Run 4. Outer Step 26. Inner Step 40.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535862,
-    5535865,
-    5535867,
-    5535869,
-    5535871,
-    5535873,
-    5535876,
-    5535879,
-    5535882
+    5535884,
+    5535886,
+    5535888,
+    5535890,
+    5535892
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e21048d1877733500b4eef6d750ffdbf041e411db7754cb88ff9de16f7b03f1a
+oid sha256:199848071c11a684a3283f3c9f526f5d8d0da878f38a93004fc53bbb855f2e36
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a99646292ac0e38a7be91e0d63cd8580c8c66ed70a30a2a3bdc137f7c0a210
+oid sha256:05060e8a74143631c58eea1b6166c31ac1659e9274b258366f4fe9bcb7a4ee28
 size 4040701744