Run 3. Outer Step 9. Inner Step 85.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5413948,
-    5413952,
-    5413956,
-    5413961,
-    5413965
+    5414000,
+    5414004,
+    5414008,
+    5414013,
+    5414017
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 83,
+  "inner_step": 85,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d24a059decf86c352f7eb9e6e6749c72fc0abbcd0296866a8de44f5cdf5b81a
+oid sha256:11ed0fda451f0f4425ab31c73fcbc68ed03f938c3150bf5877b2879aae7502c1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875fe1f57da3da4e13cc716b67ce7c61578fc7fcb968a17608ade153acd510b9
+oid sha256:9600eff28e3f67c3a5d79247754a3842283335a5720e476514052ed12428c163
 size 4040701744