Run 4. Outer Step 32. Inner Step 36.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543911,
-    5543913,
-    5543915,
-    5543917,
-    5543919,
-    5543922,
-    5543924,
-    5543926,
-    5543928,
-    5543930
+    5543933,
+    5543935,
+    5543937,
+    5543940,
+    5543942
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eea092362fc23642d89eaed96a2056595ad4de0c1047bf9d58df7cab0c374e6
+oid sha256:f6a5c28fdb9c7bfced159d5ae8243468aaee1206c2b6dbe35d95dad3c86dd59f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e54f57eba7fa05d296dfe8603792b73386eed4c8f1d04415c1df754852c87a5
+oid sha256:52c434d604ada3b10fc4a50d2e754ba6e4d20e367dd5bda329b516e301ac30a4
 size 4040701744