Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -649,3 +649,7 @@
 {"step": 12980, "tokens": 6805258240, "loss": 2.789379692077637, "tokens_per_second": 975217.6425159012, "lr": 0.0015, "gradient_norm": 0.11947929114103317, "benchmark": false}
 {"step": 13000, "tokens": 6815744000, "loss": 2.766477584838867, "tokens_per_second": 974659.1020516185, "lr": 0.0015, "gradient_norm": 0.10573747754096985, "benchmark": false}
 {"step": 13020, "tokens": 6826229760, "loss": 2.766706657409668, "tokens_per_second": 819334.3486186384, "lr": 0.0015, "gradient_norm": 0.10982190817594528, "benchmark": false}
+{"step": 13040, "tokens": 6836715520, "loss": 2.7889896392822267, "tokens_per_second": 974902.7983125558, "lr": 0.0015, "gradient_norm": 0.09978687763214111, "benchmark": false}
+{"step": 13060, "tokens": 6847201280, "loss": 2.7823381423950195, "tokens_per_second": 977186.2934301094, "lr": 0.0015, "gradient_norm": 0.10892217606306076, "benchmark": false}
+{"step": 13080, "tokens": 6857687040, "loss": 2.7726795196533205, "tokens_per_second": 978850.6546447634, "lr": 0.0015, "gradient_norm": 0.09092258661985397, "benchmark": false}
+{"step": 13100, "tokens": 6868172800, "loss": 2.800714683532715, "tokens_per_second": 980305.0475917425, "lr": 0.0015, "gradient_norm": 0.12226828932762146, "benchmark": false}