kacperwikiel commited on
Commit
a6a2446
·
verified ·
1 Parent(s): 11a02a7

Update experiment measurements and status

Browse files
reports/runs/cosmopedia-1337/metrics.jsonl CHANGED
@@ -20,3 +20,10 @@
20
  {"step": 400, "tokens": 209715200, "loss": 2.396107482910156, "optimizer_updates": 400, "effective_batch": 512, "lr": 7.321247334126042e-05, "gradient_norm": 0.27794092893600464, "tokens_per_second": 1121810.068137278, "synthetic": false, "world_size": 8}
21
  {"step": 420, "tokens": 220200960, "loss": 2.3919651031494142, "optimizer_updates": 420, "effective_batch": 512, "lr": 7.045303993926625e-05, "gradient_norm": 0.26575157046318054, "tokens_per_second": 1124573.6146211408, "synthetic": false, "world_size": 8}
22
  {"step": 440, "tokens": 230686720, "loss": 2.3904817581176756, "optimizer_updates": 440, "effective_batch": 512, "lr": 6.762603432545125e-05, "gradient_norm": 0.28393495082855225, "tokens_per_second": 1126782.1060190077, "synthetic": false, "world_size": 8}
 
 
 
 
 
 
 
 
20
  {"step": 400, "tokens": 209715200, "loss": 2.396107482910156, "optimizer_updates": 400, "effective_batch": 512, "lr": 7.321247334126042e-05, "gradient_norm": 0.27794092893600464, "tokens_per_second": 1121810.068137278, "synthetic": false, "world_size": 8}
21
  {"step": 420, "tokens": 220200960, "loss": 2.3919651031494142, "optimizer_updates": 420, "effective_batch": 512, "lr": 7.045303993926625e-05, "gradient_norm": 0.26575157046318054, "tokens_per_second": 1124573.6146211408, "synthetic": false, "world_size": 8}
22
  {"step": 440, "tokens": 230686720, "loss": 2.3904817581176756, "optimizer_updates": 440, "effective_batch": 512, "lr": 6.762603432545125e-05, "gradient_norm": 0.28393495082855225, "tokens_per_second": 1126782.1060190077, "synthetic": false, "world_size": 8}
23
+ {"step": 460, "tokens": 241172480, "loss": 2.3946918487548827, "optimizer_updates": 460, "effective_batch": 512, "lr": 6.47438182760683e-05, "gradient_norm": 0.29107579588890076, "tokens_per_second": 1130074.1232914953, "synthetic": false, "world_size": 8}
24
+ {"step": 480, "tokens": 251658240, "loss": 2.3843244552612304, "optimizer_updates": 480, "effective_batch": 512, "lr": 6.181899498855732e-05, "gradient_norm": 0.2595916986465454, "tokens_per_second": 1124637.4546975615, "synthetic": false, "world_size": 8}
25
+ {"step": 500, "tokens": 262144000, "loss": 2.394647789001465, "optimizer_updates": 500, "effective_batch": 512, "lr": 5.886435397096976e-05, "gradient_norm": 0.27273863554000854, "tokens_per_second": 1076211.2182420213, "synthetic": false, "world_size": 8}
26
+ {"step": 520, "tokens": 272629760, "loss": 2.400488090515137, "optimizer_updates": 520, "effective_batch": 512, "lr": 5.5892815116703924e-05, "gradient_norm": 0.31095069646835327, "tokens_per_second": 1005200.8233398844, "synthetic": false, "world_size": 8}
27
+ {"step": 540, "tokens": 283115520, "loss": 2.389276313781738, "optimizer_updates": 540, "effective_batch": 512, "lr": 5.291737220909842e-05, "gradient_norm": 0.2699156105518341, "tokens_per_second": 1129489.666544267, "synthetic": false, "world_size": 8}
28
+ {"step": 560, "tokens": 293601280, "loss": 2.387331962585449, "optimizer_updates": 560, "effective_batch": 512, "lr": 4.99510361029238e-05, "gradient_norm": 0.2779010236263275, "tokens_per_second": 1132375.376437183, "synthetic": false, "world_size": 8}
29
+ {"step": 580, "tokens": 304087040, "loss": 2.3826004028320313, "optimizer_updates": 580, "effective_batch": 512, "lr": 4.700677783122511e-05, "gradient_norm": 0.25527524948120117, "tokens_per_second": 1132925.6923327644, "synthetic": false, "world_size": 8}