Run 4. Outer Step 60. Inner Step 4.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607486,
-    5607488,
-    5607490,
-    5607492,
-    5607494
+    5607495,
+    5607496,
+    5607499,
+    5607501,
+    5607504
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a03fb93b91df79112e8f03f661376c5eefa271f1926e43a039a6ed6ab2b0de4
+oid sha256:929b5af7144bde31a2bd4e0e0060979d1f647ffed59363857bf811a5370efc5c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60dca8d9e4b377a36f6b760ac54296710325c4bf72f0699c4c7752e8dcc14453
+oid sha256:81d473b41241271ea0116f83a9dc628e5a6085991a4a751060c59434b8bc94cd
 size 4040701744