Run 4. Outer Step 51. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5627566,
-    5627570,
-    5627574,
-    5627578,
-    5627582
+    5627587,
+    5627592,
+    5627596,
+    5627600,
+    5627604
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5627065,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eaef22c306a80a22c9f3a5a89d79ce066eecb8f972fa15df441504f4e1f75f9
+oid sha256:85e97ff14a0187bfec9f8a9b997d4c9ba24dbf97bdc1fa6da10c32afb9baa5da
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1045ee77895aca58eab278a23aa3212660a98c22068adeed9f9aefcbb42d91f
+oid sha256:d0fe1bed9e07e01949e3a5f759009708911c42b147d5f86c1869d4f63d035d10
 size 4040701744