Run 4. Outer Step 3. Inner Step 134.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484721,
-    5484724,
-    5484726,
-    5484729,
-    5484731,
-    5484732,
-    5484734,
-    5484736,
-    5484739,
-    5484742,
-    5484745
+    5484747,
+    5484750,
+    5484751,
+    5484753,
+    5484755
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 133,
+  "inner_step": 134,
   "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 sha256:43e022ab049d7909b48f787bde81b6f807a39cbd520e32481adb48d825f834dc
+oid sha256:f7664e6bae0be52a0c33ee5367de1be80d501ca1db6ed7d1bba2e7e1f4d40397
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42ae0507743a12b72d7065b9acbe334a14ccacb76203d5c4f48fca4ec057d19
+oid sha256:2cc4df75706b86388b2bb25290130042800cb43ebe1ada46b0b984404370dd35
 size 4040701744