Run 4. Outer Step 35. Inner Step 5.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548318,
-    5548323,
-    5548328,
-    5548332,
-    5548337
+    5548342,
+    5548346,
+    5548351,
+    5548355,
+    5548360
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5546853,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdec2daf21ffcef5f831dd814f308e169fc0db34662d17fe08eb8bb53e0ed41
+oid sha256:405e522ab43d3df55869847d991bfb6fd984c39d2f1621e60ef8274378e916c3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce2540b469ca03fbc605e65c4216a19b07698b33b3752c38c850f8c31fe2609
+oid sha256:4e18ca6e33066bd70ec6c8aa434784d1d3931cbfcd3b8fff51f8ab0c0226908b
 size 4040701744