Run 4. Outer Step 58. Inner Step 25.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586784,
-    5586788,
-    5586793,
-    5586797,
-    5586802
+    5586807,
+    5586811,
+    5586816,
+    5586821,
+    5586825
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5583387,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c5e61abced5e81171e8fd1581cc3afb1a90a8bda3dbf8b936e9e1e27901a1cb
+oid sha256:1fb6ff943d8d83b77e0fcf99de0d6abc1ea7007e3922be9d05e30bdea1cc8d29
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4384942c9ec33d3342d1a0451296990129ef0a14e759aec5170e5ef2d7bfedc
+oid sha256:a8ef4cfbd6deb30504d5fbe5a18b6d19b44dcee3f2417167c9124e4053cfded7
 size 4040701744