Run 4. Outer Step 63. Inner Step 12.

config.json

@@ -268,18 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5612239,
-    5612239,
-    5612239,
-    5612239,
-    5612239
+    5612240,
+    5612240,
+    5612240,
+    5612240,
+    5612240,
+    5612240,
+    5612241
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b67544b5e243f60f476fe4feb302d814fc621127d51b261d9980c19776e4d79
+oid sha256:60b26175f1dcb45c82530356ab6991948ec0b86e6b995d3a54bdb6dc02bb8fdf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1300934fd53bf1b6ed5a2ca998568b6a80eb042cab9be059868a4fae5e841df8
+oid sha256:aa876b4c22b07536b0a6e3fbaa1f9604c2a6abd897375b8c026fd2369490022d
 size 4040701744