Run 4. Outer Step 17. Inner Step 39.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520031,
-    5520035,
-    5520039,
-    5520042,
-    5520046,
-    5520049
+    5520054,
+    5520057,
+    5520061,
+    5520065,
+    5520068,
+    5520072,
+    5520076
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "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 sha256:7c0d604690ef06289b1bf522ab14d9b04e4b00004bd784be945b0ae547d20933
+oid sha256:c902bd63323b3b3770aeeef19e29c10225682dbc421e141e4f8d0b61897fe0bf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd9883d691be39f82919abcef604c345b48419700429a532cfb0dcf25b6f59e
+oid sha256:79602013c72dc6a1aed51c4f96e949c3e3289b1629125c243df3d8bd518bf4fb
 size 4040701744