Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -249,3 +249,8 @@
 {"step": 4980, "tokens": 2610954240, "loss": 2.9437145233154296, "tokens_per_second": 980325.3360152998, "lr": 0.0015, "gradient_norm": 0.08578862994909286, "benchmark": false}
 {"step": 5000, "tokens": 2621440000, "loss": 2.933154296875, "tokens_per_second": 969211.9684460608, "lr": 0.0015, "gradient_norm": 0.09016783535480499, "benchmark": false}
 {"step": 5020, "tokens": 2631925760, "loss": 2.91949462890625, "tokens_per_second": 807039.9908925168, "lr": 0.0015, "gradient_norm": 0.0832776427268982, "benchmark": false}
+{"step": 5040, "tokens": 2642411520, "loss": 2.943686676025391, "tokens_per_second": 974883.678769598, "lr": 0.0015, "gradient_norm": 0.0810946375131607, "benchmark": false}
+{"step": 5060, "tokens": 2652897280, "loss": 2.9218799591064455, "tokens_per_second": 972867.6664382793, "lr": 0.0015, "gradient_norm": 0.08206641674041748, "benchmark": false}
+{"step": 5080, "tokens": 2663383040, "loss": 2.9323846817016603, "tokens_per_second": 980684.4591826717, "lr": 0.0015, "gradient_norm": 0.0892726480960846, "benchmark": false}
+{"step": 5100, "tokens": 2673868800, "loss": 2.968641662597656, "tokens_per_second": 977169.9362081758, "lr": 0.0015, "gradient_norm": 0.08341504633426666, "benchmark": false}
+{"step": 5120, "tokens": 2684354560, "loss": 2.94069766998291, "tokens_per_second": 971473.8473101754, "lr": 0.0015, "gradient_norm": 0.08239274471998215, "benchmark": false}