Run 4. Outer Step 18. Inner Step 34.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5522038,
-    5522042,
-    5522045,
-    5522049,
-    5522053,
-    5522057
+    5522061,
+    5522065,
+    5522069,
+    5522073,
+    5522077,
+    5522080
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e25149f4630d48c918f07ef1bcd9ad545e95f5454783be03b73ca81c58f502
+oid sha256:2571ec6c7c7995ef0c73103e3d001169c1da5a579e3b5f95c083e48db0a9a436
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e86f1140289f5069f87a03ff875f0220927425acb867db607367c0c7fae95e
+oid sha256:77e381422bddb7676a01187194dbc8424cf020031a61d782b462f1d6a54c00aa
 size 4040701744