/projects/LOLA/archive/small/global_step56341/

File Name  ↓ File Size  ↓ Date  ↓ 
Parent directory/--
expp_rank_0_mp_rank_00_optim_states.pt1.0 KiB2023-Nov-13 02:42
layer_0_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_0_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_0_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_0_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_10_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_10_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_10_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_10_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_11_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_11_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_11_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_11_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_1_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_1_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_1_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_1_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_2_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_2_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_2_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_2_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_3_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_3_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_3_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_3_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_4_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_4_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_4_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_4_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_5_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_5_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_5_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_5_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_6_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_6_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_6_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_6_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_7_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_7_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_7_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_7_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_8_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_8_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_8_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_8_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_9_expert_0_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_9_expert_1_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_9_expert_2_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
layer_9_expert_3_mp_rank_00_model_states.pt64.0 MiB2023-Nov-13 02:42
mp_rank_00_model_states.pt1.7 GiB2023-Nov-13 02:42
zero_pp_rank_0_mp_rank_00_optim_states.pt7.1 GiB2023-Nov-13 02:42
zero_pp_rank_1_mp_rank_00_optim_states.pt7.1 GiB2023-Nov-13 02:42
zero_pp_rank_2_mp_rank_00_optim_states.pt7.1 GiB2023-Nov-13 21:46
zero_pp_rank_3_mp_rank_00_optim_states.pt7.1 GiB2023-Nov-13 21:50