Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -699,3 +699,8 @@
 {"step": 13980, "tokens": 7329546240, "loss": 2.7930103302001954, "tokens_per_second": 970508.686897241, "lr": 0.0015, "gradient_norm": 0.12515392899513245, "benchmark": false}
 {"step": 14000, "tokens": 7340032000, "loss": 2.810237503051758, "tokens_per_second": 963901.6917292763, "lr": 0.0015, "gradient_norm": 0.11248497664928436, "benchmark": false}
 {"step": 14020, "tokens": 7350517760, "loss": 2.791335678100586, "tokens_per_second": 813652.9955171734, "lr": 0.0015, "gradient_norm": 0.11959215253591537, "benchmark": false}
+{"step": 14040, "tokens": 7361003520, "loss": 2.777591514587402, "tokens_per_second": 969676.2155442851, "lr": 0.0015, "gradient_norm": 0.12372884899377823, "benchmark": false}
+{"step": 14060, "tokens": 7371489280, "loss": 2.782402229309082, "tokens_per_second": 983219.0543881522, "lr": 0.0015, "gradient_norm": 0.11226522922515869, "benchmark": false}
+{"step": 14080, "tokens": 7381975040, "loss": 2.7681150436401367, "tokens_per_second": 975875.657074898, "lr": 0.0015, "gradient_norm": 0.10557014495134354, "benchmark": false}
+{"step": 14100, "tokens": 7392460800, "loss": 2.7867458343505858, "tokens_per_second": 966180.8714196938, "lr": 0.0015, "gradient_norm": 0.12427403032779694, "benchmark": false}
+{"step": 14120, "tokens": 7402946560, "loss": 2.771135711669922, "tokens_per_second": 967829.3294986727, "lr": 0.0015, "gradient_norm": 0.14234967529773712, "benchmark": false}