Run 4. Outer Step 53. Inner Step 70.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5588533,
-    5588537,
-    5588542,
-    5588546,
-    5588550
+    5588555,
+    5588559,
+    5588563,
+    5588567,
+    5588571
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 69,
+  "inner_step": 70,
   "inner_steps": 0,
   "last_allreduce_block": 5565072,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a742d7fdb56d47f17dafb174059c7585cfa5c934c79bbd03459c7048d827a61a
+oid sha256:6a77e90fafb9a99aefdd19180513bd659902fbfb75d80de0b4615a563ba117d2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104ef482f4e58665e7283ccb46effca1e718edf75468ca21d9785dadcc895acf
+oid sha256:5362c7cb8f1436f54902ffc1434f9b0f3290694a99b453931aef41845297eae5
 size 4040701744