Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -1349,3 +1349,9 @@
 {"step": 26980, "tokens": 14145290240, "loss": 2.757349967956543, "tokens_per_second": 964245.0973920216, "lr": 0.0015, "gradient_norm": 0.18727724254131317, "benchmark": false}
 {"step": 27000, "tokens": 14155776000, "loss": 2.7379180908203127, "tokens_per_second": 974215.3208308646, "lr": 0.0015, "gradient_norm": 0.2257988452911377, "benchmark": false}
 {"step": 27020, "tokens": 14166261760, "loss": 2.7172765731811523, "tokens_per_second": 811788.9719791115, "lr": 0.0015, "gradient_norm": 0.19278764724731445, "benchmark": false}
+{"step": 27040, "tokens": 14176747520, "loss": 2.7182212829589845, "tokens_per_second": 971720.963860744, "lr": 0.0015, "gradient_norm": 0.21001334488391876, "benchmark": false}
+{"step": 27060, "tokens": 14187233280, "loss": 2.7089679718017576, "tokens_per_second": 979600.6869423535, "lr": 0.0015, "gradient_norm": 0.1708393692970276, "benchmark": false}
+{"step": 27080, "tokens": 14197719040, "loss": 2.7108909606933596, "tokens_per_second": 987109.5546218049, "lr": 0.0015, "gradient_norm": 0.18828046321868896, "benchmark": false}
+{"step": 27100, "tokens": 14208204800, "loss": 2.734965133666992, "tokens_per_second": 947571.5373417245, "lr": 0.0015, "gradient_norm": 0.2005746215581894, "benchmark": false}
+{"step": 27120, "tokens": 14218690560, "loss": 2.7572681427001955, "tokens_per_second": 838238.7888027055, "lr": 0.0015, "gradient_norm": 0.2550247609615326, "benchmark": false}
+{"step": 27140, "tokens": 14229176320, "loss": 2.7336267471313476, "tokens_per_second": 956864.912182367, "lr": 0.0015, "gradient_norm": 0.1868649125099182, "benchmark": false}