qwen2.5-0.5b-expo-DPO-ES-TRY3 / all_results.json
hZzy's picture
End of training
a777d66 verified
raw
history blame contribute delete
803 Bytes
{
"epoch": 2.9976381672177608,
"eval_dpo_loss": 0.8311848640441895,
"eval_dpo_wo_beta": -5.360922813415527,
"eval_logits": -2.4477622509002686,
"eval_logps": -120.05928802490234,
"eval_loss": 0.8143295049667358,
"eval_objective": 0.8311848640441895,
"eval_ranking_idealized": 0.6045548915863037,
"eval_ranking_idealized_expo": 0.5279502868652344,
"eval_ranking_simple": 0.5838509202003479,
"eval_regularize": 0.8311848640441895,
"eval_runtime": 380.4449,
"eval_samples": 5790,
"eval_samples_per_second": 15.219,
"eval_steps_per_second": 1.27,
"total_flos": 0.0,
"train_loss": 0.022545777056648425,
"train_runtime": 4386.5835,
"train_samples": 50802,
"train_samples_per_second": 34.744,
"train_steps_per_second": 0.241
}