Run 4. Outer Step 33. Inner Step 5.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546803,
-    5546807,
-    5546811,
-    5546816,
-    5546820
+    5546825,
+    5546829,
+    5546833,
+    5546837,
+    5546841,
+    5546845
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76543a67761f15f70fb5a74b1541cff45ede3cccdf76dd87c189e38a5d0d4f55
+oid sha256:79ebf3ccf2c24fa8b75844739887c12b502d741e7db1db7594b10cf8a96cf59d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eebb2511f3302082650e04d44ca76c2cc71146f5822b5918b2e045f546dc650
+oid sha256:836a844fc05543068a9c853748585fffcb9b47639dcc4613194882ae378fd049
 size 4040701744