Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -1423,3 +1423,7 @@
 {"step": 28460, "tokens": 14921236480, "loss": 2.741766929626465, "tokens_per_second": 970294.3910813988, "lr": 0.0015, "gradient_norm": 0.2103685885667801, "benchmark": false}
 {"step": 28480, "tokens": 14931722240, "loss": 2.744537353515625, "tokens_per_second": 972864.209021596, "lr": 0.0015, "gradient_norm": 0.18234020471572876, "benchmark": false}
 {"step": 28500, "tokens": 14942208000, "loss": 2.7238285064697267, "tokens_per_second": 968884.8161675986, "lr": 0.0015, "gradient_norm": 0.20309224724769592, "benchmark": false}
+{"step": 28520, "tokens": 14952693760, "loss": 2.725404739379883, "tokens_per_second": 834541.532623829, "lr": 0.0015, "gradient_norm": 0.1847103238105774, "benchmark": false}
+{"step": 28540, "tokens": 14963179520, "loss": 2.7304409027099608, "tokens_per_second": 985902.771852649, "lr": 0.0015, "gradient_norm": 0.17321354150772095, "benchmark": false}
+{"step": 28560, "tokens": 14973665280, "loss": 2.727642059326172, "tokens_per_second": 994465.8637124703, "lr": 0.0015, "gradient_norm": 0.17678822576999664, "benchmark": false}
+{"step": 28580, "tokens": 14984151040, "loss": 2.681191825866699, "tokens_per_second": 988715.9310217054, "lr": 0.0015, "gradient_norm": 0.1811339110136032, "benchmark": false}