opt350m-qlora / all_results.json
zhangduo4610's picture
End of training
53f7e4d verified
raw
history blame contribute delete
415 Bytes
{
"epoch": 0.9999380306128772,
"eval_loss": 1.7868006229400635,
"eval_runtime": 207.2025,
"eval_samples": 23109,
"eval_samples_per_second": 68.913,
"eval_steps_per_second": 4.31,
"total_flos": 4248917998829568.0,
"train_loss": 1.863956661347298,
"train_runtime": 6909.389,
"train_samples": 207864,
"train_samples_per_second": 18.684,
"train_steps_per_second": 1.168
}