Run 4. Outer Step 37. Inner Step 18.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5551647,
-    5551649,
-    5551651,
-    5551654,
-    5551657,
-    5551659,
-    5551661
+    5551663,
+    5551666,
+    5551667,
+    5551671,
+    5551673
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5550793,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c220c30efdd788030ce328aec1c18ea6fe141a2550607d7c27a190293684944
+oid sha256:721ce0bbb7afd590e256da5bffb05770567dd83e8d709d847fc7d67fb32f0990
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b861f446a3d6c356afe181744e5d76b3d29c81aa8236ef83cd734529c3c5b956
+oid sha256:ee0cd7caab29922eca63f70cab1e18c1349d20c5933427ca5397b7941665aa03
 size 4040701744