Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -673,3 +673,7 @@
 {"step": 13460, "tokens": 7056916480, "loss": 2.801237106323242, "tokens_per_second": 977428.8533845174, "lr": 0.0015, "gradient_norm": 0.0954863652586937, "benchmark": false}
 {"step": 13480, "tokens": 7067402240, "loss": 2.813336181640625, "tokens_per_second": 990161.7610894733, "lr": 0.0015, "gradient_norm": 0.10894346982240677, "benchmark": false}
 {"step": 13500, "tokens": 7077888000, "loss": 2.8001928329467773, "tokens_per_second": 961178.7706554127, "lr": 0.0015, "gradient_norm": 0.11561203747987747, "benchmark": false}
+{"step": 13520, "tokens": 7088373760, "loss": 2.7821531295776367, "tokens_per_second": 840597.3397416604, "lr": 0.0015, "gradient_norm": 0.09781192988157272, "benchmark": false}
+{"step": 13540, "tokens": 7098859520, "loss": 2.7886821746826174, "tokens_per_second": 989633.9131038158, "lr": 0.0015, "gradient_norm": 0.1145467534661293, "benchmark": false}
+{"step": 13560, "tokens": 7109345280, "loss": 2.7986698150634766, "tokens_per_second": 992822.7311915599, "lr": 0.0015, "gradient_norm": 0.12221966683864594, "benchmark": false}
+{"step": 13580, "tokens": 7119831040, "loss": 2.81064453125, "tokens_per_second": 988468.4767134241, "lr": 0.0015, "gradient_norm": 0.11042139679193497, "benchmark": false}