Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -723,3 +723,8 @@
 {"step": 14460, "tokens": 7581204480, "loss": 2.795541000366211, "tokens_per_second": 987438.052550711, "lr": 0.0015, "gradient_norm": 0.11582837998867035, "benchmark": false}
 {"step": 14480, "tokens": 7591690240, "loss": 2.759349250793457, "tokens_per_second": 986850.0911493824, "lr": 0.0015, "gradient_norm": 0.10604269802570343, "benchmark": false}
 {"step": 14500, "tokens": 7602176000, "loss": 2.775119972229004, "tokens_per_second": 988500.8542283837, "lr": 0.0015, "gradient_norm": 0.12106780707836151, "benchmark": false}
+{"step": 14520, "tokens": 7612661760, "loss": 2.78094482421875, "tokens_per_second": 861691.7279486274, "lr": 0.0015, "gradient_norm": 0.11721201986074448, "benchmark": false}
+{"step": 14540, "tokens": 7623147520, "loss": 2.8029096603393553, "tokens_per_second": 970426.4987138406, "lr": 0.0015, "gradient_norm": 0.1039208471775055, "benchmark": false}
+{"step": 14560, "tokens": 7633633280, "loss": 2.7715450286865235, "tokens_per_second": 853681.4973439367, "lr": 0.0015, "gradient_norm": 0.1236744225025177, "benchmark": false}
+{"step": 14580, "tokens": 7644119040, "loss": 2.7071344375610353, "tokens_per_second": 990082.1098315411, "lr": 0.0015, "gradient_norm": 0.129014790058136, "benchmark": false}
+{"step": 14600, "tokens": 7654604800, "loss": 2.7800420761108398, "tokens_per_second": 985127.7685421152, "lr": 0.0015, "gradient_norm": 0.12574076652526855, "benchmark": false}