Update experiment measurements and status

reports/runs/finemath-1337/metrics.jsonl

@@ -21,3 +21,9 @@
 {"step": 420, "tokens": 220200960, "loss": 2.396063041687012, "optimizer_updates": 420, "effective_batch": 512, "lr": 7.045303993926625e-05, "gradient_norm": 0.2821289002895355, "tokens_per_second": 1137717.636516895, "synthetic": false, "world_size": 8}
 {"step": 440, "tokens": 230686720, "loss": 2.3959320068359373, "optimizer_updates": 440, "effective_batch": 512, "lr": 6.762603432545125e-05, "gradient_norm": 0.2993291914463043, "tokens_per_second": 946389.1109692265, "synthetic": false, "world_size": 8}
 {"step": 460, "tokens": 241172480, "loss": 2.4008581161499025, "optimizer_updates": 460, "effective_batch": 512, "lr": 6.47438182760683e-05, "gradient_norm": 0.2686641812324524, "tokens_per_second": 1136622.7237819468, "synthetic": false, "world_size": 8}
+{"step": 480, "tokens": 251658240, "loss": 2.3867029190063476, "optimizer_updates": 480, "effective_batch": 512, "lr": 6.181899498855732e-05, "gradient_norm": 0.2703098654747009, "tokens_per_second": 989477.7797575915, "synthetic": false, "world_size": 8}
+{"step": 500, "tokens": 262144000, "loss": 2.398288345336914, "optimizer_updates": 500, "effective_batch": 512, "lr": 5.886435397096976e-05, "gradient_norm": 0.2869747281074524, "tokens_per_second": 1141072.2862360654, "synthetic": false, "world_size": 8}
+{"step": 520, "tokens": 272629760, "loss": 2.4080339431762696, "optimizer_updates": 520, "effective_batch": 512, "lr": 5.5892815116703924e-05, "gradient_norm": 0.32183343172073364, "tokens_per_second": 1011573.0555791758, "synthetic": false, "world_size": 8}
+{"step": 540, "tokens": 283115520, "loss": 2.3961742401123045, "optimizer_updates": 540, "effective_batch": 512, "lr": 5.291737220909842e-05, "gradient_norm": 0.29093173146247864, "tokens_per_second": 1142072.4974118269, "synthetic": false, "world_size": 8}
+{"step": 560, "tokens": 293601280, "loss": 2.394169235229492, "optimizer_updates": 560, "effective_batch": 512, "lr": 4.99510361029238e-05, "gradient_norm": 0.2487589567899704, "tokens_per_second": 1141823.76897865, "synthetic": false, "world_size": 8}
+{"step": 580, "tokens": 304087040, "loss": 2.3924562454223635, "optimizer_updates": 580, "effective_batch": 512, "lr": 4.700677783122511e-05, "gradient_norm": 0.2445094883441925, "tokens_per_second": 1137594.4934738574, "synthetic": false, "world_size": 8}