Run 4. Outer Step 20. Inner Step 23.

config.json

@@ -268,25 +268,28 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525295,
-    5525297,
-    5525299,
-    5525300,
-    5525301,
-    5525303,
-    5525305,
-    5525307,
-    5525309,
-    5525311,
-    5525313,
-    5525315
+    5525316,
+    5525318,
+    5525320,
+    5525321,
+    5525321,
+    5525323,
+    5525324,
+    5525326,
+    5525327,
+    5525329,
+    5525331,
+    5525333,
+    5525334,
+    5525335,
+    5525336
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa326ae4c013f93c1a0e94bdb0486d48d1c749017c92a7d2bce7903eb09af985
+oid sha256:74e8d372a911f6e94720a60976038838bb238e08d714f693365193e7afb2eac0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c103e59e4b9222e7771bb81a36fa6a2f5887a9828e47d7b4c861d5b48cd130f
+oid sha256:bb122d7802cad875e73d010e652635b43b84ebeb561bcfb10f889a81535ea66d
 size 4040701744