Outer Step 1. Inner Step 2708. Batch Size 280

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5186726,
-    5186731,
-    5186737,
-    5186742,
-    5186747,
-    5186752,
-    5186758,
-    5186763,
-    5186768,
-    5186773
+    5186812,
+    5186817,
+    5186823,
+    5186828,
+    5186833,
+    5186838,
+    5186843,
+    5186848,
+    5186853,
+    5186858
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2698,
+  "inner_step": 2708,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17edb98080a27fd8b3e438651225004c1d35e9966c26ea4af7a6c5c850f87c8
+oid sha256:193fae5838a67fd3ddda4cec807581f83afec1f74fe115d8fa6c44baef6b4c13
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dd1c54aa628ebdd95ee1b3a68bc5ba23dd6838186d4e950379d2dc5107f42cb
+oid sha256:5efac4caf3cf5ad820397bbca1a7555f0a396aa8e6d852969f4a8ffe1f9a0b27
 size 4040701744