Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -1123,3 +1123,8 @@
 {"step": 22460, "tokens": 11775508480, "loss": 2.754163360595703, "tokens_per_second": 972285.4477234452, "lr": 0.0015, "gradient_norm": 0.1407448798418045, "benchmark": false}
 {"step": 22480, "tokens": 11785994240, "loss": 2.7208763122558595, "tokens_per_second": 971143.0324648671, "lr": 0.0015, "gradient_norm": 0.19335061311721802, "benchmark": false}
 {"step": 22500, "tokens": 11796480000, "loss": 2.7467601776123045, "tokens_per_second": 987608.7978001876, "lr": 0.0015, "gradient_norm": 0.19316506385803223, "benchmark": false}
+{"step": 22520, "tokens": 11806965760, "loss": 2.7422876358032227, "tokens_per_second": 797201.4905023478, "lr": 0.0015, "gradient_norm": 0.21255578100681305, "benchmark": false}
+{"step": 22540, "tokens": 11817451520, "loss": 2.713323402404785, "tokens_per_second": 990451.1165206017, "lr": 0.0015, "gradient_norm": 0.15564727783203125, "benchmark": false}
+{"step": 22560, "tokens": 11827937280, "loss": 2.7529138565063476, "tokens_per_second": 991175.4776028433, "lr": 0.0015, "gradient_norm": 0.17195403575897217, "benchmark": false}
+{"step": 22580, "tokens": 11838423040, "loss": 2.7437063217163087, "tokens_per_second": 989924.6231135604, "lr": 0.0015, "gradient_norm": 0.14951170980930328, "benchmark": false}
+{"step": 22600, "tokens": 11848908800, "loss": 2.7254108428955077, "tokens_per_second": 976515.8239663645, "lr": 0.0015, "gradient_norm": 0.17607435584068298, "benchmark": false}