Run 4. Outer Step 75. Inner Step 27.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5663398,
-    5663403,
-    5663407,
-    5663411,
-    5663416
+    5663421,
+    5663433,
+    5663437,
+    5663441,
+    5663445
   ],
   "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": 5662361,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04ebad2b9274952de53ca6ccecb1f5dd87e13e417ae2c964607f04e120cd055
+oid sha256:9ff7bd5a61a5c1204ce24ca45e0473d8252012ecb921a769069843974291300d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:500f659b301873c7470b1c32118a1af0ffe9c47981a602d48bd3841569953b30
+oid sha256:333fd1c40cded4ca33ae0cf215be36b66cf67bb27be24f2f3fec6379bf3a993e
 size 4040701744