Run 4. Outer Step 40. Inner Step 23.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555975,
-    5555979,
-    5555983,
-    5555987,
-    5555992
+    5555996,
+    5556001,
+    5556005,
+    5556009,
+    5556013
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db82a738578a5d3b5cbe74506fd9c9b9aab1b1351698f0801be06199ca4021fb
+oid sha256:9eee102976bbeadb95dfd12fb7bb2e2af290d17cecbb186178bf064a92fe7517
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b30ac4565acc130cdb7fbc9c92bfcf04c53b80bbbd5bd427ee4886e6c751526a
+oid sha256:14f3161b229c7adf737f5358d7bd53b05aaea8960836fbcc646edef7d5659bc8
 size 4040701744