Run 4. Outer Step 33. Inner Step 10.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544297,
-    5544299,
-    5544301,
-    5544302,
-    5544302,
-    5544304,
-    5544306,
-    5544308,
-    5544310
+    5544314,
+    5544317,
+    5544318,
+    5544318,
+    5544321
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "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:ce8b7ec11f1cdf3aec5cd1252be8ff7b641dc8537cd5251a949040c2b08723b4
+oid sha256:dee51fe10f3fdd19b939bf9fecd9678f36e6c0d209c3653ae540fd4ae3b1c543
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faad0c9133f750f57e1b0ba8c9b4de7c3c9e1d679fa5c7175b65fea5984cf2c
+oid sha256:37ccdfc2c4c89ce8265ae34136223984a9064114ab992eccc39cdcdc1d836357
 size 4040701744