Run 4. Outer Step 26. Inner Step 28.

config.json

@@ -268,18 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535515,
-    5535518,
-    5535520,
-    5535523,
-    5535525
+    5535528,
+    5535531,
+    5535532,
+    5535534,
+    5535535,
+    5535536,
+    5535538,
+    5535540,
+    5535543,
+    5535546,
+    5535548,
+    5535549
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:995c9e4a9923fcb0765e16344d32f36a55b5647fbad068669be0e41df97eb25c
+oid sha256:d7e130d3db804abe1a747f5eef9b6b5676b474a9f9fce14f1bb5124b12a05a09
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4ec055e806d591ae0a8b75ed9f0d9422c0a48ccd8388e8954f157a154c56455
+oid sha256:537c331ea85be89e469677d57c8865d9a5c3be978824ccd41fca3adf7d5a0ed1
 size 4040701744