Run 4. Outer Step 57. Inner Step 33.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601874,
-    5601878,
-    5601882,
-    5601886,
-    5601890
+    5601895,
+    5601899,
+    5601904,
+    5601909,
+    5601913
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "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 sha256:937ea6e407f6648caca0271862086e0f1ed8dc359528de35e3f6cdfeb0804764
+oid sha256:0e292c34937b173cdd644adccac2f4b1c71cca15d871adac80d78ed636085481
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e46a75400e8fea8ce3ef9177567a34909ff305ce58c6aa6a938e5ba1c3ecd9bf
+oid sha256:74c8de186d5e29ca4de1c62b4a66f398faa55376b17c1469f745af5cd3676aea
 size 4040701744