Run 4. Outer Step 18. Inner Step 8.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5521180,
-    5521184,
-    5521188,
-    5521192,
-    5521196,
-    5521199,
-    5521200
+    5521208,
+    5521212,
+    5521215,
+    5521219,
+    5521223,
+    5521224
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6002406e156888c52916331112d51d3ddfcc6d5cf27766eb72cb0f9692c25bd5
+oid sha256:3ac97401bbdf1cae3c8062f2782671031e466ef819361edb963ed7384c9bdaaf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19569e3dbaedb863745f937a78c014251d5c60cdbe71ac186e2a0fdcfea2bd94
+oid sha256:eac61d8e46ff2ffc7e687115fdb66cf40db7e8a49b00574398b706ecb806f645
 size 4040701744