Run 4. Outer Step 34. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546881,
-    5546885,
-    5546889,
-    5546894,
-    5546898
+    5546903,
+    5546907,
+    5546911,
+    5546915,
+    5546920
   ],
   "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": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06fa8c49756b028373687795a7f1291963c1323d4b285bdc5cd60b68ee8df19f
+oid sha256:068809317f4e443eb4540d337e6e81aa164aecb475c02f9ba971946ddea37911
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35479827094581c16f7baf06ba6ead5d36202763a87b88a05e3e7973e7265d42
+oid sha256:8881e4700a7d99385971e5ea01cc37c953c652073ee19f596db9605bd0d8c2a0
 size 4040701744