Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -1273,3 +1273,8 @@
 {"step": 25460, "tokens": 13348372480, "loss": 2.7270036697387696, "tokens_per_second": 979712.4978044042, "lr": 0.0015, "gradient_norm": 0.1670805960893631, "benchmark": false}
 {"step": 25480, "tokens": 13358858240, "loss": 2.7266567230224608, "tokens_per_second": 978889.1120942757, "lr": 0.0015, "gradient_norm": 0.21402980387210846, "benchmark": false}
 {"step": 25500, "tokens": 13369344000, "loss": 2.7207874298095702, "tokens_per_second": 987622.1601941576, "lr": 0.0015, "gradient_norm": 0.17039531469345093, "benchmark": false}
+{"step": 25520, "tokens": 13379829760, "loss": 2.720967102050781, "tokens_per_second": 863418.1523505475, "lr": 0.0015, "gradient_norm": 0.15465085208415985, "benchmark": false}
+{"step": 25540, "tokens": 13390315520, "loss": 2.705210494995117, "tokens_per_second": 986263.6408655782, "lr": 0.0015, "gradient_norm": 0.16867955029010773, "benchmark": false}
+{"step": 25560, "tokens": 13400801280, "loss": 2.70369815826416, "tokens_per_second": 994968.8319761851, "lr": 0.0015, "gradient_norm": 0.1720699965953827, "benchmark": false}
+{"step": 25580, "tokens": 13411287040, "loss": 2.7260082244873045, "tokens_per_second": 979677.8507507413, "lr": 0.0015, "gradient_norm": 0.18026603758335114, "benchmark": false}
+{"step": 25600, "tokens": 13421772800, "loss": 2.7517717361450194, "tokens_per_second": 987180.0865562145, "lr": 0.0015, "gradient_norm": 0.1635952591896057, "benchmark": false}