Run 3. Outer Step 5. Inner Step 81.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5381058,
-    5381062,
-    5381066,
-    5381069,
-    5381074
+    5381105,
+    5381109,
+    5381113,
+    5381117,
+    5381121
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 79,
+  "inner_step": 81,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab4808907dd820d0a4c6281552bdb25b23fd486195a4f70ec4ca8621b95484b
+oid sha256:930ba154813d0f91f51bfbbf93d45cdaa55180ce18bad1bd2b803972e1b74fa9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0823e40acf904aea6156d180b14593dd8c930d56e8b4b6d2d040a912747854c
+oid sha256:c77be83442f853ba77ed4afd86ea7f1e4f732a84be0983441ab9a5ae7571f43c
 size 4040701744