Run 4. Outer Step 20. Inner Step 14.

config.json

@@ -268,24 +268,26 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525210,
-    5525212,
-    5525214,
-    5525216,
-    5525219,
-    5525222,
-    5525225,
-    5525227,
-    5525229,
-    5525233,
-    5525235
+    5525238,
+    5525240,
+    5525242,
+    5525244,
+    5525246,
+    5525247,
+    5525248,
+    5525251,
+    5525253,
+    5525255,
+    5525258,
+    5525260,
+    5525262
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 14,
   "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:fc39e117cc47ed02d33836ad4779e4b99af4b1cabb6612b245dc020eb2d4a294
+oid sha256:1173fbfa2fcb3414d6dccb22d63dc3a49cf3f2b50c5df3941c7772a56bf96218
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aedae576caf766e732848dc141d1c26578142f2dce2cba0e23e190d4256e18a
+oid sha256:086dec6e78dd765e160f9ee61183296a91dae144efd9944c990e5e1d10b62591
 size 4040701744