Run 4. Outer Step 35. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548255,
-    5548259,
-    5548263,
-    5548268,
-    5548272
+    5548276,
+    5548281,
+    5548285,
+    5548289,
+    5548293
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5546853,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957d9bb4f04277d686a8262c015d3aa821fe947429ea1d528063ada0c06fea21
+oid sha256:6178fd8f97bf526a72e2e70e8276ab717b4aabb1b0664d4d3a22404b42d32987
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:725876919e127ee739427238e1d83b097b4c5b5ec0157afcb7d3ec2b155c161f
+oid sha256:1c03136325d07c03850c1eac68988b97b8a0163d695743b1667317ba1f3c3f94
 size 4040701744