books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

figure scaling

Browse Source
This commit is contained in:
rasbt
2024-04-01 08:05:01 -05:00
parent 005835bfce
commit 776a517d18
3 changed files with 67 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

149
appendix-D/01_main-chapter-code/appendix-D.ipynb
View File

File diff suppressed because one or more lines are too long

2
appendix-D/01_main-chapter-code/previous_chapters.py
View File

@@ -293,7 +293,7 @@ def generate_and_print_sample(model, tokenizer, device, start_context):
def plot_losses(epochs_seen, tokens_seen, train_losses, val_losses):
fig, ax1 = plt.subplots()
fig, ax1 = plt.subplots(figsize=(5, 3))
# Plot training and validation loss against epochs
ax1.plot(epochs_seen, train_losses, label="Training loss")