Run 4. Outer Step 17. Inner Step 67.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520848,
-    5520852,
-    5520855,
-    5520858,
-    5520862,
-    5520865,
-    5520869
+    5520873,
+    5520877,
+    5520881,
+    5520885,
+    5520889,
+    5520893
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 66,
+  "inner_step": 67,
   "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 sha256:984165d0d262f38c67eb5015d23e69b3936b9624c9166542c1fbcca2fe102b08
+oid sha256:647bbb95920b0d597d9e9495baa5c19adf6bc0ca45412477d62d76877bdaa110
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5baeb70ed9b6a8b528174e53ffaccd1ebc79bb9762c28df48d1dc5cd319df2a7
+oid sha256:1b00f3c40b776034688206d4f38d9157299bce56beb1d3c10ee74c079eee6f81
 size 4040701744