Run 4. Outer Step 35. Inner Step 3.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548229,
-    5548233,
-    5548237,
-    5548242,
-    5548246
+    5548251,
+    5548255,
+    5548259,
+    5548263,
+    5548268,
+    5548272
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f02d75c4e8443a0303944fc5d6f77932c952afc979571dafa50d873595a2ab1e
+oid sha256:089c551c46ca2ca6d8898bfc35ea74d8d3a10dbdb66c44722971018b5a246ce9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7308082275a77fd6e66f08e41ee6d7af8e18b858bd63a81b031dd84f9ab86be7
+oid sha256:dbc72986510e5435add94f302467d2ea6d710aaabc2aa85017bb2fccaeb4a70f
 size 4040701744