Files
qwen3-4b-instruct-2507-full…/all_results.json

8 lines
207 B
JSON
Raw Normal View History

{
"epoch": 3.0,
"total_flos": 3.143410755085271e+17,
"train_loss": 0.2539728307061725,
"train_runtime": 24192.1432,
"train_samples_per_second": 0.237,
"train_steps_per_second": 0.03
}