Run 4. Outer Step 22. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526900,
-    5526908,
-    5526915,
-    5526922,
-    5526929
+    5526937,
+    5526945,
+    5526951,
+    5526958,
+    5526965
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "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 sha256:0e767f0cb4fb0c95c3690bfdf8a59daa64e80989e1b6e03f474712cbbabe0909
+oid sha256:221d90ce0a49ca51d0335e688f1a4ded2f23b21391533b8a84d2158f5018bb88
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31bd1424009ae009ac098cecb282d879b7c3c0f34a6e0651773c629a5e1d2bf9
+oid sha256:722d31492ac7960f210676f51de4627feab796fb22436255c1041da2c7f3ad11
 size 4040701744