Run 4. Outer Step 33. Inner Step 27.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544792,
-    5544794,
-    5544797,
-    5544799,
-    5544801,
-    5544803,
-    5544804,
-    5544807,
-    5544809
+    5544811,
+    5544814,
+    5544816,
+    5544819,
+    5544822
   ],
   "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": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:663db0e7ef1590cd22d4fd6882c218efe41c6fd1c835467e217562f3f3593fa6
+oid sha256:f48e742dbe9bbbd3c68f2c966263116431453a1c9c73abca4e2fc9f1e516d3d4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b35b4307996daa9150a76a303449a766ec30ebff2b2bca03f892060777594911
+oid sha256:73608d13054fb332d6c3982db217a397a3004a15ef80d4af35975182b72ecc22
 size 4040701744