registered at /usr1/workspace/FPTA_Daily_Plugin_open_v1.8.1-3.0.rc2/CODE/build/aten/src/ATen/RegisterSchema.cpp:20
dispatch key: Math
previous kernel: registered at /usr1/workspace/FPTA_Daily_Plugin_open_v1.8.1-3.0.rc2/CODE/build/aten/src/ATen/RegisterMath.cpp:5686
new kernel: registered at /usr1/workspace/FPTA_Daily_Plugin_open_v1.8.1-3.0.rc2/Plugin/torch_npu/csrc/aten/ops/HasCompatibleShallowCopyType.cpp:37 (function registerKernel)
/opt/conda/lib/python3.7/site-packages/socks.py:58: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
from collections import Callable
04/07/2023 17:29:54 - INFO - __main__ - device: device(type='npu', index=0)
Some weights of themodel checkpoint at./save_models/graphcodebert-base were not used when initializing RobertaModel: ['lm_head.dense.weight', 'lm_head.decoder.bias', 'lm_head.layer_norm.bias', 'lm_head.layer_norm.weight', 'lm_head.decoder.weight', 'lm_head.dense.bias', 'lm_head.bias']
- This IS expected if youare initializing RobertaModel from the checkpoint of a modeltrained on another task or withanother architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected ifyouare initializing RobertaModel fromthe checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Some weights of RobertaModel were not initialized from the modelcheckpoint at ./save_models/graphcodebert-base and are newly initialized: ['roberta.pooler.dense.bias', 'roberta.pooler.dense.weight']
You should probably TRAIN this model on a down-stream taskto beable to use it for predictions and inference.
registered at /usr1/workspace/FPTA_Daily_Plugin_open_v1.8.1-3.0.rc2/CODE/build/aten/src/ATen/RegisterSchema.cpp:20
dispatch key: Math
previous kernel: registered at /usr1/workspace/FPTA_Daily_Plugin_open_v1.8.1-3.0.rc2/CODE/build/aten/src/ATen/RegisterMath.cpp:5686
new kernel: registered at /usr1/workspace/FPTA_Daily_Plugin_open_v1.8.1-3.0.rc2/Plugin/torch_npu/csrc/aten/ops/HasCompatibleShallowCopyType.cpp:37 (function registerKernel)
/opt/conda/lib/python3.7/site-packages/socks.py:58: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
from collections import Callable
04/07/2023 17:29:54- INFO - __main__ - device: device(type='npu', index=0)
Some weights of the modelcheckpoint at ./save_models/graphcodebert-base were not usedwhen initializing RobertaModel:['lm_head.dense.weight', 'lm_head.decoder.bias', 'lm_head.layer_norm.bias', 'lm_head.layer_norm.weight', 'lm_head.decoder.weight', 'lm_head.dense.bias', 'lm_head.bias']
- This IS expected if youareinitializing RobertaModel from thecheckpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing RobertaModel fromthe checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Some weights of RobertaModel were not initialized from themodelcheckpoint at ./save_models/graphcodebert-base and are newly initialized: ['roberta.pooler.dense.bias', 'roberta.pooler.dense.weight']
You shouldprobablyTRAIN this model onadown-stream task tobe able touse it for predictions andinference.
