Run 4. Outer Step 53. Inner Step 29.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577184,
-    5577186,
-    5577188,
-    5577191,
-    5577193,
-    5577195,
-    5577196,
-    5577198
+    5577200,
+    5577202,
+    5577205,
+    5577209,
+    5577211
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da9157b7d4aaaa172581c4405120b5f6d3fd9e199f0b7f9b70899fe2a2a48d4
+oid sha256:918abd68e46700fbd5c92437c1b659d34e0058e8b67ffc3f4f15e41ec7c258df
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fed132b5e74a7cf5b36967de2071a0bfaaa96b47613169a08ba02837c69817d
+oid sha256:46e205beade14acfe212ecc54fb5c667c8e3c88b4babc385954daf17eaca753a
 size 4040701744