self.pre_replay_state_update(agent);
@@ -735,6 +737,7 @@ impl FusedTrainingCtx {
             self.submit_aux_ops(agent, gpu_batch)?;
         }
 
+        eprintln!("FUSED_DIAG: step {} — aux ops done", self.steps_since_varmap_sync);
         // ── Step 4: Conditional ops (outside graph) ──────────────────────
 
         // Ensemble diversity (variable topology, complex forward passes).
@@ -764,12 +767,14 @@ impl FusedTrainingCtx {
         }
         self.pending_vaccine_batch = None;
 
+        eprintln!("FUSED_DIAG: step {} — conditional ops done, entering Adam", self.steps_since_varmap_sync);
         // ── Step 5: Pruning + Adam ───────────────────────────────────────
         self.trainer.apply_pruning_mask()
             .map_err(|e| anyhow::anyhow!("Pruning mask apply: {e}"))?;
 
         let fused_result = self.trainer.replay_adam_and_readback()
             .map_err(|e| anyhow::anyhow!("graph_adam replay: {e}"))?;
+        eprintln!("FUSED_DIAG: step {} — Adam done, entering PER update", self.steps_since_varmap_sync);
 
         // ── Step 6: PER priority update via seg_tree_update ─────────────
         // Uses the replay buffer's segment tree kernel: writes priorities,
@@ -780,6 +785,7 @@ impl FusedTrainingCtx {
             &self.stream,
         ).map_err(|e| anyhow::anyhow!("PER seg_tree_update: {e}"))?;
 
+        eprintln!("FUSED_DIAG: step {} — PER update done", self.steps_since_varmap_sync);
         // Bookkeeping.
         agent.fused_post_step_gpu_bookkeeping()
             .map_err(|e| anyhow::anyhow!("Fused GPU bookkeeping: {e}"))?;
diff --git a/crates/ml/src/trainers/dqn/trainer/training_loop.rs b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
index fbecdab13..56ae7acdd 100644
--- a/crates/ml/src/trainers/dqn/trainer/training_loop.rs
+++ b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
@@ -1175,6 +1175,7 @@ impl DQNTrainer {
         }
 
         for _step in 0..num_training_steps {
+            eprintln!("TRAIN_DIAG: step {_step}/{num_training_steps} — sampling");
             let sample_start = std::time::Instant::now();
             let (batch, vaccine_batch) = {
                 let agent = self.agent.read().await;
@@ -1187,7 +1188,9 @@ impl DQNTrainer {
                 let vb = buffer.sample(self.current_batch_size).ok();
                 (b, vb)
             };
-            sample_total_us += sample_start.elapsed().as_micros() as u64;
+            let sample_us = sample_start.elapsed().as_micros();
+            eprintln!("TRAIN_DIAG: step {_step} — sample done in {sample_us}µs");
+            sample_total_us += sample_us as u64;
 
             {
                 let mut agent = self.agent.write().await;