Run 4. Outer Step 34. Inner Step 0.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546757,
-    5546761,
-    5546765,
-    5546769,
-    5546774
+    5546778,
+    5546783,
+    5546787,
+    5546791,
+    5546795,
+    5546800,
+    5546804,
+    5546809,
+    5546813,
+    5546829
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 14,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28acf82e71d7734e5f8442e93dfa2fa1f92dda2136b527637b04d24aba553f0a
+oid sha256:a466811a6db6bd6989545db8758f5c0cbff34f3f452ad60c79583e28b1ead4e2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b68b08cb8fc921eb2754053facb2aeb8dc7111c2a394a048fc8ef6083996cd
+oid sha256:51392a79732686e75580b800ccea134d34596f5b41ae391a95f3e7445b3b4203
 size 4040701744