Run 4. Outer Step 64. Inner Step 230.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617504,
-    5617508,
-    5617512,
-    5617517,
-    5617521
+    5617527,
+    5617531,
+    5617535,
+    5617539,
+    5617544
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 229,
+  "inner_step": 230,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc784b18eda6d22b6fb2517b651d499077dfe768b2ae60fec8823b552dd0fe79
+oid sha256:2ea772dd9e3cd8bacaadb7aff3d022c2d9ee35671c07f50a8030a8545d1b5fba
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440d43943e289e285d40283d85af8fd3ec5b1ae94cb6974b0a640570e57bca86
+oid sha256:0663a9867031e66875a58662a25c588f272887065ee390a21b7dfabe477bc554
 size 4040701744