![]() ![]() ![]() This IS expected if you are initializing AlbertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). Some weights of AlbertForSequenceClassification were not initialized from the model checkpoint at albert-base-v2 and are newly initialized: This IS NOT expected if you are initializing AlbertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). ![]() LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: Ġ | model | AlbertForSequenceClassification | 11.7 MĤ6.740 Total estimated model params size (MB) You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. Mcc = cov_ytyp / np.sqrt(cov_ytyt * cov_ypyp) usr/local/lib/python3.8/dist-packages/sklearn/metrics/_classification.py:873: RuntimeWarning: invalid value encountered in double_scalars home/AzDevOps_azpcontainer/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/data_loading.py:102: UserWarning: The dataloader, val dataloader 0, does not have many workers which may be a bottleneck. home/AzDevOps_azpcontainer/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/data_loading.py:102: UserWarning: The dataloader, train dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 12 which is the number of cpus on this machine) in the `DataLoader` init to improve performance. home/AzDevOps_azpcontainer/.local/lib/python3.8/site-packages/pytorch_lightning/callbacks/model_checkpoint.py:610: LightningDeprecationWarning: Relying on `self.log('val_loss'. )` to set the ModelCheckpoint monitor is deprecated in v1.2 and will be removed in v1.4. Please, create your own `mc = ModelCheckpoint(monitor='your_monitor')` and use it as `Trainer(callbacks=)`. Usr/local/lib/python3.8/dist-packages/torch/optim/lr_scheduler.py:216: UserWarning: Please also save or load the state of the optimizer when saving or loading the scheduler. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |