Run 4. Outer Step 27. Inner Step 37.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537050,
-    5537052,
-    5537054,
-    5537057,
-    5537060
+    5537064,
+    5537066,
+    5537068,
+    5537070,
+    5537072,
+    5537073,
+    5537076,
+    5537077,
+    5537078,
+    5537080,
+    5537083
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1154cb2520202f333dd04fb93db7d6b82c0a2ad6c0499df900e115f272872f30
+oid sha256:58f96ebf5b65b9601e004a62ab49bb26c9e5ffb3bf3ea37dc9926bc19bb084d4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d6fb3b2a16b5ae5bd770c2ea3a018839d9e0813e6fc3d7131b118666e65763
+oid sha256:d62c54b6c071513ac1a5330f5ac44828de99efc2ca6ec9b67508caf445642587
 size 4040701744