distily_bench_gpt2_activation_loss / logs /distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__activations_weight_0.2__activations_loss_fn_(fn_mse_loss())__attentions_weight_0__attentions_loss_fn_(f

Commit History

Training in progress, step 24750
b618c80
verified

lapp0 commited on