Run 4. Outer Step 33. Inner Step 14.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544414,
-    5544416,
-    5544419,
-    5544421,
-    5544424,
-    5544427
+    5544430,
+    5544432,
+    5544435,
+    5544437,
+    5544439
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed48f6733a23bdbaf988f1987c5f3991a39132669f2ec3f081d4ab90a69b186c
+oid sha256:35715cfefa1f8e1f6e1118f4e8601d2ab118bbf130b7799e73637c78ce5f6ea5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b30f52e7797dea9371651950d96e28a1f5f9f9634108b3b07692d2c7702eb47
+oid sha256:101afacff8125a61b4f1d0f7fa41cb6fa026d327fabce6162c716ffa1c2bb549
 size 4040701744