diff options
| author | Void Agent <void@jayrup.hermes> | 2026-07-29 17:47:48 +0100 |
|---|---|---|
| committer | Void Agent <void@jayrup.hermes> | 2026-07-29 17:47:48 +0100 |
| commit | db4ec5bb3839bc5cc50d82e427848595d14b3070 (patch) | |
| tree | d2d9fb11e11392077a79e6a10c38d44d1d9f5a38 /config/eval_gpt2_large.py | |
| parent | 66f99ee30087a5f28ad852e581a0334c7f556091 (diff) | |
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
Diffstat (limited to 'config/eval_gpt2_large.py')
| -rw-r--r-- | config/eval_gpt2_large.py | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/config/eval_gpt2_large.py b/config/eval_gpt2_large.py new file mode 100644 index 0000000..4cbeaef --- /dev/null +++ b/config/eval_gpt2_large.py @@ -0,0 +1,8 @@ +# evaluate the base gpt2 +# n_layer=36, n_head=20, n_embd=1280 +# 774M parameters +batch_size = 8 +eval_iters = 500 # use more iterations to get good estimate +eval_only = True +wandb_log = False +init_from = 'gpt2-large' |