kacperwikiel commited on
Commit
974e479
·
verified ·
1 Parent(s): d2f0f80

Update experiment measurements and status

Browse files
reports/runs/cosmopedia-2027/metrics.jsonl CHANGED
@@ -28,3 +28,6 @@
28
  {"step": 560, "tokens": 293601280, "loss": 2.3897640228271486, "optimizer_updates": 560, "effective_batch": 512, "lr": 4.99510361029238e-05, "gradient_norm": 0.24847784638404846, "tokens_per_second": 1152737.2337354836, "synthetic": false, "world_size": 8}
29
  {"step": 580, "tokens": 304087040, "loss": 2.3887601852416993, "optimizer_updates": 580, "effective_batch": 512, "lr": 4.700677783122511e-05, "gradient_norm": 0.27951690554618835, "tokens_per_second": 1107818.9842657621, "synthetic": false, "world_size": 8}
30
  {"step": 600, "tokens": 314572800, "loss": 2.388660430908203, "optimizer_updates": 600, "effective_batch": 512, "lr": 4.409747188629462e-05, "gradient_norm": 0.2438564896583557, "tokens_per_second": 1153407.9864954299, "synthetic": false, "world_size": 8}
 
 
 
 
28
  {"step": 560, "tokens": 293601280, "loss": 2.3897640228271486, "optimizer_updates": 560, "effective_batch": 512, "lr": 4.99510361029238e-05, "gradient_norm": 0.24847784638404846, "tokens_per_second": 1152737.2337354836, "synthetic": false, "world_size": 8}
29
  {"step": 580, "tokens": 304087040, "loss": 2.3887601852416993, "optimizer_updates": 580, "effective_batch": 512, "lr": 4.700677783122511e-05, "gradient_norm": 0.27951690554618835, "tokens_per_second": 1107818.9842657621, "synthetic": false, "world_size": 8}
30
  {"step": 600, "tokens": 314572800, "loss": 2.388660430908203, "optimizer_updates": 600, "effective_batch": 512, "lr": 4.409747188629462e-05, "gradient_norm": 0.2438564896583557, "tokens_per_second": 1153407.9864954299, "synthetic": false, "world_size": 8}
31
+ {"step": 620, "tokens": 325058560, "loss": 2.3813013076782226, "optimizer_updates": 620, "effective_batch": 512, "lr": 4.123583992279283e-05, "gradient_norm": 0.3169904053211212, "tokens_per_second": 1156982.3159562275, "synthetic": false, "world_size": 8}
32
+ {"step": 640, "tokens": 335544320, "loss": 2.3803289413452147, "optimizer_updates": 640, "effective_batch": 512, "lr": 3.8434395129189505e-05, "gradient_norm": 0.27440863847732544, "tokens_per_second": 1153586.4761494203, "synthetic": false, "world_size": 8}
33
+ {"step": 660, "tokens": 346030080, "loss": 2.384285545349121, "optimizer_updates": 660, "effective_batch": 512, "lr": 3.570538751077433e-05, "gradient_norm": 0.2709105610847473, "tokens_per_second": 1153962.352711612, "synthetic": false, "world_size": 8}