fix: correct minor typos in help text, README, and comments

scripts/chat_sft.py

@@ -177,7 +177,7 @@ val_dataset = TaskMixture([
     SmolTalk(split="test"), # 24K rows in test set
     MMLU(subset="all", split="test", stop=5200), # 14K rows in test set, use only 5.2K to match the train ratios
     GSM8K(subset="main", split="test", stop=420), # 1.32K rows in test set, use only 420 to match the train ratios
-]) # total: 24K + 14K + 1.32K ~= 39K rows
+]) # total: 24K + 5.2K + 0.42K ~= 29.6K rows
 # DataLoader is defined here, it emits inputs, targets : 2D tensors of shape (device_batch_size, max_seq_len)
 # A big problem is that we don't know the final num_iterations in advance. So we create
 # these two global variables and update them from within the data generator.

scripts/tok_train.py

@@ -14,7 +14,7 @@ from nanochat.dataset import parquets_iter_batched
 # Parse command line arguments
 
 parser = argparse.ArgumentParser(description='Train a BPE tokenizer')
-parser.add_argument('--max-chars', type=int, default=2_000_000_000, help='Maximum characters to train on (default: 10B)')
+parser.add_argument('--max-chars', type=int, default=2_000_000_000, help='Maximum characters to train on (default: 2B)')
 parser.add_argument('--doc-cap', type=int, default=10_000, help='Maximum characters per document (default: 10,000)')
 parser.add_argument('--vocab-size', type=int, default=32768, help='Vocabulary size (default: 32768 = 2^15)')
 args = parser.parse_args()