qwen2.5-0.5b-expo-DPO-ES-TRY / all_results.json
hZzy's picture
End of training
f1d9b8b verified
raw
history blame contribute delete
802 Bytes
{
"epoch": 0.8502598016060463,
"eval_dpo_loss": 0.6618562340736389,
"eval_dpo_wo_beta": -2.3796472549438477,
"eval_logits": -2.269749641418457,
"eval_logps": -89.50890350341797,
"eval_loss": 0.6810693740844727,
"eval_objective": 0.6618562340736389,
"eval_ranking_idealized": 0.6045548915863037,
"eval_ranking_idealized_expo": 0.5279502868652344,
"eval_ranking_simple": 0.5734989643096924,
"eval_regularize": 0.6618562340736389,
"eval_runtime": 316.8985,
"eval_samples": 5790,
"eval_samples_per_second": 18.271,
"eval_steps_per_second": 1.524,
"total_flos": 0.0,
"train_loss": 0.15444423039754232,
"train_runtime": 3628.8607,
"train_samples": 50802,
"train_samples_per_second": 41.998,
"train_steps_per_second": 0.583
}