Run 4. Outer Step 4. Inner Step 22.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5487049,
-    5487051,
-    5487052,
-    5487054,
-    5487057,
-    5487060,
-    5487063,
-    5487065
+    5487067,
+    5487070,
+    5487072,
+    5487075,
+    5487077
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a26e1b5f5e209bc135887065b219f7c76fab189f908a95a675fd889eb1cc2498
+oid sha256:da6df14494aa4b7fcb9b0ac5ef0a1a0bcffd222ff3ee11d614db2560617c08b3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2a143f59cb53e21c73f49cced541853eaea867b8b6c17c7d38b72e517c0c55
+oid sha256:b069fcc322773dd3eafda493bb835d7b08660840b9984507fafb70693daae458
 size 4040701744