@Vidhi1290 I just want to thank you for sharing your work with us. while training the model i encountered following error.
/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
3057 if size_average is not None or reduce is not None:
3058 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 3059 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
RuntimeError: size mismatch (got input: [6], target: [1])
This error occurred during the second epoch, at approximately 96% completion. It's worth noting that initially, the model was successfully trained for 1 epoch on the CPU without any issues.
Changes Made Before Using the Model
Before training the model, I made changes to some variables at the top of the notebook according to my requirements. These changes included adjusting variables such as label_col, tokens_path, and labels_path. No other modifications were made to the code or the model architecture.
Data Information
My data is structured in a CSV file with two columns: one for the text of the questions and another for the associated labels (levels 1-6). There are a total of 6 classes in the classification, with each text question associated with a specific level in the next column.
@Vidhi1290 I just want to thank you for sharing your work with us. while training the model i encountered following error.
/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
3057 if size_average is not None or reduce is not None:
3058 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 3059 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
RuntimeError: size mismatch (got input: [6], target: [1])
This error occurred during the second epoch, at approximately 96% completion. It's worth noting that initially, the model was successfully trained for 1 epoch on the CPU without any issues.
Changes Made Before Using the Model
Before training the model, I made changes to some variables at the top of the notebook according to my requirements. These changes included adjusting variables such as label_col, tokens_path, and labels_path. No other modifications were made to the code or the model architecture.
Data Information
My data is structured in a CSV file with two columns: one for the text of the questions and another for the associated labels (levels 1-6). There are a total of 6 classes in the classification, with each text question associated with a specific level in the next column.