Outer Step 0. Inner Step 280. Batch Size 264

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5263800,
-    5263805,
-    5263809,
-    5263814,
-    5263818,
-    5263823,
-    5263827,
-    5263831,
-    5263836,
-    5263840
+    5263872,
+    5263876,
+    5263881,
+    5263886,
+    5263890,
+    5263895,
+    5263899,
+    5263903,
+    5263907,
+    5263911
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 270,
+  "inner_step": 280,
   "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:c26ddaa9d70a12a4378135e30de3a3bfce9aad33d5e921ea6fe4dcc17ba08833
+oid sha256:c81f9482672c43efc12358807c932be6aedac5f6dcd5da069a4c6e1a1bb9f436
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a95d8275dbbe330ae8eb016ff9d149b5993d95c9d7021e60723f69062154c3
+oid sha256:4ce8a2b10c53d285478f8c8d7393c829ac518c35a61aa5db6ee96204c97efc57
 size 4040701744