Run 4. Outer Step 17. Inner Step 68.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520873,
-    5520877,
-    5520881,
-    5520885,
-    5520889,
-    5520893
+    5520897,
+    5520901,
+    5520904,
+    5520908,
+    5520911,
+    5520915
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 68,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647bbb95920b0d597d9e9495baa5c19adf6bc0ca45412477d62d76877bdaa110
+oid sha256:e7ea53b13cafd7d1da5b0072ec186b3b0213c43ceec1356485de5948909e094c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b00f3c40b776034688206d4f38d9157299bce56beb1d3c10ee74c079eee6f81
+oid sha256:4786105ff8d07d1afb4d29cc5f805be68fd18f572651ae1fd4cecddc573fac1e
 size 4040701744