MNC-LLM/batch1_epochs4_lr1e-06_paged_adamw_32bit_cosine_length2048_warmup_0.05_max_grad1.0_grad_accu16 Text Generation • Updated Nov 20, 2023 • 10
MNC-LLM/batch1_epochs4_lr0.0001_paged_adamw_32bit_cosine_length2048_warmup_0.05_max_grad1.0_grad_accu16 Text Generation • Updated Nov 20, 2023 • 10