Run 4. Outer Step 29. Inner Step 33.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539545,
-    5539549,
-    5539551,
-    5539554,
-    5539556,
-    5539558,
-    5539560
+    5539562,
+    5539564,
+    5539566,
+    5539569,
+    5539572
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7a2d636987de08b5172577d74cc3d44346fee7abf174ba43e720b2d611ecea9
+oid sha256:e7a4f984ca74e2191fc80fc41b0eba92451a5024bb230eb74d6319c8a37182d8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5cfac88b53fd3ea052602c450a90794e9f3abce475d510cd67dd9c43e929df4
+oid sha256:589abceb3337748a40cd147d06297e4a80065099401be9d11443ba2c21109fee
 size 4040701744