Run 4. Outer Step 58. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603743,
-    5603748,
-    5603753,
-    5603758,
-    5603763
+    5603768,
+    5603773,
+    5603778,
+    5603783,
+    5603789
   ],
   "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": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f225d745a3296584af71e6fc998786d93938558c76a77da7542017316668e34
+oid sha256:b7a9b23830d80b4803113cbd31cb29706c5ad7ab16d4da04fa9c8c315c73068b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b1c683cd5d49dd9814e2bc287f189db7155c31a4ce6a108ab94357924bc2f5
+oid sha256:c430e85350a49b768021bed8ba87e22a63286ab52e1e76c9d8125ff95538959f
 size 4040701744