Run 4. Outer Step 4. Inner Step 13.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486769,
-    5486772,
-    5486774,
-    5486776,
-    5486777,
-    5486779,
-    5486781,
-    5486784,
-    5486786
+    5486789,
+    5486792,
+    5486794,
+    5486797,
+    5486799
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "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:ea7eae8cd0ef5781d519b4434d552b1b118143cc49223e6c817f6c3d2f696d2a
+oid sha256:ea81607516217cb333a35cb25381bd3bfdee4f2780bfb076710e8cab3dad2454
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac1ddee1ded96fa19f64efd39191b14b5ee2cc9e034af21b5a426f72b204aae
+oid sha256:659aa736aca64a64d453d46efc12a79143c92927be7ea8159fd2c397e0d359b0
 size 4040701744