135 Commits

Author SHA1 Message Date
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
rasbt
c4cd48475c Fix device setting 2024-05-22 17:51:51 -05:00
Daniel Kleine
4b0fdab1de removed empty line 2024-05-22 16:15:13 +00:00
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
3b72e55c26 remove duplicated text 2024-05-19 11:34:47 -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
5541f7c8fe add test mode for dataset download 2024-05-18 17:38:19 -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
05738f8be6 fix link 2024-05-17 08:20:35 -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
47b3ff15ec improve bonus code in chapter 06 2024-05-14 20:35:50 -04:00
Sebastian Raschka
30010c7a91 Merge branch 'main' into main 2024-05-14 08:28:02 -05:00
rasbt
6aff47ba60 fix file path name 2024-05-14 08:27:46 -05:00
Sebastian Raschka
2f1e1a3d4b Merge branch 'main' into main 2024-05-14 08:12:19 -05:00
rasbt
0b176bb1fc add previous chapters file 2024-05-14 08:11:58 -05:00
Sebastian Raschka
d499c90903 Merge branch 'main' into main 2024-05-14 08:07:58 -05:00
rasbt
df4c59cf6e add missing gpt-download.py 2024-05-14 08:05:56 -05:00
Daniel Kleine
c754b14a79 added missing python run statement 2024-05-14 12:17:09 +00:00
rasbt
87bf79e888 tokens seen -> examples seen 2024-05-13 20:08:48 -05:00
rasbt
d9e364c04a spelling 2024-05-13 20:06:38 -05:00
rasbt
b350daaa93 add readme 2024-05-13 08:50:55 -05:00
Sebastian Raschka
f8589c05c1 Merge pull request #153 from rasbt/ch06-exercises
Chapter 6 wrap-up
2024-05-13 08:14:08 -05:00
rasbt
c95abad6d1 pep8 fixes 2024-05-13 07:50:51 -05:00
rasbt
13e4282567 tests and exercises 2024-05-13 07:45:59 -05:00
Sebastian Raschka
7370ad1615 val before test acc 2024-05-13 07:36:18 -05:00
rasbt
c8bcdf5206 fix tests 2024-05-12 19:03:14 -05:00
rasbt
37c33d6fee add chapter 6 unit test 2024-05-12 18:51:28 -05:00
rasbt
6b5bc7a1cd add missing figure 2024-05-12 18:37:02 -05:00
rasbt
ccb862cc36 chapter 06 summary file 2024-05-12 18:27:50 -05:00
rasbt
73e1c68f45 use validation path 2024-05-12 09:41:46 -05:00
rasbt
1c13810d30 use path 2024-05-12 09:36:35 -05:00
rasbt
a0adf0d5d3 basepath 2024-05-12 09:27:38 -05:00
rasbt
913662ebeb basepath 2024-05-12 09:25:56 -05:00
rasbt
98c0723b3d update dataset naming 2024-05-12 09:22:42 -05:00
rasbt
beeaf323f1 rename download_and_unzip to make it more specific 2024-05-12 08:36:24 -05:00
Sebastian Raschka
49306b271f add header 2024-05-11 14:37:21 -05:00
rasbt
84edcfaf43 use spam / not spam labels 2024-05-11 13:42:18 -05:00
rasbt
c94f24e759 reorder section 6.6 2024-05-11 08:27:07 -05:00