Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
lapp0
/
distily_bench_gpt2_activation_loss
like
0
TensorBoard
Safetensors
Distily
gpt2
Generated from Trainer
8-bit precision
bitsandbytes
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
main
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
Aug 13