Run 4. Outer Step 40. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555406,
-    5555411,
-    5555415,
-    5555419,
-    5555423
+    5555430,
+    5555434,
+    5555438,
+    5555442,
+    5555447
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d377a3fac47bbe91f29c010470e351c4523893a9449d8855859534ab6d2d420
+oid sha256:1c2b71d5bd78b1991ff24399abaff8e1451bbb183a4ade9c88a44d6713f436c5
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c805aa04a48cda2266bfd808336777a73bf59e33f52cf8f20065d57791c1af
+oid sha256:4fb83b7f0e0683d01c9eedf86b7026d1ebbca141a34c09fb33445c708511df3b
 size 4040701744