Run 4. Outer Step 58. Inner Step 25.

config.json

@@ -268,20 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5605189,
-    5605193,
-    5605196,
-    5605201,
-    5605205,
-    5605207,
-    5605213
+    5605217,
+    5605222,
+    5605226,
+    5605229,
+    5605233,
+    5605237,
+    5605241,
+    5605245,
+    5605249,
+    5605252
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0734eefef22a1c88e87b25976f4dea00aa989b1a1ade6b565669eaaf2201c1d
+oid sha256:dea632bd9265ad74c3d271a1eaec032e0a65fa2886f16782ca9b310efd7a2aae
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0d75375648ab6ce8ed692d2c85a14b2a31736241bb3599f4b7add9d5dfc4ad
+oid sha256:a19bbaae1b83cf6136d7939e3436f3cc175a0412ded314ce5f3fdcf604b5a84e
 size 4040701744