Run 4. Outer Step 32. Inner Step 34.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543694,
-    5543696,
-    5543698,
-    5543701,
-    5543702,
-    5543704,
-    5543707,
-    5543709,
-    5543712,
-    5543714
+    5543717,
+    5543721,
+    5543723,
+    5543726,
+    5543729
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee7caa5c87c25d5e6bc83a7c8ad0b45159ab434089dfc4dd47f794e443574c9
+oid sha256:349dda304f28e8d7cc98fad4233c94f1f71c3c4da2d9cc37e64519726f6a6450
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d8c2d326fc0ede51eb274e02f41c9075cae9798a91dc93505329df1c5d1ce1
+oid sha256:8ad3ec6f4cae75015e910b22520cfc562c7c913b1c3fd09f7a78384dd786e4c2
 size 4040701744