Run 4. Outer Step 17. Inner Step 25.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5519662,
-    5519666,
-    5519669,
-    5519673,
-    5519677,
-    5519680,
-    5519684
+    5519688,
+    5519691,
+    5519695,
+    5519699,
+    5519702,
+    5519706,
+    5519709
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "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 sha256:46e082ca480e1c1763a9c21d5a9a8336186ffdb71336a7c52d35cb7ef3684855
+oid sha256:c30d3cd17a9325a035c11bba32e4885bdef5902ed6cfc7accb3f8d850d40c1a9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a9e6e91e280c85ecd20c000b95b16b66525e7d16fdf41484dee1d876f2b4cea
+oid sha256:a7e114e1883ce596c16bccb1fbea2e88cc0324f5bddfa862512d5a5e34fb5a3f
 size 4040701744