Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -98,3 +98,8 @@
 {"step": 1960, "tokens": 1027604480, "loss": 3.238423156738281, "tokens_per_second": 983368.2203098513, "lr": 0.00147, "gradient_norm": 0.23316670954227448, "benchmark": false}
 {"step": 1980, "tokens": 1038090240, "loss": 3.1997447967529298, "tokens_per_second": 973767.7154982816, "lr": 0.001485, "gradient_norm": 0.28141582012176514, "benchmark": false}
 {"step": 2000, "tokens": 1048576000, "loss": 3.2284637451171876, "tokens_per_second": 976823.1508784221, "lr": 0.0015, "gradient_norm": 0.2324972003698349, "benchmark": false}
+{"step": 2020, "tokens": 1059061760, "loss": 3.2090808868408205, "tokens_per_second": 730999.3999765913, "lr": 0.0015, "gradient_norm": 0.24585793912410736, "benchmark": false}
+{"step": 2040, "tokens": 1069547520, "loss": 3.1923450469970702, "tokens_per_second": 989342.0159866536, "lr": 0.0015, "gradient_norm": 0.2529505491256714, "benchmark": false}
+{"step": 2060, "tokens": 1080033280, "loss": 3.218313217163086, "tokens_per_second": 980184.8385121401, "lr": 0.0015, "gradient_norm": 0.22426177561283112, "benchmark": false}
+{"step": 2080, "tokens": 1090519040, "loss": 3.2003223419189455, "tokens_per_second": 975774.710886383, "lr": 0.0015, "gradient_norm": 0.320008784532547, "benchmark": false}
+{"step": 2100, "tokens": 1101004800, "loss": 3.149315071105957, "tokens_per_second": 972722.8815786674, "lr": 0.0015, "gradient_norm": 0.23319050669670105, "benchmark": false}