Run 4. Outer Step 3. Inner Step 131.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484701,
-    5484705,
-    5484707,
-    5484708,
-    5484710
+    5484712,
+    5484714,
+    5484717,
+    5484720,
+    5484722,
+    5484725,
+    5484727,
+    5484729,
+    5484732,
+    5484733
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 130,
+  "inner_step": 131,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614fe8ab760b6e4464ffebee8a336bf813b16c442f6c68489140edcaffc67854
+oid sha256:2ffa7cda865056bf720171a2409f43ba265e29392704a697c4d3329dd28b5e05
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3dd8405e259d015229ed4f9b062f4f554504cdd6969950764614805cb13794f
+oid sha256:093c574bee23b107f0281a90e8c324d2a703f36b9e351101addbf9195ef52ed8
 size 4040701744