Run 4. Outer Step 61. Inner Step 5.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5609002,
-    5609006,
-    5609010,
-    5609014,
-    5609018,
-    5609021
+    5609025,
+    5609029,
+    5609033,
+    5609037,
+    5609041,
+    5609045
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "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 sha256:5c1b2fa28cc21ed9264187b5f8abb60080efd564fa5c6c1a7214139dfec88e9f
+oid sha256:836e6deace847576f8c189022388d14fb91271b345b8d5fb18fc46ef33aeb129
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73acc8e300c91e3b233724f11bf4b9e1dd7d9a6d786f22407d1d1c9b2d082114
+oid sha256:c04085c738729a7bd218e8723f9f3d746e0e2cd52583220337e1bcbd081e20a9
 size 4040701744