Run 4. Outer Step 7. Inner Step 63.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494602,
-    5494608,
-    5494613,
-    5494618,
-    5494623
+    5494629,
+    5494633,
+    5494639,
+    5494644,
+    5494649
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 63,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ba34814c80a331fb14550a56c4994383258d9d0d9499e10965b8d5399b1a29
+oid sha256:a526c4fc6a45dd6a4af3007021bf03e23348131547a9cda8376636609cc08c89
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fdffd212fb9eb3ec1bde68e17409a88695af3657486137772a5963422bf4fa4
+oid sha256:ddc041873a3df666a0f2de19ced259c37e23e73f1eef1c20797279f3330b6e88
 size 4040701744