Run 4. Outer Step 11. Inner Step 33.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507881,
-    5507884,
-    5507888,
-    5507892,
-    5507896
+    5507900,
+    5507904,
+    5507907,
+    5507911,
+    5507914,
+    5507918
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c9911aa68231fe3fdde781e7106329b999281dcc968f6657bf02a5579775b7
+oid sha256:64230438aa63b436ca1f0c1c14969d52e0ad58b32224c996e45fba0b8e2cb4c4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b0c077424f2c3db494e4d975bd706f44b3d09aadcd81d882d24974ff201581
+oid sha256:ed9ae60d2b30c241a29a2c6c2cd3853b3372b08ec9cc954b7082c8daf0f7491f
 size 4040701744