Run 4. Outer Step 75. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5663374,
-    5663378,
-    5663382,
-    5663387,
-    5663391
+    5663398,
+    5663403,
+    5663407,
+    5663411,
+    5663416
   ],
   "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": 5662361,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b34060793d0b8a6e6cc6927988ca75ecc2062479dc58bcd1b42dba859c6931fe
+oid sha256:d04ebad2b9274952de53ca6ccecb1f5dd87e13e417ae2c964607f04e120cd055
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe9cc0f0dddcb035b1afa52f7f1507a2d326dd2bfaf0b434013218370f1a2a4
+oid sha256:500f659b301873c7470b1c32118a1af0ffe9c47981a602d48bd3841569953b30
 size 4040701744