Run 4. Outer Step 28. Inner Step 32.

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538014,
-    5538016,
-    5538018,
-    5538020,
-    5538022,
-    5538025,
-    5538026,
-    5538028,
-    5538031,
-    5538033
+    5538036,
+    5538038,
+    5538040,
+    5538042,
+    5538044,
+    5538047,
+    5538049,
+    5538051,
+    5538053,
+    5538055
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f551c86ae31591816bed900df7fec8a6922c0573e8ad14aea5b2a69428a2535
+oid sha256:c430a9fd813897d663c7f138d8c9315a7a23c7deeb585d754a0a62415dadd098
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e7af7c070b342b9bdd33750cf5bc7718ca34b5ece0cd6810ca5d2e2ed899167
+oid sha256:b27c4e5de61bc2de665068407d989ad34c02e1a1261f8d74ebc69a6f6709dfe0
 size 4040701744