Run 4. Outer Step 13. Inner Step 7.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5511555,
-    5511559,
-    5511563,
-    5511567,
-    5511572,
-    5511576
+    5511580,
+    5511584,
+    5511588,
+    5511592,
+    5511596,
+    5511601,
+    5511605
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 7,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1412972babf4bf2b60bfc5f8b29bcde95972e15d39a9c07efd0bf79361b94f3c
+oid sha256:d5fe05c601a6614d35b610de45b2cdec2d8773207990a293b73b5c84118f83c5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe05c9dd197a7023177a3b51d7caa0fb7e6a6719ddc619830c8ab7d35b919f3c
+oid sha256:d3ce902b6a32662f07847b29252ffa523ab45bec20d40560b995930f2e84932d
 size 4040701744