Run 4. Outer Step 41. Inner Step 6.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556640,
-    5556644,
-    5556648,
-    5556652,
-    5556656,
-    5556661
+    5556665,
+    5556669,
+    5556674,
+    5556678,
+    5556682,
+    5556686
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5546853,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684e98e6162b961aa9f0adf2dca2b058bdb2277ca633f30d58bed2ab7896badf
+oid sha256:b1521a881ccb0ec7d9c6ab254d5db30992d5febcd398e0050dba87c96d175490
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c1c739ffc4abc66b25e976eddef38c37551abf03044facce349b994129a2bf9
+oid sha256:70702e90e9ad9a133ff31102557fd46b1da3421dc38eca1b24394b8510087421
 size 4040701744