Run 4. Outer Step 76. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5663945,
-    5663964
+    5663983,
+    5664002
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5663576,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade909b7568dbb4953d1017d86cf5709d6e217d59d0eca66dc0d602e91deab3c
+oid sha256:969d8a715bb1885b039aaae0170e0c5c3588da0e91a8e907a50b90081280bb26
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15b992d383ffed6c4aba171279d904ce37dcb4d524d92c87bdcb0197b551748
+oid sha256:ea9b02fbb1d7d28b0e7cf6c12ae24869b29d295b6abe402809307cde809d7e9e
 size 4040701744