Run 4. Outer Step 50. Inner Step 190.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5626863,
-    5626868,
-    5626872,
-    5626877,
-    5626882
+    5626887,
+    5626891,
+    5626896,
+    5626900,
+    5626904
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 189,
+  "inner_step": 190,
   "inner_steps": 0,
   "last_allreduce_block": 5570305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e6534abd08f90c18f83b744223b424bee795fa8e0f61ef176be035b30a56537
+oid sha256:2b4d9757279a77d4b6cd4ba80fcbdc08e2dbfc1717e386786f49d6c9151c676e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31990202a9b71947cc3f4dee46b9f9b76319ec9c074519ccfda3650e9265d5e4
+oid sha256:8bcb9d128bc23ebbb592113671287091ae9a2cbc6f542eb268d5df0f2446edcb
 size 4040701744