SmolLM-1.7B-Instruct / eval_results.json
loubnabnl's picture
loubnabnl HF staff
End of training
6e74f71 verified
raw
history blame
587 Bytes
{
"epoch": 0.9872958257713249,
"eval_logits/chosen": 0.9550817608833313,
"eval_logits/rejected": 0.8631864190101624,
"eval_logps/chosen": -121.98506164550781,
"eval_logps/rejected": -149.43112182617188,
"eval_loss": 0.6671856641769409,
"eval_rewards/accuracies": 0.550000011920929,
"eval_rewards/chosen": -0.0465608611702919,
"eval_rewards/margins": 0.04670196771621704,
"eval_rewards/rejected": -0.09326283633708954,
"eval_runtime": 4.6203,
"eval_samples": 464,
"eval_samples_per_second": 100.425,
"eval_steps_per_second": 3.247
}