Run 4. Outer Step 57. Inner Step 32.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601829,
-    5601834,
-    5601838,
-    5601842,
-    5601846
+    5601851,
+    5601855,
+    5601860,
+    5601864,
+    5601869
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5599463,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb1b66170d3362222a6d20180cadea13d0e56a265fedf0a0609c7a59df8a0ed
+oid sha256:937ea6e407f6648caca0271862086e0f1ed8dc359528de35e3f6cdfeb0804764
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a0c99bf7debdb8d46fa9b570cc0a8a87ab82553f8e5832b24e90777eb54119f
+oid sha256:e46a75400e8fea8ce3ef9177567a34909ff305ce58c6aa6a938e5ba1c3ecd9bf
 size 4040701744