Run 4. Outer Step 15. Inner Step 69.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5515050,
-    5515054,
-    5515057,
-    5515061,
-    5515064,
-    5515068
+    5515072,
+    5515076,
+    5515079,
+    5515083,
+    5515087,
+    5515090,
+    5515094
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 68,
+  "inner_step": 69,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7818df9cf8ae379da77b3725b0c65180e5ede36d21943ba1573a0caad0a17e96
+oid sha256:4616df4e44ea189e2d88a8f3bab00e415ac23591fe7981eeabc26cdfb4c6043b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773b99c3f25a04ae524bcc2dc2b6ce304ac854f55b36857a9f3fc0cdaa66f5d4
+oid sha256:b47a64fa710215d02f890c0838bf830b56112475013978573b30605cd5636936
 size 4040701744