Run 4. Outer Step 11. Inner Step 2.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508560,
-    5508564,
-    5508568,
-    5508572,
-    5508576,
-    5508580
+    5508584,
+    5508588,
+    5508592,
+    5508596,
+    5508601,
+    5508605
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00de106fd17fe1b86bfe372c99b5fe1126338fe370812104849c0d8bce5bb93
+oid sha256:a2a5d30395f01a1d838f26611e4fc5ba286871f8a6e25652afb7c7b7a8c79a42
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73bc946f25e723e84ce8ff688a345e562841dd38247a064f0d8e639bb0d31077
+oid sha256:f3c12cad91b4662d2dbff7cb2385143769d6a78a9c59e7b3468983f88558cb19
 size 4040701744