Run 4. Outer Step 27. Inner Step 22.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536626,
-    5536628,
-    5536630,
-    5536632,
-    5536633,
-    5536634,
-    5536635,
-    5536638,
-    5536640,
-    5536642
+    5536645,
+    5536648,
+    5536650,
+    5536653,
+    5536655
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab376f073702957f46e46e2104d76447e6f7c6c5ddf0ff61afee8e3c440b0e00
+oid sha256:6c3fde88ec062fa9e862d08bfedfee6960505b96012e1a7732335cef5f39844a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c738d0c75bec0e1548dcc34ceb5846bafec9407bbfb4f8fd71cc301c9ebb17c
+oid sha256:66ced172fccfe5fb4d0400d58ecf66d94b2cb05fb83b858196ecb7c207ad7eb2
 size 4040701744