lapp0
/

distily_bench_gpt2_attn

Generated from Trainer

8-bit precision

Model card Files Files and versions Metrics Training metrics Community

distily_bench_gpt2_attn / logs

1 contributor

History: 13 commits

This model has 1 file scanned as unsafe.

lapp0's picture

End of training

f735c9d verified 3 months ago

attn_loss_fn=ce, attn_weight=2.0
End of training 3 months ago
attn_loss_fn=cos, attn_weight=2.0
Training in progress, step 12375 3 months ago
attn_loss_fn=jsd, attn_weight=2.0
Training in progress, step 12375 3 months ago
attn_loss_fn=kl, attn_weight=2.0
Training in progress, step 12375 3 months ago
attn_loss_fn=mse, attn_weight=2.0
Training in progress, step 12375 3 months ago
attn_loss_fn=mse_sum, attn_weight=2.0
Training in progress, step 12375 3 months ago
attn_loss_fn=reverse_kl, attn_weight=2.0
Training in progress, step 12375 3 months ago
events.out.tfevents.1723651220.93d6cbb3ad53

5.91 kB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723651454.93d6cbb3ad53

5.91 kB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723651737.93d6cbb3ad53

196 kB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723652161.93d6cbb3ad53

5.91 kB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723652404.93d6cbb3ad53

3.35 MB
LFS

Training in progress, step 12375 3 months ago
events.out.tfevents.1723656174.93d6cbb3ad53

520 Bytes
LFS

Training in progress, step 12375 3 months ago