Run 4. Outer Step 23. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5529470,
-    5529475,
-    5529481,
-    5529486,
-    5529492
+    5529498,
+    5529503,
+    5529509,
+    5529514,
+    5529520
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "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:ddbb5e2d8799fa2696850d6252e8d8706d600806db82f745e37463e5c0fa58ba
+oid sha256:0dd4e9277b64a4610ca64e8ef62662030dec31870b97c7a809c818ddfbef48dd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2790373182e11a6b109321397079bda8331005d8884ba9dcc06e3559c15c804b
+oid sha256:a5b25050b78f14df9ea6d6be5fe41140d643870cfc201d57120a2608f7fcb3f9
 size 4040701744