Outer Step 2. Inner Step 1522. Batch Size 480

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5113312,
-    5113316,
-    5113320,
-    5113324,
-    5113328
+    5113343,
+    5113347,
+    5113351,
+    5113356,
+    5113360
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1518,
+  "inner_step": 1522,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e529e47ac70a1ba65f49ead5ca91983f76275167410f980ccf694c0d8f8bceb
+oid sha256:f891c4d09ae5b222bb6bea80d51cc30300f172c2f39ade3c40267271756a96cb
 size 4040701744