Run 4. Outer Step 53. Inner Step 26.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577098,
-    5577100,
-    5577101,
-    5577104,
-    5577106,
-    5577108,
-    5577111
+    5577114,
+    5577117,
+    5577119,
+    5577122,
+    5577124
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6950474ef83eb40b24cd4b7e14f24018cf01ed974b550525616fbbe23b89f5bd
+oid sha256:6aa5d3e94e277f2a9dca26da756d918bc28b064984d864a156d318052fb9b516
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9001f478abb08100ffb6359cf91ac408a2fa17f3f31b41415ec1d0eec79c525
+oid sha256:8c06abdc7020452aa7eb1250dd39cdd15bb591de37fe4e4efb9a887cfd66a8dc
 size 4040701744