qwen2_coder_adamw_iter5 / train_results.json
yiran-wang3's picture
End of training
f607847 verified
raw
history blame contribute delete
216 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.4980396749200048,
"train_runtime": 139.9378,
"train_samples": 2345,
"train_samples_per_second": 16.757,
"train_steps_per_second": 0.264
}