Run 4. Outer Step 17. Inner Step 40.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520054,
-    5520057,
-    5520061,
-    5520065,
-    5520068,
-    5520072,
-    5520076
+    5520080,
+    5520084,
+    5520087,
+    5520091,
+    5520094,
+    5520098
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c902bd63323b3b3770aeeef19e29c10225682dbc421e141e4f8d0b61897fe0bf
+oid sha256:aa7016dd2059d4a2ee7b12befba68e77e44efc09a7ab06fcf63fcd1593d7f20a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79602013c72dc6a1aed51c4f96e949c3e3289b1629125c243df3d8bd518bf4fb
+oid sha256:47a0bcb57644fa8e8958ff82e3cb0ad190223fc1c8c36fc5e2faca8ad7ae0eba
 size 4040701744