Run 4. Outer Step 32. Inner Step 40.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543857,
-    5543860,
-    5543862,
-    5543864,
-    5543866,
-    5543868,
-    5543870
+    5543873,
+    5543874,
+    5543875,
+    5543877,
+    5543878
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b18d2d016bc02f1cc8b1469dcdc772ddafbf2ecc48bfe0a889fb63ef0d863c0
+oid sha256:52dbdf66785446145ee1acd8644a5ffa2f5e96aa7c2fd65a4f7f0469ab622ebb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:184cde447a2acc08a4932e038669a2dd7654da8a126b515e171a51874f4f7046
+oid sha256:6e27b81dee1858fc8ed04397fd997d6e985d916f0ea7f88ba6d1fbecc0f7abb8
 size 4040701744