Run 3. Outer Step 11. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5432146,
-    5432148,
-    5432149,
-    5432151,
-    5432153
+    5432181,
+    5432182,
+    5432183,
+    5432183,
+    5432186
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40fc2c9ee0b38d5d77b00f9fea002acc7cd631e9562240ae591fae7f8f6d1af5
+oid sha256:1be3e99a87b87c17e54747cdf94f2bbdaf444456bc0d27f55971d433cd637704
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dfcd2f86f8dc1afee231f1a342ba52c81531cfb96856e0e698d59ac929bd407
+oid sha256:386cbca613aff307505971b486f758214f3e51bfb26c09c25b7a9db9a86395ad
 size 4040701744