Fine-Tuning of Self-Supervised Models for Audio based Bird Detection. I am trying to add linear classifier on top of wav2vec2. I want to fine tune the wav2vec2 mdel for multi-class classification as below. I followed the tutorial from HuggingFace, but I am still getting the following error Valu…

How do you know which columns to use? I am using a different model but getting same error but with different model. This is my error statement and code ValueError: The model did not return a loss from the inputs, only the following keys: logits,past_key_values. For reference, the inputs it received…

Has anyone definitively solved this error? I am running into the same problem: from transformers import BertForQuestionAnswering, BertForTokenClassification, BertForSequenceClassification, pipeline, BertTokenizer, Trainer, TrainingArguments, DistilBertForSequenceClassification, DistilBertTokenizer…

In my case the perfect solution was to have a column named “label”. My data set had the column “target”, “label_name” and so on. Seems like the column names made the issue. I did toxic_encoded = toxic_encoded.rename_column("target", "label") and it started training.

I had the same issue. I removed the data_collator argument and it worked. I think it internally handles tokenizing + padding the formatted prompt. trainer = SFTTrainer( model=model, train_dataset=dataset["train"], eval_dataset=dataset["test"], peft_config=peft_config, max_seq_le…

Oh , I trained BERT model , and while investigating about it found out that model expects the input for training as text and predictions as label . So I renamed the input dataset as text and label,

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

Intermediate

Saugatkafley January 30, 2024, 4:12pm 13

Keeping the columns as text and label solved the issue.

Topic		Replies	Views
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	1250	August 25, 2023
Multi_class_classification errors when fine-tuning via TrainerAPI Beginners	0	400	February 20, 2023
Fine Tuning IMDb tutorial - Unable to reproduce and adapt Beginners	19	8734	August 21, 2020
Chapter 3 questions Course	160	11852	March 7, 2026
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	1192	March 29, 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

Related topics