Files
qwen3-1.7b-fft-math/all_results.json

8 lines
208 B
JSON
Raw Normal View History

{
"epoch": 2.0,
"total_flos": 1.2200945171646382e+18,
"train_loss": 0.2963919332032519,
"train_runtime": 3915.3376,
"train_samples_per_second": 30.649,
"train_steps_per_second": 0.24
}