Run 4. Outer Step 18. Inner Step 35.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5522061,
-    5522065,
-    5522069,
-    5522073,
-    5522077,
-    5522080
+    5522085,
+    5522089,
+    5522093,
+    5522096,
+    5522100,
+    5522103
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "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 sha256:2571ec6c7c7995ef0c73103e3d001169c1da5a579e3b5f95c083e48db0a9a436
+oid sha256:ffc6774996a844bb305bd12eb35877f2f4e7f659a84c35c99684d25ddd4b9a05
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e381422bddb7676a01187194dbc8424cf020031a61d782b462f1d6a54c00aa
+oid sha256:3f9ff07273d8063d623d363e03a4c70edbdee2d4285644ad21817a17893312a3
 size 4040701744