oh-dcft-v3.1-llama-3.1-405b / all_results.json
gsmyrnis's picture
End of training
9d13c68 verified
raw
history blame contribute delete
348 Bytes
{
"epoch": 3.0,
"eval_loss": 0.30088362097740173,
"eval_runtime": 40.4677,
"eval_samples_per_second": 280.817,
"eval_steps_per_second": 1.112,
"total_flos": 2120597152727040.0,
"train_loss": 0.2836323574444317,
"train_runtime": 7986.5453,
"train_samples_per_second": 81.101,
"train_steps_per_second": 0.159
}