TITC
d16527ddf2
total training iters may equal to warmup_iters ( #301 )
...
total_training_iters=20, warmup_iters=20= len(train_loader) 4 multiply n_epochs 5, then ZeroDivisionError occurred.
```shell
Traceback (most recent call last):
File "LLMs-from-scratch/ch05/05_bonus_hparam_tuning/hparam_search.py", line 191, in <module>
train_loss, val_loss = train_model(
^^^^^^^^^^^^
File "/mnt/raid1/docker/ai/LLMs-from-scratch/ch05/05_bonus_hparam_tuning/hparam_search.py", line 90, in train_model
progress = (global_step - warmup_iters) / (total_training_iters - warmup_iters)
~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
ZeroDivisionError: division by zero
```
2024-08-06 07:10:05 -05:00
SSebo
7643c6c0c4
Update ch05.ipynb ( #297 )
...
typo
2024-08-05 07:12:27 -05:00
Sebastian Raschka
08040f024c
Test code in pytorch 2.4 ( #285 )
...
* test code in pytorch 2.4
* update
2024-07-24 21:53:41 -05:00
TITC
6cbe6520a2
47,678-->48,725 ( #281 )
2024-07-22 21:24:57 -05:00
Sebastian Raschka
8d02cb1cee
Add download help message ( #274 )
2024-07-19 08:29:29 -05:00
rasbt
31806828d0
add links to summary sections
2024-06-29 07:33:26 -05:00
rasbt
219f45f808
refresh cross entropy figure
2024-06-29 07:22:23 -05:00
Daniel Kleine
1e69c8e0b5
fixed minor issues ( #252 )
...
* fixed typo
* fixed var name in md text
2024-06-29 06:38:25 -05:00
Daniel Kleine
81c843bdc0
minor fixes ( #246 )
...
* removed duplicated white spaces
* Update ch07/01_main-chapter-code/ch07.ipynb
* Update ch07/05_dataset-generation/llama3-ollama.ipynb
* removed duplicated white spaces
* fixed title again
---------
Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
2024-06-25 17:30:30 -05:00
Sebastian Raschka
cf0df54d7d
Show epochs as integers on x-axis ( #241 )
...
* Show epochs as integers on x-axis
* Update ch07/01_main-chapter-code/previous_chapters.py
* remove extra s
* modify exercise plots
* update chapter 7 plot
* resave ch07 for better file diff
2024-06-23 07:41:25 -05:00
rasbt
143a529c33
update generate to match output in main chapter
2024-06-22 12:01:51 -05:00
Daniel Kleine
ad9dd994dc
minor fixes ( #235 )
...
* removed unnecessary imports
* removed unnecessary semicolons
* format markdown
* format markdown
* fixed markdown
2024-06-21 08:40:54 -05:00
rasbt
6c84900af7
remove redundant line
2024-06-20 10:12:28 -05:00
rasbt
977f9c6eac
fix device loading
2024-06-20 08:07:00 -05:00
rasbt
283397aaf2
add main and optional sections
2024-06-19 17:48:25 -05:00
rasbt
85827e0a0b
note about dropout
2024-06-19 17:37:48 -05:00
Daniel Kleine
bbb2a0c3d5
fixed num_workers ( #229 )
...
* fixed num_workers
* ch06 & ch07: added num_workers to create_dataloader_v1
2024-06-19 17:36:46 -05:00
Sebastian Raschka
7bf70baf10
Remove duplicated cell ( #212 )
...
* add a suggestion since code snippet has been repeated.
* remove duplicated cell
---------
Co-authored-by: Shuyib <benmainye@gmail.com>
2024-06-15 12:48:34 -05:00
rasbt
c6466990bb
explain truncation in ch05
2024-06-12 19:50:11 -05:00
Sebastian Raschka
bcccda728b
check gpt files ( #208 )
2024-06-12 07:19:10 -05:00
Daniel Kleine
ef40f2f9ad
minor bug fixes ( #207 )
...
* fixed path arg for create_dataset_csvs()
* updated assign_check() to remove user warning
2024-06-12 06:27:56 -05:00
rasbt
e24fd98cdf
distinguish better between main chapter code and bonus materials
2024-06-11 21:07:42 -05:00
Daniel Kleine
dcbdc1d2e5
fixes for code ( #206 )
...
* 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>
2024-06-11 20:59:48 -05:00
rasbt
1b1fd21d64
fix typo in comment
2024-06-09 06:14:02 -05:00
Sebastian Raschka
72a073bbbf
Remove leftover instances of self.tokenizer ( #201 )
...
* Remove leftover instances of self.tokenizer
* add endoftext token
2024-06-08 14:57:34 -05:00
rasbt
6f0a5c320b
fix learning rate scheduler
2024-06-03 07:06:42 -05:00
rasbt
b352d9ef0a
update loss
2024-05-31 07:30:57 -05:00
Kumar Utsav
bc5d73857c
Update ch05.ipynb
...
Fixed incorrect token ids
2024-05-29 20:34:23 +05:30
Sebastian Raschka
39a831a4d8
Make header more clear
2024-05-25 10:44:12 -05:00
rasbt
98d453b666
update formatting
2024-05-24 07:20:37 -05:00
rasbt
b40c260859
update how to retrieve learning rate
2024-05-23 17:19:01 -05:00
Daniel Kleine
aa67e6e1ac
removed unnecessary .gitignore
2024-05-21 19:25:16 +00:00
rasbt
a5593f9860
change defaults to 0 temp
2024-05-19 09:04:49 -05:00
rasbt
1463b2ae47
use default value for temperature
2024-05-19 08:48:10 -05:00
rasbt
4851d5a0fa
add eos_id option for ch07
2024-05-18 12:35:40 -05:00
Daniel Kleine
cf8b6c1094
fixed empty space
2024-05-17 10:44:18 +02:00
rasbt
cd7ea15e8d
add readme
2024-05-13 08:50:55 -05:00
speed
45f6e72f40
fix 1024 characters to 1024 tokens ( #152 )
2024-05-11 13:17:07 -05:00
rasbt
aec169dc12
link formatting
2024-04-30 06:26:23 -05:00
Sebastian Raschka
97ed38116a
Rename drop_resid to drop_shortcut ( #136 )
2024-04-28 14:31:27 -05:00
rasbt
90d239b4f7
fix merge conflict
2024-04-22 07:05:40 -05:00
rasbt
72be9f4e8e
update numbering
2024-04-22 07:00:20 -05:00
rasbt
868955f6a5
file header
2024-04-22 06:53:38 -05:00
Sebastian Raschka
44b3815960
remove requests dependency ( #125 )
2024-04-21 14:15:05 -05:00
Sebastian Raschka
c70ddff558
Return nan if val loader is empty ( #124 )
2024-04-20 08:02:30 -05:00
Sebastian Raschka
155ac03f61
use torch no grad for loss ( #119 )
2024-04-14 08:13:07 -05:00
Sebastian Raschka
dd51d4ad83
Make datesets and loaders compatible with multiprocessing ( #118 )
2024-04-13 13:57:56 -05:00
Sebastian Raschka
9f3f231ac7
use correct lr
2024-04-12 19:55:07 -04:00
Sebastian Raschka
55ebabf95c
Automated link checking ( #117 )
...
* Automated link checking
* Fix links in Jupyter Nbs
2024-04-12 19:08:34 -04:00
Sebastian Raschka
e757091301
Organized setup instructions ( #115 )
...
* Organized setup instructions
* update tets
* link checker action
* raise error upon broken link
* fix links
* fix links
* delete duplicated paragraph
2024-04-10 22:09:46 -04:00
