Hyperparameters in Continual Learning: a Reality Check Paper • 2403.09066 • Published Mar 14, 2024 • 1
Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs Paper • 2408.06621 • Published Aug 13, 2024 • 3
csm9493/67_five_dataset_shuffle_10000_fewshot_lora_all_r16_alpha32_lr_1e5_decay_1e2_cosine_epoch_3_mbs_4 Text Generation • Updated Mar 6
csm9493/67_five_dataset_shuffle_10000_fewshot_lora_all_r16_alpha32_lr_1e5_decay_1e2_cosine_epoch_3_mbs_4 Text Generation • Updated Mar 6
csm9493/26_one_dataset_cot_lora_all_r16_alpha32_lr_3e5_decay_1e2_cosine_epoch_3_mbs_4 Text Generation • Updated Mar 5 • 12
csm9493/26_one_dataset_cot_lora_all_r16_alpha32_lr_3e5_decay_1e2_cosine_epoch_3_mbs_4 Text Generation • Updated Mar 5 • 12
csm9493/43_five_dataset_shuffle_10000_cot_lora_all_r4_alpha8_lr_1e-05_decay_1e2_cosine_epoch_3_mbs_16 Text Generation • Updated Mar 5 • 11
csm9493/43_five_dataset_shuffle_10000_cot_lora_all_r32_alpha64_lr_1e-05_decay_1e2_cosine_epoch_3_mbs_16 Text Generation • Updated Mar 5 • 12
csm9493/43_five_dataset_shuffle_10000_cot_lora_all_r8_alpha16_lr_1e-05_decay_1e2_cosine_epoch_3_mbs_16 Text Generation • Updated Mar 5 • 12
csm9493/43_five_dataset_shuffle_10000_cot_lora_all_r16_alpha32_lr_1e-05_decay_1e2_cosine_epoch_3_mbs_16 Text Generation • Updated Mar 5 • 12
csm9493/43_five_dataset_shuffle_10000_cot_lora_all_r32_alpha64_lr_1e-05_decay_1e2_cosine_epoch_3_mbs_16 Text Generation • Updated Mar 5 • 12
csm9493/43_five_dataset_shuffle_10000_cot_lora_all_r4_alpha8_lr_1e-05_decay_1e2_cosine_epoch_3_mbs_16 Text Generation • Updated Mar 5 • 11
csm9493/43_five_dataset_shuffle_10000_cot_lora_all_r8_alpha16_lr_1e-05_decay_1e2_cosine_epoch_3_mbs_16 Text Generation • Updated Mar 5 • 12
csm9493/43_five_dataset_shuffle_10000_cot_lora_all_r16_alpha32_lr_1e-05_decay_1e2_cosine_epoch_3_mbs_16 Text Generation • Updated Mar 5 • 12
csm9493/24_three_dataset_shuffle_50000_cot_lora_all_r16_alpha32_lr_3e5_decay_1e2_cosine_epoch_2_mbs_4 Text Generation • Updated Mar 5 • 12
csm9493/24_three_dataset_shuffle_50000_cot_lora_all_r16_alpha32_lr_3e5_decay_1e2_cosine_epoch_2_mbs_4 Text Generation • Updated Mar 5 • 12
csm9493/41_three_dataset_shuffle_3200_cot_lora_all_r128_alpha256_lr_3e5_decay_1e2_cosine_epoch_3_mbs_4 Text Generation • Updated Mar 5 • 13
csm9493/41_three_dataset_shuffle_3200_cot_lora_all_r128_alpha256_lr_3e5_decay_1e2_cosine_epoch_3_mbs_4 Text Generation • Updated Mar 5 • 13
csm9493/23_one_dataset_cot_lora_all_r16_alpha32_lr_3e5_decay_1e2_cosine_epoch_2_mbs_4 Text Generation • Updated Mar 5 • 15
csm9493/23_one_dataset_cot_lora_all_r16_alpha32_lr_3e5_decay_1e2_cosine_epoch_2_mbs_4 Text Generation • Updated Mar 5 • 15