Run 4. Outer Step 23. Inner Step 13.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531284,
-    5531287,
-    5531289,
-    5531292,
-    5531294
+    5531297,
+    5531300,
+    5531302,
+    5531304,
+    5531307,
+    5531308,
+    5531310,
+    5531312,
+    5531315
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66f9742fee20f771d0a627126c009390c5e040e691c2608637692e6f4211353a
+oid sha256:4cb5aa16022ee110b252527bd642b8c3a80651e53d6383576580017e839b6274
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68cc79a0b7f575760fb72e0ebfdecad39bf7165166bb4240cdbf9fd21ca95ff0
+oid sha256:4bea4a0f9e3d8d900ad95a3dd3a6444a54f5c7b666b246e0c2253a04223a55b7
 size 4040701744