Run 4. Outer Step 33. Inner Step 98.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546752,
-    5546757,
-    5546760,
-    5546764,
-    5546769
+    5546773,
+    5546777,
+    5546782,
+    5546786,
+    5546790
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 97,
+  "inner_step": 98,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a958df674a9f9f040477c3328dcdd0b7153b91cb538e35fff0632bf4b8a10301
+oid sha256:b0e4c0582a63a3101dae50ab814cc2142d51e225f460dff523d22a4fa7629044
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74ccc4409aa7811b72c9fb87ce0741ce81fd3a95352c362fda10ac281d4b8f8
+oid sha256:c48a8c1f018ef7976af4c79e0913a8bb6d5e1bef7185e3fdc6ed0e10147f63a4
 size 4040701744