Run 4. Outer Step 58. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586807,
-    5586811,
-    5586816,
-    5586821,
-    5586825
+    5586830,
+    5586834,
+    5586838,
+    5586842,
+    5586845
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "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 sha256:1fb6ff943d8d83b77e0fcf99de0d6abc1ea7007e3922be9d05e30bdea1cc8d29
+oid sha256:536c89021f77676ec2af5c908794cb9c2b420550cebfbced74f35fedb853cefb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ef4cfbd6deb30504d5fbe5a18b6d19b44dcee3f2417167c9124e4053cfded7
+oid sha256:0f04fdf6915f7b02a1792f4fac9355b5fc0442f665e48707fbc80398eb0467dc
 size 4040701744