Run 4. Outer Step 50. Inner Step 33.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572508,
-    5572513,
-    5572517,
-    5572521,
-    5572525
+    5572530,
+    5572534,
+    5572538,
+    5572543,
+    5572547
   ],
   "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": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c11a0112887fb59acc87b10fbe88fec910ba87cb36af292f5c362f397f0b9af3
+oid sha256:ec5bb811aad3c3bdc44673b7ff11baadd2d0d3ddc9f67f7a611723dccfa093e4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:470c9723aedc18c45e18a23843ed23cf7f436df92ecbeb44921e568177d3c9a2
+oid sha256:3aac66e70675eb00514168666fc439aa200031257482eb35a6413ba040e3483d
 size 4040701744