End of training
60db291 verified - attn_loss_fn=cos, attn_weight=10.0, projector=ensemble Training in progress, step 61875
- attn_loss_fn=cos, attn_weight=10.0, projector=identity End of training
- attn_loss_fn=cos, attn_weight=10.0, projector=linear Training in progress, step 61875
- attn_loss_fn=cos, attn_weight=10.0, projector=mlp End of training
- attn_loss_fn=cos, attn_weight=10.0, projector=orthogonal Training in progress, step 61875
- attn_loss_fn=raw_mse, attn_weight=10.0, projector=ensemble Training in progress, step 61875
- attn_loss_fn=raw_mse, attn_weight=10.0, projector=identity Training in progress, step 61875
- attn_loss_fn=raw_mse, attn_weight=10.0, projector=linear Training in progress, step 61875
- attn_loss_fn=raw_mse, attn_weight=10.0, projector=mlp Training in progress, step 61875
- attn_loss_fn=raw_mse, attn_weight=10.0, projector=orthogonal Training in progress, step 61875
- projector=linear Training in progress, step 61875
- projector=orthogonal Training in progress, step 61875
