Run 4. Outer Step 27. Inner Step 34.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536978,
-    5536980,
-    5536981,
-    5536983,
-    5536985,
-    5536987,
-    5536989,
-    5536991,
-    5536993,
-    5536995
+    5536998,
+    5537000,
+    5537002,
+    5537005,
+    5537006
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1305d70ecbcf70165e9d076e0a1f44a21c764c11d48e7fee9d14c5ab7db6560
+oid sha256:4300f02f3a66b1a8485742f43cde9d7479b214efeb4951741b0e52cdf063c790
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c3f3e13d057f4f024a0ee8197e0ae1af81a2a12d3a4ece062766273e400510
+oid sha256:90d3010190172d3e0ceffa9c1ab0068dc42bd6117b01a948ca3a67a42f2f059a
 size 4040701744