Run 4. Outer Step 26. Inner Step 42.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535908,
-    5535911,
-    5535913,
-    5535916,
-    5535918
+    5535920,
+    5535922,
+    5535925,
+    5535927,
+    5535929,
+    5535932,
+    5535934,
+    5535937,
+    5535939
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb209674a3eadebbe74b32b49a7ee83d95cddfdc1748c389c77e39158c0669c
+oid sha256:1f3c4a50792794deacdab9afea6ce7c78864380754ff06c0ca841c1a5ba284bf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:190c04df41ac6ab0ab772fb81df20f9ee9f10563887975af2245843caa8050db
+oid sha256:f7fe960f92f2e5698250908b2c43816af3b8dfcffe339311ea60fb208cb2e841
 size 4040701744