Restructure: nanoGPT at root, custom code in src/

- Move model.py, train.py, configurator.py to root for nanoGPT compatibility
- data/ and config/ directories at root with Shakespeare dataset prep scripts
- src/jlens.py updated to import model from project root
- Cleaned up stale src/config/ and duplicate src/ files
- Fixed .gitignore: exclude out-shakespeare-char/ instead of raw data dirs

1 files changed, 0 insertions, 25 deletions

diff --git a/src/finetune_shakespeare.py b/src/finetune_shakespeare.py
deleted file mode 100644
index 148a4c4..0000000
--- a/src/finetune_shakespeare.py
+++ /dev/null
@@ -1,25 +0,0 @@
-import time
-
-out_dir = 'out-shakespeare'
-eval_interval = 5
-eval_iters = 40
-wandb_log = False # feel free to turn on
-wandb_project = 'shakespeare'
-wandb_run_name = 'ft-' + str(time.time())
-
-dataset = 'shakespeare'
-init_from = 'gpt2-xl' # this is the largest GPT-2 model
-
-# only save checkpoints if the validation loss improves
-always_save_checkpoint = False
-
-# the number of examples per iter:
-# 1 batch_size * 32 grad_accum * 1024 tokens = 32,768 tokens/iter
-# shakespeare has 301,966 tokens, so 1 epoch ~= 9.2 iters
-batch_size = 1
-gradient_accumulation_steps = 32
-max_iters = 20
-
-# finetune at constant LR
-learning_rate = 3e-5
-decay_lr = False