Run 4. Outer Step 2. Inner Step 16.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5480587,
-    5480589,
-    5480591,
-    5480593,
-    5480595,
-    5480596,
-    5480598,
-    5480600,
-    5480603,
-    5480605,
-    5480607
+    5480608,
+    5480611,
+    5480614,
+    5480616,
+    5480618
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "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:bb26122fd96b31dfc88d2c64bc7df7491ca9d02f5e08e4a4add0b96d149e7e5a
+oid sha256:9572990d82e3cb07ac272a1728229d95f309ab55518f9d29b5b3b7ed8738a707
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a194c2a60e09e946f9677affb5e4446742da1d377f94e045cb85f4ec84bb82f2
+oid sha256:020f0b32c8f61e42d6031b0b9881cd30ce1f538712eac89b12834149fc63f64a
 size 4040701744