Run 4. Outer Step 31. Inner Step 32.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542123,
-    5542125,
-    5542129,
-    5542130,
-    5542132
+    5542134,
+    5542137,
+    5542139,
+    5542141,
+    5542144,
+    5542147,
+    5542149,
+    5542151
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a17e7e28d30d2094e80569a79c4271df2bc12f75e4c6ca22352a0cc8c2f69563
+oid sha256:a32d36ec98f6b32b09bede8d6c8f50a863862845cab5168d72d5e8761a588c05
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6877f1219c71207eeaeaad551eb9b32f614aaf58f516e44770097612f35d365
+oid sha256:b1c8cebf1939ae7b194a307e0705ff8db694d4c2e47f65e548be1883f3770e52
 size 4040701744