opt-125m-sft / train_results.json
pkarypis's picture
Model save
5634571
{
"epoch": 1.0,
"train_loss": 2.0571069528934043,
"train_runtime": 132.1266,
"train_samples": 207865,
"train_samples_per_second": 977.055,
"train_steps_per_second": 1.915
}