Run 4. Outer Step 56. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5584082,
-    5584086,
-    5584090,
-    5584094,
-    5584098
+    5584102,
+    5584106,
+    5584110,
+    5584114,
+    5584118
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12db3a040e9ef957177687afb53a883babac9e3b3d67fc4d676e2f8eee102989
+oid sha256:5f34edd94a471a9f1e7527afc87459791e7fbb7382926b72295f9aacf01abd87
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c662540a7873f31d4f38441abba9c9041b1eed3facc5a5406b859cba19f89517
+oid sha256:2ea8b65b406b41955d80fddb86edc9a09701545893f493e7b4f9a24594e41dfe
 size 4040701744