Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -498,3 +498,7 @@
 {"step": 9960, "tokens": 5221908480, "loss": 2.83525390625, "tokens_per_second": 985306.7973998113, "lr": 0.0015, "gradient_norm": 0.07898715138435364, "benchmark": false}
 {"step": 9980, "tokens": 5232394240, "loss": 2.809004211425781, "tokens_per_second": 990607.4548488081, "lr": 0.0015, "gradient_norm": 0.07946421951055527, "benchmark": false}
 {"step": 10000, "tokens": 5242880000, "loss": 2.8216739654541017, "tokens_per_second": 986454.10697014, "lr": 0.0015, "gradient_norm": 0.08943367004394531, "benchmark": false}
+{"step": 10020, "tokens": 5253365760, "loss": 2.8265048980712892, "tokens_per_second": 852187.0333771141, "lr": 0.0015, "gradient_norm": 0.09247152507305145, "benchmark": false}
+{"step": 10040, "tokens": 5263851520, "loss": 2.8199321746826174, "tokens_per_second": 988591.5887100031, "lr": 0.0015, "gradient_norm": 0.07508964091539383, "benchmark": false}
+{"step": 10060, "tokens": 5274337280, "loss": 2.7843997955322264, "tokens_per_second": 947101.9980625706, "lr": 0.0015, "gradient_norm": 0.08978574723005295, "benchmark": false}
+{"step": 10080, "tokens": 5284823040, "loss": 2.838224983215332, "tokens_per_second": 984909.651803646, "lr": 0.0015, "gradient_norm": 0.08179404586553574, "benchmark": false}