Skip to content

Instantly share code, notes, and snippets.

@spdin

spdin/plot.py

Created February 17, 2023 07:16
Show Gist options
  • Save spdin/63ddc9b0999da75bf226543c9b2aecf3 to your computer and use it in GitHub Desktop.
Save spdin/63ddc9b0999da75bf226543c9b2aecf3 to your computer and use it in GitHub Desktop.
Download ZIP
plot graph
Raw
plot.py
import matplotlib.pyplot as plt
training_points = [0, 10, 25, 50, 100, 250, 500]
bert_acc = [0.5310526315789473, 0.5727631578947369, 0.6130263157894736, 0.8502631578947368, 0.8619736842105263, 0.8727631578947368, 0.8660526315789474]
roberta_acc = [0.49236842105263157, 0.6001315789473685, 0.7292105263157894, 0.7705263157894737, 0.8469736842105263, 0.8442105263157895, 0.8730263157894737]
plt.plot(training_points, bert_acc, label="bert-base-uncased")
plt.plot(training_points, roberta_acc, label="roberta-base")
plt.title("Accuracy of BERT and RoBERTa at Different Training Points")
plt.xlabel("Number of Training Points")
plt.ylabel("Accuracy")
plt.legend()
plt.show()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment