Run 4. Outer Step 17. Inner Step 16.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5519461,
-    5519464,
-    5519468,
-    5519472,
-    5519476,
-    5519479
+    5519483,
+    5519487,
+    5519491,
+    5519494,
+    5519498,
+    5519501,
+    5519505
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "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 sha256:391c31312a4fb2d982d47c1ce2f55d9673cdce35f8ceb76b3c78b176e96d1983
+oid sha256:40be0b0833b0c18ddb811b4246a336aa05c41ab25477fc71a59faa8263f6700a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6e965c1e4fa5d98e7efb0b1bc02e0f4820dc3ab5c5f046f1685af45a03505f2
+oid sha256:26bf6ca27dd20c0928adc0ad22d1e8af0099677c3f1498294d5de0e826420667
 size 4040701744