Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -1173,3 +1173,8 @@
 {"step": 23460, "tokens": 12299796480, "loss": 2.698024940490723, "tokens_per_second": 968831.3757156752, "lr": 0.0015, "gradient_norm": 0.14793908596038818, "benchmark": false}
 {"step": 23480, "tokens": 12310282240, "loss": 2.734004592895508, "tokens_per_second": 980424.4883550106, "lr": 0.0015, "gradient_norm": 0.17792144417762756, "benchmark": false}
 {"step": 23500, "tokens": 12320768000, "loss": 2.752076530456543, "tokens_per_second": 980861.8585807844, "lr": 0.0015, "gradient_norm": 0.16015037894248962, "benchmark": false}
+{"step": 23520, "tokens": 12331253760, "loss": 2.692813491821289, "tokens_per_second": 862408.2630488093, "lr": 0.0015, "gradient_norm": 0.18024979531764984, "benchmark": false}
+{"step": 23540, "tokens": 12341739520, "loss": 2.728947067260742, "tokens_per_second": 987058.8550356231, "lr": 0.0015, "gradient_norm": 0.1586086004972458, "benchmark": false}
+{"step": 23560, "tokens": 12352225280, "loss": 2.7300254821777346, "tokens_per_second": 978136.5913378326, "lr": 0.0015, "gradient_norm": 0.20043253898620605, "benchmark": false}
+{"step": 23580, "tokens": 12362711040, "loss": 2.726719856262207, "tokens_per_second": 982405.9500716801, "lr": 0.0015, "gradient_norm": 0.18047048151493073, "benchmark": false}
+{"step": 23600, "tokens": 12373196800, "loss": 2.701414108276367, "tokens_per_second": 983577.6080914661, "lr": 0.0015, "gradient_norm": 0.16489489376544952, "benchmark": false}