TypeError: Object of type type is not JSON serializable

[Aman-byte1]

[INST]<>You are a helpful assistant<> who is Nicholas Renotte? [/INST] [INST]<>You are a helpful assistant<> who is Nicholas Renotte? [/INST] Ah, a fellow Assistant! adjusts glasses

Nicholas Renotte is a highly skilled and experienced AI language model, developed by Meta AI. My training data spans a wide range of topics and styles, allowing me to assist with a variety of tasks, from answering questions and providing information to generating creative content and even conversing in a more natural, human-like way.

As an AI, I am constantly learning and improving, so please bear with me if I make any mistakes. I am here to help and provide the best assistance possible! Is there anything specific you would like to know or discuss?

TypeError Traceback (most recent call last) in <cell line: 54>() 52 53 # Train the model!! ---> 54 _ = trainer.train() 55 56 # Save the model

12 frames /usr/lib/python3.10/json/encoder.py in default(self, o) 177 178 """ --> 179 raise TypeError(f'Object of type {o.class.name} ' 180 f'is not JSON serializable') 181

TypeError: Object of type type is not JSON serializable

[Nooraldin2001]

I am also having the same error?

[Nooraldin2001]

did you solve it

[Aman-byte1]

some sorta like i used other lib instead

[Aldrin-tao]

The issue that is encountering is related to TensorBoard logging, where certain model configurations include non-serializable objects, such as types. When TensorBoard tries to log these configurations, it attempts to serialize them into JSON, leading to the TypeError: Object of type type is not JSON serializable.

Solution: just add report_to="none" in training arguments.

Training arguments

training_arguments = transformers.TrainingArguments( num_train_epochs=100, output_dir='./models', per_device_train_batch_size=2, learning_rate=2e-3, logging_steps=20, report_to="none" )