Run 4. Outer Step 27. Inner Step 32.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536919,
-    5536921,
-    5536924,
-    5536925,
-    5536927,
-    5536929,
-    5536931,
-    5536934,
-    5536936
+    5536938,
+    5536941,
+    5536943,
+    5536945,
+    5536947
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9892c2564000c2053dc6e39e6a6156a80c395bc6e96767c7697e524c276fa100
+oid sha256:d72184dc8a671b8c17c3f714e74ae1dbbf911e2ba2a01758f4a33724065b5da5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20975f43380d9ef9924f92fcbc1af506cafb499fe2da8e656744d3fd62b0e041
+oid sha256:a83b6adae0e9b1ab67202779177458d15b314c517a07b188e351887a751d61ec
 size 4040701744