Qwen-14B-lora-pretrain / eval_results.json
ytcheng's picture
End of training
0102256 verified
raw
history blame contribute delete
212 Bytes
{
"epoch": 2.998264893001735,
"eval_loss": 2.0396180152893066,
"eval_runtime": 154.6591,
"eval_samples_per_second": 3.731,
"eval_steps_per_second": 3.731,
"perplexity": 7.687672064754986
}