lapp0
/

distily_bench_gpt2_activation_loss_b

Generated from Trainer

8-bit precision

Model card Files Files and versions Metrics Training metrics Community

distily_bench_gpt2_activation_loss_b / logs

1 contributor

History: 14 commits

This model has 1 file scanned as unsafe.

lapp0's picture

Training in progress, step 12375

5e015bc verified 3 months ago

hs_loss_fn=ce, hs_weight=2.0
Training in progress, step 12375 3 months ago
hs_loss_fn=cos, hs_weight=2.0
Training in progress, step 12375 3 months ago
hs_loss_fn=jsd, hs_weight=2.0
Training in progress, step 12375 3 months ago
hs_loss_fn=kl, hs_weight=2.0
Training in progress, step 12375 3 months ago
hs_loss_fn=mse, hs_weight=2.0
Training in progress, step 12375 3 months ago
hs_loss_fn=mse_sum, hs_weight=2.0
Training in progress, step 12375 3 months ago
hs_loss_fn=reverse_kl, hs_weight=2.0
Training in progress, step 12375 3 months ago
events.out.tfevents.1723650363.5f530b1cf724

6.35 kB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723650608.5f530b1cf724

7.34 kB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723650878.5f530b1cf724

11.7 kB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723651220.5f530b1cf724

5.96 kB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723651458.5f530b1cf724

5.96 kB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723651733.5f530b1cf724

3.35 MB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723655462.5f530b1cf724

520 Bytes
LFS

Training in progress, step 12375 3 months ago