Run 4. Outer Step 35. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548234,
-    5548237,
-    5548242,
-    5548246,
-    5548250
+    5548255,
+    5548259,
+    5548263,
+    5548268,
+    5548272
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "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 sha256:0a9c7b5cdc8c8236b3edecb0df33b5774a7bc8f12b97d182f31a6723bb8f49a6
+oid sha256:957d9bb4f04277d686a8262c015d3aa821fe947429ea1d528063ada0c06fea21
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:598dfe62fb12364d0d737f874822f8aa85b8e775345453a3e352df4447e86578
+oid sha256:725876919e127ee739427238e1d83b097b4c5b5ec0157afcb7d3ec2b155c161f
 size 4040701744