Run 4. Outer Step 61. Inner Step 54.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610236,
-    5610240,
-    5610244,
-    5610248,
-    5610252
+    5610256,
+    5610259,
+    5610263,
+    5610267,
+    5610271
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 53,
+  "inner_step": 54,
   "inner_steps": 0,
   "last_allreduce_block": 5608831,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f7d51931cf10e977d523ad7b019603b996c7620f87f7ddc47821bf402e4fd87
+oid sha256:34d7016d2ec1dc712c261b89029f09da6629f328a5902050911d904d61163804
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0bc88dcd41a9e8e50dfa495c2fe357816c244164ee8c330c01699499d76b6d0
+oid sha256:f2104645d59a437f50bb42dc2250f38381f0262089ac99790aed1f5fc509613a
 size 4040701744