Sebastian Raschka
38969864e6
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
rasbt
a20ce1b817
remove redundant code line
2024-10-13 15:58:11 -05:00
Sebastian Raschka
b6c4b2f9f1
Update bonus section formatting ( #400 )
2024-10-12 10:26:08 -05:00
Sebastian Raschka
7ef5129e18
Fix truncation issue in classify_review function ( #373 )
2024-09-25 19:54:36 -05:00
Daniel Kleine
5f36d2af4c
removed unnecessary imports ( #367 )
2024-09-22 11:59:37 -05:00
Sebastian Raschka
76e9a9ec02
Add user interface to ch06 and ch07 ( #366 )
...
* Add user interface to ch06 and ch07
* pep8
* fix url
2024-09-21 20:33:00 -05:00
Sebastian Raschka
52ee1c7cdb
Add missing bullet point
2024-09-21 12:59:12 -05:00
Mingyuan Xu
f77c376b05
Run generate example in ch06 optionally on GPU ( #352 )
...
* model.to("cuda")
model.to("cuda")
* update device placement
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
2024-09-13 08:01:52 -05:00
Daniel Kleine
c7267c3b09
ch06/03 fixes ( #336 )
...
* fixed bash commands
* fixed help docstrings
* added missing logreg bash cmd
* Update train_bert_hf.py
* Update train_bert_hf_spam.py
* Update README.md
---------
Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
2024-08-27 08:23:25 +02:00
rasbt
91cdfe3309
sklearn baseline and roberta-large update
2024-08-26 10:31:54 +02:00
TITC
4f791e6cc2
add RoBERTa and params frozen ( #335 )
...
* add roberta experiment result
* add roberta & params frozen
* Update README.md
* modify lr
* modify lr
---------
Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
2024-08-26 10:27:09 +02:00
Sebastian Raschka
564362044a
add BERT experiment results ( #333 )
...
* add BERT experiment results
* cleanup
* formatting
2024-08-23 08:40:40 -05:00
Sebastian Raschka
ed257789a4
grammar fix
2024-08-21 19:16:21 -05:00
Sebastian Raschka
c443035d56
Note about MPS in ch06 and ch07 ( #325 )
2024-08-19 08:11:33 -05:00
rasbt
e7cb2ebd8d
update lora experiments
2024-08-16 08:57:46 -05:00
TITC
d2befdf00e
typo fix ( #323 )
2024-08-16 06:57:30 -05:00
TITC
f6526f7766
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
4ea526908e
Update README.md
2024-08-15 08:22:47 -05:00
TITC
38390b2a8d
track tokens seen in chapter5, track examples seen in chapter6 ( #319 )
2024-08-13 07:09:05 -05:00
Sebastian Raschka
c5eaae11b1
Revert accidental edit
2024-08-06 19:54:34 -05:00
rasbt
06151a809e
note about logistic sigmoid
2024-08-06 19:48:30 -05:00
Sebastian Raschka
70e5714556
improve gradient accumulation ( #300 )
2024-08-05 18:27:20 -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
Sebastian Raschka
8d02cb1cee
Add download help message ( #274 )
2024-07-19 08:29:29 -05:00
Jeroen Van Goey
48bd72c890
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
Sebastian Raschka
4f0a107692
show how to use the finetuned model
2024-07-09 06:43:26 -07:00
Daniel Kleine
90b25ece3d
fixed spelling typos ( #258 )
2024-07-03 07:47:33 -05:00
Sebastian Raschka
f6bcdd37bd
Fix links in summary sections ( #254 )
2024-06-29 07:51:31 -05:00
rasbt
31806828d0
add links to summary sections
2024-06-29 07:33:26 -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
06921f3333
minor markdown fixes ( #236 )
2024-06-21 13:55:34 -05:00
Sebastian Raschka
6c0dc2362b
Add standalone finetuning and evaluation scripts for chapter 7 ( #234 )
...
* add finetuning and eval scripts
* update link
* update links
* fix link
2024-06-21 05:23:24 -05:00
rasbt
283397aaf2
add main and optional sections
2024-06-19 17:48:25 -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
Jinge Wang
10018e00ff
Fixed some typos in ch06.ipynb ( #219 )
2024-06-18 05:54:01 -05:00
rasbt
3e0b0c66a8
fix spelling
2024-06-18 05:50:40 -05:00
rasbt
19c5784f82
replace figure
2024-06-18 05:46:36 -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
1d278c65da
fix gradient comment
2024-06-09 20:23:18 -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
Daniel Kleine
ba1c1e74aa
updated Dockerfile and Additional Classification Finetuning Experiments ( #195 )
...
* accuracy to .2f
* added curl
2024-06-05 20:17:49 -05:00
Sebastian Raschka
49b8e2e767
Update README.md
2024-05-25 10:45:29 -05:00
rasbt
98d453b666
update formatting
2024-05-24 07:20:37 -05:00
rasbt
b43a7a8820
trainable token -> trainable token position
2024-05-23 11:43:20 -05:00
rasbt
18e729643d
add assertion about data set length
2024-05-23 06:50:43 -05:00
rasbt
86f6c2df43
Fix device setting
2024-05-22 17:51:51 -05:00
Daniel Kleine
982cbe5e40
removed empty line
2024-05-22 16:15:13 +00:00
