Run 4. Outer Step 66. Inner Step 67.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621716,
-    5621719,
-    5621722,
-    5621724,
-    5621726,
-    5621727,
-    5621729
+    5621732,
+    5621734,
+    5621736,
+    5621738,
+    5621739
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 66,
+  "inner_step": 67,
   "inner_steps": 0,
   "last_allreduce_block": 5619221,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e7e208e5bf9bebdde61942ca447798a5f322606256fb7a93084aabf2ff2dd2a
+oid sha256:0b51d8a5b73fa8ec7a6d7622f7ab56810339fa6b0e616d96f31f3af358551ae4
 size 8081782026