Run 4. Outer Step 7. Inner Step 73.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494070,
-    5494074,
-    5494078,
-    5494081,
-    5494085
+    5494090,
+    5494094,
+    5494098,
+    5494102,
+    5494106
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 72,
+  "inner_step": 73,
   "inner_steps": 0,
   "last_allreduce_block": 5490074,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0a5698aa904694e90bbc66b2a3255deb2d57f5ad7f1cb275d649acf029dcbf
+oid sha256:ed96e3796b58295860cd5a6221d46f9985dd2e72a1c8d65c67a5f369f17342db
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d40eac3eca496b3e05aaca635c4cecb78cceca0d30cad17d0a40accbd547c89
+oid sha256:add86624292434a17451ad66d61cc5f6c2c3c0e9e9d46b641461cd61cdefd836
 size 4040701744