Run 3. Outer Step 9. Inner Step 14.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5399410,
-    5399414,
-    5399419,
-    5399423,
-    5399427
+    5399457,
+    5399462,
+    5399466,
+    5399470,
+    5399474
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85342a8f5a81c7bc7e50f297dae72b9256a46e983b0a1602836d0eabab66500
+oid sha256:4f057c191f37c6e037fe3ddcb5114e450546227a771cbfe5fe17f5597c16d276
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd76707f53546b817d2e7c6c1b201806575ade50eb8c1a8ab01341767c866d22
+oid sha256:16b364e8e90949a0e7d51d24ce7bd97272daab1c2ce3455728642e86e1368bf2
 size 4040701744