pythia-410m-sft-full / train_results.json
DatPySci's picture
Model save
1b7574f verified
raw
history blame contribute delete
196 Bytes
{
"epoch": 1.0,
"train_loss": 1.6493343958478666,
"train_runtime": 16072.2247,
"train_samples": 207865,
"train_samples_per_second": 7.928,
"train_steps_per_second": 0.248
}