Files
qwen3-8b-base-sft-ultrachat…/all_results.json

14 lines
420 B
JSON
Raw Permalink Normal View History

{
"epoch": 0.9994722955145119,
"eval_loss": 1.084205985069275,
"eval_runtime": 268.589,
"eval_samples": 23109,
"eval_samples_per_second": 49.954,
"eval_steps_per_second": 0.782,
"total_flos": 2.8182891025525637e+18,
"train_loss": 1.100929617000608,
"train_runtime": 11309.6924,
"train_samples": 207864,
"train_samples_per_second": 10.721,
"train_steps_per_second": 0.084
}