Files
HT-phase_scale-Qwen-140k-ph…/train_results.json

8 lines
207 B
JSON
Raw Normal View History

{
"epoch": 3.0,
"total_flos": 1943508983758848.0,
"train_loss": 0.34943878727318023,
"train_runtime": 212376.9169,
"train_samples_per_second": 1.533,
"train_steps_per_second": 0.064
}