Run 4. Outer Step 25. Inner Step 30.

config.json

@@ -268,18 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5534283,
-    5534285,
-    5534287,
-    5534290,
-    5534292
+    5534295,
+    5534296,
+    5534298,
+    5534299,
+    5534302,
+    5534304,
+    5534306,
+    5534308,
+    5534310,
+    5534312,
+    5534313,
+    5534316
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5533305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6224c95e234b2e56820127fb21ab2a48d23696aa6730a7cda9daf13fa53a57f
+oid sha256:de0d4505764c373aa5aba12723fc0abfeec58b4b4a808f1ecb4f901ee6f92fee
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5c1dda02a19dde805f2a1b6c5f0548bfa0f40f92628e4f63c61df07cb529bc
+oid sha256:024bdc8c982d667e5f7b0f7f225e222ab2d42942fc2403280b0d5ea0acdf95ba
 size 4040701744