Files
Qwen1.5-MOE-sft-ESFT-intent/train_results.json

8 lines
218 B
JSON
Raw Normal View History

{
"total_flos": 1.0952542154391552e+17,
"train_loss": 0.13070940664814165,
"train_runtime": 1765.7438,
"train_samples": 7280,
"train_samples_per_second": 8.246,
"train_steps_per_second": 0.258
}