Run 4. Outer Step 40. Inner Step 18.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555844,
-    5555848,
-    5555852,
-    5555857,
-    5555861
+    5555865,
+    5555869,
+    5555873,
+    5555878,
+    5555882
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8a73f651119ecbb4d597728450ade9397bd6500b4865df475b54e02deb3629e
+oid sha256:ac022a4c182de43d616ba84d390f5cd6cf682c9dc13732f514af1f90926e473a
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6bbdd0224461d211ee6f9e923af5b4ab97ef49934592242af9b7ce9f73c80b
+oid sha256:7eb8a72ec48f96a424a110fb177841de552c8393c19ba659ffa56116f45ef424
 size 4040701744