Files
qwen2.5-0.5b-instruct_gsm8k…/train_results.json

9 lines
241 B
JSON
Raw Permalink Normal View History

{
"epoch": 0.010036130068245684,
"total_flos": 7693271040.0,
"train_loss": 0.6475268173217773,
"train_runtime": 260.2772,
"train_samples": 7473,
"train_samples_per_second": 0.287,
"train_steps_per_second": 0.288
}