Run 4. Outer Step 33. Inner Step 98.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546811,
-    5546813,
-    5546815,
-    5546817,
-    5546819,
-    5546821,
-    5546823,
-    5546825,
-    5546827
+    5546830,
+    5546832,
+    5546833,
+    5546834,
+    5546836
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 97,
+  "inner_step": 98,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b52d3c2b0efebae2724296c94ac74c5a11ecba4edad12dd261b4a2e28598df23
+oid sha256:7cccd4ee0094500548c9d5d566f4a078f250a43c38070841eb056717b5a3fd6a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9158de2b124827a890113485898250df7142cdc05ea5554cf2e86ae4ec7e4e6
+oid sha256:e4a1bcde9a34d0ea22ca8073d3bc2dba3328ca32d864c1c6ced369c35598ab36
 size 4040701744