The model did not return a loss from the inputs, only the following keys: logits. For reference, the inputs it received are input_values

ahsannawazch · November 10, 2024, 3:26pm

worked for me too. Don’t know why

shrijayan · February 15, 2025, 4:37pm

After reviewing the data_processor.py file, I can see the current data processing method. The prepare_dataset method currently creates a dataset with “input_ids”, “attention_mask”, and “labels” columns.

Montaque · April 2, 2025, 4:50pm

you should specifiy a proble type. change the code to

Define DistilBERT as our base model:

model = AutoModelForSequenceClassification.from_pretrained(“distilbert-base-uncased”, num_labels=9,problem_type=‘multi_label_classification’)

Atodush · April 23, 2025, 9:09am

Worked for me, too. Can somebody explain why?
I’m confused

Topic		Replies	Views
I tired and can't solve this error , ValueError: The model did not return a loss from the inputs, only the following keys: logits. For reference, the inputs it received are input_ids,attention_mask Models	1	1138	March 29, 2023
ValueError: The model did not return a loss from the inputs, only the following keys: logits. For reference, the inputs it received are input_ids,attention_mask 🤗Transformers	1	1138	August 25, 2023
ValueError: The model did not return a loss from the inputs Beginners	1	4336	December 21, 2023
Input type Runtime Error in fine-tuning hf blog tutorial Beginners	2	681	March 8, 2024
Wer is 1 when using wav2vec2pretrained model Models	0	226	October 4, 2023

The model did not return a loss from the inputs, only the following keys: logits. For reference, the inputs it received are input_values

Define DistilBERT as our base model:

Related topics