Files
openthoughts3_100k_qwen25_1…/train_results.json

8 lines
220 B
JSON
Raw Normal View History

{
"epoch": 4.961636828644501,
"total_flos": 7065760181780480.0,
"train_loss": 1.1163312366328288,
"train_runtime": 42603.8864,
"train_samples_per_second": 11.736,
"train_steps_per_second": 0.011
}