Run 4. Outer Step 55. Inner Step 33.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5581683,
-    5581687,
-    5581690,
-    5581694,
-    5581698
+    5581703,
+    5581710,
+    5581713,
+    5581717,
+    5581721
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5563454,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf06062192fde1418b7baccc2e2f65ae78270a4f5c8e7fd42de7ae3d52dd97b
+oid sha256:cfa0fa94d0117f28b5a4ce7c5a401264a46139762a7ed6d079f9b96e9eaa83cd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12eeed6b94df4feaea2ba90501f09f97703b9c28d654f90a00bdf86f3b850736
+oid sha256:13fcce4c6fb657b9ff9c0a9e573fef80b7873af4b92958eb820a29ce64566b39
 size 4040701744