oh-dcft-v3.1-llama-3.1-405b / train_results.json
gsmyrnis's picture
End of training
9d13c68 verified
raw
history blame contribute delete
205 Bytes
{
"epoch": 3.0,
"total_flos": 2120597152727040.0,
"train_loss": 0.2836323574444317,
"train_runtime": 7986.5453,
"train_samples_per_second": 81.101,
"train_steps_per_second": 0.159
}