Fine tune on all of the games

For some reason the fine tuning seems to get worse, with more examples. Not sure what the reason is, but the unmmodified model seems better at chess than the fine-tuned one!
1 year ago · 32ab1c0e01
parent 04bdf68fb5
commit 32ab1c0e01
3 changed files (6.6 KiB → 10 KiB)
--- a/08_BackToGPT2.ipynb
+++ b/08_BackToGPT2.ipynb
--- a/zach_model/pytorch_model.bin
+++ b/zach_model/pytorch_model.bin
--- a/zach_model/training_args.bin
+++ b/zach_model/training_args.bin