Run 4. Outer Step 29. Inner Step 12.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538915,
-    5538918,
-    5538920,
-    5538921,
-    5538921,
-    5538922,
-    5538924,
-    5538926,
-    5538929,
-    5538932,
-    5538935
+    5538938,
+    5538940,
+    5538942,
+    5538944,
+    5538946
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8069635878d2c7783796181368789a1f2272cf829df5f34d07b1487aeefa9326
+oid sha256:108a023414c86264a21572520abf0c03d3eab732141d80c2f51e525d77f627f9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c5d324cce5da234b0933f77f25f05e0c22ad0cd436674422e88aa700f6c270
+oid sha256:c1f4a39ef5a1022433f7ba18aa433bdc30d30cc49cf4cace0275a8e0b6951f06
 size 4040701744