Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [loss]

40 questions
4
votes
0 answers

How Does the Reward Model in ChatGPT Calculate Losses?

Reading the InstructGPT paper(which seems to be what ChatGPT was built off of), I found this equation for the reward function. However, I'm struggling to understand how this equation is used to translate rankings between different response to a…
itisyeetimetoday
  • 141
  • 1
3
votes
0 answers

Loss while fine tuning a transformer based pose estimation model not reducing

I am trying to fine-tune a transformer/encoder based pose estimation model available here at: https://huggingface.co/docs/transformers/en/model_doc/vitpose When passing "labels" attribute to the forward pass of the model, the model returns "Training…
Soham Bhaumik
  • 131
  • 1
2
votes
1 answer

HuggingFace Transformers is giving loss: nan - accuracy: 0.0000e+00

I am a HuggingFace Newbie and I am fine-tuning a BERT model (distilbert-base-cased) using the Transformers library but the training loss is not going down, instead I am getting loss: nan - accuracy: 0.0000e+00. My code is largely per the boiler…
JasonExcel
  • 21
  • 1
  • 2
2
votes
0 answers

How to calculate MAE and threshold in a multivariate time series

I'm trying to understand how to calculate the MAE in my time series and then the thresholds to understand which of my data in the test set are anomalies. I'm following this tutorial, which is based on a univariate time series, and they calculate it…
Fabio
  • 53
  • 10
2
votes
3 answers

Custom loss function for regression

I am trying to write a custom loss function for a machine learning regression task. What I want to accomplish is following: Reward higher preds, higher targets Punish higher preds, lower targets Ignore lower preds, lower targets Ignore lower preds,…
Filip
  • 21
  • 1
  • 2
1
vote
0 answers

How to interpret high loss value from model.evaluate() on test data

I'm collecting some metrics for my model's performance using: # Evaluate the model on the test data using `evaluate` print("Evaluate on test data") results = model.evaluate(test_images) print("test loss, test acc:", results) I have an very high…
TomSelleck
  • 115
  • 8
1
vote
1 answer

Accuracy graph of binary classification by CNN

Why in binary classification of images with CNN the loss and accuracy graph are so unstable? I mean accuracy of validation test does not increase smoothly, it goes to 80%, then comes to 60%, then again goes to 84% and so on. Same is the case with…
Nagh
  • 129
  • 1
  • 6
1
vote
1 answer

Should Discriminator Loss increase or decrease?

This question is purely based on the theoretical aspect of GANs. So, when training a GAN how should the discriminator loss look like? Should the loss of discriminator increase (as the generator is successfully fooled discriminator) Or should the…
Sai
  • 188
  • 1
  • 8
1
vote
3 answers

Regression problem with Deep Learning

I'm working on the Housing Price dataset, where the target is to predict the housing price. The price of the house will always be positive and according to me, it's possible that the model can predict a negative outcome for some of the samples. If…
vipin bansal
  • 1,282
  • 11
  • 19
1
vote
1 answer

What loss function can I use?

My dataset consists of 5625 Arabic examples and 5625 synsets, and my model is CNN followed by a sigmoid classification layer. I constructed this 5625 synsets to 5625 classes, and my predicted output is a probability between 0 and 1 for each class.…
rahma touzi
  • 11
  • 2
1
vote
1 answer

Does reducing the loss change the amount of change during backpropagation?

If I would do loss = loss/10 before calculating the gradient would that change the amount of change applied to the model parameters during back propagation? Or is the amount of change only dependent on the direction of the gradient and the learning…
GreedyGroot
  • 11
  • 1
1
vote
0 answers

Transfer Learning - GoogLeNet - Training Times || Loss not converging || Pytorch

Hi Community and thanks in advance for the help. I am working on transfer learning - specifically GoogLeNet model with the Food101 Dataset. Code is below. I think everything is in order from data preprocessing through to training but the training…
James
  • 21
  • 1
1
vote
0 answers

I can't understand why the validation and training loss almost constant and not converging?

df = df_1.iloc[0:200000, :] # Train-Test Split (keeping all columns) train, test = df.loc[df['index'] <= 160000], df.loc[df['index'] > 160000] # Create a StandardScaler object and fit on the first 21 columns of the training data scaler =…
user731995
  • 11
  • 2
1
vote
0 answers

Calculationg perplexity (in natural language processing) manually

I am trying to understand Perplexity within Natural Language Processing as a metric more fully. And I am doing so by creating manual examples to understand all the component parts. Is the following correctly understood: Given a lists W of words (as…
Piskator
  • 135
  • 7
1
vote
1 answer

What does that mean if the loss looks like this?

I have a problem. I have trained a model. And as you can see, there is a zigzag in the loss. In addition, the validation loss is increasing. What does this mean if you only look at the training curve? Is there an overfitting? And the model does not…
Test
  • 89
  • 9
1
2 3