Run 4. Outer Step 33. Inner Step 23.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544772,
-    5544776,
-    5544778,
-    5544781,
-    5544783,
-    5544786,
-    5544788,
-    5544790,
-    5544792,
-    5544795
+    5544799,
+    5544802,
+    5544804,
+    5544806,
+    5544808
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "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 sha256:341a19a016de894f2a78864a02d39f911e09067dd2afbc4b8c08cd22da4224eb
+oid sha256:33baae06b8a44b223ad8757432f3cb4d5aea2fc47659629b722ef699138a7d97
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de96df6cbbaa0cbbac9d1cc5b0956dfdb7d046c273a5d03123c7c4efae72d832
+oid sha256:2e234d15233f7026ce340ee39446daebf00b953cd9e950cb93914231e465e42e
 size 4040701744