Files
Qwen2.5-Coder-14B-Instruct-…/all_results.json

8 lines
205 B
JSON
Raw Normal View History

{
"epoch": 2.0,
"total_flos": 456031784665088.0,
"train_loss": 0.26182658547373117,
"train_runtime": 16760.0523,
"train_samples_per_second": 0.386,
"train_steps_per_second": 0.064
}