Run 4. Outer Step 7. Inner Step 48.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5493955,
-    5493960,
-    5493966,
-    5493971,
-    5493976
+    5493982,
+    5493987,
+    5493992,
+    5493997,
+    5494003
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656d0564fcbfff12c6481824445d9d3090206279cddce267b8cd94f9571ae445
+oid sha256:b922cada863569227c7357eeb145dcd425b877d85c4111d8ae99db5ac8f4044a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80977d7a059f5140ccc87bf0c0022ae66d59470870e485f93721279950b2782b
+oid sha256:6af5134b461d4e9311a4917f738b4cac4c18140be21b53dd79d5ac195469ebc8
 size 4040701744