Run 4. Outer Step 2. Inner Step 14.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5480569,
-    5480573,
-    5480576,
-    5480580,
-    5480582
+    5480584,
+    5480586,
+    5480588,
+    5480590,
+    5480592,
+    5480594,
+    5480596,
+    5480598,
+    5480600,
+    5480603
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e748cd8d96151724f8983f098e25c154a9a7b9d09ed08364d9f8d1e55284e8
+oid sha256:0ca006d9fcfbf8e334de8ce4a0afe94013dab919767a8c69f08251f0ba9cc43e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e02de63003c2d739e0690f4b39f9689ea077415e9426cb38fda7f89396382b
+oid sha256:baf343770a05784ac6133c8a6b755c9fe79593595b716c7ac7bc3352b4e83420
 size 4040701744