Run 3. Outer Step 5. Inner Step 79.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5381012,
-    5381016,
-    5381020,
-    5381024,
-    5381027
+    5381058,
+    5381062,
+    5381066,
+    5381069,
+    5381074
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 76,
+  "inner_step": 79,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:540b6aa12df081ba86296b24d0e689edd039581fdebec6975530d1b02699bf18
+oid sha256:2ab4808907dd820d0a4c6281552bdb25b23fd486195a4f70ec4ca8621b95484b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a1d147d45cb86d4b55e3a78cefcf37c60b9470c7dd0d9a36f004ce56037ed0e
+oid sha256:b0823e40acf904aea6156d180b14593dd8c930d56e8b4b6d2d040a912747854c
 size 4040701744