Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -549,3 +549,9 @@
 {"step": 10980, "tokens": 5756682240, "loss": 2.8020746231079103, "tokens_per_second": 977162.6497957591, "lr": 0.0015, "gradient_norm": 0.11768177151679993, "benchmark": false}
 {"step": 11000, "tokens": 5767168000, "loss": 2.8348876953125, "tokens_per_second": 987974.7411373939, "lr": 0.0015, "gradient_norm": 0.09453051537275314, "benchmark": false}
 {"step": 11020, "tokens": 5777653760, "loss": 2.8067771911621096, "tokens_per_second": 768149.5252021329, "lr": 0.0015, "gradient_norm": 0.09996025264263153, "benchmark": false}
+{"step": 11040, "tokens": 5788139520, "loss": 2.7988447189331054, "tokens_per_second": 974332.5963619035, "lr": 0.0015, "gradient_norm": 0.09607052057981491, "benchmark": false}
+{"step": 11060, "tokens": 5798625280, "loss": 2.799824905395508, "tokens_per_second": 985249.2922863617, "lr": 0.0015, "gradient_norm": 0.09087151288986206, "benchmark": false}
+{"step": 11080, "tokens": 5809111040, "loss": 2.814681816101074, "tokens_per_second": 971428.3503853546, "lr": 0.0015, "gradient_norm": 0.09317014366388321, "benchmark": false}
+{"step": 11100, "tokens": 5819596800, "loss": 2.8190017700195313, "tokens_per_second": 969915.2315686354, "lr": 0.0015, "gradient_norm": 0.08898317813873291, "benchmark": false}
+{"step": 11120, "tokens": 5830082560, "loss": 2.807066535949707, "tokens_per_second": 973064.1389007025, "lr": 0.0015, "gradient_norm": 0.10078496485948563, "benchmark": false}
+{"step": 11140, "tokens": 5840568320, "loss": 2.795416831970215, "tokens_per_second": 975718.5095579139, "lr": 0.0015, "gradient_norm": 0.10522713512182236, "benchmark": false}