Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -349,3 +349,8 @@
 {"step": 6980, "tokens": 3659530240, "loss": 2.8522924423217773, "tokens_per_second": 963148.4756019333, "lr": 0.0015, "gradient_norm": 0.07306957989931107, "benchmark": false}
 {"step": 7000, "tokens": 3670016000, "loss": 2.865734100341797, "tokens_per_second": 967669.6781736239, "lr": 0.0015, "gradient_norm": 0.0665232315659523, "benchmark": false}
 {"step": 7020, "tokens": 3680501760, "loss": 2.886398506164551, "tokens_per_second": 811736.6275375811, "lr": 0.0015, "gradient_norm": 0.0693461000919342, "benchmark": false}
+{"step": 7040, "tokens": 3690987520, "loss": 2.8966754913330077, "tokens_per_second": 972470.0973072138, "lr": 0.0015, "gradient_norm": 0.06701541692018509, "benchmark": false}
+{"step": 7060, "tokens": 3701473280, "loss": 2.89107666015625, "tokens_per_second": 968635.0652227454, "lr": 0.0015, "gradient_norm": 0.06736895442008972, "benchmark": false}
+{"step": 7080, "tokens": 3711959040, "loss": 2.884008026123047, "tokens_per_second": 972272.8872774077, "lr": 0.0015, "gradient_norm": 0.06326126307249069, "benchmark": false}
+{"step": 7100, "tokens": 3722444800, "loss": 2.858163070678711, "tokens_per_second": 969183.6295319292, "lr": 0.0015, "gradient_norm": 0.07230526953935623, "benchmark": false}
+{"step": 7120, "tokens": 3732930560, "loss": 2.923481750488281, "tokens_per_second": 974957.3125197034, "lr": 0.0015, "gradient_norm": 0.0695229098200798, "benchmark": false}