Run 4. Outer Step 15. Inner Step 68.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5515028,
-    5515031,
-    5515035,
-    5515039,
-    5515042,
-    5515046
+    5515050,
+    5515054,
+    5515057,
+    5515061,
+    5515064,
+    5515068
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 68,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f9e71a6ed10fcf0668a2890e43e3ce6b8ab3df99b8368fb4d465ff1bbae427
+oid sha256:7818df9cf8ae379da77b3725b0c65180e5ede36d21943ba1573a0caad0a17e96
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58fe421a02f7d58a58539e70599f61b074ea878529c55303c9bd61b190d38a05
+oid sha256:773b99c3f25a04ae524bcc2dc2b6ce304ac854f55b36857a9f3fc0cdaa66f5d4
 size 4040701744