Run 4. Outer Step 26. Inner Step 36.

config.json

@@ -268,22 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535509,
-    5535512,
-    5535514,
-    5535517,
-    5535520,
-    5535522,
-    5535525,
-    5535527,
-    5535530
+    5535533,
+    5535536,
+    5535537,
+    5535539,
+    5535542,
+    5535544,
+    5535546,
+    5535548,
+    5535550,
+    5535552,
+    5535553
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bded277849623276bddc04f72cb152153565df00488299cecfa86a6cd3c0062e
+oid sha256:9a6a3e006e0fb8a8635e35483ce3f9dffaf7e30cb270f59b0d1c363fa449e64f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28de28281cca01cbfdf83be8635ee5d54c136e8c50731fcfc0ea99e3b4f5e917
+oid sha256:7eebc63096da267f2d253fbf7d375bb5acfa637553da03257449bc515230b068
 size 4040701744