qwen2_chat_adamw_iter7 / train_results.json
yiran-wang3's picture
End of training
65df5da verified
raw
history blame contribute delete
216 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.4990231822698544,
"train_runtime": 145.1235,
"train_samples": 2452,
"train_samples_per_second": 16.896,
"train_steps_per_second": 0.269
}