Run 3. Outer Step 11. Inner Step 7.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5431768,
-    5431769,
-    5431771,
-    5431772,
-    5431773
+    5431801,
+    5431803,
+    5431804,
+    5431806,
+    5431807
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 7,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6e6a4411338ddb02f9b411606de99170692f06848075869b190b9c755e41639
+oid sha256:a023ec05a59d6fa62f10789d352af41c9f379728b6cb8d8d64884d2a9495df32
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cad7a7fa7c3803dccc22720a5101ba90cf5afa8deef0f077993fca17c3429b3a
+oid sha256:0ccb233dd10855db50bb23a95fb33d6368d5e005b275131da3eb975ca6074dd2
 size 4040701744