Run 4. Outer Step 62. Inner Step 27.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611499,
-    5611503,
-    5611507,
-    5611511,
-    5611515
+    5611520,
+    5611524,
+    5611529,
+    5611533,
+    5611537
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14424a4cb27a7db535328e14d5388f1b1b999eeb0d4db9f3a71b7b85c387a039
+oid sha256:37c20adaf89c47d0f30d9937e24836d1d0f7ff74b968f38e55bc77eb8968135e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98bc64cbf5fdd7fcf008278f25ea5b478a05c6f3100c4b9ed3f0d0b342c2f17d
+oid sha256:fd57fd515b0638ce698f5d0f130cea14a6683b90325f04b3a8c6909fad4d87ae
 size 4040701744