Run 4. Outer Step 24. Inner Step 24.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5532277,
-    5532279,
-    5532281,
-    5532282,
-    5532285,
-    5532287,
-    5532290,
-    5532292,
-    5532295,
-    5532297,
-    5532299
+    5532301,
+    5532302,
+    5532304,
+    5532306,
+    5532308
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1124d805e1205741e85ef16bf0e2dffbb7e70dd5346b60661550c3227fbb5127
+oid sha256:41cb823e20191919119b4089c504bcd163b2a4378777264d395943dedc49c7f5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451c66b83e383176f64bb6604aa873725390a7d397b8b7117893f42c81bfcb40
+oid sha256:6a81467b03b02a4424e446a06258dea0ee24850e2196fe529cde435e987d5ac9
 size 4040701744