Run 4. Outer Step 26. Inner Step 36.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535739,
-    5535742,
-    5535745,
-    5535746,
-    5535748
+    5535751,
+    5535754,
+    5535757,
+    5535759,
+    5535760,
+    5535762,
+    5535765,
+    5535767,
+    5535768,
+    5535771
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9487db9970a64aa8236bb0a2bf6cc2f9977568d3c06fea54efde3dea396ffbff
+oid sha256:6c4b0425fc5e649aedaa58aa5d92ebd30444046ee42eeb2dd559b59aaa0a4737
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a34500165f4cef6e6aec04e6e9d50fa0db9efddacc4da04aaca76c46f7142d9
+oid sha256:000a2d8f679b7cd799897c5f35eb5a148ff8de63024b56c69c903272b56d7ce8
 size 4040701744