Run 4. Outer Step 58. Inner Step 18.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604888,
-    5604892,
-    5604896,
-    5604900,
-    5604904,
-    5604908
+    5604913,
+    5604917,
+    5604921,
+    5604925,
+    5604928
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec523f8a6b465ca130558fdfd7815f59704006cb1f6f911cec371dfe4285863b
+oid sha256:dc74f099fc493b60c4be8dcaeb68f66b11d8d85fc4de914f531e369c22584559
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1005fe2f5c5527156ba73d260ac303d1409511d78cbb003903d74787621cde2
+oid sha256:25c07a88d983e8509793d9d762075c1ec681a4cf28bf98df46b0e89eab29ec90
 size 4040701744