Run 4. Outer Step 11. Inner Step 31.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507815,
-    5507818,
-    5507822,
-    5507826,
-    5507829,
-    5507833
+    5507837,
+    5507840,
+    5507844,
+    5507848,
+    5507851,
+    5507855
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2181ad611e93b1d53c4a16109e08f7d4c433d5972989e2e311a2f19847e1d136
+oid sha256:766655d214a4c8defccf0f55b5cc227454553ef16e27021d5292282d7894783f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2add3cdc9c36467f95007733a0ca57073026433e2f23af645a535436cae5c6c1
+oid sha256:aadfd395b3169f5498c39fd396cf8a5f6688a7c2eda8db3bcfc7a1149f559a2a
 size 4040701744