Run 4. Outer Step 22. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5527077,
-    5527085,
-    5527091,
-    5527098,
-    5527104
+    5527112,
+    5527118,
+    5527125,
+    5527132,
+    5527139
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7713ccd276f5b1b4e0eedd26e8d0f466a56e74e89f5079e4ab96417e7ec86ca
+oid sha256:2d85bef3053e42f51ef6ce1fb4618b9edfa8318bc2393f95a1186d498658f01b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7372c8f6b9c56841552c970f2384d8415af62660fdfb01be2df4fa4758dba3cb
+oid sha256:892a37d7c7c384e9e3e23071fef64f50b34c9e14289b02bf8dcf43931e597598
 size 4040701744