Run 4. Outer Step 35. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548412,
-    5548417,
-    5548421,
-    5548426,
-    5548431
+    5548437,
+    5548441,
+    5548446,
+    5548451,
+    5548455
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "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:a2eae6b2d66d13e0dfd168463fee95cf2953775bb74365de82e4b35a91c1b7d7
+oid sha256:15d5d27ff877ac79f810eaf5ac51e4c951222fe8fe14907498d371e0891e90c6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff7b1a6a2e424b6c47d2cdb0b0c902cb620282c765e6a500e6275e1b8705ea6
+oid sha256:959e0e4a36e391271d30196abbbfc89a6d12c853c61319cde6036b3e7a43f79f
 size 4040701744