| [ |
| { |
| "step": 15500, |
| "val_loss": 1.2332948386669158, |
| "tok_per_s": 448.71070718611645 |
| }, |
| { |
| "step": 16000, |
| "val_loss": 1.3245196878910064, |
| "tok_per_s": 448.7678029095942 |
| }, |
| { |
| "step": 16500, |
| "val_loss": 1.1150229454040528, |
| "tok_per_s": 448.6196532024642 |
| }, |
| { |
| "step": 17000, |
| "val_loss": 1.2729529201984406, |
| "tok_per_s": 448.67497951718235 |
| }, |
| { |
| "step": 17500, |
| "val_loss": 1.4596619069576264, |
| "tok_per_s": 448.59215489049996 |
| }, |
| { |
| "step": 18000, |
| "val_loss": 1.1688364386558532, |
| "tok_per_s": 448.6222510800553 |
| }, |
| { |
| "step": 18000, |
| "train_loss": 1.3487612009048462, |
| "lr": 0.00036618364045870307, |
| "grad_norm": 0.34604644906931464 |
| }, |
| { |
| "step": 18500, |
| "val_loss": 1.2496637105941772, |
| "tok_per_s": 448.5615559629563 |
| }, |
| { |
| "step": 19000, |
| "val_loss": 1.2581392109394074, |
| "tok_per_s": 448.5842420987772 |
| }, |
| { |
| "step": 19500, |
| "val_loss": 1.2702396273612977, |
| "tok_per_s": 448.53713417595446 |
| }, |
| { |
| "step": 20000, |
| "val_loss": 1.2604210555553437, |
| "tok_per_s": 448.5645251286915 |
| }, |
| { |
| "step": 20500, |
| "val_loss": 1.2029548704624176, |
| "tok_per_s": 448.55135546547194 |
| }, |
| { |
| "step": 21000, |
| "val_loss": 1.1747850239276887, |
| "tok_per_s": 448.5514952802606 |
| }, |
| { |
| "step": 21000, |
| "train_loss": 1.0948173999786377, |
| "lr": 0.00021936163686749426, |
| "grad_norm": 0.3434591920738562 |
| }, |
| { |
| "step": 21500, |
| "val_loss": 1.151973706483841, |
| "tok_per_s": 448.5321764246468 |
| }, |
| { |
| "step": 22000, |
| "val_loss": 1.2406252056360245, |
| "tok_per_s": 448.5538931263004 |
| }, |
| { |
| "step": 22500, |
| "val_loss": 1.4019580364227295, |
| "tok_per_s": 448.52137279121513 |
| }, |
| { |
| "step": 23000, |
| "val_loss": 1.1993014097213746, |
| "tok_per_s": 448.5355570162402 |
| }, |
| { |
| "step": 23500, |
| "val_loss": 1.1249394536018371, |
| "tok_per_s": 448.51751414452775 |
| }, |
| { |
| "step": 24000, |
| "val_loss": 1.0788813531398773, |
| "tok_per_s": 448.5232277857164 |
| }, |
| { |
| "step": 24000, |
| "train_loss": 0.978234052658081, |
| "lr": 0.00010192068998515702, |
| "grad_norm": 0.36711832860966803 |
| }, |
| { |
| "step": 24500, |
| "val_loss": 1.1137298941612244, |
| "tok_per_s": 448.50620361324445 |
| }, |
| { |
| "step": 25000, |
| "val_loss": 1.2152933448553085, |
| "tok_per_s": 448.51861800640285 |
| }, |
| { |
| "step": 25500, |
| "val_loss": 1.1968701273202895, |
| "tok_per_s": 448.50543316114755 |
| }, |
| { |
| "step": 26000, |
| "val_loss": 1.2862209349870681, |
| "tok_per_s": 448.51639794143944 |
| }, |
| { |
| "step": 26500, |
| "val_loss": 1.1776897311210632, |
| "tok_per_s": 448.49371621448375 |
| }, |
| { |
| "step": 27000, |
| "val_loss": 1.3898986995220184, |
| "tok_per_s": 448.5057616047337 |
| }, |
| { |
| "step": 27000, |
| "train_loss": 0.987281084060669, |
| "lr": 2.6156122096850034e-05, |
| "grad_norm": 0.43130715447864404 |
| }, |
| { |
| "step": 27500, |
| "val_loss": 1.2164547741413116, |
| "tok_per_s": 448.50054071928116 |
| }, |
| { |
| "step": 28000, |
| "val_loss": 1.531364518404007, |
| "tok_per_s": 448.5084187749349 |
| }, |
| { |
| "step": 28500, |
| "val_loss": 1.0895077019929886, |
| "tok_per_s": 448.4949893963017 |
| }, |
| { |
| "step": 29000, |
| "val_loss": 1.1150718003511428, |
| "tok_per_s": 448.4911373769222 |
| }, |
| { |
| "step": 29500, |
| "val_loss": 1.1861544340848922, |
| "tok_per_s": 448.48317166289644 |
| }, |
| { |
| "step": 30000, |
| "val_loss": 1.0986640840768813, |
| "tok_per_s": 448.4938181301738 |
| }, |
| { |
| "step": 30000, |
| "train_loss": 1.1195892095565796, |
| "lr": 2.933889520218003e-12, |
| "grad_norm": 0.3072912989186937 |
| } |
| ] |