Run 4. Outer Step 28. Inner Step 36.

config.json

@@ -268,23 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538116,
-    5538119,
-    5538122,
-    5538124,
-    5538125,
-    5538128,
-    5538130,
-    5538133,
-    5538134,
-    5538137
+    5538139,
+    5538142,
+    5538145,
+    5538147,
+    5538150,
+    5538152,
+    5538154,
+    5538156,
+    5538157,
+    5538158,
+    5538159,
+    5538160
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "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 sha256:5c4d3bf494217037d54a0ea59482736016ea130cfb48a339371eac6c94ae182f
+oid sha256:23a20ad0d83256b5b5a71556cc6e15a2d8ec02bb73877e4cc3068cb46ecbc616
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:305bbc207a0e8fca1e1eeb59cb63840a7fafe49528846beb63c515d2e451d8c4
+oid sha256:3c89091a5a34060288d7c9beb6e80db9bdda42a82d846aca408158f875d75083
 size 4040701744