Run 4. Outer Step 28. Inner Step 35.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538103,
-    5538106,
-    5538108,
-    5538109,
-    5538112
+    5538116,
+    5538119,
+    5538122,
+    5538124,
+    5538125,
+    5538128,
+    5538130,
+    5538133,
+    5538134,
+    5538137
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da154c342c1e723ff8270d6cf7ea014b10ee32d15295ed8c2b2dbc610d23f8f
+oid sha256:5c4d3bf494217037d54a0ea59482736016ea130cfb48a339371eac6c94ae182f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19a6054d464719290aec8fb94dbdc56632106ea1cdd6264f53f074f298b3e1ae
+oid sha256:305bbc207a0e8fca1e1eeb59cb63840a7fafe49528846beb63c515d2e451d8c4
 size 4040701744