Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -399,3 +399,8 @@
 {"step": 7980, "tokens": 4183818240, "loss": 2.8597362518310545, "tokens_per_second": 976117.0131650119, "lr": 0.0015, "gradient_norm": 0.07403507828712463, "benchmark": false}
 {"step": 8000, "tokens": 4194304000, "loss": 2.8754581451416015, "tokens_per_second": 992788.4029002639, "lr": 0.0015, "gradient_norm": 0.06957851350307465, "benchmark": false}
 {"step": 8020, "tokens": 4204789760, "loss": 2.8420690536499023, "tokens_per_second": 837867.9176074439, "lr": 0.0015, "gradient_norm": 0.07526803761720657, "benchmark": false}
+{"step": 8040, "tokens": 4215275520, "loss": 2.8559471130371095, "tokens_per_second": 983853.4840581511, "lr": 0.0015, "gradient_norm": 0.08585216850042343, "benchmark": false}
+{"step": 8060, "tokens": 4225761280, "loss": 2.8896697998046874, "tokens_per_second": 989730.2216739019, "lr": 0.0015, "gradient_norm": 0.06958837062120438, "benchmark": false}
+{"step": 8080, "tokens": 4236247040, "loss": 2.832368087768555, "tokens_per_second": 986211.1964923269, "lr": 0.0015, "gradient_norm": 0.06925537437200546, "benchmark": false}
+{"step": 8100, "tokens": 4246732800, "loss": 2.842477226257324, "tokens_per_second": 990481.1764232212, "lr": 0.0015, "gradient_norm": 0.08142078667879105, "benchmark": false}
+{"step": 8120, "tokens": 4257218560, "loss": 2.865599250793457, "tokens_per_second": 991851.2025152362, "lr": 0.0015, "gradient_norm": 0.06867492944002151, "benchmark": false}