Run 4. Outer Step 7. Inner Step 157.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5499149,
-    5499151,
-    5499153,
-    5499155,
-    5499158,
-    5499160,
-    5499162,
-    5499165
+    5499167,
+    5499170,
+    5499172,
+    5499176,
+    5499178
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 156,
+  "inner_step": 157,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e17eab7e771b79a1f4a87d0fa8334de1eb49752b4fdd0fbb043730b68349bd2
+oid sha256:c2683509f179c9990a13788ec3ec978f8ba512d7fd17ad038864094d4d212fb3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88466dc84c5039c5e8618329fbcea86c2c5ad0e0f8d550b56bab5ae922a8b99a
+oid sha256:5b8b9e36345291b8630c976f2fc934683049ae01a69de62451feaaabfd73f90f
 size 4040701744