Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -1224,3 +1224,9 @@
 {"step": 24480, "tokens": 12834570240, "loss": 2.7191001892089846, "tokens_per_second": 974751.5215301592, "lr": 0.0015, "gradient_norm": 0.1522199809551239, "benchmark": false}
 {"step": 24500, "tokens": 12845056000, "loss": 2.742268371582031, "tokens_per_second": 974151.1406168258, "lr": 0.0015, "gradient_norm": 0.14085350930690765, "benchmark": false}
 {"step": 24520, "tokens": 12855541760, "loss": 2.7326705932617186, "tokens_per_second": 859391.8270237506, "lr": 0.0015, "gradient_norm": 0.16558785736560822, "benchmark": false}
+{"step": 24540, "tokens": 12866027520, "loss": 2.748618507385254, "tokens_per_second": 988211.2074317696, "lr": 0.0015, "gradient_norm": 0.1730576902627945, "benchmark": false}
+{"step": 24560, "tokens": 12876513280, "loss": 2.7072637557983397, "tokens_per_second": 975251.9939386911, "lr": 0.0015, "gradient_norm": 0.18000374734401703, "benchmark": false}
+{"step": 24580, "tokens": 12886999040, "loss": 2.728672218322754, "tokens_per_second": 993402.8065784546, "lr": 0.0015, "gradient_norm": 0.16314634680747986, "benchmark": false}
+{"step": 24600, "tokens": 12897484800, "loss": 2.7285837173461913, "tokens_per_second": 977100.0310438578, "lr": 0.0015, "gradient_norm": 0.1763191521167755, "benchmark": false}
+{"step": 24620, "tokens": 12907970560, "loss": 2.724655342102051, "tokens_per_second": 978006.7473834212, "lr": 0.0015, "gradient_norm": 0.16820791363716125, "benchmark": false}
+{"step": 24640, "tokens": 12918456320, "loss": 2.733455467224121, "tokens_per_second": 978093.4924589752, "lr": 0.0015, "gradient_norm": 0.16100598871707916, "benchmark": false}