Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -574,3 +574,8 @@
 {"step": 11480, "tokens": 6018826240, "loss": 2.799390411376953, "tokens_per_second": 982497.6750645757, "lr": 0.0015, "gradient_norm": 0.08827927708625793, "benchmark": false}
 {"step": 11500, "tokens": 6029312000, "loss": 2.8012603759765624, "tokens_per_second": 979171.7305241188, "lr": 0.0015, "gradient_norm": 0.0993845984339714, "benchmark": false}
 {"step": 11520, "tokens": 6039797760, "loss": 2.806071090698242, "tokens_per_second": 857456.8514258185, "lr": 0.0015, "gradient_norm": 0.0953318327665329, "benchmark": false}
+{"step": 11540, "tokens": 6050283520, "loss": 2.789183235168457, "tokens_per_second": 988145.2765951087, "lr": 0.0015, "gradient_norm": 0.09696745127439499, "benchmark": false}
+{"step": 11560, "tokens": 6060769280, "loss": 2.8085102081298827, "tokens_per_second": 983786.260167913, "lr": 0.0015, "gradient_norm": 0.10099394619464874, "benchmark": false}
+{"step": 11580, "tokens": 6071255040, "loss": 2.830649185180664, "tokens_per_second": 996520.4041977315, "lr": 0.0015, "gradient_norm": 0.11824902892112732, "benchmark": false}
+{"step": 11600, "tokens": 6081740800, "loss": 2.8042892456054687, "tokens_per_second": 985062.7638370555, "lr": 0.0015, "gradient_norm": 0.09543195366859436, "benchmark": false}
+{"step": 11620, "tokens": 6092226560, "loss": 2.782301139831543, "tokens_per_second": 991400.891897373, "lr": 0.0015, "gradient_norm": 0.1080298125743866, "benchmark": false}