Run 4. Outer Step 52. Inner Step 12.

config.json

@@ -267,13 +267,19 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5575258,
+    5575264,
+    5575270,
+    5575273,
+    5575278
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5570305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed5eb1e1a6f4a1be3f4c26fa52dc20ccd48f7e11d05aae230d7f342035675a7
+oid sha256:47da6f98528c8fe5c543eb61339038ce535edeb050a18586992002a613b73130
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:059029a6d854298c5ee377fdb4f8476c990b43ce6d173d0033733f2444bf0e23
+oid sha256:5e4c68ca9e9be54f88f279afb87c0f3f24d7a624e6050dd2dd0c867af0229481
 size 4040701744