Run 4. Outer Step 33. Inner Step 20.

config.json

@@ -268,25 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544585,
-    5544587,
-    5544589,
-    5544591,
-    5544593,
-    5544595,
-    5544597,
-    5544600,
-    5544602,
-    5544604,
-    5544605,
-    5544606
+    5544607,
+    5544608,
+    5544610,
+    5544612,
+    5544612
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72868e35ae4df6af424df0cb63ead2c94be21ae7669ab2f224478522b27f28a0
+oid sha256:80dafad637ac0b10c418d5b95f6a9f20dfa14804f8159a7819affeb5dbcac9f8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0a175d2b0f4d1801e8cfed2e374005f030eca4617b418e1712a4cdfacde6a4
+oid sha256:063b8eb657648c470eb1232afc42e3df6122e722427dec6e09e372c19eebed52
 size 4040701744