1 contributor

History: 17 commits

This model has 1 file scanned as unsafe.

lapp0

Training in progress, step 24750

43a1107 verified 3 months ago

distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_cakld_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_s
Training in progress, step 24750 3 months ago
distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_cross_entropy())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(f
Training in progress, step 24750 3 months ago
distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_jsd_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_sof
Training in progress, step 24750 3 months ago
distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__activations_weight_0.1__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_
Training in progress, step 24750 4 months ago
distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_
Training in progress, step 24750 4 months ago
distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__activations_weight_0.5__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_
Training in progress, step 24750 4 months ago
distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__activations_weight_0__activations_loss_fn_(fn_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_
Training in progress, step 24750 4 months ago
distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__activations_weight_0__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn
Training in progress, step 24750 4 months ago
distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_reverse_kl_divergence_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentio
Training in progress, step 24750 3 months ago
distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_soft_mse_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(f
Training in progress, step 24750 4 months ago