Run 4. Outer Step 15. Inner Step 67.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5514932,
-    5514936,
-    5514940,
-    5514943,
-    5514947,
-    5514951
+    5514955,
+    5514959,
+    5514963,
+    5514966,
+    5514970
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 66,
+  "inner_step": 67,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a9ae41e124da8ae1b5174575ad3aefaca5b88b57e7a83da6978b28dd5a86b72
+oid sha256:22d085da22130dc7770eab49012472e711673c3b33387c969eb9519cac28b7b6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da65a843ec670ec584542e15a5442ba4cbc7586aa99bfc9d2d252e41371ca125
+oid sha256:a9bc265ad7fd715c3ad9f72ea307cd58c195d4db7366d3491c112845893ab4f9
 size 4040701744