Files
QWEN3-4B-CPT/train_results.json

8 lines
207 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 2.103177196962902e+18,
"train_loss": 1.7256613558986822,
"train_runtime": 29239.084,
"train_samples_per_second": 1.616,
"train_steps_per_second": 0.051
}