Run 4. Outer Step 33. Inner Step 24.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544707,
-    5544710,
-    5544712,
-    5544714,
-    5544716,
-    5544719,
-    5544721
+    5544723,
+    5544726,
+    5544728,
+    5544729,
+    5544732
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e277f8135ebb5d2acaf52d4c996a70139069b1d586fe3a248c755696d3424111
+oid sha256:828208983c256c569a118726f2f3b7e41a8f911ff3d66c7bb6663ba2fe44b79c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b6142dfb2f23af65e7155e32f91631ad23f352535a6e64f5a78525273a4f90
+oid sha256:07ccc95f88b9352e308425ac3f69f33e788c7d67e3a86aae541975f93380dcce
 size 4040701744