stackexchange_cstheory / all_results.json
sedrickkeh's picture
End of training
8b35fdb verified
raw
history blame contribute delete
357 Bytes
{
"epoch": 2.962566844919786,
"eval_loss": 0.9938156008720398,
"eval_runtime": 25.2096,
"eval_samples_per_second": 24.911,
"eval_steps_per_second": 0.397,
"total_flos": 115368190279680.0,
"train_loss": 1.057357843371405,
"train_runtime": 4374.2005,
"train_samples_per_second": 8.182,
"train_steps_per_second": 0.016
}