Run 4. Outer Step 12. Inner Step 40.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5509698,
-    5509702,
-    5509706,
-    5509710,
-    5509714,
-    5509718
+    5509723,
+    5509727,
+    5509731,
+    5509734,
+    5509738,
+    5509742,
+    5509746
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5508496,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf35fac13c515baa23c5a8ee3a7022a1d91220fab0b791666ff8f732cd8ccc7
+oid sha256:46dc5fc01603c9934cbcd63555f4040af7687b834973b8b53d77997e4e4e5823
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b19d77be587af1c80358725bc61e860bf7e9eb6894adca766e9f8d880b3075
+oid sha256:bfcfbb1baf9731eb89756677b517e77042b97a63fac64196700439ab2a5e3e40
 size 4040701744