Run 4. Outer Step 36. Inner Step 21.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550189,
-    5550193,
-    5550196,
-    5550201,
-    5550205
+    5550210,
+    5550215,
+    5550218,
+    5550222,
+    5550226
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96017100739dfde17b21c7fbe93af898e79a0680e4348cdc0aa7a75b210f6555
+oid sha256:dd20a298bf41042a7c59b3534591019b538446229efc13a4ead67eb7aa824f51
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea0831f1c01bbd641498ed86f1b5a037cd6de486c4004f61f1fe65b2ded85939
+oid sha256:8cda089b9fc9e85d795a89b06c26e56f587a39de13af9062d9fb49a0eebd735b
 size 4040701744