Run 4. Outer Step 60. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607664,
-    5607668,
-    5607673,
-    5607677,
-    5607682
+    5607686,
+    5607690,
+    5607693,
+    5607696,
+    5607701
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d032f31a1289ffcc07eee12271d064bc4d8bc16d306004e579b2852472fe66
+oid sha256:e4bf8537da181ae364996e5b32f3bb23708ea3f069d82104b303e0da9cbb1f85
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a24ec0932740ae52fa19bf4cc6b3386a84617ec65ef9a44393da1162cad05a2
+oid sha256:f78624cfa979a42aa0ab6c25143b8610a12f324263e88205e54aed86ae64be81
 size 4040701744