Sebastian Raschka
4fad4695f6
Fix timeout issue related to spam data backup url ( #544 )
...
* Add backup url for Spam Dataset
* import urllib
* fix url
* fix timeout issue
2025-02-20 09:26:23 -06:00
Sebastian Raschka
eb6787397c
Add backup url for Spam Dataset ( #543 )
...
* Add backup url for Spam Dataset
* import urllib
* fix url
2025-02-20 08:08:28 -06:00
Sebastian Raschka
7e2092dd01
More pythonic way to find the longest sequence ( #512 )
...
* More pythonic way to find the longest sequence
* pep8 fix
2025-02-01 10:22:47 -06:00
Sebastian Raschka
7659af7cdd
Add backup URL for gpt2 weights ( #469 )
...
* Add backup URL for gpt2 weights
* newline
2025-01-05 11:28:09 -06:00
Daniel Kleine
dcef9b7d6f
Fixed command for row 16 additional experiment ( #439 )
...
* fixed command for row 16 experiment
* Update README.md
---------
Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
2024-11-17 06:50:00 +09:00
Sebastian Raschka
841b64f2b9
Add flexible padding bonus experiment ( #438 )
...
* Add flexible padding bonus experiment
* fix links
2024-11-15 08:51:01 +09:00
Sebastian Raschka
3c3dae0967
Add mean pooling experiment to classifier bonus experiments ( #406 )
...
* Add mean pooling experiment to classifier bonus experiments
* formatting
* add average embeddings option
* pep8
2024-10-20 11:04:18 -05:00
Sebastian Raschka
296a91afb8
add BERT experiment results ( #333 )
...
* add BERT experiment results
* cleanup
* formatting
2024-08-23 08:40:40 -05:00
Sebastian Raschka
7cbfe418bf
grammar fix
2024-08-21 19:16:21 -05:00
rasbt
1a962f3983
update lora experiments
2024-08-16 08:57:46 -05:00
TITC
70a7cddf9c
typo fix ( #323 )
2024-08-16 06:57:30 -05:00
TITC
e1072bbcd6
typo fix ( #321 )
...
* typo fix
experiment 5 is the same size as experiment 1, both are 124 Million. and experiment 6 is 355M ~3x 124M.
* typo fix
all layer FT vs all layer FT, "slightly worse by 1.3% " indicates it's exp 5 vs exp 9
* exp 5 vs 9
* Update ch06/02_bonus_additional-experiments/README.md
---------
Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
2024-08-15 08:45:34 -05:00
Sebastian Raschka
e4cfcc5b66
Update README.md
2024-08-15 08:22:47 -05:00
Sebastian Raschka
895512ebee
Revert accidental edit
2024-08-06 19:54:34 -05:00
rasbt
7a5771932b
note about logistic sigmoid
2024-08-06 19:48:30 -05:00
Sebastian Raschka
192bdc3501
improve gradient accumulation ( #300 )
2024-08-05 18:27:20 -05:00
Sebastian Raschka
d0f3b034d8
Add download help message ( #274 )
2024-07-19 08:29:29 -05:00
Jeroen Van Goey
70cfced899
fix typos, add codespell pre-commit hook ( #264 )
...
* fix typos, add codespell pre-commit hook
* Update .pre-commit-config.yaml
---------
Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
2024-07-16 07:07:04 -05:00
Daniel Kleine
87f47a281a
fixed spelling typos ( #258 )
2024-07-03 07:47:33 -05:00
Daniel Kleine
fb4e37ae15
fixed minor issues ( #252 )
...
* fixed typo
* fixed var name in md text
2024-06-29 06:38:25 -05:00
Daniel Kleine
73be1c592f
fixed num_workers ( #229 )
...
* fixed num_workers
* ch06 & ch07: added num_workers to create_dataloader_v1
2024-06-19 17:36:46 -05:00
Daniel Kleine
e5c3c5ce99
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
Daniel Kleine
79210eb393
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
b9ed5811c3
fix gradient comment
2024-06-09 20:23:18 -05:00
Sebastian Raschka
40ba3a4068
Remove leftover instances of self.tokenizer ( #201 )
...
* Remove leftover instances of self.tokenizer
* add endoftext token
2024-06-08 14:57:34 -05:00
Daniel Kleine
e637393056
updated Dockerfile and Additional Classification Finetuning Experiments ( #195 )
...
* accuracy to .2f
* added curl
2024-06-05 20:17:49 -05:00
Sebastian Raschka
605b4b03d7
Update README.md
2024-05-25 10:45:29 -05:00
rasbt
30ba6a3f4b
trainable token -> trainable token position
2024-05-23 11:43:20 -05:00
rasbt
c35cf65dbf
add assertion about data set length
2024-05-23 06:50:43 -05:00
Daniel Kleine
a81ba9bd8b
fixed last_two_blocks
2024-05-22 02:02:43 +00:00
rasbt
80d857c605
fix table alignment
2024-05-21 19:51:22 -05:00
rasbt
8a27baf7c2
experiment with last two blocks
2024-05-21 19:49:34 -05:00
Daniel Kleine
130a69ce27
improved readability of Additional Experiments table
2024-05-21 19:26:25 +00:00
rasbt
7b9b53c9f2
update lora init
2024-05-19 20:11:56 -05:00
rasbt
bc5cbbf1bd
change defaults to 0 temp
2024-05-19 09:04:49 -05:00
rasbt
59f5ed8d68
use default value for temperature
2024-05-19 08:48:10 -05:00
rasbt
faffebae4b
add ignore index experiment
2024-05-19 07:24:49 -05:00
rasbt
bdea15f6c6
new experiment w/o causal mask
2024-05-18 17:03:36 -05:00
Sebastian Raschka
00a466f0b9
fix row number typo
2024-05-18 15:54:13 -05:00
rasbt
9d84935b69
add eos_id option for ch07
2024-05-18 12:35:40 -05:00
rasbt
10ebc47720
Add experiment with gradient accumulation
2024-05-17 21:31:22 -05:00
rasbt
623bc19665
fix no padding option
2024-05-17 21:06:51 -05:00
rasbt
f1db50fe9a
fix indent
2024-05-17 07:58:01 -05:00
rasbt
2653c36957
Add new experiment without padding
2024-05-17 07:55:51 -05:00
Sebastian Raschka
7370ad1615
val before test acc
2024-05-13 07:36:18 -05:00
Sebastian Raschka
03d3b6ca72
Update README.md
2024-05-11 06:42:05 -05:00
Sebastian Raschka
cf299777b6
Move GPU column so that test accuracy is always visible
2024-05-11 06:41:25 -05:00
Sebastian Raschka
cfa1d0f997
Add LoRA experiments ( #151 )
...
* Add LoRA experiments
* Update ch06/02_bonus_additional-experiments/additional-experiments.py
2024-05-10 07:26:41 -05:00
rasbt
75545e4c1b
experiments with largest model
2024-05-09 07:40:09 -05:00
rasbt
9457676640
ouput -> output
2024-05-05 12:21:10 -05:00
