Run 4. Outer Step 34. Inner Step 0.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546764,
-    5546768,
-    5546773,
-    5546777,
-    5546781
+    5546786,
+    5546790,
+    5546794,
+    5546799,
+    5546803,
+    5546807,
+    5546812,
+    5546816
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 0,
   "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 sha256:589dabae5df5849a6f785dc9110361aa909f9364300d1a457136cbcb921b3ce0
+oid sha256:40d35be23d42832f31732a68f3af134a8691274a2c2cc8a935bacf4c23bbe1e0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3be40c45ad2306425831ff28533367f20135d497d217a7593bf741f40b6d073
+oid sha256:0fa5a8a4a09fe9e6933f37382648aa8a8af2439302b71af51ec45db951bd7417
 size 4040701744