Files
qwen3-1.7b-fft-coding/qwen3_1.7b_coding_fft_20260429_153746.log
ModelHub XC 7d4564573e 初始化项目,由ModelHub XC社区提供模型
Model: KKHYA/qwen3-1.7b-fft-coding
Source: Original Platform
2026-06-16 06:52:16 +08:00

1343 lines
822 KiB
Plaintext

==== STARTING EXPERIMENT: qwen3_1.7b_coding_fft ====
Log File: saves/qwen3_1.7b/coding/fft/qwen3_1.7b_coding_fft_20260429_153746.log
HF Hub: https://huggingface.co/KKHYA/qwen3-1.7b-fft-coding
Timestamp: 2026-04-29 15:37:46
=====================================
[INFO|2026-04-29 15:37:53] llamafactory.launcher:144 >> Initializing 8 distributed tasks at: 127.0.0.1:52079
W0429 15:37:54.558000 213610 site-packages/torch/distributed/run.py:852]
W0429 15:37:54.558000 213610 site-packages/torch/distributed/run.py:852] *****************************************
W0429 15:37:54.558000 213610 site-packages/torch/distributed/run.py:852] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0429 15:37:54.558000 213610 site-packages/torch/distributed/run.py:852] *****************************************
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
[W429 15:38:05.608586790 ProcessGroupNCCL.cpp:929] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
[W429 15:38:06.629331375 ProcessGroupNCCL.cpp:929] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
[W429 15:38:06.637811309 ProcessGroupNCCL.cpp:929] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
[W429 15:38:06.648209810 ProcessGroupNCCL.cpp:929] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
[W429 15:38:06.740148869 ProcessGroupNCCL.cpp:929] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
[W429 15:38:06.830497944 ProcessGroupNCCL.cpp:929] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO ENV/Plugin: Could not find: libnccl-env.so
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Bootstrap: Using eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO cudaDriverVersion 13000
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO NCCL version 2.28.9+cuda13.0
[W429 15:38:06.840813307 ProcessGroupNCCL.cpp:929] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
[W429 15:38:06.954907523 ProcessGroupNCCL.cpp:929] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO ENV/Plugin: Could not find: libnccl-env.so
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO cudaDriverVersion 13000
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Bootstrap: Using eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO NCCL version 2.28.9+cuda13.0
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO ENV/Plugin: Could not find: libnccl-env.so
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO cudaDriverVersion 13000
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Bootstrap: Using eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO NCCL version 2.28.9+cuda13.0
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO ENV/Plugin: Could not find: libnccl-env.so
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO cudaDriverVersion 13000
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Bootstrap: Using eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO NCCL version 2.28.9+cuda13.0
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO ENV/Plugin: Could not find: libnccl-env.so
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO cudaDriverVersion 13000
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO ENV/Plugin: Could not find: libnccl-env.so
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO cudaDriverVersion 13000
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Bootstrap: Using eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO NCCL version 2.28.9+cuda13.0
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Bootstrap: Using eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO NCCL version 2.28.9+cuda13.0
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO ENV/Plugin: Could not find: libnccl-env.so
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO cudaDriverVersion 13000
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Bootstrap: Using eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO NCCL version 2.28.9+cuda13.0
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO ENV/Plugin: Could not find: libnccl-env.so
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO cudaDriverVersion 13000
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Bootstrap: Using eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO NCCL version 2.28.9+cuda13.0
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO NET/Plugin: Loaded net plugin Libfabric (v10)
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Successfully loaded external network plugin /opt/amazon/ofi-nccl/lib/libnccl-net.so
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO NET/Socket : Using [0]eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO ncclCommInitRankConfig comm 0x55cadade89e0 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId 901d0 commId 0xc429a426e310f46d - Init START
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO NET/Plugin: Loaded net plugin Libfabric (v10)
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Successfully loaded external network plugin /opt/amazon/ofi-nccl/lib/libnccl-net.so
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO NET/Socket : Using [0]eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO ncclCommInitRankConfig comm 0x55ec9c119990 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId 201c0 commId 0xc429a426e310f46d - Init START
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO NET/Plugin: Loaded net plugin Libfabric (v10)
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Successfully loaded external network plugin /opt/amazon/ofi-nccl/lib/libnccl-net.so
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO NET/Socket : Using [0]eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO NET/Plugin: Loaded net plugin Libfabric (v10)
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Successfully loaded external network plugin /opt/amazon/ofi-nccl/lib/libnccl-net.so
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO NET/Socket : Using [0]eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO ncclCommInitRankConfig comm 0x5616b5c85c30 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId 201d0 commId 0xc429a426e310f46d - Init START
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO NET/Plugin: Loaded net plugin Libfabric (v10)
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Successfully loaded external network plugin /opt/amazon/ofi-nccl/lib/libnccl-net.so
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO NET/Socket : Using [0]eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO ncclCommInitRankConfig comm 0x55e5dac15dd0 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId a01d0 commId 0xc429a426e310f46d - Init START
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO NET/Plugin: Loaded net plugin Libfabric (v10)
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Successfully loaded external network plugin /opt/amazon/ofi-nccl/lib/libnccl-net.so
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO NET/Socket : Using [0]eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO NET/Plugin: Loaded net plugin Libfabric (v10)
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Successfully loaded external network plugin /opt/amazon/ofi-nccl/lib/libnccl-net.so
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO NET/Socket : Using [0]eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO ncclCommInitRankConfig comm 0x5635e92c0280 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 101c0 commId 0xc429a426e310f46d - Init START
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO ncclCommInitRankConfig comm 0x55e8675b14b0 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId a01c0 commId 0xc429a426e310f46d - Init START
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO RAS client listening socket at ::1<28028>
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO RAS client listening socket at ::1<28028>
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO ncclCommInitRankConfig comm 0x55cfd20e4910 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId 901c0 commId 0xc429a426e310f46d - Init START
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO RAS client listening socket at ::1<28028>
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO RAS client listening socket at ::1<28028>
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO RAS client listening socket at ::1<28028>
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO NET/Plugin: Loaded net plugin Libfabric (v10)
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Successfully loaded external network plugin /opt/amazon/ofi-nccl/lib/libnccl-net.so
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO NCCL_SOCKET_IFNAME set by environment to eth
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO NET/Socket : Using [0]eth0:10.200.170.96<0>
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO ncclCommInitRankConfig comm 0x55730064a610 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 101d0 commId 0xc429a426e310f46d - Init START
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO RAS client listening socket at ::1<28028>
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO RAS client listening socket at ::1<28028>
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO RAS client listening socket at ::1<28028>
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Bootstrap timings total 0.001004 (create 0.000039, send 0.000071, recv 0.000267, ring 0.000237, delay 0.000001)
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Bootstrap timings total 0.042826 (create 0.000049, send 0.000085, recv 0.041999, ring 0.000241, delay 0.000001)
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Bootstrap timings total 0.125366 (create 0.000051, send 0.000084, recv 0.029081, ring 0.000139, delay 0.000001)
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Bootstrap timings total 0.083669 (create 0.000045, send 0.000077, recv 0.041036, ring 0.027744, delay 0.000001)
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Bootstrap timings total 0.028635 (create 0.000045, send 0.000066, recv 0.000283, ring 0.027747, delay 0.000002)
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Bootstrap timings total 0.023624 (create 0.000037, send 0.000067, recv 0.000181, ring 0.022940, delay 0.000001)
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Bootstrap timings total 0.096532 (create 0.000055, send 0.000091, recv 0.072971, ring 0.022947, delay 0.000001)
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Bootstrap timings total 0.167438 (create 0.000064, send 0.000211, recv 0.138854, ring 0.022860, delay 0.000001)
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 1 is 0-23,48-71. (GPU affinity = 0-23,48-71 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO NVLS multicast support is not available on dev 1 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 2 is 0-23,48-71. (GPU affinity = 0-23,48-71 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO NVLS multicast support is not available on dev 2 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 4 is 24-47,72-95. (GPU affinity = 24-47,72-95 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO NVLS multicast support is not available on dev 4 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 0 is 0-23,48-71. (GPU affinity = 0-23,48-71 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO NVLS multicast support is not available on dev 0 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 7 is 24-47,72-95. (GPU affinity = 24-47,72-95 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO NVLS multicast support is not available on dev 7 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 5 is 24-47,72-95. (GPU affinity = 24-47,72-95 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO NVLS multicast support is not available on dev 5 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 6 is 24-47,72-95. (GPU affinity = 24-47,72-95 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO NVLS multicast support is not available on dev 6 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 3 is 0-23,48-71. (GPU affinity = 0-23,48-71 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO NVLS multicast support is not available on dev 3 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO comm 0x55730064a610 rank 1 nRanks 8 nNodes 1 localRanks 8 localRank 1 MNNVL 0
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO comm 0x5635e92c0280 rank 0 nRanks 8 nNodes 1 localRanks 8 localRank 0 MNNVL 0
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO comm 0x55e5dac15dd0 rank 7 nRanks 8 nNodes 1 localRanks 8 localRank 7 MNNVL 0
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO comm 0x55e8675b14b0 rank 6 nRanks 8 nNodes 1 localRanks 8 localRank 6 MNNVL 0
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO comm 0x55cadade89e0 rank 5 nRanks 8 nNodes 1 localRanks 8 localRank 5 MNNVL 0
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO comm 0x55ec9c119990 rank 2 nRanks 8 nNodes 1 localRanks 8 localRank 2 MNNVL 0
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO comm 0x5616b5c85c30 rank 3 nRanks 8 nNodes 1 localRanks 8 localRank 3 MNNVL 0
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO comm 0x55cfd20e4910 rank 4 nRanks 8 nNodes 1 localRanks 8 localRank 4 MNNVL 0
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 00/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 01/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 02/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 03/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 04/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 05/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 06/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 07/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/-1/-1->1->0 [2] 2/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->0 [10] 2/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0 [16] 2/-1/-1->1->0 [17] 2/-1/-1->1->0 [18] 2/-1/-1->1->0 [19] 2/-1/-1->1->0 [20] 2/-1/-1->1->0 [21] 2/-1/-1->1->0 [22] 2/-1/-1->1->0 [23] 2/-1/-1->1->0
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 08/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] -1/-1/-1->7->6 [2] -1/-1/-1->7->6 [3] -1/-1/-1->7->6 [4] -1/-1/-1->7->6 [5] -1/-1/-1->7->6 [6] -1/-1/-1->7->6 [7] -1/-1/-1->7->6 [8] -1/-1/-1->7->6 [9] -1/-1/-1->7->6 [10] -1/-1/-1->7->6 [11] -1/-1/-1->7->6 [12] -1/-1/-1->7->6 [13] -1/-1/-1->7->6 [14] -1/-1/-1->7->6 [15] -1/-1/-1->7->6 [16] -1/-1/-1->7->6 [17] -1/-1/-1->7->6 [18] -1/-1/-1->7->6 [19] -1/-1/-1->7->6 [20] -1/-1/-1->7->6 [21] -1/-1/-1->7->6 [22] -1/-1/-1->7->6 [23] -1/-1/-1->7->6
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/-1/-1->6->5 [7] 7/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->5 [15] 7/-1/-1->6->5 [16] 7/-1/-1->6->5 [17] 7/-1/-1->6->5 [18] 7/-1/-1->6->5 [19] 7/-1/-1->6->5 [20] 7/-1/-1->6->5 [21] 7/-1/-1->6->5 [22] 7/-1/-1->6->5 [23] 7/-1/-1->6->5
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/-1/-1->5->4 [6] 6/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->4 [14] 6/-1/-1->5->4 [15] 6/-1/-1->5->4 [16] 6/-1/-1->5->4 [17] 6/-1/-1->5->4 [18] 6/-1/-1->5->4 [19] 6/-1/-1->5->4 [20] 6/-1/-1->5->4 [21] 6/-1/-1->5->4 [22] 6/-1/-1->5->4 [23] 6/-1/-1->5->4
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 09/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/-1/-1->3->2 [4] 4/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->2 [12] 4/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2 [16] 4/-1/-1->3->2 [17] 4/-1/-1->3->2 [18] 4/-1/-1->3->2 [19] 4/-1/-1->3->2 [20] 4/-1/-1->3->2 [21] 4/-1/-1->3->2 [22] 4/-1/-1->3->2 [23] 4/-1/-1->3->2
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/-1/-1->2->1 [3] 3/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->1 [11] 3/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1 [16] 3/-1/-1->2->1 [17] 3/-1/-1->2->1 [18] 3/-1/-1->2->1 [19] 3/-1/-1->2->1 [20] 3/-1/-1->2->1 [21] 3/-1/-1->2->1 [22] 3/-1/-1->2->1 [23] 3/-1/-1->2->1
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 10/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/-1/-1->4->3 [5] 5/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->3 [13] 5/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3 [16] 5/-1/-1->4->3 [17] 5/-1/-1->4->3 [18] 5/-1/-1->4->3 [19] 5/-1/-1->4->3 [20] 5/-1/-1->4->3 [21] 5/-1/-1->4->3 [22] 5/-1/-1->4->3 [23] 5/-1/-1->4->3
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 11/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 12/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 13/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 14/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 15/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 16/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 17/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 18/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 19/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 20/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 21/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 22/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 23/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Trees [0] 1/-1/-1->0->-1 [1] 1/-1/-1->0->-1 [2] 1/-1/-1->0->-1 [3] 1/-1/-1->0->-1 [4] 1/-1/-1->0->-1 [5] 1/-1/-1->0->-1 [6] 1/-1/-1->0->-1 [7] 1/-1/-1->0->-1 [8] 1/-1/-1->0->-1 [9] 1/-1/-1->0->-1 [10] 1/-1/-1->0->-1 [11] 1/-1/-1->0->-1 [12] 1/-1/-1->0->-1 [13] 1/-1/-1->0->-1 [14] 1/-1/-1->0->-1 [15] 1/-1/-1->0->-1 [16] 1/-1/-1->0->-1 [17] 1/-1/-1->0->-1 [18] 1/-1/-1->0->-1 [19] 1/-1/-1->0->-1 [20] 1/-1/-1->0->-1 [21] 1/-1/-1->0->-1 [22] 1/-1/-1->0->-1 [23] 1/-1/-1->0->-1
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213684:214061 [0] NCCL INFO [Proxy Service UDS] Device 3 CPU core 6
ywang29-p4d-debug-1-worker-0:213684:214060 [0] NCCL INFO [Proxy Service] Device 3 CPU core 50
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213686:214062 [0] NCCL INFO [Proxy Service] Device 5 CPU core 27
ywang29-p4d-debug-1-worker-0:213686:214063 [0] NCCL INFO [Proxy Service UDS] Device 5 CPU core 30
ywang29-p4d-debug-1-worker-0:213688:214064 [0] NCCL INFO [Proxy Service] Device 7 CPU core 83
ywang29-p4d-debug-1-worker-0:213688:214065 [0] NCCL INFO [Proxy Service UDS] Device 7 CPU core 33
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213682:214067 [0] NCCL INFO [Proxy Service UDS] Device 1 CPU core 3
ywang29-p4d-debug-1-worker-0:213682:214066 [0] NCCL INFO [Proxy Service] Device 1 CPU core 64
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213681:214068 [0] NCCL INFO [Proxy Service] Device 0 CPU core 63
ywang29-p4d-debug-1-worker-0:213681:214069 [0] NCCL INFO [Proxy Service UDS] Device 0 CPU core 4
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213685:214070 [0] NCCL INFO [Proxy Service] Device 4 CPU core 89
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so
ywang29-p4d-debug-1-worker-0:213685:214071 [0] NCCL INFO [Proxy Service UDS] Device 4 CPU core 32
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213683:214072 [0] NCCL INFO [Proxy Service] Device 2 CPU core 12
ywang29-p4d-debug-1-worker-0:213683:214073 [0] NCCL INFO [Proxy Service UDS] Device 2 CPU core 14
ywang29-p4d-debug-1-worker-0:213687:214074 [0] NCCL INFO [Proxy Service] Device 6 CPU core 87
ywang29-p4d-debug-1-worker-0:213687:214075 [0] NCCL INFO [Proxy Service UDS] Device 6 CPU core 95
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO TUNER/Plugin: Using nccl_ofi_tuner (v3)
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO TUNER/Plugin: Using nccl_ofi_tuner (v3)
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO TUNER/Plugin: Using nccl_ofi_tuner (v3)
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO TUNER/Plugin: Using nccl_ofi_tuner (v3)
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO CC Off, workFifoBytes 1048576
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO TUNER/Plugin: Using nccl_ofi_tuner (v3)
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO TUNER/Plugin: Using nccl_ofi_tuner (v3)
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO TUNER/Plugin: Using nccl_ofi_tuner (v3)
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO TUNER/Plugin: Using nccl_ofi_tuner (v3)
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO ncclCommInitRankConfig comm 0x55e5dac15dd0 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId a01d0 commId 0xc429a426e310f46d - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO ncclCommInitRankConfig comm 0x5616b5c85c30 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId 201d0 commId 0xc429a426e310f46d - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO ncclCommInitRankConfig comm 0x55cadade89e0 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId 901d0 commId 0xc429a426e310f46d - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO ncclCommInitRankConfig comm 0x5635e92c0280 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 101c0 commId 0xc429a426e310f46d - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO ncclCommInitRankConfig comm 0x55cfd20e4910 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId 901c0 commId 0xc429a426e310f46d - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO ncclCommInitRankConfig comm 0x55730064a610 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 101d0 commId 0xc429a426e310f46d - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Init timings - ncclCommInitRankConfig: rank 3 nranks 8 total 0.44 (kernels 0.18, alloc 0.03, bootstrap 0.10, allgathers 0.00, topo 0.04, graphs 0.00, connections 0.06, rest 0.02)
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Init timings - ncclCommInitRankConfig: rank 7 nranks 8 total 0.43 (kernels 0.19, alloc 0.03, bootstrap 0.08, allgathers 0.01, topo 0.04, graphs 0.00, connections 0.06, rest 0.03)
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Init timings - ncclCommInitRankConfig: rank 5 nranks 8 total 0.50 (kernels 0.18, alloc 0.03, bootstrap 0.17, allgathers 0.01, topo 0.04, graphs 0.00, connections 0.06, rest 0.03)
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Init timings - ncclCommInitRankConfig: rank 0 nranks 8 total 0.40 (kernels 0.18, alloc 0.05, bootstrap 0.04, allgathers 0.01, topo 0.04, graphs 0.00, connections 0.05, rest 0.03)
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Init timings - ncclCommInitRankConfig: rank 4 nranks 8 total 0.43 (kernels 0.23, alloc 0.05, bootstrap 0.02, allgathers 0.01, topo 0.04, graphs 0.00, connections 0.06, rest 0.03)
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Init timings - ncclCommInitRankConfig: rank 1 nranks 8 total 0.38 (kernels 0.23, alloc 0.02, bootstrap 0.00, allgathers 0.01, topo 0.03, graphs 0.00, connections 0.04, rest 0.05)
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO ncclCommInitRankConfig comm 0x55e8675b14b0 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId a01c0 commId 0xc429a426e310f46d - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO ncclCommInitRankConfig comm 0x55ec9c119990 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId 201c0 commId 0xc429a426e310f46d - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Init timings - ncclCommInitRankConfig: rank 6 nranks 8 total 0.40 (kernels 0.19, alloc 0.05, bootstrap 0.03, allgathers 0.01, topo 0.04, graphs 0.00, connections 0.06, rest 0.03)
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Init timings - ncclCommInitRankConfig: rank 2 nranks 8 total 0.46 (kernels 0.18, alloc 0.02, bootstrap 0.13, allgathers 0.01, topo 0.03, graphs 0.00, connections 0.06, rest 0.03)
[INFO|2026-04-29 15:38:07] llamafactory.hparams.parser:505 >> Process rank: 1, world size: 8, device: cuda:1, distributed training: True, compute dtype: torch.bfloat16
[INFO|2026-04-29 15:38:07] llamafactory.hparams.parser:505 >> Process rank: 7, world size: 8, device: cuda:7, distributed training: True, compute dtype: torch.bfloat16
[INFO|2026-04-29 15:38:07] llamafactory.hparams.parser:505 >> Process rank: 2, world size: 8, device: cuda:2, distributed training: True, compute dtype: torch.bfloat16
[INFO|2026-04-29 15:38:07] llamafactory.hparams.parser:505 >> Process rank: 5, world size: 8, device: cuda:5, distributed training: True, compute dtype: torch.bfloat16
[INFO|2026-04-29 15:38:07] llamafactory.hparams.parser:505 >> Process rank: 4, world size: 8, device: cuda:4, distributed training: True, compute dtype: torch.bfloat16
[INFO|2026-04-29 15:38:07] llamafactory.hparams.parser:505 >> Process rank: 3, world size: 8, device: cuda:3, distributed training: True, compute dtype: torch.bfloat16
[INFO|2026-04-29 15:38:07] llamafactory.hparams.parser:505 >> Process rank: 6, world size: 8, device: cuda:6, distributed training: True, compute dtype: torch.bfloat16
[INFO|2026-04-29 15:38:07] llamafactory.hparams.parser:505 >> Process rank: 0, world size: 8, device: cuda:0, distributed training: True, compute dtype: torch.bfloat16
[INFO|configuration_utils.py:670] 2026-04-29 15:38:07,681 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/config.json
[INFO|configuration_utils.py:742] 2026-04-29 15:38:07,684 >> Model config Qwen3Config {
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"masked_layers": null,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": null,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"sparsity_attn": null,
"sparsity_mlp": null,
"subnet_mode": null,
"subnet_type": null,
"threshold_attn": null,
"threshold_mlp": null,
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
[INFO|configuration_utils.py:670] 2026-04-29 15:38:11,634 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/config.json
[INFO|configuration_utils.py:742] 2026-04-29 15:38:11,635 >> Model config Qwen3Config {
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"masked_layers": null,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": null,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"sparsity_attn": null,
"sparsity_mlp": null,
"subnet_mode": null,
"subnet_type": null,
"threshold_attn": null,
"threshold_mlp": null,
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
[INFO|configuration_utils.py:670] 2026-04-29 15:38:11,758 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/config.json
[INFO|configuration_utils.py:742] 2026-04-29 15:38:11,759 >> Model config Qwen3Config {
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"masked_layers": null,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": null,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"sparsity_attn": null,
"sparsity_mlp": null,
"subnet_mode": null,
"subnet_type": null,
"threshold_attn": null,
"threshold_mlp": null,
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 06/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 14/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 16/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 17/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 18/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 19/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 20/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 21/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 22/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 23/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 04/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 12/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 16/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 17/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 18/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 19/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 20/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 21/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 22/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 23/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 00/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 08/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 16/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 17/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 18/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 19/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 20/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 21/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 22/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 23/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 02/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 10/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 16/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 17/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 18/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 19/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 20/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 21/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 22/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 23/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 05/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 13/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 16/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 17/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 18/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 19/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 20/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 21/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 22/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 23/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/CUMEM/read
[INFO|2026-04-29 15:38:13] llamafactory.data.loader:144 >> Loading dataset allenai/tulu-3-sft-personas-code...
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 03/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 11/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 16/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 17/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 18/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 19/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 20/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 21/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 22/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 23/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 07/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 15/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 16/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 17/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 18/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 19/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 20/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 21/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 22/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 23/0 : 6[6] -> 7[7] via P2P/CUMEM/read
Setting num_proc from 16 back to 1 for the train split to disable multiprocessing as it only contains one shard.
Generating train split: 0%| | 0/34999 [00:00<?, ? examples/s]
Generating train split: 31%|███▏ | 11000/34999 [00:00<00:00, 101394.96 examples/s]
Generating train split: 89%|████████▊ | 31000/34999 [00:00<00:00, 152233.13 examples/s]
Generating train split: 100%|██████████| 34999/34999 [00:00<00:00, 149748.74 examples/s]
[INFO|2026-04-29 15:38:17] llamafactory.data.loader:144 >> Sampled 10000 examples from dataset allenai/tulu-3-sft-personas-code.
Converting format of dataset (num_proc=16): 0%| | 0/10000 [00:00<?, ? examples/s]
Converting format of dataset (num_proc=16): 6%|▌ | 558/10000 [00:00<00:07, 1236.03 examples/s]
Converting format of dataset (num_proc=16): 100%|██████████| 10000/10000 [00:00<00:00, 15253.17 examples/s]
[INFO|2026-04-29 15:38:18] llamafactory.data.loader:144 >> Loading dataset KKHYA/evol_codealpaca_converted...
Repo card metadata block was not found. Setting CardData to empty.
Setting num_proc from 16 back to 1 for the train split to disable multiprocessing as it only contains one shard.
Generating train split: 0%| | 0/110999 [00:00<?, ? examples/s]
Generating train split: 5%|▌ | 6000/110999 [00:00<00:02, 50350.98 examples/s]
Generating train split: 13%|█▎ | 14000/110999 [00:00<00:01, 65763.19 examples/s]
Generating train split: 23%|██▎ | 25000/110999 [00:00<00:01, 81336.77 examples/s]
Generating train split: 32%|███▏ | 35000/110999 [00:00<00:00, 82993.39 examples/s]
Generating train split: 40%|███▉ | 44000/110999 [00:00<00:00, 82500.25 examples/s]
Generating train split: 50%|████▉ | 55000/110999 [00:00<00:00, 88557.97 examples/s]
Generating train split: 58%|█████▊ | 64000/110999 [00:00<00:00, 86219.27 examples/s]
Generating train split: 66%|██████▌ | 73000/110999 [00:00<00:00, 84685.47 examples/s]
Generating train split: 75%|███████▍ | 83000/110999 [00:01<00:00, 83871.33 examples/s]
Generating train split: 84%|████████▍ | 93000/110999 [00:01<00:00, 86235.69 examples/s]
Generating train split: 93%|█████████▎| 103000/110999 [00:01<00:00, 85282.53 examples/s]
Generating train split: 100%|██████████| 110999/110999 [00:01<00:00, 83926.23 examples/s]
[INFO|2026-04-29 15:38:26] llamafactory.data.loader:144 >> Sampled 10000 examples from dataset KKHYA/evol_codealpaca_converted.
Converting format of dataset (num_proc=16): 0%| | 0/10000 [00:00<?, ? examples/s]
Converting format of dataset (num_proc=16): 5%|▌ | 531/10000 [00:00<00:08, 1138.29 examples/s]
Converting format of dataset (num_proc=16): 100%|██████████| 10000/10000 [00:00<00:00, 14464.22 examples/s]
[INFO|2026-04-29 15:38:27] llamafactory.data.loader:144 >> Loading dataset KKHYA/codefeedback_filtered_instructions_converted...
Repo card metadata block was not found. Setting CardData to empty.
Setting num_proc from 16 to 2 for the train split as it only contains 2 shards.
Generating train split: 0%| | 0/156361 [00:00<?, ? examples/s]
Generating train split: 1%| | 1000/156361 [00:00<00:27, 5691.41 examples/s]
Generating train split: 10%|█ | 16000/156361 [00:00<00:02, 67920.11 examples/s]
Generating train split: 21%|██ | 33000/156361 [00:00<00:01, 101859.60 examples/s]
Generating train split: 36%|███▌ | 56000/156361 [00:00<00:00, 141588.48 examples/s]
Generating train split: 51%|█████ | 80000/156361 [00:00<00:00, 164893.26 examples/s]
Generating train split: 63%|██████▎ | 98000/156361 [00:00<00:00, 165183.67 examples/s]
Generating train split: 75%|███████▌ | 118000/156361 [00:00<00:00, 170743.05 examples/s]
Generating train split: 88%|████████▊ | 138000/156361 [00:00<00:00, 176318.39 examples/s]
Generating train split: 100%|██████████| 156361/156361 [00:01<00:00, 165299.41 examples/s]
Generating train split: 100%|██████████| 156361/156361 [00:01<00:00, 135177.51 examples/s]
[INFO|2026-04-29 15:38:36] llamafactory.data.loader:144 >> Sampled 10000 examples from dataset KKHYA/codefeedback_filtered_instructions_converted.
Converting format of dataset (num_proc=16): 0%| | 0/10000 [00:00<?, ? examples/s]
Converting format of dataset (num_proc=16): 5%|▌ | 514/10000 [00:00<00:09, 989.65 examples/s]
Converting format of dataset (num_proc=16): 100%|██████████| 10000/10000 [00:00<00:00, 13665.07 examples/s]
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 01/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 09/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 16/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 17/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 18/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 19/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 20/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 21/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 22/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 23/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
Running tokenizer on dataset (num_proc=16): 0%| | 0/30000 [00:00<?, ? examples/s]Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Repo card metadata block was not found. Setting CardData to empty.
Running tokenizer on dataset (num_proc=16): 3%|▎ | 1000/30000 [00:03<01:42, 282.34 examples/s]
Running tokenizer on dataset (num_proc=16): 6%|▋ | 1875/30000 [00:04<01:02, 450.57 examples/s]
Running tokenizer on dataset (num_proc=16): 10%|▉ | 2875/30000 [00:04<00:34, 787.29 examples/s]
Running tokenizer on dataset (num_proc=16): 12%|█▎ | 3750/30000 [00:05<00:31, 821.54 examples/s]
Running tokenizer on dataset (num_proc=16): 16%|█▌ | 4750/30000 [00:06<00:22, 1124.68 examples/s]
Running tokenizer on dataset (num_proc=16): 19%|█▉ | 5625/30000 [00:07<00:23, 1044.46 examples/s]
Running tokenizer on dataset (num_proc=16): 22%|██▏ | 6625/30000 [00:07<00:17, 1313.33 examples/s]
Running tokenizer on dataset (num_proc=16): 25%|██▌ | 7500/30000 [00:08<00:20, 1115.77 examples/s]
Running tokenizer on dataset (num_proc=16): 28%|██▊ | 8500/30000 [00:08<00:14, 1438.42 examples/s]
Running tokenizer on dataset (num_proc=16): 31%|███▏ | 9375/30000 [00:09<00:17, 1195.11 examples/s]
Running tokenizer on dataset (num_proc=16): 35%|███▍ | 10375/30000 [00:10<00:14, 1388.72 examples/s]
Running tokenizer on dataset (num_proc=16): 38%|███▊ | 11250/30000 [00:11<00:19, 985.10 examples/s]
Running tokenizer on dataset (num_proc=16): 41%|████ | 12250/30000 [00:12<00:13, 1323.23 examples/s]
Running tokenizer on dataset (num_proc=16): 44%|████▍ | 13250/30000 [00:13<00:15, 1067.51 examples/s]
Running tokenizer on dataset (num_proc=16): 47%|████▋ | 14125/30000 [00:13<00:11, 1341.26 examples/s]
Running tokenizer on dataset (num_proc=16): 50%|█████ | 15125/30000 [00:14<00:12, 1183.18 examples/s]
Running tokenizer on dataset (num_proc=16): 53%|█████▎ | 16000/30000 [00:14<00:09, 1505.60 examples/s]
Running tokenizer on dataset (num_proc=16): 56%|█████▋ | 16875/30000 [00:16<00:11, 1132.75 examples/s]
Running tokenizer on dataset (num_proc=16): 63%|██████▎ | 18875/30000 [00:17<00:08, 1312.03 examples/s]
Running tokenizer on dataset (num_proc=16): 66%|██████▌ | 19750/30000 [00:17<00:06, 1465.46 examples/s]
Running tokenizer on dataset (num_proc=16): 69%|██████▉ | 20750/30000 [00:18<00:06, 1349.07 examples/s]
Running tokenizer on dataset (num_proc=16): 72%|███████▏ | 21625/30000 [00:18<00:04, 1676.85 examples/s]
Running tokenizer on dataset (num_proc=16): 75%|███████▌ | 22625/30000 [00:19<00:05, 1322.76 examples/s]
Running tokenizer on dataset (num_proc=16): 78%|███████▊ | 23500/30000 [00:20<00:04, 1607.76 examples/s]
Running tokenizer on dataset (num_proc=16): 81%|████████▏ | 24375/30000 [00:21<00:04, 1245.65 examples/s]
Running tokenizer on dataset (num_proc=16): 88%|████████▊ | 26375/30000 [00:22<00:02, 1323.36 examples/s]
Running tokenizer on dataset (num_proc=16): 91%|█████████ | 27250/30000 [00:22<00:01, 1606.52 examples/s]
Running tokenizer on dataset (num_proc=16): 94%|█████████▍| 28250/30000 [00:23<00:01, 1337.23 examples/s]
Running tokenizer on dataset (num_proc=16): 97%|█████████▋| 29125/30000 [00:24<00:00, 1679.22 examples/s]
Running tokenizer on dataset (num_proc=16): 100%|██████████| 30000/30000 [00:25<00:00, 1228.53 examples/s]
Running tokenizer on dataset (num_proc=16): 100%|██████████| 30000/30000 [00:25<00:00, 1179.79 examples/s]
training example:
input_ids:
[151644, 872, 198, 7985, 264, 10135, 729, 311, 11047, 279, 2790, 1372, 315, 8845, 16548, 553, 1674, 3767, 300, 4308, 304, 264, 2661, 3200, 504, 264, 1140, 315, 2432, 3059, 13, 8886, 2432, 1102, 374, 15251, 438, 264, 10997, 448, 6894, 330, 5117, 26532, 497, 330, 13757, 26532, 497, 330, 5117, 96244, 497, 323, 330, 13757, 96244, 3263, 1674, 3767, 300, 4308, 1410, 387, 2987, 279, 2114, 476, 3123, 2083, 304, 894, 2432, 13, 576, 1946, 374, 264, 1140, 315, 1741, 2432, 1102, 57514, 11, 323, 279, 2550, 1265, 387, 458, 7546, 14064, 279, 2790, 1372, 315, 8845, 16548, 553, 1674, 3767, 300, 4308, 382, 2505, 510, 12, 1565, 6347, 13576, 44622, 362, 1140, 315, 57514, 11, 1380, 1817, 10997, 5610, 510, 220, 481, 330, 5117, 26532, 1, 320, 917, 1648, 576, 829, 315, 279, 2114, 2083, 624, 220, 481, 330, 13757, 26532, 1, 320, 917, 1648, 576, 829, 315, 279, 3123, 2083, 624, 220, 481, 330, 5117, 96244, 1, 320, 396, 1648, 576, 1372, 315, 8845, 16548, 553, 279, 2114, 2083, 624, 220, 481, 330, 13757, 96244, 1, 320, 396, 1648, 576, 1372, 315, 8845, 16548, 553, 279, 3123, 2083, 382, 5097, 510, 12, 1527, 7546, 14064, 279, 2790, 1372, 315, 8845, 16548, 553, 1674, 3767, 300, 4308, 382, 13314, 510, 73594, 12669, 198, 6347, 13576, 284, 2278, 262, 5212, 5117, 26532, 788, 330, 2101, 3767, 300, 4308, 497, 330, 13757, 26532, 788, 330, 14597, 32, 497, 330, 5117, 96244, 788, 220, 17, 11, 330, 13757, 96244, 788, 220, 16, 1583, 262, 5212, 5117, 26532, 788, 330, 14597, 33, 497, 330, 13757, 26532, 788, 330, 2101, 3767, 300, 4308, 497, 330, 5117, 96244, 788, 220, 18, 11, 330, 13757, 96244, 788, 220, 17, 1583, 262, 5212, 5117, 26532, 788, 330, 2101, 3767, 300, 4308, 497, 330, 13757, 26532, 788, 330, 14597, 34, 497, 330, 5117, 96244, 788, 220, 16, 11, 330, 13757, 96244, 788, 220, 16, 1583, 262, 5212, 5117, 26532, 788, 330, 14597, 35, 497, 330, 13757, 26532, 788, 330, 2101, 3767, 300, 4308, 497, 330, 5117, 96244, 788, 220, 15, 11, 330, 13757, 96244, 788, 220, 18, 532, 921, 2, 31021, 9258, 25, 220, 23, 198, 73594, 151645, 198, 151644, 77091, 198, 750, 11047, 8418, 3767, 300, 4308, 96244, 25401, 13576, 982, 262, 2790, 96244, 284, 220, 15, 198, 262, 369, 2432, 304, 2432, 13576, 510, 286, 421, 2432, 1183, 5117, 26532, 1341, 621, 330, 2101, 3767, 300, 4308, 4660, 310, 2790, 96244, 1421, 2432, 1183, 5117, 96244, 7026, 286, 4409, 2432, 1183, 13757, 26532, 1341, 621, 330, 2101, 3767, 300, 4308, 4660, 310, 2790, 96244, 1421, 2432, 1183, 13757, 96244, 7026, 262, 470, 2790, 96244, 151645, 198]
inputs:
<|im_start|>user
Write a python function to calculate the total number of goals scored by Alanyaspor in a given season from a list of match results. Each match result is represented as a dictionary with keys "home_team", "away_team", "home_goals", and "away_goals". Alanyaspor could be either the home or away team in any match. The input is a list of such match result dictionaries, and the output should be an integer representing the total number of goals scored by Alanyaspor.
Input:
- `match_results`: A list of dictionaries, where each dictionary contains:
- "home_team" (string): The name of the home team.
- "away_team" (string): The name of the away team.
- "home_goals" (int): The number of goals scored by the home team.
- "away_goals" (int): The number of goals scored by the away team.
Output:
- An integer representing the total number of goals scored by Alanyaspor.
Example:
```python
match_results = [
{"home_team": "Alanyaspor", "away_team": "TeamA", "home_goals": 2, "away_goals": 1},
{"home_team": "TeamB", "away_team": "Alanyaspor", "home_goals": 3, "away_goals": 2},
{"home_team": "Alanyaspor", "away_team": "TeamC", "home_goals": 1, "away_goals": 1},
{"home_team": "TeamD", "away_team": "Alanyaspor", "home_goals": 0, "away_goals": 3}
]
# Expected Output: 8
```<|im_end|>
<|im_start|>assistant
def calculate_alanyaspor_goals(match_results):
total_goals = 0
for match in match_results:
if match["home_team"] == "Alanyaspor":
total_goals += match["home_goals"]
elif match["away_team"] == "Alanyaspor":
total_goals += match["away_goals"]
return total_goals<|im_end|>
label_ids:
[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 750, 11047, 8418, 3767, 300, 4308, 96244, 25401, 13576, 982, 262, 2790, 96244, 284, 220, 15, 198, 262, 369, 2432, 304, 2432, 13576, 510, 286, 421, 2432, 1183, 5117, 26532, 1341, 621, 330, 2101, 3767, 300, 4308, 4660, 310, 2790, 96244, 1421, 2432, 1183, 5117, 96244, 7026, 286, 4409, 2432, 1183, 13757, 26532, 1341, 621, 330, 2101, 3767, 300, 4308, 4660, 310, 2790, 96244, 1421, 2432, 1183, 13757, 96244, 7026, 262, 470, 2790, 96244, 151645, 198]
labels:
def calculate_alanyaspor_goals(match_results):
total_goals = 0
for match in match_results:
if match["home_team"] == "Alanyaspor":
total_goals += match["home_goals"]
elif match["away_team"] == "Alanyaspor":
total_goals += match["away_goals"]
return total_goals<|im_end|>
[INFO|configuration_utils.py:670] 2026-04-29 15:39:04,827 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/config.json
[INFO|configuration_utils.py:742] 2026-04-29 15:39:04,828 >> Model config Qwen3Config {
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"masked_layers": null,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": null,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"sparsity_attn": null,
"sparsity_mlp": null,
"subnet_mode": null,
"subnet_type": null,
"threshold_attn": null,
"threshold_mlp": null,
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
[INFO|2026-04-29 15:39:04] llamafactory.model.model_utils.kv_cache:144 >> KV cache is disabled during training.
[INFO|modeling_utils.py:710] 2026-04-29 15:39:06,415 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/model.safetensors.index.json
Fetching 2 files: 0%| | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 0%| | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 0%| | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 0%| | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 0%| | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 0%| | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 0%| | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 0%| | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 50%|█████ | 1/2 [00:04<00:04, 4.84s/it]
Fetching 2 files: 100%|██████████| 2/2 [00:04<00:00, 2.42s/it]
[INFO|modeling_utils.py:779] 2026-04-29 15:39:11,367 >> Will use dtype=torch.bfloat16 as defined in model's config object
[INFO|configuration_utils.py:1014] 2026-04-29 15:39:11,368 >> Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645,
"output_attentions": false,
"output_hidden_states": false,
"use_cache": false
}
Fetching 2 files: 50%|█████ | 1/2 [00:04<00:04, 4.49s/it]
Fetching 2 files: 100%|██████████| 2/2 [00:04<00:00, 2.24s/it]
Fetching 2 files: 50%|█████ | 1/2 [00:04<00:04, 4.44s/it]
Fetching 2 files: 100%|██████████| 2/2 [00:04<00:00, 2.22s/it]
Fetching 2 files: 50%|█████ | 1/2 [00:04<00:04, 4.53s/it]
Fetching 2 files: 100%|██████████| 2/2 [00:04<00:00, 2.26s/it]
Fetching 2 files: 50%|█████ | 1/2 [00:04<00:04, 4.33s/it]
Fetching 2 files: 100%|██████████| 2/2 [00:04<00:00, 2.16s/it]
Fetching 2 files: 50%|█████ | 1/2 [00:04<00:04, 4.53s/it]
Fetching 2 files: 100%|██████████| 2/2 [00:04<00:00, 2.27s/it]
Fetching 2 files: 50%|█████ | 1/2 [00:04<00:04, 4.48s/it]
Fetching 2 files: 100%|██████████| 2/2 [00:04<00:00, 2.24s/it]
Fetching 2 files: 50%|█████ | 1/2 [00:04<00:04, 4.48s/it]
Fetching 2 files: 100%|██████████| 2/2 [00:04<00:00, 2.24s/it]
Loading weights: 0%| | 0/311 [00:00<?, ?it/s]
Loading weights: 0%| | 1/311 [00:00<00:00, 11125.47it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 1/311 [00:00<00:00, 5660.33it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 0/311 [00:00<?, ?it/s]
Loading weights: 0%| | 1/311 [00:00<00:00, 12228.29it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 1/311 [00:00<00:00, 6195.43it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 0/311 [00:00<?, ?it/s]
Loading weights: 0%| | 1/311 [00:00<00:00, 10255.02it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 1/311 [00:00<00:00, 5497.12it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 0/311 [00:00<?, ?it/s]
Loading weights: 0%| | 1/311 [00:00<00:00, 10699.76it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 1/311 [00:00<00:00, 5722.11it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 0/311 [00:00<?, ?it/s]
Loading weights: 0%| | 1/311 [00:00<00:00, 9532.51it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 1/311 [00:00<00:00, 5295.84it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 0/311 [00:00<?, ?it/s]
Loading weights: 0%| | 1/311 [00:00<00:00, 9664.29it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 1/311 [00:00<00:00, 5249.44it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 0/311 [00:00<?, ?it/s]
Loading weights: 0%| | 1/311 [00:00<00:00, 9686.61it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 1/311 [00:00<00:00, 5412.01it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/311 [00:00<00:17, 17.87it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/311 [00:00<00:17, 17.87it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/311 [00:00<00:17, 17.87it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/311 [00:00<00:23, 13.23it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/311 [00:00<00:23, 13.23it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/311 [00:00<00:23, 13.23it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/311 [00:00<00:38, 7.97it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/311 [00:00<00:34, 9.08it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/311 [00:00<00:38, 7.97it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/311 [00:00<00:38, 7.97it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/311 [00:00<00:34, 9.08it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 3/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 1%| | 2/311 [00:00<00:34, 9.08it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 3/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:38, 7.97it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:37, 7.97it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:33, 9.08it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:36, 7.97it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 1%| | 2/311 [00:00<00:43, 7.14it/s, Materializing param=lm_head.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 1%| | 2/311 [00:00<00:43, 7.14it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:32, 9.08it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 1%| | 2/311 [00:00<00:43, 7.14it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 3/311 [00:00<00:43, 7.14it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 1%| | 3/311 [00:00<00:43, 7.14it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:35, 7.97it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:17, 17.87it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 1%| | 3/311 [00:00<00:17, 17.87it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:42, 7.14it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:34, 7.97it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:31, 9.08it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:33, 7.97it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 1%| | 2/311 [00:00<00:43, 7.17it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/311 [00:00<00:43, 7.17it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/311 [00:00<00:43, 7.17it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:30, 9.08it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:23, 13.23it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:23, 13.23it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:23, 13.22it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:23, 13.22it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:23, 13.22it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:32, 7.97it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:41, 7.14it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:31, 7.97it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:31, 7.97it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:31, 7.97it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:31, 7.97it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:31, 7.97it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:31, 7.97it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:23, 13.22it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:23, 13.22it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:40, 7.14it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:42, 7.17it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:29, 9.08it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:23, 13.22it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:23, 13.22it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:20, 14.63it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:31, 7.97it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:31, 7.97it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:41, 7.17it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:39, 7.14it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:19, 14.63it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:40, 7.17it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:22, 13.22it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:38, 7.14it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 1%| | 2/311 [00:00<00:52, 5.92it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/311 [00:00<00:52, 5.92it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/311 [00:00<00:52, 5.92it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:52, 5.92it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:52, 5.92it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:39, 7.17it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:02, 131.66it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:18, 14.63it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:17, 14.63it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:17, 14.63it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:51, 5.92it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:17, 14.63it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:17, 14.63it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:21, 13.22it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:38, 7.17it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:01, 215.36it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:50, 5.92it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:37, 7.17it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:20, 13.22it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:49, 5.92it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:19, 13.22it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:19, 13.22it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:19, 13.22it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:19, 13.22it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:48, 5.92it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 170.61it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 215.36it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:47, 5.92it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 0%| | 0/311 [00:00<?, ?it/s]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 0%| | 1/311 [00:00<00:00, 11214.72it/s, Materializing param=lm_head.weight]
Loading weights: 0%| | 1/311 [00:00<00:00, 6009.03it/s, Materializing param=lm_head.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:46, 5.92it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:45, 5.92it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:45, 5.92it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:45, 5.92it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:45, 5.92it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:45, 5.92it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:45, 5.92it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:45, 5.92it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:45, 5.92it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 131.66it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:01, 182.36it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:02, 125.96it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 153.69it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:01, 217.98it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 164.73it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 344.57it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 240.50it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 125.96it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 217.98it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 272.74it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 1%| | 2/311 [00:00<00:23, 13.38it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/311 [00:00<00:23, 13.38it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/311 [00:00<00:23, 13.38it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 240.41it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 241.89it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:01, 205.70it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 264.09it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 379.91it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 205.70it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 257.53it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 342.90it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 286.65it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 1%| | 3/311 [00:00<00:23, 13.38it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 1%| | 3/311 [00:00<00:23, 13.38it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 1%|▏ | 4/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 2%|▏ | 5/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 2%|▏ | 6/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 284.92it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 2%|▏ | 7/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 3%|▎ | 8/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.k_norm.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 3%|▎ | 9/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.k_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 3%|▎ | 10/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 4%|▎ | 11/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.q_norm.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 4%|▍ | 12/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.q_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 4%|▍ | 13/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.0.self_attn.v_proj.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 5%|▍ | 14/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 5%|▍ | 15/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 286.26it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 5%|▌ | 16/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 427.40it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 5%|▌ | 17/311 [00:00<00:19, 15.44it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 6%|▌ | 18/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▌ | 19/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.k_norm.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 6%|▋ | 20/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.k_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 7%|▋ | 21/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 7%|▋ | 22/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.q_norm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 7%|▋ | 23/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.q_proj.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 8%|▊ | 24/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.1.self_attn.v_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 8%|▊ | 25/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 8%|▊ | 26/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 9%|▊ | 27/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 243.85it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 9%|▉ | 28/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 9%|▉ | 29/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 10%|▉ | 30/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.self_attn.k_norm.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 10%|▉ | 31/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.self_attn.k_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 94%|█████████▎| 291/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 10%|█ | 32/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 33/311 [00:00<00:18, 15.44it/s, Materializing param=model.layers.2.self_attn.q_norm.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 11%|█ | 34/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.2.self_attn.q_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 11%|█▏ | 35/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.2.self_attn.v_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 301.37it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 12%|█▏ | 36/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 94%|█████████▍| 293/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 12%|█▏ | 37/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 95%|█████████▍| 294/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 95%|█████████▍| 295/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 12%|█▏ | 38/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 95%|█████████▌| 296/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 96%|█████████▌| 298/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 96%|█████████▌| 298/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 96%|█████████▌| 299/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 96%|█████████▋| 300/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 372.65it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 39/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 13%|█▎ | 40/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 13%|█▎ | 41/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.k_norm.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 14%|█▎ | 42/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.k_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 321.69it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 14%|█▍ | 43/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 306/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 14%|█▍ | 44/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.q_norm.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 14%|█▍ | 45/311 [00:00<00:17, 15.44it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.3.self_attn.q_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 15%|█▍ | 46/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.3.self_attn.v_proj.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 47/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 15%|█▌ | 48/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 99%|█████████▉| 309/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:00<00:00, 445.12it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 445.12it/s, Materializing param=model.norm.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 445.12it/s, Materializing param=model.norm.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 368.99it/s, Materializing param=model.norm.weight]
Loading weights: 16%|█▌ | 49/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 16%|█▌ | 50/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 325.79it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 16%|█▋ | 51/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 52/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.k_norm.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 53/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.k_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 17%|█▋ | 54/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 55/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.q_norm.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 18%|█▊ | 56/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.q_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 18%|█▊ | 57/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.4.self_attn.v_proj.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 19%|█▊ | 58/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 19%|█▉ | 59/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 298.88it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 19%|█▉ | 60/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 20%|█▉ | 61/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 20%|█▉ | 62/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 20%|██ | 63/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.k_norm.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 21%|██ | 64/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.k_proj.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 21%|██ | 65/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 21%|██ | 66/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.q_norm.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 22%|██▏ | 67/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.q_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 22%|██▏ | 68/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.5.self_attn.v_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 22%|██▏ | 69/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 23%|██▎ | 70/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 71/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 292.42it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 23%|██▎ | 72/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 23%|██▎ | 73/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 24%|██▍ | 74/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.k_norm.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 24%|██▍ | 75/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.k_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 24%|██▍ | 76/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 325.64it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 25%|██▍ | 77/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.q_norm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 25%|██▌ | 78/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.q_proj.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 25%|██▌ | 79/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.6.self_attn.v_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 26%|██▌ | 80/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 26%|██▌ | 81/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 403.08it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 26%|██▋ | 82/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]The tied weights mapping and config for this model specifies to tie model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 27%|██▋ | 83/311 [00:00<00:01, 174.43it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 331.98it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 27%|██▋ | 84/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 27%|██▋ | 85/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.k_norm.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 86/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.k_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 28%|██▊ | 87/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 28%|██▊ | 88/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.q_norm.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 29%|██▊ | 89/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 29%|██▉ | 90/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.7.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 29%|██▉ | 91/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 30%|██▉ | 92/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 30%|██▉ | 93/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 94%|█████████▍| 292/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 356.98it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 30%|███ | 94/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 94%|█████████▍| 293/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 95%|█████████▌| 296/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 95%|█████████▌| 297/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 96%|█████████▌| 298/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 96%|█████████▌| 298/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 326.69it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 95/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 31%|███ | 96/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.k_norm.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 31%|███ | 97/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.k_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 32%|███▏ | 98/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 32%|███▏ | 99/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.q_norm.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 32%|███▏ | 100/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.q_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 32%|███▏ | 101/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.8.self_attn.v_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 102/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 33%|███▎ | 103/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 33%|███▎ | 104/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 98%|█████████▊| 304/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 306/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 308/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 309/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 105/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 100%|█████████▉| 310/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:00<00:00, 414.14it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 414.14it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 414.14it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 329.45it/s, Materializing param=model.norm.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 106/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 34%|███▍ | 107/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.k_norm.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 35%|███▍ | 108/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.k_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 35%|███▌ | 109/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 35%|███▌ | 110/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.q_norm.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 36%|███▌ | 111/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 304.07it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 36%|███▌ | 112/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.9.self_attn.v_proj.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 36%|███▋ | 113/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 37%|███▋ | 114/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 37%|███▋ | 115/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 116/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:01<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:01<00:00, 344.20it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 89%|████████▉ | 278/311 [00:01<00:00, 344.20it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 89%|████████▉ | 278/311 [00:01<00:00, 344.20it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:01<00:00, 344.20it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:01<00:00, 344.20it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 90%|█████████ | 280/311 [00:01<00:00, 344.20it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 90%|█████████ | 280/311 [00:01<00:00, 344.20it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 38%|███▊ | 117/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 38%|███▊ | 118/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.k_norm.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 38%|███▊ | 119/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 39%|███▊ | 120/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 121/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.q_norm.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 39%|███▉ | 122/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.q_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 123/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.10.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 40%|███▉ | 124/311 [00:00<00:00, 247.98it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 333.67it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 91%|█████████ | 282/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 282/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 283/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████ | 283/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 91%|█████████▏| 284/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 374.67it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 286/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 286/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 287/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 352.10it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 289/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 289/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 290/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 40%|████ | 125/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 41%|████ | 126/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 41%|████ | 127/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:00<00:00, 378.32it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:00<00:00, 378.32it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:00<00:00, 378.32it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 328.70it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████ | 128/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 41%|████▏ | 129/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.k_norm.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 130/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.k_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 42%|████▏ | 131/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 42%|████▏ | 132/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.q_norm.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 43%|████▎ | 133/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.q_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 43%|████▎ | 134/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.11.self_attn.v_proj.weight]
Loading weights: 91%|█████████ | 282/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 282/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 283/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 283/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 43%|████▎ | 135/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 80%|████████ | 249/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 249/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 250/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 80%|████████ | 250/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 81%|████████ | 251/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 251/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 286/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 286/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 81%|████████ | 252/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 81%|████████▏ | 253/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 81%|████████▏ | 253/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 82%|████████▏ | 254/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 254/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 93%|█████████▎| 289/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 44%|████▎ | 136/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 374.67it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 289/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 44%|████▍ | 137/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 82%|████████▏ | 256/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 256/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 44%|████▍ | 138/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 45%|████▍ | 139/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 45%|████▌ | 140/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.k_norm.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 45%|████▌ | 141/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.k_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 46%|████▌ | 142/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 333.67it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 46%|████▌ | 143/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.q_norm.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 46%|████▋ | 144/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.q_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 47%|████▋ | 145/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.12.self_attn.v_proj.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 146/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 47%|████▋ | 147/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 388.59it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▎ | 260/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 388.59it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 388.59it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 295.46it/s, Materializing param=model.norm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 84%|████████▍ | 262/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 84%|████████▍ | 262/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 85%|████████▍ | 263/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 48%|████▊ | 148/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 363.06it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 85%|████████▍ | 264/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▍ | 264/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▌ | 265/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 85%|████████▌ | 265/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 363.06it/s, Materializing param=model.norm.weight]
Loading weights: 86%|████████▌ | 266/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 363.06it/s, Materializing param=model.norm.weight]
Loading weights: 86%|████████▌ | 266/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 267/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 287.39it/s, Materializing param=model.norm.weight]
Loading weights: 86%|████████▌ | 267/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 268/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 48%|████▊ | 149/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 378.32it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 378.32it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 378.32it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 296.63it/s, Materializing param=model.norm.weight]
Loading weights: 86%|████████▋ | 269/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 86%|████████▋ | 269/311 [00:01<00:00, 328.70it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 48%|████▊ | 150/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 49%|████▊ | 151/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.k_norm.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 49%|████▉ | 152/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.k_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 49%|████▉ | 153/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 154/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.q_norm.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 50%|████▉ | 155/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.q_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 50%|█████ | 156/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.13.self_attn.v_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 50%|█████ | 157/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 51%|█████ | 158/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 51%|█████ | 159/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 271/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 88%|████████▊ | 273/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 273/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 51%|█████▏ | 160/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 88%|████████▊ | 275/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 89%|████████▊ | 276/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 327.89it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 327.89it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 327.89it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 284.99it/s, Materializing param=model.norm.weight]
Loading weights: 89%|████████▉ | 278/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 89%|████████▉ | 278/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 52%|█████▏ | 161/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 52%|█████▏ | 162/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.k_norm.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 52%|█████▏ | 163/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.k_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 53%|█████▎ | 164/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 165/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.q_norm.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 53%|█████▎ | 166/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.q_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 54%|█████▎ | 167/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.14.self_attn.v_proj.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 168/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 54%|█████▍ | 169/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 170/311 [00:00<00:00, 296.91it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 91%|█████████ | 282/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 282/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 283/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████ | 283/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 91%|█████████▏| 284/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 286/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 286/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 287/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 55%|█████▍ | 171/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 289/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 289/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 290/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 55%|█████▌ | 172/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 173/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.k_norm.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 56%|█████▌ | 174/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.k_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 56%|█████▋ | 175/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 57%|█████▋ | 176/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.q_norm.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 177/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.q_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 57%|█████▋ | 178/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.15.self_attn.v_proj.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 58%|█████▊ | 179/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 180/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 58%|█████▊ | 181/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 59%|█████▊ | 182/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 96%|█████████▌| 298/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 183/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 184/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.k_norm.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 59%|█████▉ | 185/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.k_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 60%|█████▉ | 186/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 187/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.q_norm.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 60%|██████ | 188/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.q_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 189/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.16.self_attn.v_proj.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████ | 190/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 61%|██████▏ | 191/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 62%|██████▏ | 192/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 62%|██████▏ | 193/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 308/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:01<00:00, 332.21it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 332.21it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 332.21it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:01<00:00, 270.93it/s, Materializing param=model.norm.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 62%|██████▏ | 194/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 195/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.k_norm.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 63%|██████▎ | 196/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.k_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 63%|██████▎ | 197/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 64%|██████▎ | 198/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.q_norm.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 64%|██████▍ | 199/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.q_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 64%|██████▍ | 200/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.17.self_attn.v_proj.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 65%|██████▍ | 201/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 65%|██████▍ | 202/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 65%|██████▌ | 203/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 204/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 205/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 66%|██████▌ | 206/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.k_norm.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 207/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.k_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 67%|██████▋ | 208/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 67%|██████▋ | 209/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.q_norm.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 210/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.q_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 211/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.18.self_attn.v_proj.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 212/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 68%|██████▊ | 213/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 214/311 [00:00<00:00, 347.41it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 215/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 69%|██████▉ | 216/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|██████▉ | 217/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.k_norm.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 218/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.k_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 70%|███████ | 219/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 220/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.q_norm.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████ | 221/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.q_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 71%|███████▏ | 222/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.19.self_attn.v_proj.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 223/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 224/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 72%|███████▏ | 225/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 226/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 73%|███████▎ | 227/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 73%|███████▎ | 228/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.k_norm.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▎ | 229/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.k_proj.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 74%|███████▍ | 230/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 74%|███████▍ | 231/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.q_norm.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 232/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.q_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 75%|███████▍ | 233/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.20.self_attn.v_proj.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 75%|███████▌ | 234/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 76%|███████▌ | 235/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.mlp.down_proj.weight]The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 76%|███████▌ | 236/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 76%|███████▌ | 237/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 238/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 239/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.k_norm.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 240/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.k_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 77%|███████▋ | 241/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 242/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.q_norm.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 243/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.q_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 78%|███████▊ | 244/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.21.self_attn.v_proj.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 245/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.input_layernorm.weight]The tied weights mapping and config for this model specifies to tie model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.mlp.down_proj.weight] The tied weights mapping and config for this model specifies to tie model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning
Loading weights: 79%|███████▉ | 246/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.mlp.down_proj.weight]The tied weights mapping and config for this model specifies to tie model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 79%|███████▉ | 247/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 80%|███████▉ | 248/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 249/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 80%|████████ | 250/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.k_norm.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 251/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.k_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 81%|████████ | 252/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 81%|████████▏ | 253/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.q_norm.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 254/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.q_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 255/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.22.self_attn.v_proj.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 82%|████████▏ | 256/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 257/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 258/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 83%|████████▎ | 259/311 [00:00<00:00, 370.79it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▎ | 260/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 261/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.k_norm.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 84%|████████▍ | 262/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.k_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 85%|████████▍ | 263/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▍ | 264/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.q_norm.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 85%|████████▌ | 265/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.q_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 266/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.23.self_attn.v_proj.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 267/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 86%|████████▌ | 268/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 86%|████████▋ | 269/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 87%|████████▋ | 270/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 271/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 87%|████████▋ | 272/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.k_norm.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 273/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.k_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 88%|████████▊ | 274/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 88%|████████▊ | 275/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.q_norm.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 89%|████████▊ | 276/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.q_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 277/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.24.self_attn.v_proj.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 89%|████████▉ | 278/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|████████▉ | 279/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 90%|█████████ | 280/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 90%|█████████ | 281/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 282/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████ | 283/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.k_norm.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 91%|█████████▏| 284/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.k_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 285/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 286/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.q_norm.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 92%|█████████▏| 287/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.q_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 288/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.25.self_attn.v_proj.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 289/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 93%|█████████▎| 290/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▎| 291/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 94%|█████████▍| 292/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 94%|█████████▍| 293/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 94%|█████████▍| 293/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 294/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.k_norm.weight]
Loading weights: 95%|█████████▍| 295/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 95%|█████████▍| 295/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.k_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 95%|█████████▌| 296/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 95%|█████████▌| 297/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 95%|█████████▌| 297/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.q_norm.weight]
Loading weights: 96%|█████████▌| 298/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 96%|█████████▌| 298/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.q_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▌| 299/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.26.self_attn.v_proj.weight]
Loading weights: 96%|█████████▋| 300/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 96%|█████████▋| 300/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 97%|█████████▋| 301/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 301/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 302/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 97%|█████████▋| 303/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 98%|█████████▊| 304/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 304/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 305/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.self_attn.k_norm.weight]
Loading weights: 98%|█████████▊| 306/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 98%|█████████▊| 306/311 [00:00<00:00, 392.54it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:00<00:00, 415.94it/s, Materializing param=model.layers.27.self_attn.k_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:00<00:00, 415.94it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▊| 307/311 [00:00<00:00, 415.94it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▉| 308/311 [00:00<00:00, 415.94it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 308/311 [00:00<00:00, 415.94it/s, Materializing param=model.layers.27.self_attn.q_norm.weight]
Loading weights: 99%|█████████▉| 309/311 [00:00<00:00, 415.94it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 99%|█████████▉| 309/311 [00:00<00:00, 415.94it/s, Materializing param=model.layers.27.self_attn.q_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:00<00:00, 415.94it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|█████████▉| 310/311 [00:00<00:00, 415.94it/s, Materializing param=model.layers.27.self_attn.v_proj.weight]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 415.94it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 415.94it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 315.40it/s, Materializing param=model.norm.weight]
[WARNING|modeling_utils.py:2496] 2026-04-29 15:39:12,987 >> The tied weights mapping and config for this model specifies to tie model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning
The tied weights mapping and config for this model specifies to tie model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning
The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
[INFO|configuration_utils.py:967] 2026-04-29 15:39:13,129 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/generation_config.json
[INFO|configuration_utils.py:1014] 2026-04-29 15:39:13,129 >> Generate config GenerationConfig {
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}
The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
The tied weights mapping and config for this model specifies to tie model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Comm config Blocking set to 1
The tied weights mapping and config for this model specifies to tie model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning
[INFO|dynamic_module_utils.py:406] 2026-04-29 15:39:13,231 >> Could not locate the custom_generate/generate.py inside Qwen/Qwen3-1.7B.
[INFO|2026-04-29 15:39:13] llamafactory.model.model_utils.checkpointing:144 >> Gradient checkpointing enabled.
[INFO|2026-04-29 15:39:13] llamafactory.model.model_utils.attention:144 >> Using torch SDPA for faster training and inference.
[INFO|2026-04-29 15:39:13] llamafactory.model.adapter:144 >> Upcasting trainable params to float32.
[INFO|2026-04-29 15:39:13] llamafactory.model.adapter:144 >> Fine-tuning method: Full
[INFO|2026-04-29 15:39:13] llamafactory.model.loader:144 >> trainable params: 2,031,739,904 || all params: 2,031,739,904 || trainable%: 100.0000
The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Comm config Blocking set to 1
The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Comm config Blocking set to 1
[WARNING|trainer_utils.py:1234] 2026-04-29 15:39:13,812 >> The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Comm config Blocking set to 1
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Initialized NET plugin Socket
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Assigned NET plugin Socket to comm
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Using network Socket
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO ncclCommSplit comm 0x5616c2ee4db0 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId 201d0 parent 0x5616b5c85c30 splitCount 1 color 1266629538 key 3- Init START
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO ncclCommSplit comm 0x55cfdde9b730 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId 901c0 parent 0x55cfd20e4910 splitCount 1 color 1266629538 key 4- Init START
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO ncclCommSplit comm 0x55e5e87890a0 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId a01d0 parent 0x55e5dac15dd0 splitCount 1 color 1266629538 key 7- Init START
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO ncclCommSplit comm 0x55cae6fe89c0 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId 901d0 parent 0x55cadade89e0 splitCount 1 color 1266629538 key 5- Init START
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO ncclCommSplit comm 0x55eca298cda0 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId 201c0 parent 0x55ec9c119990 splitCount 1 color 1266629538 key 2- Init START
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO ncclCommSplit comm 0x55e875022b30 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId a01c0 parent 0x55e8675b14b0 splitCount 1 color 1266629538 key 6- Init START
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO ncclCommSplit comm 0x557309603670 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 101d0 parent 0x55730064a610 splitCount 1 color 1266629538 key 1- Init START
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO ncclCommSplit comm 0x5635f6273520 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 101c0 parent 0x5635e92c0280 splitCount 1 color 1266629538 key 0- Init START
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 7 is 24-47,72-95. (GPU affinity = 24-47,72-95 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO NVLS multicast support is not available on dev 7 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 6 is 24-47,72-95. (GPU affinity = 24-47,72-95 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO NVLS multicast support is not available on dev 6 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 5 is 24-47,72-95. (GPU affinity = 24-47,72-95 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO NVLS multicast support is not available on dev 5 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 1 is 0-23,48-71. (GPU affinity = 0-23,48-71 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO NVLS multicast support is not available on dev 1 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 3 is 0-23,48-71. (GPU affinity = 0-23,48-71 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO NVLS multicast support is not available on dev 3 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 0 is 0-23,48-71. (GPU affinity = 0-23,48-71 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO NVLS multicast support is not available on dev 0 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 4 is 24-47,72-95. (GPU affinity = 24-47,72-95 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO NVLS multicast support is not available on dev 4 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO ncclTopoGetCpuAffinity: Affinity for GPU 2 is 0-23,48-71. (GPU affinity = 0-23,48-71 ; CPU affinity = 0-95).
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO NVLS multicast support is not available on dev 2 (NVLS_NCHANNELS 0)
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO comm 0x55eca298cda0 rank 2 nRanks 8 nNodes 1 localRanks 8 localRank 2 MNNVL 0
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO comm 0x557309603670 rank 1 nRanks 8 nNodes 1 localRanks 8 localRank 1 MNNVL 0
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO comm 0x5635f6273520 rank 0 nRanks 8 nNodes 1 localRanks 8 localRank 0 MNNVL 0
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO comm 0x55cae6fe89c0 rank 5 nRanks 8 nNodes 1 localRanks 8 localRank 5 MNNVL 0
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO comm 0x55e875022b30 rank 6 nRanks 8 nNodes 1 localRanks 8 localRank 6 MNNVL 0
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO comm 0x55cfdde9b730 rank 4 nRanks 8 nNodes 1 localRanks 8 localRank 4 MNNVL 0
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO comm 0x55e5e87890a0 rank 7 nRanks 8 nNodes 1 localRanks 8 localRank 7 MNNVL 0
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO comm 0x5616c2ee4db0 rank 3 nRanks 8 nNodes 1 localRanks 8 localRank 3 MNNVL 0
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 00/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 01/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 02/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 03/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 04/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 05/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/-1/-1->2->1 [3] 3/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->1 [11] 3/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1 [16] 3/-1/-1->2->1 [17] 3/-1/-1->2->1 [18] 3/-1/-1->2->1 [19] 3/-1/-1->2->1 [20] 3/-1/-1->2->1 [21] 3/-1/-1->2->1 [22] 3/-1/-1->2->1 [23] 3/-1/-1->2->1
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 06/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 07/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/-1/-1->1->0 [2] 2/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->0 [10] 2/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0 [16] 2/-1/-1->1->0 [17] 2/-1/-1->1->0 [18] 2/-1/-1->1->0 [19] 2/-1/-1->1->0 [20] 2/-1/-1->1->0 [21] 2/-1/-1->1->0 [22] 2/-1/-1->1->0 [23] 2/-1/-1->1->0
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 08/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/-1/-1->5->4 [6] 6/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->4 [14] 6/-1/-1->5->4 [15] 6/-1/-1->5->4 [16] 6/-1/-1->5->4 [17] 6/-1/-1->5->4 [18] 6/-1/-1->5->4 [19] 6/-1/-1->5->4 [20] 6/-1/-1->5->4 [21] 6/-1/-1->5->4 [22] 6/-1/-1->5->4 [23] 6/-1/-1->5->4
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 09/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/-1/-1->6->5 [7] 7/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->5 [15] 7/-1/-1->6->5 [16] 7/-1/-1->6->5 [17] 7/-1/-1->6->5 [18] 7/-1/-1->6->5 [19] 7/-1/-1->6->5 [20] 7/-1/-1->6->5 [21] 7/-1/-1->6->5 [22] 7/-1/-1->6->5 [23] 7/-1/-1->6->5
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/-1/-1->4->3 [5] 5/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->3 [13] 5/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3 [16] 5/-1/-1->4->3 [17] 5/-1/-1->4->3 [18] 5/-1/-1->4->3 [19] 5/-1/-1->4->3 [20] 5/-1/-1->4->3 [21] 5/-1/-1->4->3 [22] 5/-1/-1->4->3 [23] 5/-1/-1->4->3
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 10/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/-1/-1->3->2 [4] 4/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->2 [12] 4/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2 [16] 4/-1/-1->3->2 [17] 4/-1/-1->3->2 [18] 4/-1/-1->3->2 [19] 4/-1/-1->3->2 [20] 4/-1/-1->3->2 [21] 4/-1/-1->3->2 [22] 4/-1/-1->3->2 [23] 4/-1/-1->3->2
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 11/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] -1/-1/-1->7->6 [2] -1/-1/-1->7->6 [3] -1/-1/-1->7->6 [4] -1/-1/-1->7->6 [5] -1/-1/-1->7->6 [6] -1/-1/-1->7->6 [7] -1/-1/-1->7->6 [8] -1/-1/-1->7->6 [9] -1/-1/-1->7->6 [10] -1/-1/-1->7->6 [11] -1/-1/-1->7->6 [12] -1/-1/-1->7->6 [13] -1/-1/-1->7->6 [14] -1/-1/-1->7->6 [15] -1/-1/-1->7->6 [16] -1/-1/-1->7->6 [17] -1/-1/-1->7->6 [18] -1/-1/-1->7->6 [19] -1/-1/-1->7->6 [20] -1/-1/-1->7->6 [21] -1/-1/-1->7->6 [22] -1/-1/-1->7->6 [23] -1/-1/-1->7->6
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 12/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 13/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 14/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 15/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 16/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 17/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 18/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 19/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 20/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 21/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 22/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 23/24 : 0 1 2 3 4 5 6 7
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Trees [0] 1/-1/-1->0->-1 [1] 1/-1/-1->0->-1 [2] 1/-1/-1->0->-1 [3] 1/-1/-1->0->-1 [4] 1/-1/-1->0->-1 [5] 1/-1/-1->0->-1 [6] 1/-1/-1->0->-1 [7] 1/-1/-1->0->-1 [8] 1/-1/-1->0->-1 [9] 1/-1/-1->0->-1 [10] 1/-1/-1->0->-1 [11] 1/-1/-1->0->-1 [12] 1/-1/-1->0->-1 [13] 1/-1/-1->0->-1 [14] 1/-1/-1->0->-1 [15] 1/-1/-1->0->-1 [16] 1/-1/-1->0->-1 [17] 1/-1/-1->0->-1 [18] 1/-1/-1->0->-1 [19] 1/-1/-1->0->-1 [20] 1/-1/-1->0->-1 [21] 1/-1/-1->0->-1 [22] 1/-1/-1->0->-1 [23] 1/-1/-1->0->-1
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO P2P Chunksize set to 524288
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213685:215779 [0] NCCL INFO [Proxy Service] Device 4 CPU core 75
ywang29-p4d-debug-1-worker-0:213685:215780 [0] NCCL INFO [Proxy Service UDS] Device 4 CPU core 86
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213682:215781 [0] NCCL INFO [Proxy Service] Device 1 CPU core 3
ywang29-p4d-debug-1-worker-0:213682:215782 [0] NCCL INFO [Proxy Service UDS] Device 1 CPU core 6
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213687:215783 [0] NCCL INFO [Proxy Service] Device 6 CPU core 40
ywang29-p4d-debug-1-worker-0:213687:215785 [0] NCCL INFO [Proxy Service UDS] Device 6 CPU core 44
ywang29-p4d-debug-1-worker-0:213686:215784 [0] NCCL INFO [Proxy Service] Device 5 CPU core 43
ywang29-p4d-debug-1-worker-0:213686:215786 [0] NCCL INFO [Proxy Service UDS] Device 5 CPU core 85
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213688:215787 [0] NCCL INFO [Proxy Service] Device 7 CPU core 81
ywang29-p4d-debug-1-worker-0:213688:215788 [0] NCCL INFO [Proxy Service UDS] Device 7 CPU core 77
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213684:215789 [0] NCCL INFO [Proxy Service] Device 3 CPU core 4
ywang29-p4d-debug-1-worker-0:213683:215790 [0] NCCL INFO [Proxy Service] Device 2 CPU core 9
ywang29-p4d-debug-1-worker-0:213683:215792 [0] NCCL INFO [Proxy Service UDS] Device 2 CPU core 59
ywang29-p4d-debug-1-worker-0:213684:215791 [0] NCCL INFO [Proxy Service UDS] Device 3 CPU core 58
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 isAllCudaP2p 1
ywang29-p4d-debug-1-worker-0:213681:215794 [0] NCCL INFO [Proxy Service UDS] Device 0 CPU core 16
ywang29-p4d-debug-1-worker-0:213681:215793 [0] NCCL INFO [Proxy Service] Device 0 CPU core 60
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO NET/OFI NCCL_OFI_TUNER is not available for platform : p4de.24xlarge, Fall back to NCCL's tuner
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO CC Off, workFifoBytes 1048576
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO ncclCommSplit comm 0x5616c2ee4db0 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId 201d0 parent 0x5616b5c85c30 splitCount 1 color 1266629538 key 3 - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO ncclCommSplit comm 0x55e5e87890a0 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId a01d0 parent 0x55e5dac15dd0 splitCount 1 color 1266629538 key 7 - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Init timings - ncclCommSplit: rank 3 nranks 8 total 1.17 (kernels 0.00, alloc 0.00, bootstrap 0.00, allgathers 0.01, topo 0.10, graphs 0.00, connections 0.06, rest 1.00)
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO ncclCommSplit comm 0x55cae6fe89c0 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId 901d0 parent 0x55cadade89e0 splitCount 1 color 1266629538 key 5 - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO ncclCommSplit comm 0x557309603670 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 101d0 parent 0x55730064a610 splitCount 1 color 1266629538 key 1 - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Init timings - ncclCommSplit: rank 7 nranks 8 total 0.55 (kernels 0.00, alloc 0.00, bootstrap 0.00, allgathers 0.01, topo 0.09, graphs 0.00, connections 0.06, rest 0.39)
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Init timings - ncclCommSplit: rank 5 nranks 8 total 0.77 (kernels 0.00, alloc 0.00, bootstrap 0.00, allgathers 0.01, topo 0.10, graphs 0.00, connections 0.05, rest 0.62)
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Init timings - ncclCommSplit: rank 1 nranks 8 total 0.76 (kernels 0.00, alloc 0.00, bootstrap 0.00, allgathers 0.01, topo 0.10, graphs 0.00, connections 0.06, rest 0.60)
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO ncclCommSplit comm 0x55e875022b30 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId a01c0 parent 0x55e8675b14b0 splitCount 1 color 1266629538 key 6 - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO ncclCommSplit comm 0x55eca298cda0 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId 201c0 parent 0x55ec9c119990 splitCount 1 color 1266629538 key 2 - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO ncclCommSplit comm 0x55cfdde9b730 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId 901c0 parent 0x55cfd20e4910 splitCount 1 color 1266629538 key 4 - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Init timings - ncclCommSplit: rank 6 nranks 8 total 0.84 (kernels 0.00, alloc 0.00, bootstrap 0.00, allgathers 0.01, topo 0.10, graphs 0.00, connections 0.05, rest 0.68)
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO ncclCommSplit comm 0x5635f6273520 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 101c0 parent 0x5635e92c0280 splitCount 1 color 1266629538 key 0 - Init COMPLETE
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Init timings - ncclCommSplit: rank 2 nranks 8 total 0.33 (kernels 0.00, alloc 0.00, bootstrap 0.00, allgathers 0.00, topo 0.10, graphs 0.00, connections 0.06, rest 0.17)
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Init timings - ncclCommSplit: rank 4 nranks 8 total 0.36 (kernels 0.00, alloc 0.00, bootstrap 0.00, allgathers 0.00, topo 0.10, graphs 0.00, connections 0.06, rest 0.19)
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Init timings - ncclCommSplit: rank 0 nranks 8 total 0.19 (kernels 0.00, alloc 0.00, bootstrap 0.00, allgathers 0.00, topo 0.10, graphs 0.00, connections 0.06, rest 0.02)
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 00/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 02/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 03/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 04/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 01/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 08/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 05/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 06/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 07/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 10/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 11/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 12/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 09/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 16/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 16/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 13/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 16/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 17/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 17/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 16/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 15/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 18/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 17/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 14/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 18/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 17/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 18/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 18/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 19/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 16/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 19/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 19/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 16/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 19/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 16/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 20/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 20/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 17/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 20/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 20/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 21/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 17/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 21/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 18/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 21/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 16/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 17/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 22/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 19/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 21/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 22/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 22/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 18/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 22/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 17/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Channel 23/0 : 1[1] -> 2[2] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 20/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Channel 23/0 : 3[3] -> 4[4] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Channel 23/0 : 7[7] -> 0[0] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Channel 23/0 : 2[2] -> 3[3] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 19/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 18/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 21/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 18/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 19/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 20/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 21/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 19/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 22/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 20/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 22/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 20/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 21/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Channel 23/0 : 6[6] -> 7[7] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Channel 23/0 : 5[5] -> 6[6] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 21/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 22/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 22/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Channel 23/0 : 4[4] -> 5[5] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Channel 23/0 : 0[0] -> 1[1] via P2P/CUMEM/read
ywang29-p4d-debug-1-worker-0:213686:213686 [5] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213687:213687 [6] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213682:213682 [1] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213684:213684 [3] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213688:213688 [7] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213681:213681 [0] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213685:213685 [4] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
ywang29-p4d-debug-1-worker-0:213683:213683 [2] NCCL INFO Connected all rings, use ring PXN 0 GDR 1
Before initializing optimizer states
MA 4.73 GB Max_MA 4.73 GB CA 4.77 GB Max_CA 5 GB
CPU Virtual Memory: used = 66.75 GB, percent = 6.0%
After initializing optimizer states
MA 4.73 GB Max_MA 5.68 GB CA 5.71 GB Max_CA 6 GB
CPU Virtual Memory: used = 66.76 GB, percent = 6.0%
After initializing ZeRO optimizer
MA 4.73 GB Max_MA 4.73 GB CA 5.71 GB Max_CA 6 GB
CPU Virtual Memory: used = 66.76 GB, percent = 6.0%
[INFO|trainer.py:1587] 2026-04-29 15:39:23,284 >> ***** Running training *****
[INFO|trainer.py:1588] 2026-04-29 15:39:23,284 >> Num examples = 30,000
[INFO|trainer.py:1589] 2026-04-29 15:39:23,284 >> Num Epochs = 2
[INFO|trainer.py:1590] 2026-04-29 15:39:23,284 >> Instantaneous batch size per device = 2
[INFO|trainer.py:1593] 2026-04-29 15:39:23,284 >> Total train batch size (w. parallel, distributed & accumulation) = 128
[INFO|trainer.py:1594] 2026-04-29 15:39:23,284 >> Gradient Accumulation steps = 8
[INFO|trainer.py:1595] 2026-04-29 15:39:23,284 >> Total optimization steps = 470
[INFO|trainer.py:1596] 2026-04-29 15:39:23,285 >> Number of trainable parameters = 2,031,739,904
wandb: [wandb.login()] Loaded credentials for https://api.wandb.ai from WANDB_API_KEY.
wandb: Currently logged in as: kkhya (maskmoe) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
wandb: setting up run igs7r887
wandb: Tracking run with wandb version 0.26.1
wandb: Run data is saved locally in /nfs/ywang29/lm-factory/wandb/run-20260429_153923-igs7r887
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run qwen3_1.7b_coding_fft
wandb: ⭐️ View project at https://wandb.ai/maskmoe/MFT-LM
wandb: 🚀 View run at https://wandb.ai/maskmoe/MFT-LM/runs/igs7r887
0%| | 0/470 [00:00<?, ?it/s]
0%| | 1/470 [00:04<34:04, 4.36s/it]
0%| | 2/470 [00:07<28:24, 3.64s/it]
1%| | 3/470 [00:09<24:14, 3.11s/it]