Run 4. Outer Step 61. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5609050,
-    5609054,
-    5609058,
-    5609062,
-    5609066
+    5609070,
+    5609075,
+    5609079,
+    5609083,
+    5609087
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5608831,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:836e6deace847576f8c189022388d14fb91271b345b8d5fb18fc46ef33aeb129
+oid sha256:b5fcbbc29439367fa021edbf0bae3962e639cd07661c7a9dcd69a55e505046ba
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c04085c738729a7bd218e8723f9f3d746e0e2cd52583220337e1bcbd081e20a9
+oid sha256:7ac1efad49c61057aa7c6669384c9ed8276be4c554f4273dd7c3dafd383eed3c
 size 4040701744