Update tokenizer, configuration and training reports

reports/run/metrics.jsonl

@@ -524,3 +524,8 @@
 {"step": 10480, "tokens": 5494538240, "loss": 2.8141708374023438, "tokens_per_second": 949083.8431879994, "lr": 0.0015, "gradient_norm": 0.07634645700454712, "benchmark": false}
 {"step": 10500, "tokens": 5505024000, "loss": 2.8515233993530273, "tokens_per_second": 977063.5599389477, "lr": 0.0015, "gradient_norm": 0.09103018790483475, "benchmark": false}
 {"step": 10520, "tokens": 5515509760, "loss": 2.8071733474731446, "tokens_per_second": 856841.5024644048, "lr": 0.0015, "gradient_norm": 0.08776334673166275, "benchmark": false}
+{"step": 10540, "tokens": 5525995520, "loss": 2.800252151489258, "tokens_per_second": 981046.9636411724, "lr": 0.0015, "gradient_norm": 0.08854340016841888, "benchmark": false}
+{"step": 10560, "tokens": 5536481280, "loss": 2.83626708984375, "tokens_per_second": 983463.9553301485, "lr": 0.0015, "gradient_norm": 0.10051717609167099, "benchmark": false}
+{"step": 10580, "tokens": 5546967040, "loss": 2.828484535217285, "tokens_per_second": 986980.0541079927, "lr": 0.0015, "gradient_norm": 0.0855020210146904, "benchmark": false}
+{"step": 10600, "tokens": 5557452800, "loss": 2.812819480895996, "tokens_per_second": 979840.0683955124, "lr": 0.0015, "gradient_norm": 0.08613714575767517, "benchmark": false}
+{"step": 10620, "tokens": 5567938560, "loss": 2.830562210083008, "tokens_per_second": 980664.4530554473, "lr": 0.0015, "gradient_norm": 0.08211514353752136, "benchmark": false}