diff --git a/train_gpt.py b/train_gpt.py
index a9b3f62..9ae8e7a 100644
--- a/train_gpt.py
+++ b/train_gpt.py
@@ -1494,8 +1494,8 @@ def _load_data_shard(file: Path):
         assert nbytes == 2 * num_tokens, "number of tokens read does not match header"
     return tokens
 
-BOS_ID = 50256
-TRAIN_MAX_NUM_DOCS = {16384: 64, 32768: 96, 49152: 128}
+BOS_ID = 0  # Polish BPE <|endoftext|>
+TRAIN_MAX_NUM_DOCS = {16384: 384, 32768: 768, 49152: 1152}  # bumped: dense short Polish docs
 
 class Shard:
     def __init__(self, tokens: Tensor, world_size: int = 1):
@@ -1602,7 +1602,7 @@ def distributed_data_generator(filename_pattern: str, num_tokens: int, max_seq_l
 
     while True:
         num_tokens_local = num_tokens // world_size
-        max_num_docs = TRAIN_MAX_NUM_DOCS.get(num_tokens_local, next_multiple_of_n(num_tokens_local // 300, n=128))
+        max_num_docs = TRAIN_MAX_NUM_DOCS.get(num_tokens_local, next_multiple_of_n(num_tokens_local // 48, n=128))
 
         if align_to_bos:
             try:
@@ -1669,13 +1669,13 @@ def distributed_data_generator(filename_pattern: str, num_tokens: int, max_seq_l
 class Hyperparameters:
     # data
     data_path = os.environ.get("DATA_PATH", ".")
-    train_files: str = os.path.join(data_path, "data/fineweb10B/fineweb_train_*.bin") # input .bin to train on
-    val_files: str = os.path.join(data_path, "data/fineweb10B/fineweb_val_*.bin") # input .bin to eval validation loss on
+    train_files: str = os.path.expanduser("~/dynaword/shards/polish_train_*.bin") # input .bin to train on
+    val_files: str = os.path.expanduser("~/dynaword/shards/polish_val_*.bin") # input .bin to eval validation loss on
     val_tokens: int = 10485760 # how many tokens of validation data? it's important to keep this fixed for consistent comparisons
     # batch sizes
     val_batch_size: int = 4 * 64 * 1024 * 8
     # schedule
-    num_scheduled_iterations: int = 1375  # number of steps to complete lr and ws schedule
+    num_scheduled_iterations: int = 13200  # ~1 epoch of 3.47B Polish tokens  # number of steps to complete lr and ws schedule
     num_extension_iterations: int = 10  # number of steps to continue training at final lr and ws
     # evaluation and logging
     run_id: str = f"{uuid.uuid4()}"
@@ -1684,7 +1684,8 @@ class Hyperparameters:
     #   - (1 + m_r9) * x self-reference fuse on layer 9
     #   - backout_lambda fully removed (slot dropped from self.scalars; absorbed into MUDD bias init)
     val_loss_every: int = 250  # every how many steps to evaluate val loss? 0 for only at the end
-    save_checkpoint: bool = False
+    save_checkpoint: bool = True
+    checkpoint_every: int = 500  # save every N steps for crash-resume
     run_evals: bool = False  # run additional evaluations after training is completed
     # bigram hash embedding
     bigram_vocab_size: int = 50304 * 15
@@ -2014,7 +2015,7 @@ print0(nvidia_smi())
 print0("="*100)
 
 model: nn.Module = GPT(
-    vocab_size=50257,
+    vocab_size=32896,  # mult of 128, not power-of-2 (Karpathy); tokenizer stays 32768
     num_layers=11,
     num_heads=6,
     head_dim=128,
@@ -2118,12 +2119,11 @@ for step in range(train_steps + 1):
         torch.cuda.synchronize()
         t0 = time.perf_counter()
 
+    if master_process and args.save_checkpoint and (last_step or (step > 0 and step % args.checkpoint_every == 0)):
+        log = dict(step=step, code=code, model=model.state_dict(), optimizer=training_manager.get_state())
+        os.makedirs(f"logs/{run_id}", exist_ok=True)
+        torch.save(log, f"logs/{run_id}/state_step{step:06d}.pt")
     if last_step:
-        if master_process and args.save_checkpoint:
-            log = dict(step=step, code=code, model=model.state_dict(), optimizer=training_manager.get_state())
-            os.makedirs(f"logs/{run_id}", exist_ok=True)
-            torch.save(log, f"logs/{run_id}/state_step{step:06d}.pt")
-        # the last step only has the validation loop, so break to avoid training
         break
 
     # --------------- TRAINING SECTION -----------------
diff --git a/triton_kernels.py b/triton_kernels.py
index 4f377ce..6b40884 100644
--- a/triton_kernels.py
+++ b/triton_kernels.py
@@ -898,7 +898,7 @@ ce_fwd_bwd_kernel = torch.cuda._compile_kernel(
     CE_KERNEL_DECLS + CE_KERNEL_SOURCE,
     "ce_fwd_bwd_kernel",
     compute_capability="90",
-    cuda_include_dirs=["/usr/local/cuda/include/"],
+    cuda_include_dirs=['/home/ubuntu/modded-nanogpt/.venv/lib/python3.14/site-packages/triton/backends/nvidia/include', '/home/ubuntu/modded-nanogpt/.venv/lib/python3.14/site-packages/nvidia/cuda_runtime/include'],
     nvcc_options=["-lineinfo", "--use_fast_math"],
 )
 ce_fwd_bwd_kernel.set_shared_memory_config(CE_KERNEL_VOCAB_SIZE * 2)