Run 4. Outer Step 50. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572083,
-    5572088,
-    5572093,
-    5572097,
-    5572101
+    5572106,
+    5572111,
+    5572115,
+    5572120,
+    5572124
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad4c4d20c88f311ef00fc3526c7e398dddf569138d0fc0422359d6555a23cc3
+oid sha256:4f48d4cb7e09e49c798c82ab41cc1f428d46bd6e5dfe5bf0c5d1a745c6252f68
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a1fd6463606add9819a66afe92cd7721e4614b6dd9138a487497acb58a141da
+oid sha256:d52d3e3c27aa800e86f10635c2318a8e723b0b05a960e5203e47302267ab6315
 size 4040701744