Files
Qwen3-4B_Paper_Impact_datas…/all_results.json

12 lines
351 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"eval_loss": 0.08800426870584488,
"eval_runtime": 243.1299,
"eval_samples_per_second": 12.783,
"eval_steps_per_second": 0.403,
"total_flos": 2.587386052566057e+17,
"train_loss": 0.13282569709108838,
"train_runtime": 1624.0926,
"train_samples_per_second": 2.629,
"train_steps_per_second": 0.041
}