r1qw1.5B-sve-distill-r1_all / all_results.json
celinelee's picture
End of training
5ed00d9 verified
{
"epoch": 4.930232558139535,
"total_flos": 1.39778636906496e+16,
"train_loss": 0.7324335098266601,
"train_runtime": 1281.5831,
"train_samples_per_second": 0.336,
"train_steps_per_second": 0.039
}