Run 4. Outer Step 66. Inner Step 23.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651636,
-    5651663
+    5651691,
+    5651717
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5651055,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:966b859424ede6b3c036480ee6d395d124299d630424513a202ec98c63253d2a
+oid sha256:cd46d394261c2ce89387fa3248532b201a200e428b1e0e8a6481ec0d6b1b9a73
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04039aab8b354c155ba451ca1dae49ee249378485d34fef9ef949e8069de2fb7
+oid sha256:3e3f85cb823b1b484458432cafd5f957990cc4576325052cc4e3ead690127232
 size 4040701744