Outer Step 1. Inner Step 1638. Batch Size 364

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5184298,
-    5184302,
-    5184307,
-    5184311,
-    5184315,
-    5184319,
-    5184324,
-    5184328,
-    5184332,
-    5184337
+    5184368,
+    5184373,
+    5184377,
+    5184381,
+    5184385,
+    5184390,
+    5184394,
+    5184399,
+    5184403,
+    5184408
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1628,
+  "inner_step": 1638,
   "inner_steps": 0,
   "last_allreduce_block": 5160840,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddef3fcb4abe0f8917fc947658111127220f6ca3618fbec5efd405ba864b1a0e
+oid sha256:c4b72745a0e28f423d3e2c4b7a728bdd16c62554ed0ff2d9be8b02e52f3174ad
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19af7385c208ea7ed8cb3ba686893479d1652fe522f1a01fd16eed4f9d04259c
+oid sha256:9eb410af84ed706c40b60d49f743853701121e7a1579e969230aeafc749a6103
 size 4040701744