Run 4. Outer Step 10. Inner Step 81.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5505941,
-    5505945,
-    5505948,
-    5505952,
-    5505955,
-    5505959
+    5505963,
+    5505967,
+    5505970,
+    5505974,
+    5505978,
+    5505982
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 80,
+  "inner_step": 81,
   "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:adb8d49b3a01681a9a9717d3f15823506d05b58ffdb896b4fd29cc1fee4d959e
+oid sha256:db3c976d818805d9e40495884ab48d062ee2e1037f62af36edc13d6838d108a0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15be7581a7602a123136a27fac4c8f70a9322e6d591d57c532fd2eee20c856
+oid sha256:ee02f5a04f368eb392edb471c7b2541852064786a5f3c6d49d6e7f0fa98c2e35
 size 4040701744