Run 4. Outer Step 26. Inner Step 35.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535720,
-    5535722,
-    5535724,
-    5535725,
-    5535727
+    5535729,
+    5535732,
+    5535734,
+    5535737,
+    5535739,
+    5535742,
+    5535745,
+    5535748,
+    5535749
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf0c1235da4da1285afcda7994da79524665f0e568aad65d54dcc4e0af37fb0
+oid sha256:c6aa3aea31fb6a7829369f44198e99dd2e711268f1c39fadf68347210dcf7d7f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f969815b7744f8ef2248c32bc414e89dcdb7d616ead55114e3e35e61dba7aa
+oid sha256:022493d0d40677169cb9ccd1f449840ed8fa5fe3406635a11d4b185fb77f0934
 size 4040701744