Run 4. Outer Step 60. Inner Step 20.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607859,
-    5607863,
-    5607868,
-    5607872,
-    5607877
+    5607884,
+    5607888,
+    5607892,
+    5607897,
+    5607901
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32aa214b8dcdbd4a1caa8c178fa6cdae36651d926d78e1636e8312c513eb0a5d
+oid sha256:9138b6264c9f935fdd571ff2867551a4cb61d9b3a4a8d3b993fb300d2cdb2ba5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddc59f36caf0c391802880644a8ab737a38b1bd44e87b5e33f997551aca7c41
+oid sha256:df5c5c119a54f63c7700c4edb278475f8eb8aa5a6a386741a954df755328f4a5
 size 4040701744