Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -1149,3 +1149,9 @@
 {"step": 22980, "tokens": 12048138240, "loss": 2.6979450225830077, "tokens_per_second": 983168.0924193689, "lr": 0.0015, "gradient_norm": 0.15850849449634552, "benchmark": false}
 {"step": 23000, "tokens": 12058624000, "loss": 2.7307880401611326, "tokens_per_second": 839554.3026868133, "lr": 0.0015, "gradient_norm": 0.24211981892585754, "benchmark": false}
 {"step": 23020, "tokens": 12069109760, "loss": 2.7809255599975584, "tokens_per_second": 823841.549096626, "lr": 0.0015, "gradient_norm": 0.1513972282409668, "benchmark": false}
+{"step": 23040, "tokens": 12079595520, "loss": 2.7394290924072267, "tokens_per_second": 988362.8729466494, "lr": 0.0015, "gradient_norm": 0.15792645514011383, "benchmark": false}
+{"step": 23060, "tokens": 12090081280, "loss": 2.7023691177368163, "tokens_per_second": 820437.2006449708, "lr": 0.0015, "gradient_norm": 0.17823415994644165, "benchmark": false}
+{"step": 23080, "tokens": 12100567040, "loss": 2.715198516845703, "tokens_per_second": 995391.4749122, "lr": 0.0015, "gradient_norm": 0.15440329909324646, "benchmark": false}
+{"step": 23100, "tokens": 12111052800, "loss": 2.7461761474609374, "tokens_per_second": 988061.972473647, "lr": 0.0015, "gradient_norm": 0.15957710146903992, "benchmark": false}
+{"step": 23120, "tokens": 12121538560, "loss": 2.724147987365723, "tokens_per_second": 980578.3726612739, "lr": 0.0015, "gradient_norm": 0.17278163135051727, "benchmark": false}
+{"step": 23140, "tokens": 12132024320, "loss": 2.754043769836426, "tokens_per_second": 985226.7322503136, "lr": 0.0015, "gradient_norm": 0.22024716436862946, "benchmark": false}