Run 4. Outer Step 20. Inner Step 22.

config.json

@@ -268,28 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525270,
-    5525272,
-    5525274,
-    5525276,
-    5525278,
-    5525279,
-    5525280,
-    5525283,
-    5525285,
-    5525286,
-    5525287,
-    5525288,
-    5525289,
-    5525290,
-    5525292
+    5525295,
+    5525297,
+    5525299,
+    5525300,
+    5525301,
+    5525303,
+    5525305,
+    5525307,
+    5525309,
+    5525311,
+    5525313,
+    5525315
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "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 sha256:71452cde91221cdfe0e41b5fc40412d826796652c43fb305e932ac6729b081fc
+oid sha256:aa326ae4c013f93c1a0e94bdb0486d48d1c749017c92a7d2bce7903eb09af985
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a039a60f30d50b2cb9904cc89503642b6a1020b3de5c424484b7c760e13196
+oid sha256:7c103e59e4b9222e7771bb81a36fa6a2f5887a9828e47d7b4c861d5b48cd130f
 size 4040701744