/projects/LOLA/large/250_checkpoints/global_step12000/

File Name  ↓ File Size  ↓ Date  ↓ 
Parent directory/--
zero_pp_rank_9_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_95_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_94_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_93_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_92_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_91_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_90_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_8_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_89_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_88_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_87_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_86_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_85_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_84_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_83_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_82_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_81_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_80_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_7_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_79_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_78_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_77_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_76_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_75_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_74_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_73_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_72_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_71_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_70_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_6_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_69_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_68_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_67_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_66_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_65_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_64_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_63_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_62_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_61_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_60_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_5_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_59_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_58_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_57_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_56_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_55_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_54_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_53_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_52_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_51_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_50_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_4_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_49_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_48_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_47_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_46_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_45_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_44_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_43_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_42_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_41_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_40_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_3_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_39_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_38_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_37_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_36_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_35_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_34_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_33_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_32_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_31_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_30_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_2_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_29_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_28_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_27_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_26_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_25_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_24_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_23_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_22_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_21_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_20_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_1_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_19_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_18_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_17_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_16_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_15_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_14_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_13_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_12_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_11_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_10_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
zero_pp_rank_0_mp_rank_00_optim_states.pt889.3 MiB2023-Nov-15 19:00
mp_rank_00_model_states.pt1.9 GiB2023-Nov-15 19:00
layer_9_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_9_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_8_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_7_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_6_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_5_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_4_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_3_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_2_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_1_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_11_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_10_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_9_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_8_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_7_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_6_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_5_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_4_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_15_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_14_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_13_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_12_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_11_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_10_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
layer_0_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-15 18:59
expp_rank_9_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_8_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_7_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_6_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_5_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_4_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_3_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_2_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_1_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_15_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_14_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_13_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_12_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_11_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_10_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59
expp_rank_0_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-15 18:59