mistral_strategyqa_sft / train_results.json
weijie210's picture
Model save
5cb3d2f verified
raw
history blame contribute delete
193 Bytes
{
"epoch": 1.0,
"train_loss": 0.38626466322653363,
"train_runtime": 734.6882,
"train_samples": 1604,
"train_samples_per_second": 2.183,
"train_steps_per_second": 0.137
}