Run 3. Outer Step 12. Inner Step 233.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5464537,
-    5464542,
-    5464547,
-    5464551,
-    5464556
+    5464562,
+    5464566,
+    5464571,
+    5464576,
+    5464581
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 232,
+  "inner_step": 233,
   "inner_steps": 0,
   "last_allreduce_block": 5450451,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f47ca523e289a4123e4f1404b7c1c5ef7d985280616c384021f2818285d3393
+oid sha256:26e71f7d027a077505ea84dd6c234893567e84cae9e1d815bc492be7208c794e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac0fa04c22084fb26fb6568b2e12e8fa65d77b064c54879d19dd96e510de596
+oid sha256:14bed59012d5458edd833d3ed973996cd0e8140574d2cf76f66925e8b1dc4021
 size 4040701744