Run 4. Outer Step 66. Inner Step 18.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651693,
-    5651725
+    5651760,
+    5651826
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5643114,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f083b30bff225c653d39bffeff3954e12c3b314f9a6f36a870f6e62062531814
+oid sha256:bceb8d39c5634bd5adbcb160789fa9b24231f39b647022aa97aea2847d3459f0
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ce274acabea850519e548de615e068cad490caf2cdd69661355d90042891ddf
+oid sha256:f55421373de27a861f38f28827cb351c46f11996c6af56b360a63ab7babaf3d5
 size 4040701744