Run 4. Outer Step 10. Inner Step 80.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5505919,
-    5505922,
-    5505926,
-    5505930,
-    5505933,
-    5505937
+    5505941,
+    5505945,
+    5505948,
+    5505952,
+    5505955,
+    5505959
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 79,
+  "inner_step": 80,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e5298bc6099309c800f83da4edca9fa2fd53ff0a990f195b035370c3618825
+oid sha256:adb8d49b3a01681a9a9717d3f15823506d05b58ffdb896b4fd29cc1fee4d959e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e60504027e5e3bd4e96b21dec6cd8dacbe4692557e9232199a60d75713778618
+oid sha256:eb15be7581a7602a123136a27fac4c8f70a9322e6d591d57c532fd2eee20c856
 size 4040701744