Skip to content

terminate called after throwing an instance of 'c10::Error' what(): [enforce fail at inline_container.cc:319] . unexpected pos 2302963008 vs 2302962896 frame #0: c10::ThrowEnforceNotMet(char const*, int, char const*, std::string const&, void const*) + 0x55 (0x15158b1320a5 in /usr/local/lib/python3.8/dist-packages/torch/lib/libc10.so) #63

@lldd1001

Description

@lldd1001

frame #1: + 0x34396bc (0x1514c3a796bc in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_cpu.so)
frame #2: mz_zip_writer_add_mem_ex_v2 + 0x5b1 (0x1514c3a73a91 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_cpu.so)
frame #3: caffe2::serialize::PyTorchStreamWriter::writeRecord(std::string const&, void const*, unsigned long, bool) + 0xb9 (0x1514c3a7ac79 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_cpu.so)
frame #4: caffe2::serialize::PyTorchStreamWriter::writeEndOfFile() + 0x2c3 (0x1514c3a7b143 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_cpu.so)
frame #5: caffe2::serialize::PyTorchStreamWriter::~PyTorchStreamWriter() + 0x125 (0x1514c3a7b3b5 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_cpu.so)
frame #6: + 0x6d90a5 (0x15155c0700a5 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_python.so)
frame #7: + 0x36658f (0x15155bcfd58f in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_python.so)
frame #8: + 0x36747f (0x15155bcfe47f in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_python.so)
frame #9: /usr/bin/python3.8() [0x5ec780]
frame #10: /usr/bin/python3.8() [0x5441f8]
frame #11: /usr/bin/python3.8() [0x54424a]
frame #12: _PyEval_EvalFrameDefault + 0x286b (0x56d1eb in /usr/bin/python3.8)
frame #13: _PyFunction_Vectorcall + 0x1b6 (0x5f6836 in /usr/bin/python3.8)
frame #14: _PyEval_EvalFrameDefault + 0x72e (0x56b0ae in /usr/bin/python3.8)
frame #15: _PyEval_EvalCodeWithName + 0x26a (0x56939a in /usr/bin/python3.8)
frame #16: _PyFunction_Vectorcall + 0x393 (0x5f6a13 in /usr/bin/python3.8)
frame #17: _PyEval_EvalFrameDefault + 0x190c (0x56c28c in /usr/bin/python3.8)
frame #18: _PyFunction_Vectorcall + 0x1b6 (0x5f6836 in /usr/bin/python3.8)
frame #19: _PyEval_EvalFrameDefault + 0x85a (0x56b1da in /usr/bin/python3.8)
frame #20: _PyEval_EvalCodeWithName + 0x26a (0x56939a in /usr/bin/python3.8)
frame #21: _PyFunction_Vectorcall + 0x393 (0x5f6a13 in /usr/bin/python3.8)
frame #22: _PyEval_EvalFrameDefault + 0x56b5 (0x570035 in /usr/bin/python3.8)
frame #23: _PyFunction_Vectorcall + 0x1b6 (0x5f6836 in /usr/bin/python3.8)
frame #24: _PyEval_EvalFrameDefault + 0x72e (0x56b0ae in /usr/bin/python3.8)
frame #25: _PyFunction_Vectorcall + 0x1b6 (0x5f6836 in /usr/bin/python3.8)
frame #26: PyObject_Call + 0x1f7 (0x5f3547 in /usr/bin/python3.8)
frame #27: _PyEval_EvalFrameDefault + 0x1f4d (0x56c8cd in /usr/bin/python3.8)
frame #28: _PyEval_EvalCodeWithName + 0x26a (0x56939a in /usr/bin/python3.8)
frame #29: _PyFunction_Vectorcall + 0x393 (0x5f6a13 in /usr/bin/python3.8)
frame #30: _PyEval_EvalFrameDefault + 0x72e (0x56b0ae in /usr/bin/python3.8)
frame #31: _PyFunction_Vectorcall + 0x1b6 (0x5f6836 in /usr/bin/python3.8)
frame #32: PyObject_Call + 0x1f7 (0x5f3547 in /usr/bin/python3.8)
frame #33: _PyEval_EvalFrameDefault + 0x1f4d (0x56c8cd in /usr/bin/python3.8)
frame #34: _PyEval_EvalCodeWithName + 0x26a (0x56939a in /usr/bin/python3.8)
frame #35: _PyFunction_Vectorcall + 0x393 (0x5f6a13 in /usr/bin/python3.8)
frame #36: _PyEval_EvalFrameDefault + 0x56b5 (0x570035 in /usr/bin/python3.8)
frame #37: /usr/bin/python3.8() [0x6b2b5c]
frame #38: _PyEval_EvalFrameDefault + 0x72e (0x56b0ae in /usr/bin/python3.8)
frame #39: _PyEval_EvalCodeWithName + 0x26a (0x56939a in /usr/bin/python3.8)
frame #40: PyEval_EvalCode + 0x27 (0x68d047 in /usr/bin/python3.8)
frame #41: /usr/bin/python3.8() [0x67e351]
frame #42: /usr/bin/python3.8() [0x67e3cf]
frame #43: /usr/bin/python3.8() [0x67e471]
frame #44: PyRun_SimpleFileExFlags + 0x197 (0x67e817 in /usr/bin/python3.8)
frame #45: Py_RunMain + 0x212 (0x6b6fe2 in /usr/bin/python3.8)
frame #46: Py_BytesMain + 0x2d (0x6b736d in /usr/bin/python3.8)
frame #47: __libc_start_main + 0xf3 (0x15158ed860b3 in /usr/lib/x86_64-linux-gnu/libc.so.6)
frame #48: _start + 0x2e (0x5fa5ce in /usr/bin/python3.8)

train.sh: line 21: 7442 Aborted (core dumped) fairseq-train ../../data/DDI/relis-bin --save-dir ${SAVE_DIR} --user-dir ../../src --finetune-from-model ../../checkpoints/Pre-trained-BioGPT/checkpoint.pt --task language_modeling_prompt --arch transformer_lm_prompt_biogpt --share-decoder-input-output-embed --decoder-learned-pos --optimizer adam --adam-betas '(0.9, 0.98)' --weight-decay 0.01 --clip-norm 0.0 --lr 1e-4 --lr-scheduler inverse_sqrt --warmup-updates 500 --warmup-init-lr 1e-07 --tokens-per-sample 1024 --max-source-positions 640 --max-target-positions 1024 --max-tokens 1024 --update-freq 32 --skip-invalid-size-inputs-valid-test --max-epoch 100 --keep-last-epochs 5 --learned-prompt 9

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions