Run 4. Outer Step 27. Inner Step 30.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536849,
-    5536852,
-    5536854,
-    5536856,
-    5536859
+    5536862,
+    5536865,
+    5536867,
+    5536870,
+    5536873,
+    5536876,
+    5536879,
+    5536881
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641911f5a2d367e39947f00d699ccaaafb936d7816055936746c4b892b892314
+oid sha256:52a77aa4b088b74a5319a067bd3700542749d411588427aff2450331e77f2850
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e80366256fa7a9271eca6086d6c6fc55b02b8ce5ba9eed3df40f66fae4cc56
+oid sha256:e6ef81fb7f82674302fca4f9eda87bc4b22dd6e1c97c2fa33c7cde5471218bcf
 size 4040701744