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

fixes for code (#206)

Browse Source 
* updated .gitignore

* removed unused GELU import

* fixed model_configs, fixed all tensors on same device

* removed unused tiktoken

* update

* update hparam search

* remove redundant tokenizer argument

---------

Co-authored-by: rasbt <mail@sebastianraschka.com>
This commit is contained in:
Daniel Kleine
2024-06-12 03:59:48 +02:00
committed by GitHub
parent e91718f1e7
commit 79210eb393
12 changed files with 33 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
appendix-E/01_main-chapter-code/appendix-E.ipynb
View File

@@ -1370,7 +1370,6 @@
"train_losses, val_losses, train_accs, val_accs, examples_seen = train_classifier_simple(\n",
" model, train_loader, val_loader, optimizer, device,\n",
" num_epochs=num_epochs, eval_freq=50, eval_iter=5,\n",
" tokenizer=tokenizer\n",
")\n",
"\n",
"end_time = time.time()\n",
@@ -1495,7 +1494,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.6"
"version": "3.11.4"
}
},
"nbformat": 4,

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

@@ -484,7 +484,7 @@ def calc_loss_batch(input_batch, target_batch, model, device):
# Overall the same as `train_model_simple` in chapter 5
def train_classifier_simple(model, train_loader, val_loader, optimizer, device, num_epochs,
eval_freq, eval_iter, tokenizer):
eval_freq, eval_iter):
# Initialize lists to track losses and tokens seen
train_losses, val_losses, train_accs, val_accs = [], [], [], []
examples_seen, global_step = 0, -1