1 contributor

History: 20 commits

This model has 1 file scanned as unsafe.

lapp0

End of training

5d994a8 verified 5 months ago

attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=0, hs_weight=0, learning_rate=0.0004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=0, optim=p
Training in progress, step 6188 5 months ago
attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=0, hs_weight=0, learning_rate=0.0004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=1000, opti
Training in progress, step 773 5 months ago
attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=0, hs_weight=0, learning_rate=0.0004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, optim=paged_adamw_8bit, per
Training in progress, step 6188 5 months ago
attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=0, hs_weight=0, learning_rate=0.0004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, optim=paged_lion_32bit, per
Training in progress, step 6188 5 months ago
attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=0, hs_weight=0, learning_rate=0.004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=0, optim=pa
Training in progress, step 6188 5 months ago
attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=0, hs_weight=0, learning_rate=0.004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=1000, optim
Training in progress, step 773 5 months ago
attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=8, hs_loss_fn=0, hs_weight=0, learning_rate=0.0004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=0, optim=p
Training in progress, step 773 5 months ago
attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=8, hs_loss_fn=0, hs_weight=0, learning_rate=0.0004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=1000, opti
Training in progress, step 6188 5 months ago
attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=8, hs_loss_fn=0, hs_weight=0, learning_rate=0.004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=0, optim=pa
Training in progress, step 773 5 months ago
attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=8, hs_loss_fn=0, hs_weight=0, learning_rate=0.004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=1000, optim
End of training 5 months ago