Run 4. Outer Step 40. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556125,
-    5556129,
-    5556135,
-    5556138,
-    5556141
+    5556148,
+    5556152,
+    5556156,
+    5556160,
+    5556164
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "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 sha256:85e068f2965947934b12331d83ced7a6f2ef33a4b0d3e6c882a647d1a90d8f8b
+oid sha256:387bbfc57e6dec59d8cae163613dfd3e4470a4a27a22c5218cf6ddadcaa7bd90
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a7a19125479ebe0d2bce11c42dfc613bbfd89f96b18879d22ac8749f6c1cb4
+oid sha256:4fcc73a88aa79f19582e71f3dac03aa23615d7c62e86472c6a34b0d1a8ed5021
 size 4040701744