qwen2_coder_adamw_iter11 / all_results.json
yiran-wang3's picture
End of training
1905fc6 verified
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.4992363979419073,
"train_runtime": 128.0208,
"train_samples": 1882,
"train_samples_per_second": 14.701,
"train_steps_per_second": 0.234
}