Run 4. Outer Step 58. Inner Step 3.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586797,
-    5586799,
-    5586802,
-    5586805,
-    5586808,
-    5586810,
-    5586812,
-    5586814,
-    5586816
+    5586820,
+    5586822,
+    5586824,
+    5586826,
+    5586828
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5586129,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c1e3ee5037eebcaf7ca5cd8b3e146e04b6290fdd017412f61282cf08e42750
+oid sha256:63bc2c5dbcf85661dcd2b8837c2d35e5dcfb287975281a847d5626fd96158ec3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcdb3797db9ca7b678850e6ed94620fd2bc5d23399bb13f47eb90c6e340b9b20
+oid sha256:ac0c695bd9920bb653abcb3621297ae901c1029a91534001b69f5d4994c92d8c
 size 4040701744