Run 4. Outer Step 29. Inner Step 20.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539132,
-    5539135,
-    5539137,
-    5539138,
-    5539140
+    5539143,
+    5539146,
+    5539147,
+    5539151,
+    5539152,
+    5539155,
+    5539156,
+    5539159,
+    5539161,
+    5539164,
+    5539166
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f683991a7ef4ac114e50d7e029c393ef7664f6b591bd654072df7fc11a5a02bf
+oid sha256:7a4f14ab2df9ca1ac1b67c9a8e1007ab576f658b3b14f667a654af876087d290
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8805f8e954f46267ae414bdfdb068888d14cc73033c9fbec2cd6cab53cb694fd
+oid sha256:45288124d97301006a2d1f9042482ce06453470a56a3351f1fd97a33d1efc42a
 size 4040701744