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, 37 insertions, 0 deletions

diff --git a/config/train_shakespeare_char.py b/config/train_shakespeare_char.py
new file mode 100644
index 0000000..41c81df
--- /dev/null
+++ b/config/train_shakespeare_char.py
@@ -0,0 +1,37 @@
+# train a miniature character-level shakespeare model
+# good for debugging and playing on macbooks and such
+
+out_dir = 'out-shakespeare-char'
+eval_interval = 250 # keep frequent because we'll overfit
+eval_iters = 200
+log_interval = 10 # don't print too too often
+
+# we expect to overfit on this small dataset, so only save when val improves
+always_save_checkpoint = False
+
+wandb_log = False # override via command line if you like
+wandb_project = 'shakespeare-char'
+wandb_run_name = 'mini-gpt'
+
+dataset = 'shakespeare_char'
+gradient_accumulation_steps = 1
+batch_size = 64
+block_size = 256 # context of up to 256 previous characters
+
+# baby GPT model :)
+n_layer = 6
+n_head = 6
+n_embd = 384
+dropout = 0.2
+
+learning_rate = 1e-3 # with baby networks can afford to go a bit higher
+max_iters = 5000
+lr_decay_iters = 5000 # make equal to max_iters usually
+min_lr = 1e-4 # learning_rate / 10 usually
+beta2 = 0.99 # make a bit bigger because number of tokens per iter is small
+
+warmup_iters = 100 # not super necessary potentially
+
+# on macbook also add
+# device = 'cpu'  # run on cpu only
+# compile = False # do not torch compile the model