Run 4. Outer Step 52. Inner Step 32.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575974,
-    5575976,
-    5575978,
-    5575979,
-    5575983,
-    5575985,
-    5575987,
-    5575990
+    5575993,
+    5575994,
+    5575998,
+    5576000,
+    5576001
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83281830088032167f2a082ebc4275566b619ec865d5c6ee7d8b8e1191e0dde
+oid sha256:3fb707d90f27896d04df5b161016aec4e2c052ab6e43e00bbb8ca33dffd2ddf8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f2a09860ac1fb6ffb4ae4bb06a96bffcc1e65a91a1a78bc04bd833db7b9369
+oid sha256:0e77559cac406b2fa331b924eef520ce9f394579184fef63cb49f5f0bb2f3dc0
 size 4040701744