Run 4. Outer Step 33. Inner Step 26.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544764,
-    5544766,
-    5544768,
-    5544770,
-    5544772,
-    5544774,
-    5544776,
-    5544777,
-    5544778,
-    5544780
+    5544782,
+    5544785,
+    5544787,
+    5544788,
+    5544790
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "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:bed3df4969ddee8f0aa8d2e6eab9ed29f7166bf08b2a44c6615f61c83ee1c601
+oid sha256:663db0e7ef1590cd22d4fd6882c218efe41c6fd1c835467e217562f3f3593fa6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:316d06bd41418166473d7925aa96e9b9c38cda72e7b9e7747de928bdf51e5300
+oid sha256:b35b4307996daa9150a76a303449a766ec30ebff2b2bca03f892060777594911
 size 4040701744