Files
qwen3-1.7b-fft-if/train_results.json

8 lines
208 B
JSON
Raw Normal View History

{
"epoch": 2.0,
"total_flos": 2.312523470065369e+18,
"train_loss": 1.0307597314738572,
"train_runtime": 2075.8497,
"train_samples_per_second": 53.887,
"train_steps_per_second": 0.421
}