(.jrexenv) raphy@raohy:~/jerex$ python3 ./jerex_train.py --config-path configs/docred_joint
/home/raphy/jerex/./jerex_train.py:12: UserWarning:
The version_base parameter is not specified.
Please specify a compatability version level, or None.
Will assume defaults for version 1.1
@hydra.main(config_name='train', config_path='configs/docred_joint')
sys:1: UserWarning:
'train' is validated against ConfigStore schema with the same name.
This behavior is deprecated in Hydra 1.1 and will be removed in Hydra 1.2.
See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/automatic_schema_matching for migration instructions.
/home/raphy/jerex/.jrexenv/lib/python3.12/site-packages/hydra/main.py:94: UserWarning:
'train' is validated against ConfigStore schema with the same name.
This behavior is deprecated in Hydra 1.1 and will be removed in Hydra 1.2.
See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/automatic_schema_matching for migration instructions.
_run_hydra(
/home/raphy/jerex/.jrexenv/lib/python3.12/site-packages/hydra/_internal/hydra.py:119: UserWarning: Future Hydra versions will no longer change working directory at job runtime by default.
See https://hydra.cc/docs/1.2/upgrades/1.1_to_1.2/changes_to_job_working_dir/ for more information.
ret = run_job(
datasets:
train_path: ./data/datasets/docred_joint/train_joint.json
valid_path: ./data/datasets/docred_joint/dev_joint.json
test_path: null
types_path: ./data/datasets/docred_joint/types.json
model:
model_type: joint_multi_instance
encoder_path: bert-base-cased
tokenizer_path: bert-base-cased
mention_threshold: 0.85
coref_threshold: 0.85
rel_threshold: 0.6
prop_drop: 0.1
meta_embedding_size: 25
size_embeddings_count: 30
ed_embeddings_count: 300
token_dist_embeddings_count: 700
sentence_dist_embeddings_count: 50
position_embeddings_count: 700
sampling:
neg_mention_count: 200
neg_coref_count: 200
neg_relation_count: 200
max_span_size: 10
sampling_processes: 8
neg_mention_overlap_ratio: 0.5
lowercase: false
loss:
mention_weight: 1.0
coref_weight: 1.0
entity_weight: 0.25
relation_weight: 1.0
inference:
valid_batch_size: 1
test_batch_size: 1
max_spans: null
max_coref_pairs: null
max_rel_pairs: null
training:
batch_size: 1
min_epochs: 20
max_epochs: 20
lr: 5.0e-05
lr_warmup: 0.1
weight_decay: 0.01
max_grad_norm: 1.0
accumulate_grad_batches: 1
max_spans: null
max_coref_pairs: null
max_rel_pairs: null
distribution:
gpus: []
accelerator: ''
prepare_data_per_node: false
misc:
store_predictions: true
store_examples: true
flush_logs_every_n_steps: 1000
log_every_n_steps: 1000
deterministic: false
seed: null
cache_path: null
precision: 32
profiler: null
final_valid_evaluate: true
Parse dataset '/home/raphy/jerex/data/datasets/docred_joint/train_joint.json': 77%|█████████████████████████████████████████████████▉ | 2309/3008 [00:21<00:10, 65.20it/s]
Parse dataset '/home/raphy/jerex/data/datasets/docred_joint/train_joint.json': 100%|████████████████████████████████████████████████████████████████| 3008/3008 [00:28<00:00, 106.67it/s]
Parse dataset '/home/raphy/jerex/data/datasets/docred_joint/dev_joint.json': 100%|█████████████████████████████████████████████████████████████████████| 300/300 [00:03<00:00, 94.99it/s]
Some weights of JointMultiInstanceModel were not initialized from the model checkpoint at bert-base-cased and are newly initialized: ['coreference_resolution.coref_classifier.bias', 'coreference_resolution.coref_classifier.weight', 'coreference_resolution.coref_ed_embeddings.weight', 'coreference_resolution.coref_linear.bias', 'coreference_resolution.coref_linear.weight', 'entity_classification.entity_classifier.bias', 'entity_classification.entity_classifier.weight', 'entity_classification.linear.bias', 'entity_classification.linear.weight', 'mention_localization.linear.bias', 'mention_localization.linear.weight', 'mention_localization.mention_classifier.bias', 'mention_localization.mention_classifier.weight', 'mention_localization.size_embeddings.weight', 'relation_classification.entity_type_embeddings.weight', 'relation_classification.pair_linear.bias', 'relation_classification.pair_linear.weight', 'relation_classification.rel_classifier.bias', 'relation_classification.rel_classifier.weight', 'relation_classification.rel_linear.bias', 'relation_classification.rel_linear.weight', 'relation_classification.sentence_distance_embeddings.weight', 'relation_classification.token_distance_embeddings.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
Error executing job with overrides: []
Traceback (most recent call last):
File "/home/raphy/jerex/./jerex_train.py", line 20, in train
model.train(cfg)
File "/home/raphy/jerex/jerex/model.py", line 328, in train
trainer = pl.Trainer(callbacks=[checkpoint_callback, LearningRateMonitor(logging_interval='step')],
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/raphy/jerex/.jrexenv/lib/python3.12/site-packages/pytorch_lightning/utilities/argparse.py", line 70, in insert_env_defaults
return fn(self, **kwargs)
^^^^^^^^^^^^^^^^^^
TypeError: Trainer.__init__() got an unexpected keyword argument 'gpus'
In the training phase I get this error :
python version: 3.12.3
OS: Ubuntu 24.04
How to make it work?