Run 4. Outer Step 4. Inner Step 2.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486411,
-    5486413,
-    5486416,
-    5486419,
-    5486421,
-    5486424,
-    5486427
+    5486433,
+    5486433,
+    5486438,
+    5486441,
+    5486445
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c5c2cb34ce6684f1a9181c4cec71db3d5813fdfaf7d21896d0542c6193e2fc
+oid sha256:454a56f33c7413ac5f2592e2585ed9e6a9dbb7ad513d96a59af49f79ed668990
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c067d5436c5b21692b7f973331358bb70e6ae9c2a76a03a0593e02539170e6e
+oid sha256:396c8bbd2930bf443f9b26b8f137b581026f40edf48953be78999ed40d2fea95
 size 4040701744