File size: 1,916 Bytes
d7ce189 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
import matplotlib.pyplot as plt
import numpy as np
from scipy.optimize import curve_fit
def parse_file(file_path):
data = []
with open(file_path, 'r') as file:
for line in file:
parts = line.strip().split()
step = int(parts[0].split(':')[1].split('/')[0])
is_train = 'val' not in parts[1]
if is_train:
loss_key = 'train_loss'
else:
loss_key = 'val_loss'
loss = float(parts[1].split(':')[1])
step_avg = float(parts[3].split(':')[1].replace('ms', ''))
data.append({
'step': step,
'loss': loss,
'step_avg': step_avg,
'is_train': is_train
})
return data
# Usage
file_path = 'baseline_log.txt'
data = parse_file(file_path)
# Extract the steps and losses into separate lists
steps = np.array([d['step'] for d in filter(lambda item: item['is_train'],data)])
losses = np.array([d['loss'] for d in filter(lambda item: item['is_train'],data)])
# Take the logarithm of the data
log_steps = np.log10(steps)
log_losses = np.log10(losses)
# Define a linear function
def linear_func(x, a, b):
return a * x + b
# Fit the linear function to the logarithmic data
popt, pcov = curve_fit(linear_func, log_steps, log_losses)
# Create the plot
plt.loglog(steps, losses, label='Data')
# Plot the fitted line
x_fit = np.logspace(np.log10(np.min(steps)), np.log10(np.max(steps)), 100)
y_fit = 10 ** (popt[0] * np.log10(x_fit) + popt[1])
plt.loglog(x_fit, y_fit, label='Fitted line', color='red')
# Add title and labels
plt.title('Loss as a function of step')
plt.xlabel('Step')
plt.ylabel('Loss')
plt.legend()
# Print the fitted parameters
print('Fitted parameters: a = {:.2f}, b = {:.2f}'.format(popt[0], popt[1]))
# Save the plot to a file
plt.savefig('loss_plot2.png')
# Show the plot
plt.show()
|