Update experiment measurements and status
Browse files
reports/runs/cosmopedia-2027/metrics.jsonl
CHANGED
|
@@ -18,3 +18,7 @@
|
|
| 18 |
{"step": 360, "tokens": 188743680, "loss": 2.3924930572509764, "optimizer_updates": 360, "effective_batch": 512, "lr": 7.848070654808249e-05, "gradient_norm": 0.2605448067188263, "tokens_per_second": 1118116.0370178986, "synthetic": false, "world_size": 8}
|
| 19 |
{"step": 380, "tokens": 199229440, "loss": 2.4007030487060548, "optimizer_updates": 380, "effective_batch": 512, "lr": 7.589226823127036e-05, "gradient_norm": 0.30334964394569397, "tokens_per_second": 1161447.0223372327, "synthetic": false, "world_size": 8}
|
| 20 |
{"step": 400, "tokens": 209715200, "loss": 2.389419364929199, "optimizer_updates": 400, "effective_batch": 512, "lr": 7.321247334126042e-05, "gradient_norm": 0.26134854555130005, "tokens_per_second": 1158062.0119972792, "synthetic": false, "world_size": 8}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
{"step": 360, "tokens": 188743680, "loss": 2.3924930572509764, "optimizer_updates": 360, "effective_batch": 512, "lr": 7.848070654808249e-05, "gradient_norm": 0.2605448067188263, "tokens_per_second": 1118116.0370178986, "synthetic": false, "world_size": 8}
|
| 19 |
{"step": 380, "tokens": 199229440, "loss": 2.4007030487060548, "optimizer_updates": 380, "effective_batch": 512, "lr": 7.589226823127036e-05, "gradient_norm": 0.30334964394569397, "tokens_per_second": 1161447.0223372327, "synthetic": false, "world_size": 8}
|
| 20 |
{"step": 400, "tokens": 209715200, "loss": 2.389419364929199, "optimizer_updates": 400, "effective_batch": 512, "lr": 7.321247334126042e-05, "gradient_norm": 0.26134854555130005, "tokens_per_second": 1158062.0119972792, "synthetic": false, "world_size": 8}
|
| 21 |
+
{"step": 420, "tokens": 220200960, "loss": 2.391482925415039, "optimizer_updates": 420, "effective_batch": 512, "lr": 7.045303993926625e-05, "gradient_norm": 0.29452261328697205, "tokens_per_second": 1154460.6133946823, "synthetic": false, "world_size": 8}
|
| 22 |
+
{"step": 440, "tokens": 230686720, "loss": 2.387767791748047, "optimizer_updates": 440, "effective_batch": 512, "lr": 6.762603432545125e-05, "gradient_norm": 0.3393482267856598, "tokens_per_second": 1158380.080961725, "synthetic": false, "world_size": 8}
|
| 23 |
+
{"step": 460, "tokens": 241172480, "loss": 2.387031364440918, "optimizer_updates": 460, "effective_batch": 512, "lr": 6.47438182760683e-05, "gradient_norm": 0.2886233627796173, "tokens_per_second": 1147776.7145807238, "synthetic": false, "world_size": 8}
|
| 24 |
+
{"step": 480, "tokens": 251658240, "loss": 2.3926759719848634, "optimizer_updates": 480, "effective_batch": 512, "lr": 6.181899498855732e-05, "gradient_norm": 0.2845536470413208, "tokens_per_second": 1152892.381298327, "synthetic": false, "world_size": 8}
|