Run 4. Outer Step 63. Inner Step 61.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5613874,
-    5613874,
-    5613875,
-    5613875,
-    5613875
+    5613876,
+    5613876,
+    5613876,
+    5613877,
+    5613877
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 60,
+  "inner_step": 61,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe1b35d9db792f9baa6181bfa4fec81a668e491f8b2a9c739920d375659b28e
+oid sha256:7af9ca09a832d00b7ef3983ceb8ddaa8865e3f08e3b3aaf1262aa62c0aa5f70a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0be37b26b1daa71e8d08f23ae1ca4108821383eb0f1909dbc780d983c2f554b8
+oid sha256:2f363744e6766d92e3b1821fd2a3e970e7f2b7fcc778db9249d160846804851e
 size 4040701744