Outer Step 4. Inner Step 72. Batch Size 500

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5149414,
-    5149418,
-    5149422,
-    5149426,
-    5149430,
-    5149434,
-    5149438,
-    5149442,
-    5149445,
-    5149449
+    5149479,
+    5149483,
+    5149488,
+    5149492,
+    5149496,
+    5149500,
+    5149504,
+    5149508,
+    5149512,
+    5149516
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 63,
+  "inner_step": 72,
   "inner_steps": 0,
   "last_allreduce_block": 5148895,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3baf399d287d4993802a2d34014f8fffbc0555f547e5677749c2c821ff8266d2
+oid sha256:bbd84dd8840fa3e41e9597d477c5730e0186bda561920623cf6cdcff480d445a
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b536fea5ec1b75a73705807ac98ee79bb956d2139b5a6dbe23455ac9ab561cd5
+oid sha256:ff4b3a5c0ce829e3ed2b5ebb9e018fc2842efbd0f837821fe400e7fc16ddb684
 size 4040701744