Run 4. Outer Step 54. Inner Step 90.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580241,
-    5580243,
-    5580246,
-    5580248,
-    5580250,
-    5580252,
-    5580254
+    5580256,
+    5580258,
+    5580260,
+    5580264,
+    5580266
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 89,
+  "inner_step": 90,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf824e3fbe49a99e7aef58c4809a62f8d847636a2b173268bb7a1a59ab4aa9a0
+oid sha256:114f829b7554ca2b79953c7a595e4b013d078bd96f3add5e8def711c9d825e8a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d9401f7aa61d72028df96c699fc713f998ad32a43e6d404dc7c31b337dc404
+oid sha256:be3c32ba7a89a3c9db6c98c3f00f15ff246ff5730205e1594cddd1760e98d745
 size 4040701744