Run 4. Outer Step 20. Inner Step 11.

config.json

@@ -268,28 +268,29 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525051,
-    5525053,
-    5525054,
-    5525057,
-    5525058,
-    5525060,
-    5525061,
-    5525064,
-    5525066,
-    5525067,
-    5525067,
-    5525069,
-    5525070,
-    5525072,
-    5525074
+    5525076,
+    5525077,
+    5525080,
+    5525082,
+    5525083,
+    5525085,
+    5525086,
+    5525088,
+    5525090,
+    5525091,
+    5525092,
+    5525093,
+    5525094,
+    5525095,
+    5525096,
+    5525098
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 11,
   "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 sha256:6c4a931c0492fb5f5d8793c22967a172f54b708dafbc9b3eac988c33079040b4
+oid sha256:29d205cf43af6e67b1f809c2d5a64dfc1c2ff30330c09ec2f8b69b786bc3a00a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b164552ed64b1bca61c76139e457326fcae17cb7bb9a339070a79ad09aa0694
+oid sha256:a994fa317803e43263b9a3cf7aa831a93248e483c55bd14f6e5362a1319c3737
 size 4040701744