Run 3. Outer Step 9. Inner Step 1006.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421279,
-    5421285,
-    5421289,
-    5421292,
-    5421295
+    5421322,
+    5421326,
+    5421329,
+    5421332,
+    5421336
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1004,
+  "inner_step": 1006,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7810379184aec53fa0a6baa6a008526aab2abe2dfe4b580f711d4baa23e6dcc
+oid sha256:4af3b3c8c750779ee6c882923c3d073af32d380c396c36765f93d89e32a0d651
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:077eb39f3717858a3b3cf82b1ba506788f4b04c71a2e371eb4987c21f9fce707
+oid sha256:3eda7b312b6e978c91c14a8b3a6f754b0d0790a0a642fbba7647539712bc1066
 size 4040701744