Run 4. Outer Step 54. Inner Step 65.

config.json

@@ -268,21 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5579496,
-    5579499,
-    5579502,
-    5579504,
-    5579506,
-    5579508,
-    5579510,
-    5579511
+    5579512,
+    5579514,
+    5579517,
+    5579520,
+    5579523,
+    5579526
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 64,
+  "inner_step": 65,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8284ec0f65689bbe44f32ad8f403de9446a88ec9153f73d092b365006e2a3b1
+oid sha256:010869e298526401b0a4c5644ba0d4508131fceec1027c434557b81440d26473
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc49db3a74e793cbb8286774877d8a150a65113d0aac860f55450e661cda3fd9
+oid sha256:315036551f1064a39bd15233a5ab474cf95d38482576061d46623c83810c4822
 size 4040701744