Llama-8b-SimPO-Plus1-6-7 / train_results.json
Teng Xiao
TX
9154ce5
{
"epoch": 0.998691442030882,
"total_flos": 0.0,
"train_loss": 4.822632607948269e-06,
"train_runtime": 8193.4913,
"train_samples": 61135,
"train_samples_per_second": 7.461,
"train_steps_per_second": 0.058
}