Run 4. Outer Step 1. Inner Step 1.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    4530653,
-    4530656,
-    4530659,
-    4530664,
-    4530668
+    4530672,
+    4530676,
+    4530680,
+    4530684,
+    4530688
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d497b0fc388de4b54255cb53ccf527fd54ac04932a22c2758de481eb49079cf
+oid sha256:337d1b81ef5a660f7919bc661cc4106a68c15af12778cbf7bc4d9a52c5cc5479
 size 8081781962

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0022954b192ad813c5088f095a0cc93b93c92ee58bd986f0ba37ba676e887f
+oid sha256:34cba1c9b1c0ff3e5ef399b0a7d821544f1fa61482f7caa5e6af04e7379148b3
 size 4040701744