osmarks/nanogpt-experiments
1
0
Fork 0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2024-12-18 14:10:28 +00:00
Code Issues Releases Wiki Activity

Merge pull request #463 from goswamig/test1

Browse Source 
Fixing eval path in README
This commit is contained in:
Andrej 2024-06-03 09:51:52 -07:00 committed by GitHub
commit 9755682b98
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -131,10 +131,10 @@ Finally, to train on a single GPU simply run the `python train.py` script. Have
OpenAI GPT-2 checkpoints allow us to get some baselines in place for openwebtext. We can get the numbers as follows: OpenAI GPT-2 checkpoints allow us to get some baselines in place for openwebtext. We can get the numbers as follows:
```sh ```sh
python train.py eval_gpt2 $ python train.py config/eval_gpt2.py
python train.py eval_gpt2_medium $ python train.py config/eval_gpt2_medium.py
python train.py eval_gpt2_large $ python train.py config/eval_gpt2_large.py
python train.py eval_gpt2_xl $ python train.py config/eval_gpt2_xl.py
``` ```
and observe the following losses on train and val: and observe the following losses on train and val: