Run 4. Outer Step 25. Inner Step 43.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5534654,
-    5534656,
-    5534659,
-    5534661,
-    5534663,
-    5534666,
-    5534668,
-    5534670,
-    5534672,
-    5534674
+    5534677,
+    5534679,
+    5534683,
+    5534686,
+    5534688
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 43,
   "inner_steps": 0,
   "last_allreduce_block": 5533305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35cbad20327eb604e5e792ebb5a4c8f297c26bf4b2cc9f0ba014373354cee432
+oid sha256:2f619f6ab1e9de82a81a28c44fab12cb9715a69112d5f5dc21ba1bd28ba7822f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:396cc3939e9ab74d8736f14de8a99a9d8be578e77cef8baaec8c1fbb8f6c9e8f
+oid sha256:f36a00a63c78fcab9ad0267a1189921d796071078b72006270c4feec69fa693f
 size 4040701744