Devatri commited on
Commit
7b59443
·
verified ·
1 Parent(s): de197de

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ # ANLP Assignment 2 - Part 2, dense LM trained with lion
2
+
3
+ One pass over browndw/human-ai-parallel-corpus (train split by document family). `checkpoint.pt` holds `model` (state dict), `model_configuration`, `optimizer`, `grad_scaler` and token/step counters. Rebuild with `DenseTransformer(ModelConfig(**checkpoint['model_configuration']))` from `model.py`. `metrics.csv` lists every optimizer's 0.1-1.0 checkpoints.
4
+
5
+ checkpoint sha256: `74d4cfa3423734035c29f6279c9050cc72cf676fbc24cac7c5286631a5188df5`