Run 4. Outer Step 4. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5487193,
-    5487195,
-    5487197,
-    5487200,
-    5487201
+    5487203,
+    5487204,
+    5487208,
+    5487210,
+    5487212
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a004c4067c9c9c1c380b6fed5febeae8cb54b0144ac33339072705e66e3a6a
+oid sha256:587b131db77723a06a13f9e2c99cd7891d128f95b01f7d8638c3762204f675b7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ee1f8572d3773576f50e7e0ca59f0967e8ef62072a38cc02a666cc443f09e1
+oid sha256:abb18f5b74b233c48dfa18d6c8a0d2ca45725b494cb1d1c03eaefc475000bec7
 size 4040701744