Run 4. Outer Step 33. Inner Step 26.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544784,
-    5544786,
-    5544787,
-    5544789,
-    5544792,
-    5544794,
-    5544796,
-    5544798
+    5544800,
+    5544803,
+    5544804,
+    5544807,
+    5544810
   ],
   "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:f7d8b16e68892b99e3afcdc6da9f303729431d0581f29fa0d37d12da63410ca0
+oid sha256:7bfb305a0af1db00ee1e643c6d823a1f83751dbb985cf9652e376f550067a158
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24036ae121f3ce747eb69027a317fe2f960a5475d190ea3fed11c748d64450ca
+oid sha256:4b4c4b3f71aea38d64b41a4c073dc6d8d8f0262afd1819f4fb1a4988f8cd9698
 size 4040701744