Run 4. Outer Step 17. Inner Step 29.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5519739,
-    5519743,
-    5519746,
-    5519749,
-    5519753,
-    5519757,
-    5519760
+    5519790,
+    5519794,
+    5519814,
+    5519818,
+    5519822
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edb8f6b6451748bb077b0cb1edb555df70c1ea38ffac61d1ba1d515966982492
+oid sha256:f9e87aeb1ae32eb58030adcb78bde96734b8c55bd9c4b57b501aadb558f18a9d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0ecf19eb9e7e4280725e1fbb16a116eecc4290d382d74438970283d2d5e2e5
+oid sha256:2584a718af09358d46d22e67ce0fee2929ec62a9ff5aa200842069734075aea6
 size 4040701744